CN110415094A - Asset-liabilities intelligent management, device and computer readable storage medium - Google Patents
Asset-liabilities intelligent management, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110415094A CN110415094A CN201910525957.0A CN201910525957A CN110415094A CN 110415094 A CN110415094 A CN 110415094A CN 201910525957 A CN201910525957 A CN 201910525957A CN 110415094 A CN110415094 A CN 110415094A
- Authority
- CN
- China
- Prior art keywords
- debt
- business data
- data
- asset
- liabilities
- 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
- 238000013528 artificial neural network Methods 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000000556 factor analysis Methods 0.000 claims abstract description 34
- 230000010354 integration Effects 0.000 claims abstract description 31
- 239000000284 extract Substances 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 67
- 238000000034 method Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 6
- 230000001537 neural effect Effects 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract 1
- 238000000605 extraction Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000000151 deposition Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of artificial intelligence technologys, disclose a kind of asset-liabilities intelligent management, comprising: source data layer receives business data and debt label, and is stored in database to after the business data and debt tag number；Data Integration layer extracts the business data according to the number from the database, by Factor Analysis Model from the business data withdrawal of assets feature；The assets feature and the debt label are input to training in BP Neural Network network layers, until the loss function value of the BP Neural Network network layers exits training when meeting threshold requirement；The corporate debt inquiry instruction for receiving user carries out the calculating of corporate debt situation using the Data Integration layer and the BP Neural Network network layers, exports corporate debt result.The present invention also proposes a kind of asset-liabilities intelligent management apapratus and a kind of computer readable storage medium.Efficient Asset/liability management may be implemented in the present invention.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of assets based on intelligence inquiry corporate debt situation
Debt intelligent management, device and computer readable storage medium.
Background technique
At present majority enterprise debt querying methods all in the conventional way based on, such as examine enterprise accounting's account book, utilize bank
Loan Management System inquiry business loan situation etc., but examine enterprise accounting's account book time and effort consuming, and serious forgiveness is higher；And it is silver-colored
The information that capable Loan Management System can be inquired is not comprehensive enough, therefore conventional method not can effectively solve that enterprise debt inquiry is asked
Topic.
Summary of the invention
The present invention provides a kind of asset-liabilities intelligent management, device and computer readable storage medium, main mesh
Be show accurately enterprise debt situation to user when user inputs enterprise debt to be checked.
To achieve the above object, a kind of asset-liabilities intelligent management provided by the invention, comprising:
Business data and debt label are received by source data layer, and to depositing after the business data and debt tag number
Enter in database；
Using Data Integration layer according to the number, the business data is extracted from the database, passes through Factor minute
Analyse model withdrawal of assets feature from the business data；
The assets feature and the debt label are input to training in BP Neural Network network layers, until before described Godwards
When loss function value through network layer meets preset threshold requirement, the BP Neural Network network layers exit training；
The corporate debt inquiry instruction for receiving user is carried out using the Data Integration layer and the BP Neural Network network layers
Corporate debt situation calculates, and exports corporate debt result.
Optionally, described that business data and debt label are received by source data layer, and to the business data and debt
It is stored in database after tag number, comprising:
Source data layer receives business data and debt label, and according to the type of business data to the business data point
Class；
After the current number of the source data layer inquiry database, using next number of the current number as classification
The number of the business data and the debt label afterwards；
The sorted business data and the debt label are input to database by the source data layer, and update institute
State the current number of database.
Optionally, described to utilize Data Integration layer according to the number, the business data is extracted from the database,
By Factor Analysis Model from the business data withdrawal of assets feature, comprising:
The Data Integration layer inquires the current number of the database, is extracted from the database according to the number
The business data；
The Data Integration layer is using the business data as the input data of Factor Analysis Model and the training factor
Analysis model, until the Factor Analysis Model is moved back when the maximization likelihood function value of the Factor Analysis Model is less than threshold value
It trains out and exports assets feature.
