CN115482075A

CN115482075A - Financial data anomaly analysis method and device, electronic equipment and storage medium

Info

Publication number: CN115482075A
Application number: CN202211151581.XA
Authority: CN
Inventors: 涂朋成
Original assignee: Ping An Bank Co Ltd
Current assignee: Ping An Bank Co Ltd
Priority date: 2022-09-21
Filing date: 2022-09-21
Publication date: 2022-12-16

Abstract

The embodiment of the application provides a financial data abnormity analysis method, a financial data abnormity analysis device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring financial data; performing feature extraction on the financial data according to a pre-constructed wind control model to obtain financial data features; performing parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter; obtaining a label corresponding to the financial data according to the financial data characteristic and the wind control parameter; and obtaining an analysis result according to the label. By implementing the embodiment of the application, the financial data in the virtual resource analysis process can be analyzed, manual examination is not needed, examination time is shortened, error probability is reduced, and manpower and material resources are saved.

Description

Financial data anomaly analysis method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of data analysis technologies, and in particular, to an anomaly analysis method and apparatus for financial data, an electronic device, and a computer-readable storage medium.

Background

When an enterprise loans, particularly small and micro enterprises loans, qualification evaluation and abnormal evaluation need to be carried out on the small and micro enterprises, the small and medium enterprises cannot use a traditional financial rating model to carry out comprehensive credit rating on the small and medium enterprises due to the fact that the small scale is small and financial statements or financial non-specifications are not available, and therefore many existing banks can go to a manual link when carrying out credit approval on the small and medium enterprises, and make decisions on an approval process through experience judgment and manual information cross verification of an approval group.

However, this method is time-consuming, and the flow material submitted by the user cannot be edited, needs manual accounting by the business approval staff, has low work technology content, needs a lot of manpower and physical resources, is long in time consumption, is prone to errors, and has operation abnormity.

Disclosure of Invention

An object of the embodiments of the present application is to provide a method and an apparatus for analyzing financial data, an electronic device, and a computer-readable storage medium, which can analyze financial data in a virtual resource analysis process, do not need manual review, shorten review time, reduce error probability, and save manpower and material resources.

In a first aspect, an embodiment of the present application provides an anomaly analysis method for financial data, where the method includes:

acquiring financial data;

performing feature extraction on the financial data according to a pre-constructed wind control model to obtain financial data features;

performing parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter;

obtaining a label corresponding to the financial data according to the financial data characteristics and the wind control parameters;

and obtaining an analysis result according to the label.

In the implementation process, the financial data is subjected to feature extraction, parameter configuration is carried out on the financial data and the offline model result to obtain the label, the analysis result is obtained according to the label, the financial data in the virtual resource analysis process can be analyzed, manual examination is not needed, examination time is shortened, error probability is reduced, and manpower and material resources are saved.

Further, before the step of obtaining financial data, the method further comprises: and constructing a wind control model.

Further, the step of constructing the wind control model in advance includes:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

and inputting the index data, the label information and the unstructured data into the basic machine learning model for training to obtain the wind control model.

In the implementation process, the content and the structure of the data can be expressed by the index data, the label information and the unstructured data, so that the characteristics of the index data, the label information and the unstructured data are more obvious, the analysis result is favorably improved, the index data, the label information and the unstructured data are used for training, and the redundancy in the training process can be reduced.

Further, the step of obtaining the offline model result in advance includes:

acquiring historical financial data;

and inputting the historical financial data into the wind control model to obtain the result of the off-line model.

In the implementation process, the offline model result is obtained according to the historical financial data, so that the referential property in the anomaly analysis process can be increased, the anomaly analysis is more stable, and the accuracy of the analysis result is improved.

Further, the step of performing parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter includes:

configuring a proportional parameter, a threshold value and a keyword according to the financial data and the offline model result;

and obtaining the wind control parameter according to the proportion parameter, the threshold and the keyword.

In the implementation process, the wind control data is obtained according to the proportion parameters, the threshold values and the keywords, so that the wind control data comprises various key information, the practicability of the wind control parameters is improved, and the time for obtaining the analysis result is shortened.

In a second aspect, an embodiment of the present application further provides an apparatus for analyzing financial data, where the apparatus includes:

the acquisition module is used for acquiring financial data;

the characteristic extraction module is used for carrying out characteristic extraction on the financial data according to a pre-constructed wind control model to obtain financial data characteristics;

the parameter configuration module is used for performing parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter;

the data obtaining module is used for obtaining a label corresponding to the financial data according to the financial data characteristics and the wind control parameters;

and the analysis module is used for obtaining an analysis result according to the label.

In the implementation process, the financial data are subjected to feature extraction, parameter configuration is carried out on the financial data and the offline model result to obtain the label, and the analysis result is obtained according to the label, so that the financial data in the loan process can be analyzed, manual examination is not needed, the examination time is shortened, the error probability is reduced, and manpower and material resources are saved.

