Bill generation method

Abstract

The invention relates to the technical field of Excel data processing, in particular to a bill generation method. The method comprises the following steps: storing related data of a bill needing to be generated into a data column, selecting a tag column in the data column based on a demand, extracting tag data, performing conversion and integration processing on the extracted tag data, generating a bill distribution curve according to the processed tag data, and learning data in a training set to form a preset distribution curve. And superposing the generated bill distribution curve and a preset distribution curve to the same coordinate system, calculating the area of a distribution region enclosed by the bill distribution curve and the preset distribution curve, judging the generated bill based on the area of the distribution region, and generating a corresponding processing instruction or completing judgment on the generated bill based on a judgment result. And re-determining the operation parameters in the bill generation process based on the received processing instruction. According to the invention, intelligent analysis and accurate regulation and control of the bill generation process are effectively realized, and the bill generation efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Excel data processing, and in particular to a bill generating method. Background Art

[0002] Using Excel to process relevant data and generate corresponding bills is a common method at present. The process is generally preparing data, creating Excel tables, inputting data, data analysis, data processing, data visualization and generating bills. Data analysis and data processing are the key links in generating bills from data. They can accurately identify and process relevant data, so as to accurately generate bills. Generating curve chart bills based on data is a common data analysis method. Curve charts can clearly and intuitively analyze data. Therefore, it is particularly important to conduct relevant research on data analysis and data processing, which has important research significance in ensuring the accuracy of bills, improving decision-making quality, discovering rules, optimizing processes and preventing risks.

[0003] Chinese patent application publication number: CN116361366A, discloses a method for Excel data analysis and extraction, in which the server receives the Excel upload request sent by the client, and then uses the uploaded Excel to perform feature value calculation and data extraction as a task and adds it to the task queue. The data extraction and analysis center in the server executes the tasks to be executed in the task queue, then saves the extracted data, and saves the execution result feedback in the task queue to provide it to the client when the client queries the execution result.

[0004] It can be seen that the above solution provides a method for analyzing and extracting Excel data, and extracting and transforming Excel structure data. However, the above solution cannot realize intelligent analysis and precise control of the bill generation process, and thus cannot ensure the efficiency of bill generation. Summary of the invention

[0005] To this end, the present invention provides a bill generation method to overcome the problem in the prior art that it is impossible to perform intelligent analysis and precise regulation on the bill generation process, thereby resulting in low bill generation efficiency.

[0006] To achieve the above object, the present invention provides a bill generation method, comprising: Store the relevant data for generating bills in the data column; Select a label column in the data column based on the requirement and extract label data; Converting and integrating the extracted label data; Generate a bill distribution curve based on the processed label data, and form a preset distribution curve by learning the data in the training set; Superimposing the generated bill distribution curve and the preset distribution curve into the same coordinate system; Calculating the area of ​​a distribution region enclosed by the bill distribution curve and the preset distribution curve; Making a determination on the generated bill based on the area of ​​the distribution region; Generate corresponding processing instructions based on the judgment results, or, completing the determination of the generated bill; The determination includes determining whether the generated bill is qualified and determining the reason for not being qualified; The operating parameters in the bill generation process are re-determined based on the received processing instruction.

[0007] Furthermore, the process of determining the generated bill based on the area of ​​the distribution region includes: Determining a preset curve area enclosed by the preset distribution curve and the abscissa axis of the coordinate system; Calculating the ratio of the distribution area to the preset curve area, and recording the obtained ratio as the area ratio; When the area ratio of the region is less than the area ratio of the first preset region, the generated bill is determined to be qualified, and the determination of the generated bill is completed; When the area ratio of the region is greater than or equal to the area ratio of the first preset region and less than the area ratio of the second preset region, the generated bill is determined to be unqualified, and whether the area ratio of the preset distribution region meets the standard is determined based on the tag data; When the area ratio of the region is greater than or equal to the area ratio of the second preset region, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio.