Optionally, the Factor Analysis Model includes likelihood functionWith the maximization likelihood function,
In, the likelihood functionAre as follows:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data number
Amount, p is probability function, Xi, ZiThe respectively described business data and the assets feature；
The maximization likelihood function are as follows:
Wherein Qi(Zi) be Jensen ineguality parameter value:
Optionally, the assets feature and the debt label are input to training in BP Neural Network network layers, until institute
When stating the loss function values of BP Neural Network network layers and meeting threshold requirement, the BP Neural Network network layers exit training, comprising:
The assets feature is input to the input layer of the BP Neural Network network layers, the debt label is input to described
In the loss function of BP Neural Network network layers；
The BP Neural Network network layers are trained according to the input layer data and obtain trained values, and by the training
Value is input in the loss function；
By the loss function, penalty values are calculated according to the trained values and the debt label, and described in judgement
The size of penalty values and the preset threshold, until the BP Neural Network network layers are moved back when the penalty values are less than the threshold value
It trains out.
In addition, to achieve the above object, the present invention also provides a kind of asset-liabilities intelligent management apapratus, which includes depositing
Reservoir and processor are stored with the asset-liabilities intelligent management program that can be run on the processor, institute in the memory
It states when asset-liabilities intelligent management program is executed by the processor and realizes following steps:
Business data and debt label are received by source data layer, and to depositing after the business data and debt tag number
Enter in database；
Using Data Integration layer according to the number, the business data is extracted from the database, passes through Factor minute
Analyse model withdrawal of assets feature from the business data；
The assets feature and the debt label are input to training in BP Neural Network network layers, until before described Godwards
When loss function value through network layer meets preset threshold requirement, the BP Neural Network network layers exit training；
The corporate debt inquiry instruction for receiving user is carried out using the Data Integration layer and the BP Neural Network network layers
Corporate debt situation calculates, and exports corporate debt result.
Optionally, described that business data and debt label are received by source data layer, and to the business data and debt
It is stored in database after tag number, comprising:
Source data layer receives business data and debt label, and according to the type of business data to the business data point
Class；
After the current number of the source data layer inquiry database, using next number of the current number as described in
The number of sorted business data and the debt label；
The sorted business data and the debt label are input to database by the source data layer, and update institute
State the current number of database.
Optionally, described to utilize Data Integration layer according to the number, the business data is extracted from the database,
By Factor Analysis Model from the business data withdrawal of assets feature, comprising:
The Data Integration layer inquires the current number of the database, is extracted from the database according to the number
The business data；
The Data Integration layer is using the business data as the input data of Factor Analysis Model and the training factor
Analysis model, until the Factor Analysis Model is moved back when the maximization likelihood function value of the Factor Analysis Model is less than threshold value
It trains out and exports assets feature.
Optionally, the Factor Analysis Model includes likelihood functionWith the maximization likelihood function,
In, the likelihood functionAre as follows:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data number
Amount, p is probability function, Xi, ZiThe respectively described business data and the assets feature；
The maximization likelihood function are as follows:
Wherein Qi(Zi) be Jensen ineguality parameter value:
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Asset-liabilities intelligent management program is stored on storage medium, the asset-liabilities intelligent management program can be by one or more
Processor executes, the step of to realize asset-liabilities intelligent management as described above.
Asset-liabilities intelligent management, device and computer readable storage medium proposed by the present invention, source data layer connect
Business data and debt label are received, and is stored in database to after the business data and debt tag number；Data Integration layer
According to the number, the business data is extracted from the database, through Factor Analysis Model from the business data
Withdrawal of assets feature；The assets feature and the debt label are input to training in BP Neural Network network layers, until described
The loss function value of BP Neural Network network layers exits training when meeting threshold requirement；The corporate debt inquiry instruction of user is received,
The calculating of corporate debt situation is carried out using the Data Integration layer and the BP Neural Network network layers, exports corporate debt result.
Efficient Asset/liability management may be implemented for user.
Detailed description of the invention
Fig. 1 is the flow diagram for the asset-liabilities intelligent management that one embodiment of the invention provides；
Fig. 2 is the schematic diagram of internal structure for the asset-liabilities intelligent management apapratus that one embodiment of the invention provides；
Asset-liabilities intelligent management program in the asset-liabilities intelligent management apapratus that Fig. 3 provides for one embodiment of the invention
Module diagram.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The present invention provides a kind of asset-liabilities intelligent management.Shown in referring to Fig.1, provided for one embodiment of the invention
The flow diagram of asset-liabilities intelligent management.This method can be executed by device, the device can by software and/
Or hardware realization.