Further, the apparatus further comprises a construction module configured to:

and constructing a wind control model.

Further, the build module is further configured to:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

In the implementation process, the content and the structure of the data can be expressed by the index data, the label information and the unstructured data, so that the characteristics of the index data, the label information and the unstructured data are more obvious, the analysis result is favorably improved, the training is performed by utilizing the index data, the label information and the unstructured data, and the redundancy in the training process can be reduced.

In a third aspect, an electronic device provided in an embodiment of the present application includes: memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method according to any of the first aspect when executing the computer program.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, cause the computer to perform the method according to any one of the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program product, which when run on a computer, causes the computer to perform the method according to any one of the first aspect.

Additional features and advantages of the disclosure will be set forth in the description which follows, or in part may be learned by the practice of the above-described techniques of the disclosure, or may be learned by practice of the disclosure.

The present invention can be implemented in accordance with the content of the specification, and the following detailed description of the preferred embodiments of the present application is made with reference to the accompanying drawings.

Drawings

To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.

Fig. 1 is a schematic flowchart of an anomaly analysis method for financial data according to an embodiment of the present application;

fig. 2 is a schematic structural composition diagram of an anomaly analysis apparatus for financial data according to an embodiment of the present application;

fig. 3 is a schematic structural component diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not construed as indicating or implying relative importance.

The following detailed description of embodiments of the present application will be described in conjunction with the accompanying drawings and examples. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.

Example one

Fig. 1 is a schematic flowchart of an anomaly analysis method for financial data according to an embodiment of the present application, where as shown in fig. 1, the method includes:

s1, acquiring financial data;

s2, extracting the characteristics of the financial data according to a pre-constructed wind control model to obtain the characteristics of the financial data;

s3, performing parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter;

s4, obtaining a label corresponding to the financial data according to the financial data characteristics and the wind control parameters;

and S5, obtaining an analysis result according to the label.

In the embodiment of the application, by using a machine learning algorithm, such as an Optical Character Recognition (OCR) algorithm, a Neuro-Linguistic Programming (NLP) algorithm, and the like, in combination with financial data, the data value of the financial data is fully mined from three major aspects of mining quantization, OCR and NLP, effective information scattered in a worker report, a complaint record and a referee document is structured, and an intelligent approval Robot Process Automation (RPA) is created, so that information collection and text summarization functions are provided, and the wind control level, the automatic approval efficiency, the operation management capability and the like of a small enterprise are comprehensively improved.

The RPA has the main function of executing the interaction between the working information and the service according to a flow designed in advance through a robot. Therefore, if the interaction between the working information and the service is excessive, the RPA can efficiently solve the complex processes, and the labor cost is saved. The RPA mainly enables a user to generate an automatic flow by dragging the control through various packaged controls and simple operation, and realizes automatic mouse click, keyboard input, excel operation, data processing, timing execution and automatic interface generation interaction of a browser application program on a computer. The basic tool type RPA is composed of a controller, an editor and a runner. Application scenarios include financial accounting, human resources, purchasing, supply chain management, etc., such as expense reimbursement, document review, personnel entry, proof of opening, order reconciliation, etc.

In the embodiment of the application, the RPA is a group of technologies for executing business processes by using software, and the same processes are executed according to the execution rules and operation procedures of banks. The RPA technology can reduce the labor input in the work, avoid the artificial operation error, greatly reduce the processing time and convert the work environment into a higher-order work environment.

The use of RPA enables banks to achieve full life-cycle management of automation requirements, bottom-up mining of automation opportunities, rapid generation of requirement specification documents, and intelligent analysis processes to continuously improve Return On Investment (ROI). And the desktop end and the mobile end are simple and easy to use, can be used quickly, have rich component templates, can be used after being opened, can self-define Artificial Intelligence (AI) functions, can be upgraded intelligently, and can be deployed by public cloud/private cloud.

The method provides great help for comprehensive management, scheduling and monitoring of banks, can realize full view of the hole case business, improve the operation efficiency and trace the auditable authority separation high safety compliance.

With the application and popularization of AI technology, RPA becomes an accelerator for enterprise process combing and governing. Besides tool habits, the development of the RPA must depend on the AI technology, and the RPA can be considered to be the most important application scene of the AI technology; in the RPA process, AI technology has been widely used. Through typical AI technologies, such as OCR, NLP and the like, the RPA platform has an ever-increasing capability, and is helping the flow management of banks to gradually realize intellectualization and convenience.

In S1, the process of obtaining financial data of a company requiring virtual resource analysis includes obtaining related companies from a company dimension and a natural person dimension in the virtual resource analysis application case, respectively. And screening out the influential associated companies from all the associated companies according to the dimensions of the stock holding ratio and the annual income of the companies. Where the proportion and annual revenue are configurable. And acquiring information such as official documents, information lost bulletins, information opened bulletins, information punished bulletins and the like related to all related companies, and forming financial data by the various information and data.