[0008] Furthermore, the process of determining whether the area ratio of the preset region meets the standard based on the tag data includes: Sum the data of the tag data in each of the tag columns to obtain the tag sum; Calculate the difference between the label sum and the preset label sum, and record the obtained difference as the label sum difference; When the tag sum difference is greater than zero, it is determined that the preset area ratio does not meet the standard, and the preset area ratio is corrected based on the tag sum difference; When the difference in the total of the labels is less than or equal to zero, it is determined that the area ratio of the preset region meets the standard, the generated bill is unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region.

[0009] Furthermore, the process of correcting the area ratio of the preset region based on the tag sum difference includes: Calculate the ratio of the label sum difference to the preset label sum, and record the obtained ratio as the sum ratio; The area ratio of the preset region is increased based on the total ratio, and the increase in the area ratio of the preset region is proportional to the total ratio.

[0010] Further, after the preset area ratio is increased, the process of re-determining the generated bill based on the area ratio includes: When the area ratio of the region is less than the area ratio of the first preset region, the generated bill is determined to be qualified, and the determination of the generated bill is completed; When the area ratio of the region is greater than or equal to the area ratio of the first preset region, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region.

[0011] Further, the process of determining the reason why the generated bill is unqualified based on the area ratio includes: Calculating the difference between the area ratio of the region and the area ratio of the second preset region, and recording the obtained difference as the area ratio difference of the region; When the area ratio difference is less than or equal to the first preset area ratio difference, the generated bill is determined to be unqualified because the identification of the label data does not meet the standard when the label data is extracted, and the noise reduction factor of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve; When the area ratio difference is greater than the first preset area ratio difference and less than or equal to the second preset area ratio difference, determining the reason why the generated bill is unqualified based on the tag column; When the regional area ratio difference is greater than the second preset regional area ratio difference, the reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

[0012] Furthermore, the process of correcting the noise reduction ratio of the tag data based on the superimposed bill distribution curve and the preset distribution curve includes: Separately counting the label columns in the preset distribution curve and the bill distribution curve; Determine the preset item value of each of the label columns in the preset distribution curve, and the actual item value of each of the label columns in the bill distribution curve; Calculating the absolute value of the difference between each of the preset item values ​​and each of the corresponding actual item values, and recording the obtained absolute value of the difference as the item deviation value; Calculate the ratio of each item deviation value to the corresponding preset item value, and record the obtained ratio as the item deviation ratio; Calculate the average value of the deviation ratios of the items, and record the average value as the deviation average value; The noise reduction factor of the label data is increased based on the deviation average value, and the increase of the noise reduction factor is proportional to the deviation average value.

[0013] Further, the process of determining the reason why the generated bill is unqualified based on the tag column includes: Counting the number of the tag columns, and recording the obtained number as the total number of tag columns; When the total number of label columns is greater than the preset total number of label columns, the reason for determining that the generated bill is unqualified is that the identification of the label data during the extraction of the label data does not meet the standard, and the noise reduction ratio of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve; When the total number of the label columns is less than or equal to the preset total number of the label columns, the reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

[0014] Further, the process of determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve includes: Overlapping the bill distribution curve with the preset distribution curve; Determining the overlap curve length of the overlapped portion of the bill distribution curve and the preset distribution curve; Calculating the ratio of the length of the coincidence curve to the total length of the preset distribution curve, and recording the obtained ratio as the coincidence curve ratio; When the coincidence curve ratio is less than or equal to the preset coincidence curve ratio, it is determined that the training set used to form the preset distribution curve does not meet the standard, and a notification that the training set needs to be optimized is issued; When the coincidence curve ratio is greater than the preset coincidence curve ratio, it is determined that the generation process of the bill distribution curve does not meet the standard, and the bill distribution curve is vertically corrected.

[0015] Furthermore, the process of vertically correcting the bill distribution curve includes: Based on the preset distribution curve, the bill distribution curve is scanned to overlap with the preset distribution curve; sequentially determining the overlap degree of the bill distribution curve and the preset distribution curve when the data points at each of the label columns overlap; Determine the label column when the overlap degree is the largest, and record the obtained label column as a reference label column; The bill distribution curve is moved based on the reference label column to complete the vertical correction.