In the present embodiment, asset-liabilities intelligent management includes:
S1, business data and debt label are received by source data layer, and to the business data and debt tag number
It is stored in database afterwards.
The business data of present pre-ferred embodiments includes number of applications, asset-liabilities data, the investment and financing amount of money, stock
Weigh alteration, wholesale special fund amount of flow, annual financial flash report, enterprise operation funds etc..The debt label is divided into just
Often profit and two kinds of labels of being in debt.The source data layer is a multilayer circulation nesting model, receive the business data and
Label.
Relational DBMS MySQL, the number can be used in the database of present pre-ferred embodiments building
Usable company name writes a Chinese character in simplified form plus the mode of numeric sorting, such as PA00001 mode.
The present invention preferably implements the source data layer and receives business data and debt label, and according to the class of business data
Type classifies to the business data, and the classification type includes patent, fixed assets, current assets and investment concerning foreign affairs.Further
Ground, after the source data layer inquires the current number of database, using next number of the current number as the classification
The number of business data and the debt label afterwards, the current number of such as source data layer inquiry database are PA89757,
Then next number can be referred to as PA89758 with query result according to the company name, and using the PA89758 as the enterprise
Industry data and debt tag number.Further, the source data layer marks the sorted business data and the debt
Label are stored in database.
S2, using Data Integration layer according to the number, extract the business data from the database, pass through the factor
Analysis model withdrawal of assets feature from the business data.
The Data Integration layer of present pre-ferred embodiments building includes data extraction layer and feature extraction layer, and the data mention
It takes layer according to the number, business data is extracted from Relational DBMS MySQL, and the business data is defeated
Enter to feature extraction layer.
Constructed feature extraction layer is using the business data as Factor Analysis Model in present pre-ferred embodiments
Input data and training, until when the maximization likelihood function value of the Factor Analysis Model is less than preset threshold, the factor
Analysis model exits training and exports assets feature.The Factor Analysis Model includes likelihood functionAnd maximization
Two steps of likelihood function.
Further, likelihood function described in present pre-ferred embodimentsAccording to maximum likelihood estimate and p
(Xi, Zi) probability distribution, building μ, ∧,Likelihood function:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data number
Amount, p is probability function, Xi, ZiThe respectively described business data and the assets feature.
Further, present pre-ferred embodiments maximize likelihood function according to Jensen inequality, if function f (x) is
Convex function, then the expectation function of f (x) is greater than or equal to the expectation of function, and mathematic(al) representation is f (E [x])≤E [f (x)], because
This:
Wherein, according to Jensen inequality equal sign establishment condition, f (E [x])=E [f (x)] when x is constant.
Wherein Qi(Zi) be Jensen ineguality parameter value, therefore Qi(Zi) value are as follows:
Maximization likelihood function described in present pre-ferred embodiments is therefore are as follows:
Further, after the maximization likelihood function value of present pre-ferred embodiments is less than threshold value, the feature extraction layer
Training is exited, the extraction of assets feature is completed.
S3, the assets feature and the debt label are input to training in BP Neural Network network layers, until before described
When meeting preset threshold requirement to the loss function value of neural net layer, the BP Neural Network network layers exit training.
BP Neural Network network layers described in present pre-ferred embodiments include input layer, hidden layer and output layer, the money
It produces feature and is input to the input layer of the BP Neural Network network layers, and the debt label is input in the loss function.
Further, BP Neural Network network layers described in present pre-ferred embodiments are according to the input layer data and described hidden
Hiding layer obtains trained values, and the trained values are input in the loss function.The loss function is according to the trained values
Penalty values are calculated with the debt label, and judge the size of the penalty values Yu the threshold value, until the penalty values are small
When the threshold value, the BP Neural Network network layers exit training, and the loss function is least square method, and the penalty values are
L (e):
Wherein, e is the error amount of the trained values and the debt label, and k is the quantity of the assets feature, yiFor institute
State assets feature, y 'iFor the trained values, the threshold value is traditionally arranged to be 0.01.
S4, the corporate debt inquiry instruction for receiving user, utilize the Data Integration layer and the BP Neural Network network layers
The calculating of corporate debt situation is carried out, corporate debt result is exported.
Present pre-ferred embodiments receive user corporate debt inquiry instruction, and to the corporate debt inquiry instruction into
Database accession number is inquired after row coding, the business data of the database accession number and debt label are input to the Data Integration
Layer and the BP Neural Network network layers carry out the calculating of corporate debt situation, export corporate debt result.
