CN118037455A - Financial data prediction method, device, equipment and storage medium thereof - Google Patents
Financial data prediction method, device, equipment and storage medium thereof Download PDFInfo
- Publication number
- CN118037455A CN118037455A CN202410194056.9A CN202410194056A CN118037455A CN 118037455 A CN118037455 A CN 118037455A CN 202410194056 A CN202410194056 A CN 202410194056A CN 118037455 A CN118037455 A CN 118037455A
- Authority
- CN
- China
- Prior art keywords
- quarter
- data
- month
- prediction
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 111
- 238000012545 processing Methods 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000009825 accumulation Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 12
- 125000004122 cyclic group Chemical group 0.000 claims description 10
- 230000000306 recurrent effect Effects 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 9
- 238000005096 rolling process Methods 0.000 abstract description 9
- 239000010410 layer Substances 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000002355 dual-layer Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the application belongs to the technical field of artificial intelligence, is applied to a financial data prediction scene of financial business, and relates to a financial data prediction method, a financial data prediction device, financial data prediction equipment and a storage medium thereof, wherein historical income and expense data are acquired; carrying out serialization treatment; inputting a quarter balance prediction model, and obtaining balance prediction data corresponding to the first month, the second month and the last month of the quarter in the target quarter respectively; acquiring a summary calculation result; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
Description
Technical Field
The application relates to the technical field of artificial intelligence, and is applied to a financial business data prediction scene, in particular to a financial data prediction method, a financial business data prediction device, financial business data prediction equipment and a financial business data storage medium.
Background
With the rapid development of the internet, various industries seek industry breakthrough points by relying on the internet, and in recent years, the financial industry is expanding online business around the internet. Because the financial industry involves a large amount of traffic and data, the financial products are continuously updated in category as the demand of users for products is continuously increased.
At present, a large amount of payment of a group company and subordinate units is concentrated at the end of a month, the end of a season and the end of a year, and a large amount of payment business is concentrated at the end of the month, the end of the season and the end of the year for payment. Then, at the end of the month, the end of the season, and the end of the year, sufficient funds need to be prepared to satisfy the business's payment business. In order to solve the problem, the current financing budgeting method of group companies and subordinate units is as follows: annual financing budgets are compiled at the beginning of the year, and monthly and quarterly financing budgets are manually filled in at the beginning of the month and Ji Chushi. Month, quarter and year financing budgets are respectively compiled, lack of correlation between data and lack of effective data support in annual adjustment of the year financing budgets. The existing financing budget planning method lacks accuracy and scientificity, and can greatly influence the financing decision of the company, thereby being unfavorable for scientifically carrying out the financing decision of the company.
Disclosure of Invention
The embodiment of the application aims to provide a financial data prediction method, a device, equipment and a storage medium thereof, which are used for solving the problems that in the existing financing budget planning method, monthly, quarterly and annual financing budgets are respectively planned, the correlation among data is lacked, the accuracy and the scientificity cannot be ensured, the financing decision of a company is influenced to a great extent, and the scientifically carried out financing decision of the company is not facilitated.
In order to solve the above technical problems, the embodiment of the present application provides a financial data prediction method, which adopts the following technical scheme:
A financial data prediction method, comprising the steps of:
acquiring historical income and expenditure data filled by a target business department according to month dimension and business type dimension;
Carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively;
inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model;
performing summary calculation based on the balance prediction data and a preset prediction updating mechanism to obtain a summary calculation result;
And determining the state of the target quarter fund flow according to the summarized calculation result and the preset identification condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the target quarter fund flow is in shortage.
Further, after performing the step of obtaining the historical revenue and expense data filled by the target business segment according to the month dimension and the business type dimension, the method further includes:
identifying the historical income and expenditure data according to different data field contents, and respectively identifying the historical income data and the historical expenditure data;
Importing the identified historical income data into a pre-constructed collection settlement pool in form according to month dimension and business type dimension;
And importing the identified historical expenditure data into a pre-constructed payment settlement pool in form according to month dimension and business type dimension.
Further, the step of serializing the historical revenue and expenditure data corresponding to all the service types based on the month dimension to obtain the serialized historical revenue data and the serialized historical expenditure data corresponding to all the service types respectively specifically includes:
Taking a preset quarter as a target quarter;
Sequentially acquiring historical income data of N months before the target quarter from the collection settlement pool according to the month sequence, wherein N is a positive integer;
Sequentially acquiring historical expenditure data of N months before the target quarter from the payment settlement pool according to a month sequence, wherein N is a positive integer;
performing dimension splitting on the first serialized data according to the service type dimension to obtain the serialized historical income data;
And dimension splitting is carried out on the second serialized data according to the service type dimension, so that the serialized historical expenditure data is obtained.
Further, the step of determining the state of the target quarter fund flow according to the summary calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the target quarter fund flow is in shortage specifically includes:
judging the fund flow state of the target quarter according to the summarized calculation result and a preset identification condition;
when the fund flow state of the target quarter is sufficient, directly acquiring the summarized calculation result, and marking the target quarter by adopting a distinguishing mark;
and when the state of the target quarter fund flow is in shortage, inputting the summarized calculation result into a preset quarter financing budget model, acquiring the financing budget result output by the quarter financing budget model, and generating a financial data financing prediction report according to the financing budget result.