[0016] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention generates a bill distribution curve according to the processed label data, forms a preset distribution curve by learning the data in the training set, superimposes the generated bill distribution curve and the preset distribution curve to the same coordinate system, calculates the area of ​​the distribution area enclosed by the bill distribution curve and the preset distribution curve, and makes a judgment on the generated bill based on the area of ​​the distribution area. The judgment of the generated bill can be completed in a timely and accurate manner, and the intelligent analysis of the bill generation process is effectively realized. The corresponding processing instructions are generated based on the judgment results, and the operating parameters in the bill generation process are re-determined based on the received processing instructions. While effectively realizing the precise control of the bill generation process, the bill generation efficiency is effectively improved.

[0017] Furthermore, the present invention makes a judgment on the generated bill based on the regional area ratio. According to the regional area ratio, the ratio of the distribution area between the bill distribution curve and the preset distribution curve can be accurately determined, so as to more accurately complete the judgment on the generated bill, and further realize the intelligent analysis of the bill generation process, while further improving the bill generation efficiency.

[0018] Furthermore, the present invention determines whether the area ratio of the preset area meets the standards based on the difference in the total number of labels, and promptly and accurately completes the determination of whether the area ratio of the preset area meets the standards, thereby avoiding the occurrence of misjudgment. While further realizing intelligent analysis of the bill generation process, the bill generation efficiency is further improved.

[0019] Furthermore, the present invention increases the area ratio of the preset area based on the total ratio when it is determined that the area ratio of the preset area does not meet the standard, thereby avoiding the occurrence of the situation where the area ratio of the preset area does not meet the standard, and further realizes the precise control of the bill generation process, while further improving the bill generation efficiency.

[0020] Furthermore, the present invention re-judges the generated bill based on the area ratio after the preset area ratio is increased, and accurately re-judges whether the generated bill meets the standards. While further realizing intelligent analysis of the bill generation process, it further improves the bill generation efficiency.

[0021] Furthermore, the present invention determines the reason why the generated bill is unqualified based on the difference in regional area ratio, and promptly and accurately completes the determination of the reason why the generated bill is unqualified, while further realizing intelligent analysis of the bill generation process and further improving the bill generation efficiency.

[0022] Furthermore, when the present invention determines that the reason for the generated bill being unqualified is that the recognition of the label data does not meet the standards when extracting the label data, the noise reduction factor of the label data is increased based on the deviation average value, thereby effectively avoiding the occurrence of unqualified generated bills due to the noise reduction factor not meeting the standards, while further realizing precise control of the bill generation process and further improving the bill generation efficiency.

[0023] Furthermore, when the regional area ratio difference is greater than the first preset regional area ratio difference and less than or equal to the second preset regional area ratio difference, the present invention determines the reason why the generated bill is unqualified based on the label column, thereby avoiding misjudgment, further realizing intelligent analysis of the bill generation process, and further improving the bill generation efficiency.

[0024] Furthermore, when the regional area ratio difference is greater than the second preset regional area ratio difference, the present invention overlaps the bill distribution curve and the preset distribution curve, calculates the overlapping curve ratio, and determines the reason for the unqualified generated bill based on the overlapping curve ratio, thereby further realizing intelligent analysis of the data bill generation process. When the overlapping curve ratio is less than or equal to the preset overlapping curve ratio, a notification of the need to optimize the training set is issued, thereby further realizing precise control of the bill generation process, avoiding the situation where the training set used does not meet the standards, and further improving the bill generation efficiency.