Further, the step of constructing the wind control model in advance comprises the following steps:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

and inputting the index data, the label information and the unstructured data into a basic machine learning model for training to obtain a wind control model.

Alternatively, the basic machine learning model includes models constructed according to various machine learning algorithms, for example, the basic machine learning model is constructed according to an OCR, which refers to a process that an electronic device (such as a scanner or a digital camera) checks characters printed on paper, determines the shapes of the characters by detecting dark and light patterns, and then translates the shapes into computer characters by using a character recognition method, that is, for the characters of the printed form, characters in a paper document are optically converted into an image file of black and white dot matrixes, and the characters in the image are converted into a text format by recognition software for further editing and processing by word processing software. The main indicators for measuring the performance of a basic machine learning model constructed according to OCR are: the rejection rate, the false recognition rate, the recognition speed, the user interface friendliness, the product stability, the usability, the feasibility and the like.

OCR is an important aspect in the field of automatic recognition technology research and application. The software technology is a main software matched with a scanner, belongs to the non-keyboard input category, and requires that an image input device is mainly matched with the scanner.

The basic machine learning model built according to OCR mainly comprises the following steps:

an image processing step comprising:

the image processing steps mainly have functions of document scanning, image zooming, image rotation and the like. After the characters are input by the scanner, the manuscript forms an image file, the image processing module can amplify the image to remove stains and scratches, and if the image is not placed correctly, the image can be manually or automatically rotated, so that better conditions are created for character recognition, and the recognition rate is higher.

The layout division step includes:

the layout dividing step mainly comprises layout dividing and modification dividing, namely understanding of layout, character segmentation, normalization and the like, and two automatic or manual layout dividing modes can be selected. The purpose is to tell the basic machine learning model to separate articles, forms and the like on the same layout so as to be processed respectively and to identify according to which sequence.

A character recognition step, comprising:

the character recognition step is the core part of OCR software, the character recognition module mainly carries out 'reading' on the input Chinese characters, but can not carry out line-by-line cutting, and the Chinese characters are usually recognized word by word, namely single character recognition, and then normalization is carried out. The character recognition module extracts the characteristics of the Chinese characters of different samples to complete recognition and automatically search suspicious characters, and has the functions of front-back association and the like.

A text editing step, comprising:

the character editing step is mainly used for modifying and editing the characters recognized by the OCR, if the recognition is wrong, the characters can be displayed in a striking red or blue color, similar characters are provided for selection, an editor is selected for output, and the like.

Illustratively, after the index data, the label information and the unstructured data are input into the basic machine learning model constructed according to the OCR, the image data is converted, so that graphs in the image data are continuously stored, and data in a table and characters in the image are uniformly changed into computer characters when the table exists, so that the storage amount of the image data is reduced, the recognized characters can be reused and analyzed, and the labor and time for keyboard input can be saved.

From image data to result output, the image input, image pre-processing, character feature extraction, comparison and identification are carried out, and finally the error characters are corrected through manual correction, and the result is output.

NLP is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language.

NLP is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will relate to natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics, but has important difference. Natural language processing does not generally study natural language but rather develops computer systems, and particularly software systems therein, that can efficiently implement natural language communications.

Optionally, a model warehouse may be constructed, that is, a plurality of different wind control models may be obtained according to different index data, tag information, and unstructured data training, the plurality of wind control models constitute the model warehouse, and when a wind control model is required, selection may be performed according to the model warehouse.

Further, the step of obtaining the offline model result in advance includes:

acquiring historical financial data;

and inputting the historical financial data into a wind control model to obtain an offline model result.

In the implementation process, the off-line model result is obtained according to historical financial data, so that the reference in the anomaly analysis process can be increased, the anomaly analysis is more stable, and the accuracy of the analysis result is improved.

Further, S3 includes:

configuring a ratio parameter, a threshold value and a keyword according to the financial data and the offline model result;

and acquiring a wind control parameter according to the proportion parameter, the threshold value and the keyword.

In the embodiment of the application, except for diversified operation judgment, more than 90% of request programs can be approved in most scenes, the labor cost of the service is reduced, and the whole service flow is shortened.

And obtaining labels required by each scene through the wind control model service, and outputting an analysis result. The analysis result comprises passing, denying and manual work. Optionally, the probability corresponding to the analysis result may be adjusted according to the needs of the bank and the virtual resource analysis company.

