A financial data early warning method and system

Abstract

The present application relates to a financial data early warning method and system, including obtaining each original basic financial data to be processed of each current financial service subject, and performing original error correction processing on each of the original basic financial data to be processed to generate the corrected financial data to be processed; performing feature collection, and respectively obtaining the current actual features of each of the corrected financial data to be processed, and respectively forming financial data associated data units; classifying each of the current actual features, and obtaining multiple financial classification data sets after classification; sending each of the financial classification data sets to a preset standard financial data analysis team, and respectively obtaining financial risk analysis data sets; generating the current financial early warning analysis. The present invention generates a financial early warning display interface, and the financial early warning display interface is used to display the current financial early warning analysis.

Description

Technical Field

[0001] The present application relates to the technical field of financial data processing, and in particular to a financial data early warning method and system. Background Art

[0002] At present, with the development of the financial economy, there is an urgent need for financial data processing methods to manage financial data. For example, the invention patent with application number CN202011635804.0 discloses a financial data processing method, device, equipment and storage medium. The method includes: obtaining the user financial data to be predicted and obtaining market financial data and enterprise financial data and performing preprocessing to obtain financial indicator data; matching the financial indicator data with the financial data to obtain multiple financial data of the same period and performing univariate analysis to obtain average financial data; inputting the average financial data and the financial data into the financial data processing model set to perform financial data prediction respectively, and obtaining the distribution weight and financial prediction value of each prediction model; normalizing the financial prediction value to obtain new user financial data; and determining the change trend of user financial data corresponding to the next period based on the difference between the two user financial data.

[0003] Although the above scheme can realize the connection between multiple data into the financial data processing model set according to the present invention, it still has drawbacks in the early warning of financial data. There is an urgent need for a financial data early warning method and system that can improve the early warning effect. Summary of the Invention

[0004] Based on this, it is necessary to provide a financial data early warning method and system that can improve the early warning effect in response to the above technical problems.

[0005] The technical solutions of the present invention are as follows:

[0006] A financial data early warning method, the method comprising:

[0007] Obtain each of the to-be-processed original basic financial data of each current financial service subject, perform original error correction processing on each of the to-be-processed original basic financial data, and generate corresponding error-corrected to-be-processed financial data after the original error correction processing is completed; collect features on each of the error-corrected to-be-processed financial data, respectively obtain current actual features of each of the error-corrected to-be-processed financial data, establish a connection relationship between each of the current actual features and the corresponding error-corrected to-be-processed financial data, and respectively form financial data-related data units; classify each of the current actual features, and obtain multiple financial classification data sets after classification, wherein each of the financial classification data sets includes multiple financial data-related data units ; Send each of the financial classification data sets to a preset standard financial data analysis team, and obtain a financial risk analysis data set respectively, wherein each of the standard financial data analysis teams includes multiple financial data analysts, and each of the financial data analysts generates a current financial analysis data after analyzing the financial data-related data units in the financial classification data set, and the combination of each of the current financial analysis data is the financial risk analysis data set; generate a current financial early warning analysis based on each of the financial risk analysis data sets, and generate a financial early warning display interface based on the current financial early warning analysis, and the financial early warning display interface is used to display the current financial early warning analysis.

[0008] Furthermore, the current financial warning analysis includes current financial warning reminders and current financial risk-free reminders;

[0009] Generating a current financial early warning analysis based on each of the financial risk analysis data sets, and generating a financial early warning display interface based on the current financial early warning analysis, wherein the financial early warning display interface is used to display the current financial early warning analysis, specifically including:

[0010] According to each of the financial risk analysis data, each of the current financial analysis data is compared with the preset standard qualified analysis data, and a current financial data comparison value is generated respectively; according to each of the current financial data comparison values, the current financial data comparison value that is less than the preset qualified score value is recorded as the current re-evaluation data value, and the number of the current re-evaluation data values ​​is counted and recorded as the current number value to be evaluated; the current professional ability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and it is judged whether the current professional ability value is qualified. If it is judged to be qualified, a current data accuracy indication is generated; if it is judged to be unqualified, Then the corresponding current re-evaluation data value is eliminated; after eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated; if it is judged that the updated quantity value to be evaluated is greater than or equal to the preset risky quantity value, a current financial early warning reminder is generated; if it is judged that the updated quantity value to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial early warning display interface is generated according to the current financial early warning reminder and the current financial risk-free reminder, and the financial early warning display interface is used to display the current financial early warning reminder and the current financial risk-free reminder.