[0025] Furthermore, when the present invention determines that the generation process of the bill distribution curve does not meet the standards, the bill distribution curve is vertically corrected, which effectively solves the problem that the generation process of the bill distribution curve does not meet the standards. While further realizing the precise control of the bill generation process, the bill generation efficiency is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A structural block diagram of a bill generation system according to an embodiment of the present invention; Figure 2 A flowchart of a bill generation method according to an embodiment of the present invention; Figure 3 A flowchart for determining whether a generated bill is qualified and whether the area ratio of a preset area meets the standard according to an embodiment of the present invention; Figure 4 A flow chart of determining the reason why a generated bill is unqualified according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0029] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] See also Figure 1 As shown, it is a structural block diagram of the bill generation system of the embodiment of the present invention. The system of the embodiment of the present invention includes a storage unit, an extraction unit, a processing unit, a generation unit, a training unit, a matching unit, an analysis unit and a control unit; wherein, The storage unit is used to store the relevant data for generating bills in the data column; The extraction unit is connected to the storage unit, and is used to select the label column in the data column based on demand and extract the label data; The processing unit is connected to the extraction unit and is used to convert and integrate the extracted tag data; The generating unit is connected to the processing unit and is used to generate a bill distribution curve according to the processed label data, and the training unit is used to form a preset distribution curve by learning the data in the training set; The matching unit is connected to the generating unit and the training unit respectively, and is used to superimpose the generated bill distribution curve and the preset distribution curve into the same coordinate system; The analysis unit is connected to the generation unit and is used to calculate the area of ​​the distribution region enclosed by the bill distribution curve and the preset distribution curve; The analysis unit is also used to make a decision on the generated bill based on the area of ​​the distribution area; The analysis unit is also used to generate corresponding processing instructions based on the determination result. or, completing the determination of the generated bill; The determination includes determining whether the generated bill is qualified and determining the reason for not being qualified; The control unit is connected to the extraction unit, the generation unit and the analysis unit respectively, and is used to redetermine the operating parameters in the bill generation process based on the received processing instruction.

[0031] See also Figure 2 As shown, it is a flow chart of a bill generation method according to an embodiment of the present invention. The method according to the embodiment of the present invention comprises: Step S1, storing the relevant data for which the bill needs to be generated into the data column; Step S2, selecting the label column in the data column based on demand and extracting the label data; Step S3, converting and integrating the extracted tag data; Step S4, generating the bill distribution curve according to the processed label data, and forming the preset distribution curve by learning the data in the training set; Step S5, superimposing the generated bill distribution curve and the preset distribution curve into the same coordinate system; Step S6, calculating the area of ​​the distribution region enclosed by the bill distribution curve and the preset distribution curve; Step S7, determining the generated bill based on the area of ​​the distribution region; Step S8, generating the corresponding processing instruction based on the determination result, or, completing the determination of the generated bill; The determination includes determining whether the generated bill is qualified and determining the reason for not being qualified; Step S9: re-determine the operating parameters in the bill generation process based on the received processing instruction.

[0032] See also Figure 3 As shown, it is a flow chart of determining whether the generated bill is qualified and determining whether the area ratio of the preset area meets the standard according to an embodiment of the present invention. In step S7, the process of determining the generated bill based on the area of ​​the distribution area includes: Step S71, determining a preset curve area enclosed by the preset distribution curve and the abscissa axis of the coordinate system; Step S72, calculating the ratio of the distribution area to the preset curve area, and recording the obtained ratio as the area ratio; Step S73, determining the generated bill based on the area ratio of the region; Step S74, comparing the area ratio of the region with the area ratio of a preset region; When the area ratio of the region is less than the first preset area ratio A1, the generated bill is determined to be qualified, and the determination of the generated bill is completed, wherein the first preset area ratio A1 in this embodiment is 2.1%; When the area ratio of the area is greater than or equal to the first preset area ratio A1 and less than the second preset area ratio A2, the generated bill is determined to be unqualified, and whether the preset distribution area ratio meets the standard is determined based on the tag data, wherein the second preset area ratio A2 in this embodiment is 3.9%; When the area ratio of the region is greater than or equal to the second preset area ratio A2, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region; Specifically, when the regional area ratio is less than the first preset regional area ratio A1, it indicates that the bill distribution curve is within the error range and meets the standards, and the generated bill is judged to be qualified. When the regional area ratio is greater than or equal to the first preset regional area ratio A1 and less than the second preset regional area ratio A2, it is necessary to further judge whether the bill distribution curve meets the standards. When the regional area ratio is greater than or equal to the second preset regional area ratio A2, the distribution area does not meet the standards, and the bill distribution curve does not meet the standards. The reason why the generated bill is unqualified is determined based on the regional area ratio.