Further, the preset quarter balance prediction model is a GRU model based on a double-layer cyclic neural network, and the steps of inputting the serialized historical income data and the serialized historical expense data into the preset quarter balance prediction model to obtain balance prediction data corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model specifically include:
step 301, inputting the serialized historical revenue data into a first layer of cyclic neural network of the quarter balance prediction model, and obtaining revenue prediction data of a quarter first month in the target quarter;
Step 302, adding the income prediction data of the first month of the quarter in the target quarter to the sequence tail of the serialized historical income data to generate the latest serialized income data;
step 303, inputting the serialized historical expense data into a second-layer recurrent neural network of the quarter expense prediction model to obtain expense prediction data of a quarter first month in the target quarter;
Step 304, adding the payout prediction data of the first month of the quarter of the target quarter to the sequence tail of the serialized historical payout data to generate the latest serialized payout data;
Step 305, updating the latest serialized revenue data into the serialized historical revenue data, and circularly executing steps 301 to 302 twice by using the updated serialized historical revenue data to obtain revenue prediction data corresponding to the quarter next month and the quarter last month in the target quarter;
Step 306, updating the latest serialized expense data into the serialized historical expense data, and circularly executing the steps 303 to 304 twice by using the updated serialized historical expense data to obtain expense prediction data corresponding to the quarter next month and the quarter final month in the target quarter;
Step 307, integrating the income prediction data and the expenditure prediction data of the first quarter month in the target quarter as the expense prediction data of the first quarter month in the target quarter; integrating the income prediction data and the expenditure prediction data of the quarter next month in the target quarter as the expense prediction data of the quarter next month in the target quarter; and integrating income prediction data and expenditure prediction data of the final month of the quarter in the target quarter as expense prediction data of the final month of the quarter in the target quarter.
Further, the summary calculation result includes a quarter initial summary calculation result, a quarter middle summary calculation result, and a quarter end summary calculation result, and the step of performing summary calculation based on the balance prediction data and a preset prediction update mechanism to obtain a summary calculation result specifically includes:
accumulating revenue prediction data of first month of quarter, second month of quarter and last month of quarter in the target quarter as first prediction data of quarter revenue;
Accumulating the first quarter month, the second quarter month and the last quarter month of the target quarter as first quarter expense prediction data;
Integrating the first prediction data of quarter income and the first prediction data of quarter expenditure to generate the initial summary calculation result of the quarter;
obtaining actual income data and actual expenditure data of the first month of the target quarter of the current year;
Accumulating the actual income data of the first month of the quarter, the income prediction data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of the income of the quarter;
Accumulating the actual expenditure data of the first month of the quarter, the expenditure prediction data of the next month of the quarter and the expenditure prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of expenditure of the quarter;
Integrating the quarter income second prediction data and the quarter expenditure second prediction data to generate a quarter mid-term summarization calculation result;
obtaining actual income data and actual expenditure data of the next month of the quarter in the target quarter of the current year;
accumulating the actual income data of the first month of the quarter, the actual income data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of the income of the quarter;
accumulating the actual expenditure data of the first month of the quarter, the actual expenditure data of the next month of the quarter and the expenditure prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of expenditure of the quarter;
And integrating the third prediction data of quarter income and the third prediction data of quarter expenditure to generate the summary calculation result of the end of quarter.
Further, the step of judging the state of the fund flow of the target quarter according to the summary calculation result and the preset recognition condition specifically includes:
Comparing the magnitude relation between the first prediction data of the quarter income and the first prediction data of the quarter expenditure according to the initial summary calculation result of the quarter;
determining that the state of the funds flow is sufficient at the initial stage of the target quarter if the first prediction data of quarter income exceeds the first prediction data of quarter expenditure;
if the quarter income first prediction data does not exceed the quarter expenditure first prediction data, determining that the fund flow state at the initial stage of the target quarter is a shortage;
comparing the magnitude relation between the quarter income second prediction data and the quarter expenditure second prediction data according to the quarter mid-term summarization calculation result;
If the quarter income second prediction data exceeds the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is sufficient;
if the quarter income second prediction data does not exceed the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is a shortage;
comparing the magnitude relation of the third prediction data of the quarter income with the third prediction data of the quarter expenditure according to the summary calculation result of the end of the quarter;
If the quaternary income third prediction data exceeds the quaternary expenditure third prediction data, determining that the fund flow state of the target end of the quarter is sufficient;
and if the third prediction data of quarter income does not exceed the third prediction data of quarter expenditure, determining that the state of the fund flow at the end of the target quarter is a shortage.
Further, the financing budget result includes financing time and financing amount, and the step of inputting the summarized calculation result into a preset quarter financing budget model to obtain the financing budget result output by the quarter financing budget model specifically includes:
analyzing the summarized calculation results according to the quarter financing budget model to obtain analysis results;
If the fund flow state at the initial stage of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between the first prediction data of the quarter income and the first prediction data of the quarter expenditure based on the calculation result of the initial stage of the quarter, setting the difference value as a minimum financing amount, and setting the last month of the quarter of the last quarter before the target quarter as the final financing time;
If the state of the fund flow in the middle of the target quarter is recognized to be a shortage based on the analysis result, calculating a difference value between second prediction data of quarter income and second prediction data of quarter expenditure based on the calculation result of mid-quarter summarization, setting the difference value as a minimum financing amount, and setting the first month in the target quarter as a final financing time;
If the fund flow state at the end of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between third prediction data of the quarter income and third prediction data of the quarter expenditure based on the summary calculation result of the end of the quarter, setting the difference value as a minimum financing amount, and setting the second month in the target quarter as a final financing time;
and outputting corresponding minimum financing amount and final financing time as the financing budget result through the quarter financing budget model.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
According to the financial data prediction method, historical income expense data filled by a target business department according to month dimension and business type dimension is obtained; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a financial data prediction method in accordance with the present application;
FIG. 3 is a flow chart of one embodiment of step 203 shown in FIG. 2;
FIG. 4 is a flow chart of one embodiment of step 204 shown in FIG. 2;
FIG. 5 is a schematic diagram illustrating the construction of one embodiment of a financial data prediction apparatus in accordance with the present application;
FIG. 6 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture ExpertsGroup Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving PictureExperts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the method for predicting financial data provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the apparatus for predicting financial data is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of a financial data prediction method in accordance with the present application is shown. The financial data prediction method comprises the following steps:
step 201, obtaining historical income and expense data filled by a target business department according to a month dimension and a business type dimension.