[0011] Specifically, the current professional competence value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and whether the current professional competence value is qualified is determined. If it is determined to be qualified, a current data accuracy indication is generated; if it is determined to be unqualified, the corresponding current re-evaluation data value is discarded, and then the following further comprises:

[0012] After determining that the current professional ability value is unqualified and eliminating the corresponding current re-evaluation data value, the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the financial data analyst whose current professional ability value is unqualified is an unqualified practitioner; based on the current actual basic situation, a current special handling matter entry interface is generated; the current work special matter data entered by the unqualified practitioner through the current special handling matter entry interface is obtained; a first influence weight is generated based on the current actual basic situation, and a second influence weight is generated based on the current work special matter data; a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; based on the current comprehensive influence weight, it is determined whether the current comprehensive influence weight is a hard work influence factor; if it is determined that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address.

[0013] Specifically, the process includes obtaining each of the to-be-processed original basic financial data of each current financial service subject, performing original error correction processing on each of the to-be-processed original basic financial data, and generating corresponding error-corrected to-be-processed financial data after the original error correction processing is completed; specifically, the process includes:

[0014] According to each of the original basic financial data to be processed, a first error correction process is performed on each of the original basic financial data to be processed, and a first error correction process result is generated, wherein the first error correction process result includes the current number of errors and the current error importance; the current number of errors is compared with a preset standard number of errors for matching, and a current matching comparison value is obtained; the current error importance is compared with a preset standard important error, and a current importance matching value is obtained; a current error correction comprehensive consideration value is generated according to the current matching comparison value and the current importance matching value; according to the current error correction comprehensive consideration value, whether the current error correction comprehensive consideration value is greater than a preset standard preset consideration value is judged; if it is judged that the current error correction comprehensive consideration value is greater than the preset standard preset consideration value, a current data adjustment indication is generated.

[0015] Furthermore, each of the current actual features is classified, and after classification, a plurality of financial classification data sets are obtained, wherein each of the financial classification data sets includes a plurality of financial data association data units; and then further comprising:

[0016] Obtain the post-error-corrected financial data to be processed, the current actual features, and the financial classification data set corresponding to a preset N number of service times, and generate current feature processing training samples based on the post-error-corrected financial data to be processed, the current actual features, and the financial classification data set; import the N current feature processing training samples into a preset original feature classification neural model for training; after the training is completed, obtain an updated classification neural model.

[0017] Furthermore, a financial data early warning system includes:

[0018] A data acquisition module is used to acquire each of the original basic financial data to be processed of each current financial service subject, perform original error correction processing on each of the original basic financial data to be processed, and generate corresponding error-corrected financial data to be processed after the original error correction processing is completed;

[0019] a feature collection module, configured to collect features of each of the error-corrected financial data to be processed, obtain current actual features of each of the error-corrected financial data to be processed, establish a connection relationship between each of the current actual features and the corresponding error-corrected financial data to be processed, and form financial data-related data units;

[0020] a feature classification module, configured to classify each of the current actual features and obtain a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data-related data units;

[0021] a data analysis module, configured to send each of the financial classification data sets to a preset standard financial data analysis team, and obtain a financial risk analysis data set respectively, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, each of the financial data analysts generates a current financial analysis data after analyzing the financial data-related data units within the financial classification data set, and the current financial analysis data, when combined, constitute the financial risk analysis data set;

[0022] The display interface module is used to generate a current financial warning analysis based on each of the financial risk analysis data sets, and to generate a financial warning display interface based on the current financial warning analysis. The financial warning display interface is used to display the current financial warning analysis.

[0023] Furthermore, the display interface module is also used to:

[0024] According to each of the financial risk analysis data, each of the current financial analysis data is compared with the preset standard qualified analysis data, and a current financial data comparison value is generated respectively; according to each of the current financial data comparison values, the current financial data comparison value that is less than the preset qualified score value is recorded as the current re-evaluation data value, and the number of the current re-evaluation data values ​​is counted and recorded as the current number value to be evaluated; the current professional ability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and it is judged whether the current professional ability value is qualified. If it is judged to be qualified, a current data accuracy indication is generated; if it is judged to be unqualified, Then, the corresponding current re-evaluation data value is eliminated; after eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated; if it is determined that the updated quantity value to be evaluated is greater than or equal to a preset risky quantity value, a current financial early warning reminder is generated; if it is determined that the updated quantity value to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial early warning display interface is generated based on the current financial early warning reminder and the current financial risk-free reminder, and the financial early warning display interface is used to display the current financial early warning reminder and the current financial risk-free reminder;

[0025] After determining that the current professional ability value is unqualified and eliminating the corresponding current re-evaluation data value, the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the financial data analyst whose current professional ability value is unqualified is an unqualified practitioner; based on the current actual basic situation, a current special handling matter entry interface is generated; the current work special matter data entered by the unqualified practitioner through the current special handling matter entry interface is obtained; a first influence weight is generated based on the current actual basic situation, and a second influence weight is generated based on the current work special matter data; a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; based on the current comprehensive influence weight, it is determined whether the current comprehensive influence weight is a hard work influence factor; if it is determined that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address.