[0033] Please continue reading Figure 3 As shown, the process of determining whether the area ratio of the preset region meets the standard based on the tag data in the embodiment of the present invention includes: Sum the data of the tag data in each of the tag columns to obtain the tag sum; Calculate the difference between the label sum and the preset label sum, and record the obtained difference as the label sum difference; Determining whether the area ratio of the preset area meets the standard based on the difference of the total tag value; When the tag sum difference is greater than zero, it is determined that the preset area ratio does not meet the standard, and the preset area ratio is corrected based on the tag sum difference; When the difference in the sum of the tags is less than or equal to zero, it is determined that the area ratio of the preset area meets the standard, the generated bill is unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the area; Specifically, when further determining whether the bill distribution curve meets the standards, it is determined whether the label data has increased. When the label sum is greater than the preset label sum, it indicates that the label data has increased, and the preset area ratio is corrected to make the preset area ratio match the label data. When the label data has not increased, it is determined that the distribution area does not meet the standards, and the bill distribution curve does not meet the standards. The reason why the generated bill is unqualified is determined based on the area ratio.

[0034] Please continue reading Figure 3As shown, the process of correcting the area ratio of the preset region based on the tag sum difference in the embodiment of the present invention includes: Calculate the ratio of the label sum difference to the preset label sum, and record the obtained ratio as the sum ratio; Increasing the area ratio of the preset region based on the total ratio; When the sum ratio is greater than the second preset sum ratio R2, the area ratio of the preset region is increased to 1.28 times the area ratio of the initial preset region, wherein the second preset sum ratio R2 in this embodiment is 68.9%; When the sum ratio is less than or equal to the second preset sum ratio R2 and greater than the first preset sum ratio R1, the preset area ratio is increased to 1.21 times the initial preset area ratio, wherein the first preset sum ratio R1 in this embodiment is 32.6%; When the total ratio is less than or equal to the first preset total ratio R1, increasing the area ratio of the preset region to 1.12 times the area ratio of the initial preset region; Specifically, when correcting the area ratio of the preset area, the area ratio of the preset area is increased based on the label data, the ratio of the label sum difference to the preset label sum is calculated, recorded as the sum ratio, and the area ratio of the preset area is increased based on the sum ratio. The increase in the area ratio of the preset area is proportional to the sum ratio, so that the area ratio of the preset area matches the label data.

[0035] Please continue reading Figure 3 As shown, in the embodiment of the present invention, after the area ratio of the preset area is increased, the process of re-determining the generated bill based on the area ratio of the area includes: When the area ratio of the region is less than the first preset area ratio A1, the generated bill is determined to be qualified, and the determination of the generated bill is completed; When the area ratio of the region is greater than or equal to the first preset area ratio A1, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region; Specifically, after increasing the preset area ratio based on the total ratio, the generated bill is re-determined whether it is qualified based on the area ratio. When the area ratio is less than the first preset area ratio A1, the generated bill is determined to be qualified within the error range. When the area ratio is greater than or equal to the first preset area ratio A1, it indicates that the increase in the label data does not meet the adjustment range of the preset area ratio, the distribution area does not meet the standards, and the bill distribution curve does not meet the standards. The reason why the generated bill is unqualified is determined based on the area ratio.

[0036] See also Figure 4 As shown, it is a flow chart of determining the reason why the generated bill is unqualified according to an embodiment of the present invention. The process of determining the reason why the generated bill is unqualified based on the area ratio according to the embodiment of the present invention includes: Calculating the difference between the area ratio of the region and the area ratio of the second preset region, and recording the obtained difference as the area ratio difference of the region; The reason why the generated bill is unqualified is determined based on the difference in the area ratio; When the area ratio difference is less than or equal to the first preset area ratio difference △E1, the reason for determining that the generated bill is unqualified is that the identification of the label data does not meet the standard when the label data is extracted, and the noise reduction factor of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve, wherein the first preset area ratio difference △E1 in this embodiment is 12.9%; When the area ratio difference is greater than the first preset area ratio difference △E1 and less than or equal to the second preset area ratio difference △E2, the reason why the generated bill is unqualified is determined based on the label column, wherein the second preset area ratio difference △E2 in this embodiment is 36.7%; When the area ratio difference is greater than the second preset area ratio difference ΔE2, determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve; Specifically, based on the regional area ratio difference, the reason why the generated bill is unqualified can be accurately determined. When the regional area ratio difference is less than or equal to the first preset regional area ratio difference △E1, it indicates that part of the label data is incorrectly extracted, and the noise reduction ratio in the identification and extraction process of the label data does not meet the standard, and the noise reduction ratio needs to be corrected. When the regional area ratio difference is greater than the first preset regional area ratio difference △E1 and less than or equal to the second preset regional area ratio difference △E2, the accuracy of the bill distribution curve is analyzed according to the label column to accurately determine the reason why the generated bill is unqualified. When the regional area ratio difference is greater than the second preset regional area ratio difference △E2, the reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