In this embodiment, before executing the step of obtaining the historical revenue and expense data filled by the target business department according to the month dimension and the business type dimension, the method further includes: the front-end filling input system of the business department plus the business type dimension plus the month dimension is constructed in advance, each business department subordinate to the company is respectively used as a target business department, and the front-end filling system is used for filling the historical income expenditure data of the department according to the month dimension and the business type dimension.
Through pre-constructing a front-end filling input system of a business department plus a business type dimension plus a month dimension, each business department subordinate to a company is respectively used as a target business department, and the front-end filling system is used for filling the historical income expense data of the department according to the month dimension and the business type dimension, so that a data receiving cache party is facilitated, and the historical income expense data is scientifically received and arranged.
In this embodiment, the front-end filling input system may further include: the target business department performs the historical income and expense data prediction and report, the target business department performs the next annual income and expense financial data prediction and report, the upper audit department performs a hierarchical approval mechanism for predicting and auditing information, the historical income and expense data can be obtained if the approval is passed, the target business department performs the next annual income and expense financial data prediction and report data, and the target business department cannot obtain the historical income and expense data which is reported by the target business department according to the month dimension and the business type dimension if the approval is not passed.
In this embodiment, the step of obtaining the historical revenue and expenditure data filled by the target service department according to the month dimension and the service type dimension specifically includes: outputting the historical income and expense data filled by the target business department according to the month dimension and the business type dimension into a preset storage form for caching, wherein the preset storage form at least comprises a month dimension field column, a business type dimension field column and a historical income and expense data writing column.
The historical income and expense data filled by the target business department according to the month dimension and the business type dimension are output into a preset storage form to be cached, so that the historical income and expense data can be reused later.
In this embodiment, after the step of obtaining the historical revenue and expense data filled by the target business department according to the month dimension and the business type dimension is performed, the method further includes: identifying the historical income and expenditure data according to different data field contents, and respectively identifying the historical income data and the historical expenditure data; importing the identified historical income data into a pre-constructed collection settlement pool in form according to month dimension and business type dimension; and importing the identified historical expenditure data into a pre-constructed payment settlement pool in form according to month dimension and business type dimension.
The collection settlement pool and the payment settlement pool which are constructed in advance are convenient for classifying and caching the historical income data and the historical expenditure data, so that the historical income data and the historical expenditure data are mutually and separately processed, the historical income expenditure data are prevented from being mixed together, and the consumption of calculation and processing resources is reduced as much as possible.
Step 202, performing serialization processing on the historical income expense data corresponding to all the service types based on the month dimension, and obtaining the serialized historical income data and the serialized historical expense data corresponding to all the service types respectively.
By carrying out serialization processing on the historical income expense data corresponding to all the business types, the serialized historical income data and the historical expense data which are arranged according to the month sequence are obtained, so that the subsequent data processing by adopting a corresponding serialized data processing model is facilitated, and the processing capability of the serialized data processing model is more suitable.
In this embodiment, the step of serializing the historical revenue and expenditure data corresponding to all the service types based on the month dimension to obtain the serialized historical revenue data and the serialized historical expenditure data corresponding to all the service types respectively includes: taking a preset quarter as a target quarter; sequentially acquiring historical income data of N months before the target quarter from the collection settlement pool according to the month sequence, wherein N is a positive integer; sequentially acquiring historical expenditure data of N months before the target quarter from the payment settlement pool according to a month sequence, wherein N is a positive integer; performing dimension splitting on the first serialized data according to the service type dimension to obtain the serialized historical income data; and dimension splitting is carried out on the second serialized data according to the service type dimension, so that the serialized historical expenditure data is obtained.
Firstly, the historical income data of N months before the target quarter is sequentially obtained from the collection settlement pool according to the month sequence, and as the first serialization data, the N value can be freely set by the management end according to the actual target quarter, for example: the target quarter is a fourth quarter, and N is8, then 8 months before the fourth quarter in the current year, namely, historical revenue data of 2 months, 3 months, 4 months, 5 months, 6 months, 7 months, 8 months and 9 months in the same year are obtained, and are sequentially sorted according to the month order to obtain the first serialized data, then dimension splitting is performed on the first serialized data according to the dimension of the service type, and the first serialized data is split into serialized revenue data of four types of revenue service provided that the revenue corresponds to 4 types of service types, such as sales commodity revenue, service revenue and other business revenue; similarly, the historical payout data of N months before the target quarter is sequentially obtained from the payment settlement pool according to the month order as the second serialized data, and then, it is assumed that there are at least 8 types of corresponding business types for payout, for example: material purchasing expenditures, management consultation expenditures, research development expenditures, wage expenditures, social insurance expenditures, housing public accumulation expenditures, employee welfare expenditures, and conviction expenditures, splitting the second serialized data into serialized expenditures data of eight expense business types.
Furthermore, the value of N may also be determined by a functional relationship, such as: identifying the target quarter as the Kth quarter of the year, wherein the K is a positive integer from 2 to 4, and according to a preset functional relation: and determining the value of N to be 3× (K-1), wherein when the value of N is 2, N is 3, namely, the historical income data and the historical expense data of 3 months before the second quarter of the current year are obtained, and similarly, when the value of K is 3, N is 6, namely, the historical income data and the historical expense data of 6 months before the third quarter of the current year are obtained, and similarly, when the value of K is 4, N is 9, namely, the historical income data and the historical expense data of 9 months before the fourth quarter of the current year are obtained.