[0026] Furthermore, the system further includes a data processing module, which is configured to:

[0027] According to each of the original basic financial data to be processed, a first error correction process is performed on each of the original basic financial data to be processed, and a first error correction process result is generated, wherein the first error correction process result includes the current error number and the current error importance; the current error number is compared with a preset standard error number for matching, and a current matching comparison value is obtained; the current error importance is compared with a preset standard important error, and a current importance matching value is obtained; a current error correction comprehensive consideration value is generated according to the current matching comparison value and the current importance matching value; and the current error correction comprehensive consideration value is judged according to the current error correction comprehensive consideration value. Whether the comprehensive consideration value of the previous error correction is greater than the preset standard preset consideration value; if it is judged that the current comprehensive consideration value of the error correction is greater than the preset standard preset consideration value, a current data adjustment indication is generated; the post-error correction financial data to be processed, the current actual features and the financial classification data set corresponding to the preset N service times are obtained, and current feature processing training samples are generated according to the post-error correction financial data to be processed, the current actual features and the financial classification data set; the N current feature processing training samples are imported into the preset original feature classification neural model for training; after the training is completed, an updated classification neural model is obtained.

[0028] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned financial data early warning method when executing the computer program.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned financial data early warning method.

[0030] The present invention achieves the following technical effects:

[0031] The above-mentioned financial data early warning method and system obtains each of the original basic financial data to be processed of each current financial service subject in turn, and performs original error correction processing on each of the original basic financial data to be processed, and generates corresponding error-corrected financial data to be processed after the original error correction processing is completed; collects features of each of the error-corrected financial data to be processed, and obtains the current actual features of each of the error-corrected financial data to be processed, establishes a connection relationship between each of the current actual features and the corresponding error-corrected financial data to be processed, and forms financial data associated data units respectively; classifies each of the current actual features, and obtains multiple financial classified data sets after classification, wherein each The financial classification data set includes a plurality of financial data associated data units; each of the financial classification data sets is sent to a preset standard financial data analysis team, and a financial risk analysis data set is obtained respectively, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, each of the financial data analysts generates a current financial analysis data after analyzing the financial data associated data units in the financial classification data set, and each of the current financial analysis data is combined to form the financial risk analysis data set; a current financial early warning analysis is generated according to each of the financial risk analysis data sets, and a financial early warning analysis is generated according to the current financial early warning analysis. The early warning display interface is used to display the current financial early warning analysis. In order to improve the accuracy and efficiency of subsequent data processing, the present invention needs to first perform error correction processing on the acquired basic data, that is, after obtaining the original basic financial data to be processed of each current financial service subject, the original basic financial data to be processed is subjected to original error correction processing, thereby achieving that the acquired financial data to be processed after error correction is accurate and error-free data. In order to achieve efficient and accurate processing of subsequent data, feature collection is first performed and feature connection is established, that is, by respectively performing feature collection on each financial data to be processed after error correction, and respectively obtaining each financial data to be processed after error correction. According to the current actual characteristics of the data, each of the current actual characteristics is connected to the corresponding financial data to be processed after error correction, and financial data association data units are formed respectively. The formation of the financial data association data units facilitates the correlation and reliability of subsequent data processing. Based on the financial data association data units, after obtaining the current actual characteristics, the associated financial data to be processed after error correction can be obtained. In order to achieve detailed classification processing of financial data, each of the current actual characteristics is further classified, and multiple financial classification data sets are obtained after classification, wherein each of the financial classification data sets includes multiple financial data association data units.That is, the multiple financial data-related data units included in each of the financial classification data sets belong to the same category, such as trust data or consulting data. In order to achieve more accurate and efficient early warning, the current financial early warning analysis is generated according to each of the financial risk analysis data sets, and a financial early warning display interface is generated according to the current financial early warning analysis. The financial early warning display interface is used to display the current financial early warning analysis. In order to achieve a more surprising and intuitive display, a financial early warning display interface is generated. The financial early warning display interface is used to display the current financial early warning analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 1 is a flow chart of a financial data early warning method according to an embodiment;

[0033] Figure 2 This is a structural block diagram of a financial data early warning system in one embodiment;

[0034] Figure 3 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0036] In one embodiment, Figure 1 As shown, step S100 is provided: obtaining each to-be-processed original basic financial data of each current financial service subject, performing original error correction processing on each to-be-processed original basic financial data, and generating corresponding error-corrected to-be-processed financial data after the original error correction processing is completed;

[0037] Furthermore, in this step, in order to ensure the accuracy and efficiency of subsequent data processing, it is necessary to first perform error correction processing on the acquired basic data, that is, after obtaining the original basic financial data to be processed of each current financial service entity, the original basic financial data to be processed are subjected to original error correction processing, so as to ensure that the acquired financial data to be processed after error correction is accurate and error-free data.

[0038] Furthermore, in this embodiment, the specific error correction process is to manually review the data to achieve error correction.