Invention also provides a kind of asset-liabilities intelligent management apapratus.Referring to shown in Fig. 2, provided for one embodiment of the invention
The schematic diagram of internal structure of asset-liabilities intelligent management apapratus.
In the present embodiment, the asset-liabilities intelligent management apapratus 1 can be PC (Personal Computer, individual
Computer) or terminal devices such as smart phone, tablet computer, portable computer, it is also possible to a kind of server etc..The money
It produces debt intelligent management apapratus 1 and includes at least memory 11, processor 12, communication bus 13 and network interface 14.
Wherein, memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), magnetic storage, disk, CD etc..Memory 11
It can be the internal storage unit of asset-liabilities intelligent management apapratus 1 in some embodiments, such as the asset-liabilities are intelligently managed
Manage the hard disk of device 1.Memory 11 is also possible to the external storage of asset-liabilities intelligent management apapratus 1 in further embodiments
The plug-in type hard disk being equipped in equipment, such as asset-liabilities intelligent management apapratus 1, intelligent memory card (Smart Media Card,
SMC), secure digital (Secure Digital, SD) blocks, flash card (Flash Card) etc..Further, memory 11 may be used also
With the internal storage unit both including asset-liabilities intelligent management apapratus 1 or including External memory equipment.Memory 11 not only may be used
It is installed on the application software and Various types of data of asset-liabilities intelligent management apapratus 1 for storage, such as asset-liabilities are intelligently managed
The code etc. for managing program 01, can be also used for temporarily storing the data that has exported or will export.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 11
Code or processing data, such as execute asset-liabilities intelligent management program 01 etc..
Communication bus 13 is for realizing the connection communication between these components.
Network interface 14 optionally may include standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the device 1 and other electronic equipments.
Optionally, which can also include user interface, and user interface may include display (Display), defeated
Enter unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.It is optional
Ground, in some embodiments, display can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and OLED
(Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..Wherein, display can also be appropriate
Referred to as display screen or display unit, for being shown in the information handled in asset-liabilities intelligent management apapratus 1 and for showing
Visual user interface.
Fig. 2 illustrates only the asset-liabilities intelligent management with component 11-14 and asset-liabilities intelligent management program 01
Device 1, it will be appreciated by persons skilled in the art that structure shown in fig. 1 is not constituted to asset-liabilities intelligent management apapratus 1
Restriction, may include perhaps combining certain components or different component layouts than illustrating less perhaps more components.
In 1 embodiment of device shown in Fig. 2, asset-liabilities intelligent management program 01 is stored in memory 11；Processing
Device 12 realizes following steps when executing the asset-liabilities intelligent management program 01 stored in memory 11:
Step 1: source data layer receives business data and debt label, and to the business data and debt tag number
It is stored in database afterwards.
The business data of present pre-ferred embodiments includes number of applications, asset-liabilities data, the investment and financing amount of money, stock
Weigh alteration, wholesale special fund amount of flow, annual financial flash report, enterprise operation funds etc..The debt label is divided into just
Often profit and two kinds of labels of being in debt.The source data layer is a multilayer circulation nesting model, receive the business data and
Label.
Relational DBMS MySQL, the number can be used in the database of present pre-ferred embodiments building
Usable company name writes a Chinese character in simplified form plus the mode of numeric sorting, such as PA00001 mode.
The present invention preferably implements the source data layer and receives business data and debt label, and according to the class of business data
Type classifies to the business data, and the classification type includes patent, fixed assets, current assets and investment concerning foreign affairs.Further
Ground, after the source data layer inquires the current number of database, using next number of the current number as the classification
The number of business data and the debt label afterwards, the current number of such as source data layer inquiry database are PA89757,
Then next number can be referred to as PA89758 with query result according to the company name, and using the PA89758 as the enterprise
Industry data and debt tag number.Further, the source data layer marks the sorted business data and the debt
Label are stored in database.
Step 2: Data Integration layer according to the number, extracts the business data from the database, passes through the factor
Analysis model withdrawal of assets feature from the business data.
The Data Integration layer of present pre-ferred embodiments building includes data extraction layer and feature extraction layer, and the data mention
It takes layer according to the number, business data is extracted from Relational DBMS MySQL, and the business data is defeated
Enter to feature extraction layer.