The historical income expense data corresponding to all the service types are subjected to serialization processing to obtain the serialized historical income data and the historical expense data which are arranged according to the month sequence, and then the first serialized data and the second serialized data are subjected to dimension splitting according to the dimension of the service types, so that the data processing is conveniently carried out by adopting a corresponding serialized data processing model, and the processing capability of the serialized data processing model is more suitable.
And 203, inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model.
In this embodiment, the preset quarter balance prediction model is a GRU model based on a dual-layer cyclic neural network, because the serialized data corresponding to the historical income data and the historical expenditure data respectively need to be processed at the same time, the dual-layer cyclic neural network is considered to be introduced, that is, one layer of cyclic neural network, that is, the first layer of cyclic neural network processes the serialized data corresponding to the historical income data independently, and the other layer of cyclic neural network, that is, the second layer of cyclic neural network processes the serialized data corresponding to the historical expenditure data independently.
With continued reference to fig. 3, fig. 3 is a flow chart of one embodiment of step 203 shown in fig. 2, comprising:
step 301, inputting the serialized historical revenue data into a first layer of cyclic neural network of the quarter balance prediction model, and obtaining revenue prediction data of a quarter first month in the target quarter;
Step 302, adding the income prediction data of the first month of the quarter in the target quarter to the sequence tail of the serialized historical income data to generate the latest serialized income data;
step 303, inputting the serialized historical expense data into a second-layer recurrent neural network of the quarter expense prediction model to obtain expense prediction data of a quarter first month in the target quarter;
Step 304, adding the payout prediction data of the first month of the quarter of the target quarter to the sequence tail of the serialized historical payout data to generate the latest serialized payout data;
Step 305, updating the latest serialized revenue data into the serialized historical revenue data, and circularly executing steps 301 to 302 twice by using the updated serialized historical revenue data to obtain revenue prediction data corresponding to the quarter next month and the quarter last month in the target quarter;
Step 306, updating the latest serialized expense data into the serialized historical expense data, and circularly executing the steps 303 to 304 twice by using the updated serialized historical income data to obtain expense prediction data corresponding to the quarter next month and the quarter last month in the target quarter respectively;
Step 307, integrating the income prediction data and the expenditure prediction data of the first quarter month in the target quarter as the expense prediction data of the first quarter month in the target quarter; integrating the income prediction data and the expenditure prediction data of the quarter next month in the target quarter as the expense prediction data of the quarter next month in the target quarter; and integrating income prediction data and expenditure prediction data of the final month of the quarter in the target quarter as expense prediction data of the final month of the quarter in the target quarter.
Because month financial data are adopted to predict quarter data, when target quarter income and expense financial data are predicted, firstly, income data and expense data of a target quarter first month are predicted in sequence according to month dimension, then, the income data and expense data of the target quarter first month are used as update data, corresponding serialized income data and serialized expense data are updated, income data and expense data of a target quarter next month are predicted, and then, the serialized income data and the serialized expense data are updated again to predict income data and expense data of a target quarter last month, and the income and expense financial data of the target quarter are predicted and converted into income and expense financial data of the target quarter first month, the income and expense financial data of the target quarter last month are predicted, so that the prediction dimension of the income and expense financial data of the target quarter is lower, and the prediction result is more accurate.
And 204, performing summary calculation based on the balance prediction data and a preset prediction updating mechanism, and obtaining a summary calculation result.
In this embodiment, the summary calculation results include a quarter initial summary calculation result, a quarter middle summary calculation result, and a quarter end summary calculation result.
With continued reference to fig. 4, fig. 4 is a flow chart of one embodiment of step 204 shown in fig. 2, comprising:
wherein referring to fig. 4, 4a shows the generation of the quaternary early summary calculation results through steps 401, 402 and 403,
Step 401, accumulating income prediction data of first month of quarter, second month of quarter and last month of quarter in the target quarter as first prediction data of income of quarter;
step 402, accumulating the first quarter month, the second quarter month and the last quarter month of the target quarter as first quarter expense prediction data;
Step 403, integrating the first prediction data of quarter income and the first prediction data of quarter expenditure to generate the initial summary calculation result of quarter;
And when the quarter initial summary calculation result is generated, the income prediction data and the expenditure prediction data of the first month, the second month and the last month of the quarter in the target quarter predicted in the step 203 are directly adopted to integrate the quarter initial summary calculation result, so that the overall prediction of the income expenditure of the whole target quarter is ensured when the target quarter is in the initial stage.
Wherein referring to fig. 4b, the mid-quarter summary calculation is shown as being generated by steps 404, 405, 406 and 407,
Step 404, obtaining actual income data and actual expense data of a quarter first month in the target quarter of the current year;
Step 405, accumulating the actual income data of the first month of the quarter, the income prediction data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of the income of the quarter;
Step 406, accumulating the actual expenditure data of the first month of the quarter, the expenditure prediction data of the next month of the quarter and the expenditure prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of expenditure of the quarter;
step 407, integrating the quarter income second prediction data and the quarter expenditure second prediction data to generate the quarter mid-term summary calculation result;
and introducing actual income data and actual expenditure data of a first month of a quarter in the target quarter of the current year to carry out expansion prediction in the next month of the target quarter, integrating the mid-quarter summarization calculation result, and ensuring that the income expenditure in the mid-quarter is predicted in stages in the mid-quarter.