[0037] Please continue reading Figure 4 As shown, the process of correcting the noise reduction ratio of the tag data based on the superimposed bill distribution curve and the preset distribution curve in the embodiment of the present invention includes: Separately counting the label columns in the preset distribution curve and the bill distribution curve; Determine the preset item value of each of the label columns in the preset distribution curve, and the actual item value of each of the label columns in the bill distribution curve; Calculating the absolute value of the difference between each of the preset item values ​​and each of the corresponding actual item values, and recording the obtained absolute value of the difference as the item deviation value; Calculate the ratio of each item deviation value to the corresponding preset item value, and record the obtained ratio as the item deviation ratio; Calculate the average value of the deviation ratios of the items, and record the average value as the deviation average value; Increasing the noise reduction factor of the label data based on the deviation average value; When the deviation average value is greater than the second preset deviation average value V2, the noise reduction ratio is increased to 1.122 times the initial noise reduction ratio, wherein the second preset deviation average value V2 in this embodiment is 52%; When the deviation average value is less than or equal to the second preset deviation average value V2 and greater than the first preset deviation average value V1, the noise reduction ratio is increased to 1.089 times the initial noise reduction ratio, wherein the first preset deviation average value V1 of this embodiment is 16%; When the deviation average value is less than or equal to the first preset deviation average value V1, the noise reduction ratio is increased to 1.056 times of the initial noise reduction ratio; Specifically, when the noise reduction ratio needs to be corrected, the absolute value of the difference between each preset item value and the corresponding actual item value is calculated as the item deviation value, the ratio of each item deviation value to the corresponding preset item value is calculated as the item deviation ratio, and the average value of each item deviation ratio is obtained as the deviation average value. The deviation average value can determine the degree of deviation between each actual item value and the preset item value. Increasing the noise reduction ratio according to the deviation average value can accurately correct the noise reduction ratio. The degree of increase in the noise reduction ratio is proportional to the deviation average value, so that the corrected noise reduction ratio can make the recognition and extraction of label data meet the standards.

[0038] Please continue reading Figure 4 As shown, the process of determining the reason why the generated bill is unqualified based on the tag column in the embodiment of the present invention includes: Counting the number of the tag columns, and recording the obtained number as the total number of tag columns; Determining the reason why the generated bill is unqualified based on the total number of the tag columns; When the total number of label columns is greater than the preset total number of label columns G, the reason for determining that the generated bill is unqualified is that the identification of the label data during the extraction of the label data does not meet the standard, and the noise reduction ratio of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve, wherein the preset total number of label columns G in this embodiment is 229; When the total number of the label columns is less than or equal to the preset total number of the label columns G, determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve; Specifically, when determining the reason why the generated bill is unqualified based on the label column, when the total number of label columns is greater than the preset total number of label columns, it is determined that the accuracy of the generated bill distribution curve meets the standard, and the reason is that the noise reduction ratio of the label data does not meet the standard. When the total number of label columns is less than or equal to the preset total number of label columns, it is determined that the accuracy of the generated bill does not meet the standard. The reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