[0039] Step S200: collecting features of each of the error-corrected financial data to be processed, obtaining current actual features of each of the error-corrected financial data to be processed, establishing a connection relationship between each of the current actual features and the corresponding error-corrected financial data to be processed, and forming financial data associated data units;

[0040] Furthermore, in this step, in order to achieve efficient and accurate processing of subsequent data, feature collection is first performed and feature connections are established, that is, by collecting features for each of the error-corrected financial data to be processed, and respectively obtaining the current actual features of each of the error-corrected financial data to be processed, each of the current actual features is connected to the corresponding error-corrected financial data to be processed, and financial data-related data units are formed respectively. The formation of the financial data-related data units facilitates the subsequent correlation and reliability of data processing. Based on the financial data-related data units, after obtaining the current actual features, the associated error-corrected financial data to be processed can be obtained.

[0041] Furthermore, feature collection is to perform comprehensive feature collection based on the attributes, time, validity period, etc. of the financial data to be processed after error correction, such as classifying data within the same time period into the same category and having the same current actual features.

[0042] Step S300: Classifying each of the current actual features, and obtaining a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data-related data units;

[0043] Furthermore, in this step, to achieve detailed classification of the financial data, each of the current actual features is further classified to obtain multiple financial classification data sets. Each of the financial classification data sets includes multiple financial data-related data units. In other words, the multiple financial data-related data units included in each of the financial classification data sets all belong to the same general category, such as trust data or consulting data.

[0044] Step S400: Sending each of the financial classification data sets to a preset standard financial data analysis team, and obtaining a financial risk analysis data set respectively, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, each of the financial data analysts generates a current financial analysis data after analyzing the financial data-related data units in the financial classification data set, and the current financial analysis data are combined to form the financial risk analysis data set;

[0045] Furthermore, in this step, the standard financial data analysis team is pre-set, and multiple financial data analysts are simultaneously set up to form one standard financial data analysis team. Subsequently, each of the financial classification data sets is sent to the pre-set standard financial data analysis team, and the financial data analysts analyze the financial data-related data units within the financial classification data sets to generate current financial analysis data.

[0046] That is, a financial classification data set is sent to a standard financial data analysis team, and the financial data analysts within the standard financial data analysis team analyze the financial data-related data units in the financial classification data set respectively, and generate a current financial analysis data respectively. The combination of each current financial analysis data is the financial risk analysis data set.

[0047] Step S500: generating a current financial warning analysis based on each of the financial risk analysis data sets, and generating a financial warning display interface based on the current financial warning analysis, wherein the financial warning display interface is used to display the current financial warning analysis.

[0048] Furthermore, in this step, in order to achieve more accurate and efficient early warning, the current financial early warning analysis is generated based on each of the financial risk analysis data sets, and a financial early warning display interface is generated based on the current financial early warning analysis. The financial early warning display interface is used to display the current financial early warning analysis. In order to achieve a more surprising and intuitive display, a financial early warning display interface is generated. The financial early warning display interface is used to display the current financial early warning analysis.

[0049] In one embodiment, the current financial warning analysis includes a current financial warning reminder and a current financial risk-free reminder;

[0050] Step S500: generating a current financial early warning analysis based on each of the financial risk analysis data sets, and generating a financial early warning display interface based on the current financial early warning analysis. The financial early warning display interface is used to display the current financial early warning analysis, specifically including:

[0051] Step S510: comparing each current financial analysis data with preset standard qualified analysis data according to each financial risk analysis data, and generating current financial data comparison values ​​respectively;

[0052] Specifically, the standard qualified analysis data is pre-set, and the financial risk analysis data is compared with the standard qualified analysis data to determine whether the financial risk analysis data is qualified.

[0053] Furthermore, the financial risk analysis data is compared one-to-one with the standard qualified analysis data, such as a one-to-one comparison of satisfaction values, or other methods, thereby achieving refined comparison.

[0054] Step S520: Based on the current financial data comparison values, the current financial data comparison values ​​that are less than the preset passing score are recorded as current re-evaluated data values, and the number of the current re-evaluated data values ​​is counted and recorded as the current number to be evaluated;

[0055] Specifically, the current financial data comparison value is pre-set, and is compared digitally to determine whether the current financial data comparison value meets expectations. By recording the current financial data comparison value that is less than the preset qualified score value as the current re-evaluation data value, a separate definition of unqualified data is achieved, which facilitates subsequent processing.

[0056] Step S530: obtaining the current professional competence value of the financial data analyst corresponding to the current re-evaluation data value, determining whether the current professional competence value is qualified, and if so, generating a current data accuracy indication; if not, discarding the corresponding current re-evaluation data value;

[0057] Step S540: after removing the corresponding current re-evaluation data value, updating the current quantity value to be evaluated, and generating an updated quantity value to be evaluated;

[0058] Specifically, in order to achieve more accurate evaluation and then determine whether the current re-evaluation data value is valid, it is necessary to consider the current professional ability value of the corresponding financial data analyst, and then determine whether the current professional ability value is qualified. Specifically, it is through assessing the actual ability of the corresponding financial data analyst, and then through digital comparison. At the same time, if it is judged to be unqualified, the corresponding current re-evaluation data value is eliminated, that is, the financial evaluation data made by the unqualified evaluator is eliminated. After eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated.