Wherein referring to fig. 4, 4c, the generation of the end-of-quarter summary calculation is shown by steps 408, 409, 410 and 411,
Step 408, obtaining actual income data and actual expense data of the next month of the quarter in the target quarter of the current year;
Step 409, accumulating the actual income data of the first month of the quarter, the actual income data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of income of the quarter;
Step 410, accumulating the actual expense data of the first month of the quarter, the actual expense data of the next month of the quarter and the expense prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of the expense of the quarter;
step 411, integrating the third prediction data of quarter income and the third prediction data of quarter expenditure to generate the summary calculation result of the end of quarter.
And introducing actual income data and actual expenditure data of the second month of the target quarter in the current year again to carry out expansion prediction at the last month of the target quarter, integrating the summary calculation result of the final stage of the quarter, and ensuring that the income expenditure of the final stage of the target quarter is predicted in stages when the final stage of the target quarter.
In essence, the preset prediction updating mechanism combines the actual income data and the actual expense data of each month in the target quarter of the year, performs month rolling update prediction, and introduces the prediction updating mechanism, so that the prediction result can be combined with the historical income expense data of the previous N months, and can also be combined with the actual income expense data of the appointed month of the target quarter of the year, and the prediction result is more scientific and has referential property.
Step 205, determining the state of the target quarter fund flow according to the summary calculation result and the preset identification condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the target quarter fund flow is in shortage.
In addition, annual financial data financing prediction reports can be generated according to the financing budget results corresponding to each quarter in the year, and the quarternary or annual financial data financing prediction reports are sent to the target receiving end.
Specifically, firstly, judging the state of the fund flow of the target quarter according to the summarized calculation result and a preset identification condition;
in this embodiment, the step of determining the state of the fund flow in the target quarter according to the summary calculation result and the preset identification condition includes:
Comparing the magnitude relation between the first prediction data of the quarter income and the first prediction data of the quarter expenditure according to the initial summary calculation result of the quarter; determining that the state of the funds flow is sufficient at the initial stage of the target quarter if the first prediction data of quarter income exceeds the first prediction data of quarter expenditure; if the quarter income first prediction data does not exceed the quarter expenditure first prediction data, determining that the fund flow state at the initial stage of the target quarter is a shortage;
Comparing the magnitude relation between the quarter income second prediction data and the quarter expenditure second prediction data according to the quarter mid-term summarization calculation result; if the quarter income second prediction data exceeds the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is sufficient; if the quarter income second prediction data does not exceed the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is a shortage;
Comparing the magnitude relation of the third prediction data of the quarter income with the third prediction data of the quarter expenditure according to the summary calculation result of the end of the quarter; if the quaternary income third prediction data exceeds the quaternary expenditure third prediction data, determining that the fund flow state of the target end of the quarter is sufficient; and if the third prediction data of quarter income does not exceed the third prediction data of quarter expenditure, determining that the state of the fund flow at the end of the target quarter is a shortage.
By means of comparison, whether a fund flow gap is generated at the initial stage of the target quarter, the middle stage of the target quarter and the final stage of the target quarter is respectively identified, so that financing can be timely carried out when the fund flow gap is predicted to be generated, financial dilemma caused by the target quarter is avoided, and financial loss of a company is reduced as much as possible.
And then, when the state of the fund flow in the target quarter is sufficient, directly acquiring the summarized calculation result, and marking the target quarter by adopting a distinguishing mark, wherein the state of the fund flow in the initial stage of the target quarter is sufficient, the state of the fund flow in the middle stage of the target quarter is sufficient, and the state of the fund flow in the final stage of the target quarter is sufficient, and the distinguishing mark can be used for displaying the target quarter by adopting a receiving interface of a distinguishing color or dynamic text at the receiving end of the target quarter.
And when the state of the target quarter fund flow is in shortage, inputting the summarized calculation result into a preset quarter financing budget model, acquiring the financing budget result output by the quarter financing budget model, and generating a financial data financing prediction report according to the financing budget result.
In this embodiment, the financing budget result includes a financing time and a financing amount.
In this embodiment, the quarter financing budget model is a preset accounting statistical model capable of analyzing the summary calculation result based on a month dimension and a business type dimension, and the accounting statistical model is capable of performing summation operation and difference operation on actual expense data, expense prediction data, actual income data and income prediction data corresponding to all months and all business types in a target quarter, so as to calculate differences of income prediction data and expense prediction data corresponding to the initial stage of the target quarter, the middle stage of the target quarter and the final stage of the target quarter, and identify fund flow states of the initial stage of the target quarter, the middle stage of the target quarter and the final stage of the target quarter according to the differences.
In this embodiment, the step of inputting the summary calculation result into a preset quarter financing budget model and obtaining the financing budget result output by the quarter financing budget model specifically includes: analyzing the summarized calculation results according to the quarter financing budget model to obtain analysis results; if the fund flow state at the initial stage of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between the first prediction data of the quarter income and the first prediction data of the quarter expenditure based on the calculation result of the initial stage of the quarter, setting the difference value as a minimum financing amount, and setting the last month of the quarter of the last quarter before the target quarter as the final financing time; if the state of the fund flow in the middle of the target quarter is recognized to be a shortage based on the analysis result, calculating a difference value between second prediction data of quarter income and second prediction data of quarter expenditure based on the calculation result of mid-quarter summarization, setting the difference value as a minimum financing amount, and setting the first month in the target quarter as a final financing time; if the fund flow state at the end of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between third prediction data of the quarter income and third prediction data of the quarter expenditure based on the summary calculation result of the end of the quarter, setting the difference value as a minimum financing amount, and setting the second month in the target quarter as a final financing time; and outputting corresponding minimum financing amount and final financing time as the financing budget result through the quarter financing budget model.
And finally, outputting corresponding minimum financing amount and final financing time according to the quarter financing budget model, generating a financial data financing prediction report, and sending the financial data financing prediction report to a target receiving end.