Constructed feature extraction layer is using the business data as Factor Analysis Model in present pre-ferred embodiments
Input data and training, until when the maximization likelihood function value of the Factor Analysis Model is less than threshold value, the factorial analysis
Model exits training and exports assets feature.The Factor Analysis Model includes likelihood functionWith maximization likelihood
Two steps of function.
Further, likelihood function described in present pre-ferred embodimentsAccording to maximum likelihood estimate and p
(Xi, Zi) probability distribution, building μ, ∧,Likelihood function:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data number
Amount, p is probability function, Xi, ZiThe respectively described business data and the assets feature.
Further, present pre-ferred embodiments maximize likelihood function according to Jensen inequality, if function f (x) is
Convex function, then the expectation function of f (x) is greater than or equal to the expectation of function, and mathematic(al) representation is f (E [x])≤E [f (x)], because
This:
Wherein, according to Jensen inequality equal sign establishment condition, f (E [x])=E [f (x)] when x is constant.
Wherein Qi(Zi) be Jensen ineguality parameter value, therefore Qi(Zi) value are as follows:
Maximization likelihood function described in present pre-ferred embodiments is therefore are as follows:
Further, after the maximization likelihood function value of present pre-ferred embodiments is less than threshold value, the feature extraction layer
Training is exited, the extraction of assets feature is completed.
Step 3: the assets feature and the debt label are input to training in BP Neural Network network layers, until institute
When stating the loss function values of BP Neural Network network layers and meeting threshold requirement, the BP Neural Network network layers exit training.
BP Neural Network network layers described in present pre-ferred embodiments include input layer, hidden layer and output layer, the money
It produces feature and is input to the input layer of the BP Neural Network network layers, and the debt label is input in the loss function.
Further, BP Neural Network network layers described in present pre-ferred embodiments are according to the input layer data and described hidden
Hiding layer obtains trained values, and the trained values are input in the loss function.The loss function is according to the trained values
Penalty values are calculated with the debt label, and judge the size of the penalty values Yu the threshold value, until the penalty values are small
In the threshold value, the BP Neural Network network layers exit training.Wherein, the loss function is least square method, the loss
Value is L (e):
Wherein, e is the error amount of the trained values and the debt label, and k is the quantity of the assets feature, yiFor institute
State assets feature, y 'iFor the trained values, the threshold value is traditionally arranged to be 0.01.
Step 4: receiving the corporate debt inquiry instruction of user, the Data Integration layer and the BP Neural Network are utilized
Network layers carry out the calculating of corporate debt situation, export corporate debt result.
Present pre-ferred embodiments receive user corporate debt inquiry instruction, and to the corporate debt inquiry instruction into
Database accession number is inquired after row coding, the business data of the database accession number and debt label are input to the Data Integration
Layer and the BP Neural Network network layers carry out the calculating of corporate debt situation, export corporate debt result.
Optionally, in other embodiments, asset-liabilities intelligent management program can also be divided into one or more
Module, one or more module are stored in memory 11, and (the present embodiment is processor by one or more processors
12) performed to complete the present invention, the so-called module of the present invention is the series of computation machine program for referring to complete specific function
Instruction segment, for describing implementation procedure of the asset-liabilities intelligent management program in asset-liabilities intelligent management apapratus.
It is that the asset-liabilities in one embodiment of asset-liabilities intelligent management apapratus of the present invention are intelligent for example, referring to shown in Fig. 3
The program module schematic diagram of management program, in the embodiment, the asset-liabilities intelligent management program can be divided into source number
According to receiving module 10, characteristic extracting module 20, characteristics analysis module 30 and corporate debt object module 40, illustratively:
The source data receiving module 10 is used for: source data layer receives business data and debt label, and to the enterprise
It is stored in database after data and debt tag number.
The characteristic extracting module 20 is used for: Data Integration layer is according to the number, from the database described in extraction
Business data, by Factor Analysis Model from the business data withdrawal of assets feature.
The characteristics analysis module 30 is used for: the assets feature and the debt label are input to feedforward neural network
Training in layer, until the loss function value of the BP Neural Network network layers exits training when meeting threshold requirement.