[0059] Step S550: If it is determined that the updated quantity value to be evaluated is greater than or equal to the preset risky quantity value, a current financial warning reminder is generated; if it is determined that the updated quantity value to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial warning display interface is generated based on the current financial warning reminder and the current financial risk-free reminder. The financial warning display interface is used to display the current financial warning reminder and the current financial risk-free reminder.

[0060] Specifically, there are two possible financial risks, one is the current financial warning reminder, and the other is the current financial risk-free reminder. Then, a financial warning display interface is generated based on the current financial warning reminder and the current financial risk-free reminder. The financial warning display interface is used to display the current financial warning reminder and the current financial risk-free reminder.

[0061] In one embodiment, step S530: obtaining the current professional competence value of the financial data analyst corresponding to the current re-evaluation data value, determining whether the current professional competence value is qualified, and if so, generating a current data accuracy indication; if so, discarding the corresponding current re-evaluation data value, and then further comprising:

[0062] Step S531: after determining that the current professional capability value is unqualified and eliminating the corresponding current re-evaluation data value, obtaining the current actual basic situation of the financial data analyst whose current professional capability value is unqualified, wherein the financial data analyst whose current professional capability value is unqualified is an unqualified practitioner;

[0063] Step S532: generating a current special handling item entry interface based on the current actual basic situation;

[0064] Step S533: obtaining the current work special matters data entered by the unqualified practitioner through the current special matters entry interface;

[0065] Furthermore, in order to determine the working ability of the financial data analyst whose current professional ability value is unqualified when it is found that the current professional ability value is unqualified, an updated assessment is conducted, and then the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the current actual basic situation is the basic situation that characterizes the unqualified practitioner.

[0066] In order to further obtain detailed data, a current special handling matters entry interface is generated according to the current actual basic situation; then, the current work special matters data entered by the unqualified practitioners through the current special handling matters entry interface is obtained.

[0067] The current work special matters data are basic data entered by oneself that may affect work ability.

[0068] Step S534: generating a first impact weight according to the current actual basic situation, and generating a second impact weight according to the current work special matter data;

[0069] Step S535: generating a current comprehensive influence weight according to the first influence weight and the second influence weight;

[0070] Step S536: judging whether the current comprehensive impact weight is a hard work impact factor according to the current comprehensive impact weight;

[0071] Step S537: If it is determined that the current comprehensive impact weight is a hard work impact factor, a current assistance reminder is generated and sent to a preset assistance staff contact address.

[0072] Furthermore, in order to achieve comprehensive assessment, the present invention further generates a first influence weight through numerical processing, and then generates a second influence weight based on the current work special matters data; then, a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; then, based on the current comprehensive influence weight, it is judged whether the current comprehensive influence weight is a hard work influence factor; and then, if it is judged that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address, and further, the relevant assistance personnel are enabled to provide assistance through the assistance staff contact address.

[0073] In one embodiment, step S100: obtaining each of the to-be-processed original basic financial data of each current financial service subject, performing original error correction processing on each of the to-be-processed original basic financial data, and generating corresponding error-corrected to-be-processed financial data after the original error correction processing is completed; specifically includes:

[0074] Step S110: performing a first error correction process on each of the original basic financial data to be processed, and generating a first error correction process result, wherein the first error correction process result includes a current error number and a current error severity;

[0075] Specifically, the current error number is the number of errors. The current error importance is whether the error is important, and an evaluation is generated by the current error number and the current error importance.

[0076] Step S120: performing a matching comparison between the current number of errors and a preset standard number of errors, and obtaining a current matching comparison value;

[0077] Step S130: comparing the current error importance with a preset standard important error, and obtaining a current importance matching value;

[0078] Furthermore, numerical display of data is achieved through the current matching comparison value and the current importance matching value.

[0079] Step S140: generating a current error correction comprehensive consideration value according to the current matching comparison value and the current importance matching value;

[0080] Step S150: determining whether the current error correction comprehensive consideration value is greater than a preset standard consideration value according to the current error correction comprehensive consideration value;

[0081] Step S160: If it is determined that the current error correction comprehensive consideration value is greater than the preset standard consideration value, a current data adjustment instruction is generated.

[0082] Furthermore, in order to achieve more accurate indication, the present invention generates a current error correction comprehensive consideration value based on the current matching comparison value and the current importance matching value; then, based on the current error correction comprehensive consideration value, it is judged whether the current error correction comprehensive consideration value is greater than the preset standard preset consideration value; finally, if it is judged that the current error correction comprehensive consideration value is greater than the preset standard preset consideration value, a current data adjustment indication is generated.