In this embodiment, the first quarter, the second quarter, the third quarter and the fourth quarter in the target year may be sequentially used as the target quarters, and the financial data financing prediction report corresponding to each quarter in the target year is predicted, and combined with the financial data financing prediction report corresponding to each quarter in the target year, the annual financial data financing prediction report is generated, so that a company financing decision-making department or a person can make an annual financing decision, and by using the month dimension and combining with a month rolling update mechanism, a dynamic financing budget is introduced into the quarter balance prediction model and the quarter financing budget model, so that the month, the quarter and the annual financing budget are compiled according to the data association, and the company can be more scientized and accurate to make the financing decision.
The application obtains the historical income and expenditure data filled by the target business department according to the month dimension and the business type dimension; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
In the embodiment of the application, the historical income expense data filled by a target business department according to the month dimension and the business type dimension is obtained; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
With further reference to fig. 5, as an implementation of the method shown in fig. 2 described above, the present application provides an embodiment of a financial data prediction apparatus, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 5, the financial data prediction apparatus 500 according to the present embodiment includes: a historical data acquisition module 501, a serialization processing module 502, a quarter balance prediction module 503, a summary calculation module 504, and a financing budget module 505. Wherein:
a historical data obtaining module 501, configured to obtain historical income and expenditure data filled by a target service department according to a month dimension and a service type dimension;
the serialization processing module 502 is configured to perform serialization processing on the historical revenue and expenditure data corresponding to all the service types based on the month dimension, so as to obtain serialized historical revenue data and serialized historical expenditure data corresponding to all the service types respectively;
a quarter balance prediction module 503, configured to input the serialized historical revenue data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtain balance prediction data corresponding to a first quarter month, a second quarter month, and a last quarter month in a target quarter output by the quarter balance prediction model;
the summary calculation module 504 is configured to perform summary calculation based on the balance prediction data and a preset prediction update mechanism, and obtain a summary calculation result;
And the financing budget module 505 is configured to determine a state of the target quarter of the fund flow according to the summary calculation result and a preset identification condition, and combine a preset quarter financing budget model to generate a financial data financing prediction report when the state of the target quarter of the fund flow is a shortage.
The application obtains the historical income and expenditure data filled by the target business department according to the month dimension and the business type dimension; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by computer readable instructions, stored on a computer readable storage medium, that the program when executed may comprise the steps of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 6, fig. 6 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 6 comprises a memory 6a, a processor 6b, a network interface 6c communicatively connected to each other via a system bus. It should be noted that only a computer device 6 having components 6a-6c is shown in the figures, but it should be understood that not all of the illustrated components need be implemented, and that more or fewer components may alternatively be implemented. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 6a includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 6a may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 6a may also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 6. Of course, the memory 6a may also comprise both an internal memory unit of the computer device 6 and an external memory device. In this embodiment, the memory 6a is typically used to store an operating system and various application software installed on the computer device 6, such as computer readable instructions of a financial data prediction method. Further, the memory 6a may also be used to temporarily store various types of data that have been output or are to be output.
The processor 6b may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 6b is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is configured to execute computer readable instructions stored in the memory 6a or process data, such as computer readable instructions for executing the financial data prediction method.
The network interface 6c may comprise a wireless network interface or a wired network interface, which network interface 6c is typically used to establish a communication connection between the computer device 6 and other electronic devices.
The computer equipment provided by the embodiment belongs to the technical field of artificial intelligence and is applied to financial business financial data prediction scenes. The application obtains the historical income and expenditure data filled by the target business department according to the month dimension and the business type dimension; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by a processor to cause the processor to perform the steps of the financial data prediction method as described above.
The computer readable storage medium provided by the embodiment belongs to the technical field of artificial intelligence and is applied to financial business financial data prediction scenes. The application obtains the historical income and expenditure data filled by the target business department according to the month dimension and the business type dimension; carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively; inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model; summarizing calculation is carried out based on the balance prediction data and a preset prediction updating mechanism, and a summarizing calculation result is obtained; and determining the state of the fund flow of the target quarter according to the summarized calculation result and the preset recognition condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the fund flow of the target quarter is in shortage. Based on month dimension, dynamic financing budget is carried out by combining a month rolling updating mechanism, and a quarter balance prediction model and a quarter financing budget model are introduced, so that month, quarter and year financing budget is compiled according to data relevance, and a company is helped to carry out financing decision more scientifically and accurately.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (11)
1. A method of predicting financial data, comprising the steps of:
acquiring historical income and expenditure data filled by a target business department according to month dimension and business type dimension;
Carrying out serialization processing on the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively;
inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model, and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model;
performing summary calculation based on the balance prediction data and a preset prediction updating mechanism to obtain a summary calculation result;
And determining the state of the target quarter fund flow according to the summarized calculation result and the preset identification condition, and generating a financial data financing prediction report by combining a preset quarter financing budget model when the state of the target quarter fund flow is in shortage.
2. The financial data prediction method according to claim 1, wherein after performing the step of acquiring the historical revenue and expense data filled by the target business segment in terms of the month dimension and the business type dimension, the method further comprises:
identifying the historical income and expenditure data according to different data field contents, and respectively identifying the historical income data and the historical expenditure data;
Importing the identified historical income data into a pre-constructed collection settlement pool in form according to month dimension and business type dimension;
And importing the identified historical expenditure data into a pre-constructed payment settlement pool in form according to month dimension and business type dimension.