Example two

In order to implement the method corresponding to the above embodiment to achieve the corresponding functions and technical effects, the following provides an abnormality analysis device for financial data, as shown in fig. 2, the device comprising:

the acquisition module 1 is used for acquiring financial data;

the characteristic extraction module 2 is used for carrying out characteristic extraction on the financial data according to a pre-constructed wind control model to obtain financial data characteristics;

the parameter configuration module 3 is used for carrying out parameter configuration according to the financial data and a pre-obtained offline model result to obtain a wind control parameter;

the data obtaining module 4 is used for obtaining a label corresponding to the financial data according to the financial data characteristics and the wind control parameters;

and the analysis module 5 is used for obtaining an analysis result according to the label.

In the implementation process, the financial data are subjected to feature extraction, parameter configuration is carried out on the financial data and the offline model result to obtain the label, the analysis result is obtained according to the label, the financial data in the virtual resource analysis process can be analyzed, manual review is not needed, the review time is shortened, the error probability is reduced, and manpower and material resources are saved.

Further, the apparatus further comprises a construction module configured to:

and constructing a wind control model.

Further, the building module is further configured to:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

Further, the data obtaining module 4 is further configured to:

acquiring historical financial data;

Further, the parameter configuration module 3 is further configured to:

configuring a proportion parameter, a threshold value and a keyword according to the financial data and the offline model result;

In the implementation process, the wind control data are obtained according to the proportion parameters, the threshold values and the keywords, so that the wind control data contain various key information, the practicability of the wind control parameters is improved, and the time for obtaining the analysis result is shortened.

The above-mentioned abnormality analysis device for financial data can implement the method of the first embodiment. The alternatives in the first embodiment are also applicable to the present embodiment, and are not described in detail here.

The rest of the embodiments of the present application may refer to the contents of the first embodiment, and in this embodiment, details are not repeated.

EXAMPLE III

An embodiment of the present application provides an electronic device, which includes a memory and a processor, where the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method for analyzing the abnormality of the financial data according to the first embodiment.

Optionally, the electronic device may be a server.

Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device may include a processor 31, a communication interface 32, a memory 33, and at least one communication bus 34. Wherein the communication bus 34 is used for realizing direct connection communication of these components. The communication interface 32 of the device in the embodiment of the present application is used for performing signaling or data communication with other node devices. The processor 31 may be an integrated circuit chip having signal processing capabilities.

The Processor 31 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor 31 may be any conventional processor or the like.

The Memory 33 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The memory 33 has stored therein computer readable instructions which, when executed by the processor 31, enable the apparatus to perform the various steps involved in the method embodiment of fig. 1 described above.

Optionally, the electronic device may further include a memory controller, an input output unit. The memory 33, the memory controller, the processor 31, the peripheral interface, and the input/output unit are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components may be electrically connected to each other via one or more communication buses 34. The processor 31 is adapted to execute executable modules stored in the memory 33, such as software functional modules or computer programs comprised by the device.

The input and output unit is used for providing a task for a user to create and start an optional time period or preset execution time for the task creation so as to realize the interaction between the user and the server. The input/output unit may be, but is not limited to, a mouse, a keyboard, and the like.

It will be appreciated that the configuration shown in fig. 3 is merely illustrative and that the electronic device may include more or fewer components than shown in fig. 3 or have a different configuration than shown in fig. 3. The components shown in fig. 3 may be implemented in hardware, software, or a combination thereof.

In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method for analyzing financial data according to the first embodiment is implemented.

Embodiments of the present application further provide a computer program product, which, when running on a computer, causes the computer to execute the method described in the method embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application.

In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.

Claims

1. A method of anomaly analysis of financial data, the method comprising:

acquiring financial data;

obtaining a label corresponding to the financial data according to the financial data characteristic and the wind control parameter;

and obtaining an analysis result according to the label.

2. A method of anomaly analysis of financial data according to claim 1 and further comprising, prior to said step of obtaining financial data: and constructing the wind control model.

3. A method of anomaly analysis of financial data according to claim 2 wherein said step of constructing a wind control model comprises:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

4. A method of anomaly analysis of financial data according to claim 1 wherein said step of pre-obtaining said off-line model results comprises:

acquiring historical financial data;

5. A method for anomaly analysis of financial data according to claim 1 wherein said step of performing a parameter configuration based on said financial data and a previously obtained offline model result to obtain a wind control parameter comprises:

6. An anomaly analysis apparatus for financial data, said apparatus comprising:

the acquisition module is used for acquiring financial data;

7. An apparatus for anomaly analysis of financial data according to claim 6 further comprising a construction module for:

and constructing a wind control model.

8. An anomaly analysis apparatus for financial data according to claim 6 wherein said construction module is further configured to:

constructing a basic machine learning model;

acquiring index data, label information and unstructured data;

9. An electronic device, comprising a memory for storing a computer program and a processor for executing the computer program to cause the electronic device to perform the method of anomaly analysis of financial data according to any one of claims 1-5.

10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements a method of anomaly analysis of financial data according to any one of claims 1 to 5.