[0083] In one embodiment, step S300: classifying each of the current actual features and obtaining a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data-related data units; and then further comprising:

[0084] Step S310: Obtaining the error-corrected financial data to be processed, the current actual features, and the financial classification data set corresponding to a preset N number of service times, and generating current feature processing training samples based on the error-corrected financial data to be processed, the current actual features, and the financial classification data set;

[0085] Step S320: importing the N current feature processing training samples into a preset original feature classification neural model for training;

[0086] Step S330: After the training is completed, the updated classification neural model is obtained.

[0087] Furthermore, the original feature classification neural model described in the present invention is a pre-established model, which is a complex network system formed by a large number of simple processing units widely interconnected. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system.

[0088] Furthermore, the original feature classification neural model is set up by technicians in this field. In order to achieve more accurate subsequent classification, the corrected financial data to be processed, the current actual features and the financial classification data set corresponding to the preset N service times are obtained, and the current feature processing training samples are generated based on the corrected financial data to be processed, the current actual features and the financial classification data set. After the training is completed, the updated classification neural model is obtained.

[0089] In one embodiment, Figure 2 As shown, a financial data early warning system, the system includes:

[0090] A data acquisition module is used to acquire each of the original basic financial data to be processed of each current financial service subject, perform original error correction processing on each of the original basic financial data to be processed, and generate corresponding error-corrected financial data to be processed after the original error correction processing is completed;

[0091] a feature collection module, configured to collect features of each of the error-corrected financial data to be processed, obtain current actual features of each of the error-corrected financial data to be processed, establish a connection relationship between each of the current actual features and the corresponding error-corrected financial data to be processed, and form financial data-related data units;

[0092] a feature classification module, configured to classify each of the current actual features and obtain a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data-related data units;

[0093] a data analysis module, configured to send each of the financial classification data sets to a preset standard financial data analysis team, and obtain a financial risk analysis data set respectively, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, each of the financial data analysts generates a current financial analysis data after analyzing the financial data-related data units within the financial classification data set, and the current financial analysis data, when combined, constitute the financial risk analysis data set;

[0094] The display interface module is used to generate a current financial warning analysis based on each of the financial risk analysis data sets, and to generate a financial warning display interface based on the current financial warning analysis. The financial warning display interface is used to display the current financial warning analysis.

[0095] In one embodiment, the display interface module is further used to:

[0096] According to each of the financial risk analysis data, each of the current financial analysis data is compared with the preset standard qualified analysis data, and a current financial data comparison value is generated respectively; according to each of the current financial data comparison values, the current financial data comparison value that is less than the preset qualified score value is recorded as the current re-evaluation data value, and the number of the current re-evaluation data values ​​is counted and recorded as the current number value to be evaluated; the current professional ability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and it is judged whether the current professional ability value is qualified. If it is judged to be qualified, a current data accuracy indication is generated; if it is judged to be unqualified, Then, the corresponding current re-evaluation data value is eliminated; after eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated; if it is determined that the updated quantity value to be evaluated is greater than or equal to a preset risky quantity value, a current financial early warning reminder is generated; if it is determined that the updated quantity value to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial early warning display interface is generated based on the current financial early warning reminder and the current financial risk-free reminder, and the financial early warning display interface is used to display the current financial early warning reminder and the current financial risk-free reminder;

[0097] After determining that the current professional ability value is unqualified and eliminating the corresponding current re-evaluation data value, the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the financial data analyst whose current professional ability value is unqualified is an unqualified practitioner; based on the current actual basic situation, a current special handling matter entry interface is generated; the current work special matter data entered by the unqualified practitioner through the current special handling matter entry interface is obtained; a first influence weight is generated based on the current actual basic situation, and a second influence weight is generated based on the current work special matter data; a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; based on the current comprehensive influence weight, it is determined whether the current comprehensive influence weight is a hard work influence factor; if it is determined that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address.

[0098] In one embodiment, the system further comprises a data processing module, wherein the data processing module is configured to:

[0099] According to each of the original basic financial data to be processed, a first error correction process is performed on each of the original basic financial data to be processed, and a first error correction process result is generated, wherein the first error correction process result includes the current error number and the current error importance; the current error number is compared with a preset standard error number for matching, and a current matching comparison value is obtained; the current error importance is compared with a preset standard important error, and a current importance matching value is obtained; a current error correction comprehensive consideration value is generated according to the current matching comparison value and the current importance matching value; and the current error correction comprehensive consideration value is judged according to the current error correction comprehensive consideration value. Whether the comprehensive consideration value of the previous error correction is greater than the preset standard preset consideration value; if it is judged that the current comprehensive consideration value of the error correction is greater than the preset standard preset consideration value, a current data adjustment indication is generated; the post-error correction financial data to be processed, the current actual features and the financial classification data set corresponding to the preset N service times are obtained, and current feature processing training samples are generated according to the post-error correction financial data to be processed, the current actual features and the financial classification data set; the N current feature processing training samples are imported into the preset original feature classification neural model for training; after the training is completed, an updated classification neural model is obtained.