3. The financial data prediction method according to claim 2, wherein the step of serializing the historical revenue and expenditure data corresponding to all the business types based on the month dimension to obtain the serialized historical revenue and expenditure data corresponding to all the business types respectively specifically comprises:
Taking a preset quarter as a target quarter;
Sequentially acquiring historical income data of N months before the target quarter from the collection settlement pool according to the month sequence, wherein N is a positive integer;
Sequentially acquiring historical expenditure data of N months before the target quarter from the payment settlement pool according to a month sequence, wherein N is a positive integer;
performing dimension splitting on the first serialized data according to the service type dimension to obtain the serialized historical income data;
And dimension splitting is carried out on the second serialized data according to the service type dimension, so that the serialized historical expenditure data is obtained.
4. The financial data prediction method according to claim 1, wherein the step of determining the state of the target quarter of the fund flow according to the summary calculation result and the preset recognition condition, and generating the financial data financing prediction report by combining with a preset quarter financing budget model when the state of the target quarter of the fund flow is in shortage specifically comprises:
judging the fund flow state of the target quarter according to the summarized calculation result and a preset identification condition;
when the fund flow state of the target quarter is sufficient, directly acquiring the summarized calculation result, and marking the target quarter by adopting a distinguishing mark;
and when the state of the target quarter fund flow is in shortage, inputting the summarized calculation result into a preset quarter financing budget model, acquiring the financing budget result output by the quarter financing budget model, and generating a financial data financing prediction report according to the financing budget result.
5. The financial data prediction method according to claim 4, wherein the predetermined quarter balance prediction model is a GRU model based on a two-layer recurrent neural network, and the step of inputting the serialized historical income data and the serialized historical expense data into the predetermined quarter balance prediction model to obtain the balance prediction data corresponding to the first month, the second month and the last month of the quarter in the target quarter output by the quarter balance prediction model specifically includes:
step 301, inputting the serialized historical revenue data into a first layer of cyclic neural network of the quarter balance prediction model, and obtaining revenue prediction data of a quarter first month in the target quarter;
Step 302, adding the income prediction data of the first month of the quarter in the target quarter to the sequence tail of the serialized historical income data to generate the latest serialized income data;
step 303, inputting the serialized historical expense data into a second-layer recurrent neural network of the quarter expense prediction model to obtain expense prediction data of a quarter first month in the target quarter;
Step 304, adding the payout prediction data of the first month of the quarter of the target quarter to the sequence tail of the serialized historical payout data to generate the latest serialized payout data;
Step 305, updating the latest serialized revenue data into the serialized historical revenue data, and circularly executing steps 301 to 302 twice by using the updated serialized historical revenue data to obtain revenue prediction data corresponding to the quarter next month and the quarter last month in the target quarter;
Step 306, updating the latest serialized expense data into the serialized historical expense data, and circularly executing the steps 303 to 304 twice by using the updated serialized historical expense data to obtain expense prediction data corresponding to the quarter next month and the quarter final month in the target quarter;
Step 307, integrating the income prediction data and the expenditure prediction data of the first quarter month in the target quarter as the expense prediction data of the first quarter month in the target quarter; integrating the income prediction data and the expenditure prediction data of the quarter next month in the target quarter as the expense prediction data of the quarter next month in the target quarter; and integrating income prediction data and expenditure prediction data of the final month of the quarter in the target quarter as expense prediction data of the final month of the quarter in the target quarter.
6. The financial data prediction method according to claim 5, wherein the summary calculation result includes a quarter initial summary calculation result, a quarter middle summary calculation result, and a quarter end summary calculation result, and the step of performing summary calculation based on the expense prediction data and a preset prediction update mechanism to obtain a summary calculation result specifically includes:
accumulating revenue prediction data of first month of quarter, second month of quarter and last month of quarter in the target quarter as first prediction data of quarter revenue;
Accumulating the first quarter month, the second quarter month and the last quarter month of the target quarter as first quarter expense prediction data;
Integrating the first prediction data of quarter income and the first prediction data of quarter expenditure to generate the initial summary calculation result of the quarter;
obtaining actual income data and actual expenditure data of the first month of the target quarter of the current year;
Accumulating the actual income data of the first month of the quarter, the income prediction data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of the income of the quarter;
Accumulating the actual expenditure data of the first month of the quarter, the expenditure prediction data of the next month of the quarter and the expenditure prediction data of the last month of the quarter to obtain an accumulation result as second prediction data of expenditure of the quarter;
Integrating the quarter income second prediction data and the quarter expenditure second prediction data to generate a quarter mid-term summarization calculation result;
obtaining actual income data and actual expenditure data of the next month of the quarter in the target quarter of the current year;
accumulating the actual income data of the first month of the quarter, the actual income data of the next month of the quarter and the income prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of the income of the quarter;
accumulating the actual expenditure data of the first month of the quarter, the actual expenditure data of the next month of the quarter and the expenditure prediction data of the last month of the quarter to obtain an accumulation result as third prediction data of expenditure of the quarter;
And integrating the third prediction data of quarter income and the third prediction data of quarter expenditure to generate the summary calculation result of the end of quarter.
7. The financial data prediction method according to claim 6, wherein the step of determining the state of the target quarter of the fund flow according to the summary calculation result and a preset recognition condition specifically includes:
Comparing the magnitude relation between the first prediction data of the quarter income and the first prediction data of the quarter expenditure according to the initial summary calculation result of the quarter;
determining that the state of the funds flow is sufficient at the initial stage of the target quarter if the first prediction data of quarter income exceeds the first prediction data of quarter expenditure;
if the quarter income first prediction data does not exceed the quarter expenditure first prediction data, determining that the fund flow state at the initial stage of the target quarter is a shortage;
comparing the magnitude relation between the quarter income second prediction data and the quarter expenditure second prediction data according to the quarter mid-term summarization calculation result;
If the quarter income second prediction data exceeds the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is sufficient;
if the quarter income second prediction data does not exceed the quarter expenditure second prediction data, determining that the state of the fund flow in the middle of the target quarter is a shortage;
comparing the magnitude relation of the third prediction data of the quarter income with the third prediction data of the quarter expenditure according to the summary calculation result of the end of the quarter;
If the quaternary income third prediction data exceeds the quaternary expenditure third prediction data, determining that the fund flow state of the target end of the quarter is sufficient;
and if the third prediction data of quarter income does not exceed the third prediction data of quarter expenditure, determining that the state of the fund flow at the end of the target quarter is a shortage.