The corporate debt object module 40 is used for: the corporate debt inquiry instruction of user is received, it is whole using the data
It closes layer and the BP Neural Network network layers carries out the calculating of corporate debt situation, export corporate debt result.
Above-mentioned source data receiving module 10, characteristic extracting module 20, characteristics analysis module 30 and corporate debt result mould
The program modules such as block 40 are performed realized functions or operations step and are substantially the same with above-described embodiment, no longer superfluous herein
It states.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with asset-liabilities intelligent management program, the asset-liabilities intelligent management program can be held by one or more processors
Row, to realize following operation:
Source data layer receives business data and debt label, and to being stored in number after the business data and debt tag number
According in library.
Data Integration layer extracts the business data according to the number from the database, passes through factorial analysis mould
Type withdrawal of assets feature from the business data.
The assets feature and the debt label are input to training in BP Neural Network network layers, until before described Godwards
When loss function value through network layer meets threshold requirement, the BP Neural Network network layers exit training.
The corporate debt inquiry instruction for receiving user is carried out using the Data Integration layer and the BP Neural Network network layers
Corporate debt situation calculates, and exports corporate debt result.
Computer readable storage medium specific embodiment of the present invention and above-mentioned asset-liabilities intelligent management apapratus and method
Each embodiment is essentially identical, does not make tired state herein.
It should be noted that the serial number of the above embodiments of the invention is only for description, do not represent the advantages or disadvantages of the embodiments.And
The terms "include", "comprise" herein or any other variant thereof is intended to cover non-exclusive inclusion, so that packet
Process, device, article or the method for including a series of elements not only include those elements, but also including being not explicitly listed
Other element, or further include for this process, device, article or the intrinsic element of method.Do not limiting more
In the case where, the element that is limited by sentence "including a ...", it is not excluded that including process, device, the article of the element
Or there is also other identical elements in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of asset-liabilities intelligent management, which is characterized in that the described method includes:
Business data and debt label are received by source data layer, and to being stored in number after the business data and debt tag number
According in library；
Using Data Integration layer according to the number, the business data is extracted from the database, passes through factorial analysis mould
Type withdrawal of assets feature from the business data；
The assets feature and the debt label are input to training in BP Neural Network network layers, until the BP Neural Network
When the loss function value of network layers meets preset threshold requirement, the BP Neural Network network layers exit training；
The corporate debt inquiry instruction for receiving user carries out enterprise using the Data Integration layer and the BP Neural Network network layers
Debt situation calculates, and exports corporate debt result.
2. asset-liabilities intelligent management as described in claim 1, which is characterized in that described received by source data layer is looked forward to
Industry data and debt label, and be stored in database to after the business data and debt tag number, comprising:
Business data and debt label are received, and is classified according to the type of business data to the business data；
After inquiring the current number of database, using next number of the current number as the sorted business data
And the number of the debt label；
The sorted business data and the debt label are input to database, and update the current volume of the database
Number.
3. asset-liabilities intelligent management as claimed in claim 2, which is characterized in that it is described using Data Integration layer according to
The number extracts the business data from the database, is extracted from the business data by Factor Analysis Model
Assets feature, comprising:
The current number for inquiring the database extracts the business data according to the number from the database；
Using the business data as the input data of Factor Analysis Model and the training Factor Analysis Model, until it is described because
When the maximization likelihood function value of sub- analysis model is less than threshold value, the Factor Analysis Model exits training and exports assets spy
Sign.
4. asset-liabilities intelligent management as claimed in claim 3, which is characterized in that the Factor Analysis Model includes seemingly
Right functionWith the maximization likelihood function, wherein the likelihood functionAre as follows:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data quantity, and p is
Probability function, Xi, ZiThe respectively described business data and the assets feature；
The maximization likelihood function are as follows:
Wherein Qi(Zi) be Jensen ineguality parameter value:
5. the asset-liabilities intelligent management as described in any one of Claims 1-4, which is characterized in that by the money
It produces feature and the debt label is input to training in BP Neural Network network layers, until the loss letter of the BP Neural Network network layers
When numerical value meets threshold requirement, the BP Neural Network network layers exit training, comprising:
The assets feature is input to the input layer of the BP Neural Network network layers, the debt label is input to the forward direction
In the loss function of neural net layer；
The BP Neural Network network layers are trained according to the input layer data and obtain trained values, and the trained values are defeated
Enter into the loss function；
By the loss function, penalty values are calculated according to the trained values and the debt label, and judge the loss
The size of value and the preset threshold, until the BP Neural Network network layers exit instruction when the penalty values are less than the threshold value
Practice.