[0100] In one embodiment, Figure 3 As shown, a computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps described in the above-mentioned financial data early warning method when executing the computer program.

[0101] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned financial data early warning method.

[0102] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0103] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0104] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A financial data early warning method, characterized in that: The method comprises: Obtain each to-be-processed original basic financial data of each current financial service subject, perform original error correction processing on each to-be-processed original basic financial data, and generate corresponding to-be-processed financial data after error correction after the original error correction processing is completed; perform feature collection on each to-be-processed financial data after error correction, and obtain the current actual features of each to-be-processed financial data after error correction, establish a connection relationship between each current actual feature and the corresponding to-be-processed financial data after error correction, and form financial data associated data units respectively; classify each current actual feature, and obtain multiple financial classified data sets after classification, wherein each of the financial classified data sets includes multiple financial data associated data units ; Send each of the financial classification data sets to a preset standard financial data analysis team respectively, and obtain a financial risk analysis data set respectively, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, and each of the financial data analysts generates a current financial analysis data after analyzing the financial data associated data units in the financial classification data set, and each of the current financial analysis data is combined to form the financial risk analysis data set; generate a current financial early warning analysis according to each of the financial risk analysis data sets, and generate a financial early warning display interface according to the current financial early warning analysis, and the financial early warning display interface is used to display the current financial early warning analysis; The obtaining of each to-be-processed original basic financial data of each current financial service subject, performing original error correction processing on each to-be-processed original basic financial data, and generating corresponding to-be-processed financial data after error correction after the original error correction processing is completed; specifically includes: According to each of the original basic financial data to be processed, a first error correction process is performed on each of the original basic financial data to be processed, and a first error correction process result is generated, wherein the first error correction process result includes the current number of errors and the current error importance; the current number of errors is compared with a preset standard number of errors for matching, and a current matching comparison value is obtained; the current error importance is compared with a preset standard important error, and a current importance matching value is obtained; a current error correction comprehensive consideration value is generated according to the current matching comparison value and the current importance matching value; according to the current error correction comprehensive consideration value, whether the current error correction comprehensive consideration value is greater than a preset standard preset consideration value is judged; if it is judged that the current error correction comprehensive consideration value is greater than the preset standard preset consideration value, a current data adjustment indication is generated.

2. The financial data early warning method according to claim 1, characterized in that: The current financial warning analysis includes current financial warning reminders and current financial risk-free reminders; Generate a current financial early warning analysis according to each of the financial risk analysis data sets, and generate a financial early warning display interface according to the current financial early warning analysis, wherein the financial early warning display interface is used to display the current financial early warning analysis, specifically including: According to each of the financial risk analysis data, each of the current financial analysis data is compared with the preset standard qualified analysis data, and current financial data comparison values ​​are generated respectively; according to each of the current financial data comparison values, the current financial data comparison value that is less than the preset qualified score value is recorded as the current re-evaluation data value, and the number of the current re-evaluation data values ​​is counted at the same time, and recorded as the current number value to be evaluated; the current professional ability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and it is judged whether the current professional ability value is qualified. If it is judged to be qualified, a current data accuracy indication is generated; if it is judged to be unqualified, Then the corresponding current re-evaluation data value is eliminated; after eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated; if it is judged that the updated quantity value to be evaluated is greater than or equal to the preset risky quantity value, a current financial early warning reminder is generated; if it is judged that the updated quantity value to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial early warning display interface is generated according to the current financial early warning reminder and the current financial risk-free reminder, and the financial early warning display interface is used to display the current financial early warning reminder and the current financial risk-free reminder.

3. The financial data early warning method according to claim 2, characterized in that: The current professional capability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and whether the current professional capability value is qualified is determined. If it is determined to be qualified, a current data accuracy indication is generated; if it is determined to be unqualified, the corresponding current re-evaluation data value is discarded, and then the following is further included: After determining that the current professional ability value is unqualified and excluding the corresponding current re-evaluation data value, the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the financial data analyst whose current professional ability value is unqualified is an unqualified practitioner; based on the current actual basic situation, a current special handling matter entry interface is generated; the current work special matter data entered by the unqualified practitioner through the current special handling matter entry interface is obtained; a first influence weight is generated based on the current actual basic situation, and a second influence weight is generated based on the current work special matter data; a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; based on the current comprehensive influence weight, it is determined whether the current comprehensive influence weight is a hard work influence factor; if it is determined that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address.