8. The financial data prediction method according to claim 6 or 7, wherein the financing budget result includes financing time and financing amount, and the step of inputting the summarized calculation result into a preset quarter financing budget model to obtain the financing budget result output by the quarter financing budget model specifically includes:
analyzing the summarized calculation results according to the quarter financing budget model to obtain analysis results;
If the fund flow state at the initial stage of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between the first prediction data of the quarter income and the first prediction data of the quarter expenditure based on the calculation result of the initial stage of the quarter, setting the difference value as a minimum financing amount, and setting the last month of the quarter of the last quarter before the target quarter as the final financing time;
If the state of the fund flow in the middle of the target quarter is recognized to be a shortage based on the analysis result, calculating a difference value between second prediction data of quarter income and second prediction data of quarter expenditure based on the calculation result of mid-quarter summarization, setting the difference value as a minimum financing amount, and setting the first month in the target quarter as a final financing time;
If the fund flow state at the end of the target quarter is recognized as shortage based on the analysis result, calculating a difference value between third prediction data of the quarter income and third prediction data of the quarter expenditure based on the summary calculation result of the end of the quarter, setting the difference value as a minimum financing amount, and setting the second month in the target quarter as a final financing time;
and outputting corresponding minimum financing amount and final financing time as the financing budget result through the quarter financing budget model.
9. A financial data prediction apparatus, comprising:
the historical data acquisition module is used for acquiring historical income expense data filled by a target business department according to month dimension and business type dimension;
The serialization processing module is used for serializing the historical income expense data corresponding to all the service types based on the month dimension to obtain serialized historical income data and serialized historical expense data corresponding to all the service types respectively;
The quarter balance prediction module is used for inputting the serialized historical income data and the serialized historical expenditure data into a preset quarter balance prediction model and obtaining balance prediction data respectively corresponding to a first quarter month, a second quarter month and a last quarter month in a target quarter output by the quarter balance prediction model;
The summarizing calculation module is used for summarizing calculation based on the expense prediction data and a preset prediction updating mechanism to obtain a summarizing calculation result;
And the financing budget module is used for determining the state of the target quarter fund flow according to the summarized calculation result and the preset identification condition, and generating a financial data financing prediction report by combining with the preset quarter financing budget model when the state of the target quarter fund flow is in shortage.
10. A computer device comprising a memory having stored therein computer readable instructions which when executed by the processor implement the steps of the financial data prediction method of any one of claims 1 to 8.
11. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the financial data prediction method of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410194056.9A CN118037455A (en) | 2024-02-21 | 2024-02-21 | Financial data prediction method, device, equipment and storage medium thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410194056.9A CN118037455A (en) | 2024-02-21 | 2024-02-21 | Financial data prediction method, device, equipment and storage medium thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118037455A true CN118037455A (en) | 2024-05-14 |
Family
ID=91001910
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410194056.9A Pending CN118037455A (en) | 2024-02-21 | 2024-02-21 | Financial data prediction method, device, equipment and storage medium thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118037455A (en) |
-
2024
- 2024-02-21 CN CN202410194056.9A patent/CN118037455A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
CN112861662B (en) | Target object behavior prediction method based on face and interactive text and related equipment | |
CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
CN112487109A (en) | Entity relationship extraction method, terminal and computer readable storage medium | |
CN115936895A (en) | Risk assessment method, device and equipment based on artificial intelligence and storage medium | |
CN117875320A (en) | Data processing method, device, equipment and storage medium based on artificial intelligence | |
CN117391866A (en) | Data processing method, device, equipment and storage medium thereof | |
CN116703466A (en) | System access quantity prediction method based on improved wolf algorithm and related equipment thereof | |
CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
CN117114901A (en) | Method, device, equipment and medium for processing insurance data based on artificial intelligence | |
CN116703515A (en) | Recommendation method and device based on artificial intelligence, computer equipment and storage medium | |
CN116166858A (en) | Information recommendation method, device, equipment and storage medium based on artificial intelligence | |
CN114565470A (en) | Financial product recommendation method based on artificial intelligence and related equipment thereof | |
CN118037455A (en) | Financial data prediction method, device, equipment and storage medium thereof | |
CN112069807A (en) | Text data theme extraction method and device, computer equipment and storage medium | |
CN114579860B (en) | User behavior portrait generation method, device, electronic equipment and storage medium | |
CN117076243A (en) | Method and device for processing expansion and contraction capacity of application, computer equipment and storage medium | |
CN116703487A (en) | Data analysis method, device, equipment and storage medium based on artificial intelligence | |
CN116542733A (en) | Product recommendation method, device, computer equipment and storage medium | |
CN117078406A (en) | Customer loss early warning method and device, computer equipment and storage medium | |
CN116611432A (en) | Drunk driving risk identification method and device, computer equipment and storage medium | |
CN115859998A (en) | Problem data processing method and device, computer equipment and storage medium | |
CN116797380A (en) | Financial data processing method and related equipment thereof | |
CN117541884A (en) | Sample data processing method, device, storage medium and system | |
CN116757771A (en) | Scheme recommendation method, device, equipment and storage medium based on artificial intelligence |
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 |