6. a kind of asset-liabilities intelligent management apapratus, which is characterized in that described device includes memory and processor, the storage
The asset-liabilities intelligent management program that can be run on the processor, the asset-liabilities intelligent management program are stored on device
Following steps are realized when being executed by the processor:
Business data and debt label are received by source data layer, and to being stored in number after the business data and debt tag number
According in library；
Using Data Integration layer according to the number, the business data is extracted from the database, passes through factorial analysis mould
Type withdrawal of assets feature from the business data；
The assets feature and the debt label are input to training in BP Neural Network network layers, until the BP Neural Network
When the loss function value of network layers meets preset threshold requirement, the BP Neural Network network layers exit training；
The corporate debt inquiry instruction for receiving user carries out enterprise using the Data Integration layer and the BP Neural Network network layers
Debt situation calculates, and exports corporate debt result.
7. asset-liabilities intelligent management apapratus as claimed in claim 6, which is characterized in that described received by source data layer is looked forward to
Industry data and debt label, and be stored in database to after the business data and debt tag number, comprising:
Business data and debt label are received, and is classified according to the type of business data to the business data；
After inquiring the current number of database, using next number of the current number as the sorted business data
And the number of the debt label；
The sorted business data and the debt label are input to database, and update the current volume of the database
Number.
8. asset-liabilities intelligent management apapratus as claimed in claim 7, which is characterized in that it is described using Data Integration layer according to
The number extracts the business data from the database, is extracted from the business data by Factor Analysis Model
Assets feature, comprising:
The current number for inquiring the database extracts the business data according to the number from the database；
Using the business data as the input data of Factor Analysis Model and the training Factor Analysis Model, until it is described because
When the maximization likelihood function value of sub- analysis model is less than threshold value, the Factor Analysis Model exits training and exports assets spy
Sign.
9. asset-liabilities intelligent management apapratus as claimed in claim 8, which is characterized in that the Factor Analysis Model includes seemingly
Right functionWith the maximization likelihood function, wherein the likelihood functionAre as follows:
Wherein ∧ is transformation matrices, and μ is the mean value of Gaussian Profile,For the variance of Gaussian Profile, m is business data quantity, and p is
Probability function, Xi, ZiThe respectively described business data and the assets feature；
The maximization likelihood function are as follows:
Wherein Qi(Zi) be Jensen ineguality parameter value:
10. a kind of computer readable storage medium, which is characterized in that it is negative to be stored with assets on the computer readable storage medium
Debt intelligent management program, the asset-liabilities intelligent management program can be executed by one or more processor, to realize as weighed
Benefit require any one of 1 to 5 described in asset-liabilities intelligent management the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910525957.0A CN110415094A (en) | 2019-06-18 | 2019-06-18 | Asset-liabilities intelligent management, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910525957.0A CN110415094A (en) | 2019-06-18 | 2019-06-18 | Asset-liabilities intelligent management, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110415094A true CN110415094A (en) | 2019-11-05 |
Family
ID=68359312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910525957.0A Pending CN110415094A (en) | 2019-06-18 | 2019-06-18 | Asset-liabilities intelligent management, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415094A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506439A (en) * | 2020-12-16 | 2021-03-16 | 平安银行股份有限公司 | High-dimensional data storage method and device, electronic equipment and storage medium |
| CN115860925A (en) * | 2023-02-19 | 2023-03-28 | 广东德澳智慧医疗科技有限公司 | Intelligent data query and investment management system based on artificial intelligence liability |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022908A (en) * | 2016-05-17 | 2016-10-12 | 中国建设银行股份有限公司 | Method and system for querying information of assets and liabilities |
| CN107038256A (en) * | 2017-05-05 | 2017-08-11 | 平安科技（深圳）有限公司 | Business customizing device, method and computer-readable recording medium based on data source |