4. The financial data early warning method according to any one of claims 1 to 3, characterized in that: Classifying each of the current actual features, and obtaining a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data associated data units; and then further comprising: Obtain the post-error-corrected financial data to be processed, the current actual features and the financial classification data set corresponding to the preset N service times, and generate current feature processing training samples based on the post-error-corrected financial data to be processed, the current actual features and the financial classification data set; import the N current feature processing training samples into a preset original feature classification neural model for training; after the training is completed, obtain an updated classification neural model.

5. A financial data early warning system, characterized in that: The system comprises: A data acquisition module is used to acquire each original basic financial data to be processed of each current financial service subject, and to perform original error correction processing on each of the original basic financial data to be processed, and to generate corresponding error-corrected financial data to be processed after the original error correction processing is completed; A feature collection module, used to collect features of each of the error-corrected financial data to be processed, and respectively obtain current actual features of each of the error-corrected financial data to be processed, respectively establish a connection relationship between each of the current actual features and the corresponding error-corrected financial data to be processed, and respectively form financial data associated data units; A feature classification module, used for classifying each of the current actual features and obtaining a plurality of financial classification data sets after classification, wherein each of the financial classification data sets includes a plurality of financial data associated data units; A data analysis module, used to send each of the financial classification data sets to a preset standard financial data analysis team, and obtain a financial risk analysis data set, wherein each of the standard financial data analysis teams includes a plurality of financial data analysts, each of the financial data analysts generates a current financial analysis data after analyzing the financial data associated data unit in the financial classification data set, and each of the current financial analysis data is combined to form the financial risk analysis data set; A display interface module, used to generate a current financial early warning analysis according to each of the financial risk analysis data sets, and to generate a financial early warning display interface according to the current financial early warning analysis, wherein the financial early warning display interface is used to display the current financial early warning analysis; According to each of the original basic financial data to be processed, a first error correction process is performed on each of the original basic financial data to be processed, and a first error correction process result is generated, wherein the first error correction process result includes a current error number and a current error importance; the current error number is compared with a preset standard error number for matching, and a current matching comparison value is obtained; the current error importance is compared with a preset standard important error, and a current importance matching value is obtained; a current error correction comprehensive consideration value is generated according to the current matching comparison value and the current importance matching value; and the current error correction comprehensive consideration value is judged according to the current error correction comprehensive consideration value. Whether the previous error correction comprehensive consideration value is greater than the preset standard preset consideration value; if it is judged that the current error correction comprehensive consideration value is greater than the preset standard preset consideration value, then generate a current data adjustment indication; obtain the post-error correction financial data to be processed, the current actual characteristics and the financial classification data set corresponding to the preset N service times, and generate current feature processing training samples according to the post-error correction financial data to be processed, the current actual characteristics and the financial classification data set; import the N current feature processing training samples into the preset original feature classification neural model for training; after the training is completed, obtain the updated classification neural model.

6. The financial data early warning system according to claim 5, characterized in that: The display interface module is also used for: According to each of the financial risk analysis data, each of the current financial analysis data is compared with the preset standard qualified analysis data, and current financial data comparison values ​​are generated respectively; according to each of the current financial data comparison values, the current financial data comparison value that is less than the preset qualified score value is recorded as the current re-evaluation data value, and the number of the current re-evaluation data values ​​is counted at the same time, and recorded as the current quantity value to be evaluated; the current professional ability value of the financial data analyst corresponding to the current re-evaluation data value is obtained, and it is judged whether the current professional ability value is qualified, if it is judged to be qualified, then the current data accuracy indication is generated, if it is judged to be unqualified, then the corresponding current re-evaluation data value is eliminated; after eliminating the corresponding current re-evaluation data value, the current quantity value to be evaluated is updated, and an updated quantity value to be evaluated is generated; If it is determined that the updated quantity value to be evaluated is greater than or equal to the preset risky quantity value, a current financial early warning reminder is generated; If it is determined that the updated value of the quantity to be evaluated is not greater than or equal to the preset risky quantity value, a current financial risk-free reminder is generated, and a financial warning display interface is generated according to the current financial warning reminder and the current financial risk-free reminder, and the financial warning display interface is used to display the current financial warning reminder and the current financial risk-free reminder; After determining that the current professional ability value is unqualified and excluding the corresponding current re-evaluation data value, the current actual basic situation of the financial data analyst whose current professional ability value is unqualified is obtained, wherein the financial data analyst whose current professional ability value is unqualified is an unqualified practitioner; based on the current actual basic situation, a current special handling matter entry interface is generated; the current work special matter data entered by the unqualified practitioner through the current special handling matter entry interface is obtained; a first influence weight is generated based on the current actual basic situation, and a second influence weight is generated based on the current work special matter data; a current comprehensive influence weight is generated based on the first influence weight and the second influence weight; based on the current comprehensive influence weight, it is determined whether the current comprehensive influence weight is a hard work influence factor; if it is determined that the current comprehensive influence weight is a hard work influence factor, a current assistance reminder is generated, and the current assistance reminder is sent to the preset assistance staff contact address.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images