| CN107463953A (en) * | 2017-07-21 | 2017-12-12 | 上海交通大学 | Image classification method and system based on quality insertion in the case of label is noisy |
| CN109002942A (en) * | 2018-09-28 | 2018-12-14 | 河南理工大学 | A kind of short-term load forecasting method based on stochastic neural net |
| CN109214714A (en) * | 2018-10-16 | 2019-01-15 | 重庆金融资产交易所有限责任公司 | Asset-liabilities early warning analysis method, apparatus and computer readable storage medium |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
| CN109872188A (en) * | 2019-01-28 | 2019-06-11 | 平安科技（深圳）有限公司 | Assets suggest generation method, device, computer equipment and storage medium |
-
2019
- 2019-06-18 CN CN201910525957.0A patent/CN110415094A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022908A (en) * | 2016-05-17 | 2016-10-12 | 中国建设银行股份有限公司 | Method and system for querying information of assets and liabilities |
| CN107038256A (en) * | 2017-05-05 | 2017-08-11 | 平安科技（深圳）有限公司 | Business customizing device, method and computer-readable recording medium based on data source |
| CN107463953A (en) * | 2017-07-21 | 2017-12-12 | 上海交通大学 | Image classification method and system based on quality insertion in the case of label is noisy |
| CN109002942A (en) * | 2018-09-28 | 2018-12-14 | 河南理工大学 | A kind of short-term load forecasting method based on stochastic neural net |
| CN109214714A (en) * | 2018-10-16 | 2019-01-15 | 重庆金融资产交易所有限责任公司 | Asset-liabilities early warning analysis method, apparatus and computer readable storage medium |
| CN109829631A (en) * | 2019-01-14 | 2019-05-31 | 北京中兴通网络科技股份有限公司 | A kind of business risk early warning analysis method and system based on memory network |
| CN109872188A (en) * | 2019-01-28 | 2019-06-11 | 平安科技（深圳）有限公司 | Assets suggest generation method, device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 吴娜等: "上市公司资产结构与负债结构的财务预警模型研究", 《第六届（2011）中国管理学年会-会计与财务分会场论文集》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506439A (en) * | 2020-12-16 | 2021-03-16 | 平安银行股份有限公司 | High-dimensional data storage method and device, electronic equipment and storage medium |
| CN115860925A (en) * | 2023-02-19 | 2023-03-28 | 广东德澳智慧医疗科技有限公司 | Intelligent data query and investment management system based on artificial intelligence liability |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163476A (en) | Project intelligent recommendation method, electronic device and storage medium | |
| CN110349009B (en) | Multi-head lending default prediction method and device and electronic equipment | |
| CN110232114A (en) | Sentence intension recognizing method, device and computer readable storage medium | |
| CN110135687A (en) | Business risk assesses method for early warning, device and computer readable storage medium | |
| CN110135942A (en) | Products Show method, apparatus and computer readable storage medium | |
| CN112507936B (en) | Image information auditing method and device, electronic equipment and readable storage medium | |
| CN107784517A (en) | A kind of customer information screening method and terminal device | |
| CN110163204A (en) | Businessman's monitoring and managing method, device and storage medium based on image recognition | |
| CN113688923B (en) | Order abnormity intelligent detection method and device, electronic equipment and storage medium | |
| CN107203866A (en) | The processing method and device of order | |
| CN113626607B (en) | Abnormal work order identification method and device, electronic equipment and readable storage medium | |
| CN114265967A (en) | Sensitive data security level marking method and device | |
| CN110415094A (en) | Asset-liabilities intelligent management, device and computer readable storage medium | |
| CN114626731A (en) | Risk identification method and device, electronic equipment and computer readable storage medium | |
| CN110147540A (en) | Service security requirement documents generation method and system | |
| CN110059137A (en) | Transaction categorization system | |
| CN115730597A (en) | Multi-level semantic intention recognition method and related equipment thereof | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN113658002B (en) | Transaction result generation method and device based on decision tree, electronic equipment and medium | |
| CN113902569A (en) | Method for identifying the proportion of green assets in digital assets and related products | |
| CN106708869B (en) | Group data processing method and device | |
| CN116797098A (en) | Working quality assessment method, device, equipment and medium based on model training | |
| CN113705201B (en) | Text-based event probability prediction evaluation algorithm, electronic device and storage medium | |
| CN116342137A (en) | Client data recycling allocation method, device, computer equipment and storage medium | |
| CN107172311B (en) | Service evaluation method and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191105 |