[0039] Please continue reading Figure 4 As shown, the process of determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve in the embodiment of the present invention includes: Overlapping the bill distribution curve with the preset distribution curve; Determining the overlap curve length of the overlapped portion of the bill distribution curve and the preset distribution curve; Calculating the ratio of the length of the coincidence curve to the total length of the preset distribution curve, and recording the obtained ratio as the coincidence curve ratio; Determining the reason why the generated bill is unqualified based on the coincidence curve ratio; When the coincidence curve ratio is less than or equal to the preset coincidence curve ratio L, it is determined that the training set used to form the preset distribution curve does not meet the standard, and a notification that the training set needs to be optimized is issued, wherein the preset coincidence curve ratio L in this embodiment is 99.3%; When the coincidence curve ratio is greater than the preset coincidence curve ratio L, it is determined that the generation process of the bill distribution curve does not meet the standard, and the bill distribution curve is vertically corrected; Specifically, when determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve, the ratio of the overlapping curves between the bill distribution curve and the preset distribution curve is determined. When the overlapping curve ratio is less than or equal to the preset overlapping curve ratio, it indicates that the overlapping curve lengths of the bill distribution curve and the preset distribution curve do not meet the standard, and the preset distribution curve needs to be reformed and the training set needs to be reselected. When the overlapping curve ratio is greater than the preset overlapping curve ratio, it indicates that the bill distribution curve meets the standard, and the vertical gap between the bill distribution curve and the preset distribution curve does not meet the standard, and the bill distribution curve needs to be vertically corrected.

[0040] Please continue reading Figure 4 As shown, the process of vertically correcting the bill distribution curve in the embodiment of the present invention includes: Based on the preset distribution curve, the bill distribution curve is scanned to overlap with the preset distribution curve; sequentially determining the overlap degree of the bill distribution curve and the preset distribution curve when the data points at each of the label columns overlap; Determine the label column when the overlap degree is the largest, and record the obtained label column as a reference label column; Moving the bill distribution curve based on the reference label column to complete the vertical correction; Specifically, when the overlap curve ratio is greater than the preset overlap curve ratio, the bill distribution curve can be accurately corrected based on the overlap degree scanned when the data points at each of the label columns overlap. Example 1

[0041] The relevant data on the social security payment details of 26 insured employees in the company for which bills need to be generated in March are selected to obtain the distribution curve of the insured employees-social security payment bills in that month, analyze the social security payment situation of the insured employees in the company in that month, store the relevant data on the social security payment details in the data column, determine the individual insured person in a single label column in the data column, and extract the social security payment label data of the insured person in that month corresponding to the label column, and complete the extraction of the social security payment label data corresponding to the insured person in each label column in the data column in turn, and convert and integrate the extracted social security payment label data in that month. The conversion processing can unify the format of the social security payment label data, and the integration processing can classify the label column and label data of the social security payment label data in a regular manner. A bill distribution curve is generated according to the processed label data to complete the generation of the bill, and the data in the training set are selected for learning to generate a preset distribution curve. The data in the training set include basic information of company employees, salary data, social security policy-related data, and historical payment data.

[0042] If you need to obtain the social security payment bill distribution curve of the insured employees in each department of the company in that month, after converting the social security payment tag data with the department name in that month, integrate the social security payment tag data, integrate and classify the social security payment tag data in that month by department, and generate the bill distribution curve of each department of the company based on the converted and sorted tag data.

[0043] The generated bill distribution curve and the preset distribution curve are superimposed on the same coordinate system, the area of ​​the distribution region enclosed by the bill distribution curve and the preset distribution curve is calculated, and the area of ​​the preset curve enclosed by the preset distribution curve and the horizontal axis of the coordinate system is determined.

[0044] Calculate the distribution area: 1.45 cm 2 With the preset curve area of ​​80.56cm 2 The ratio of the regional area is 1.8%, which is less than or equal to the first preset regional area ratio of 2.1%. The generated bill is judged to be qualified, and the judgment of the generated bill is completed. Example 2

[0045] The social security payment details of 26 insured employees within the company for which bills need to be generated in May are selected to obtain a distribution curve of insured employees and social security payment bills in that month, and the social security payment situation of the insured employees within the company in that month is analyzed. The process of generating a bill distribution curve based on the social security payment details is the same as that in Example 1, and the process of selecting data in the training set for learning to generate a preset distribution curve is the same as that in Example 1. The generated bill distribution curve and the preset distribution curve are superimposed on the same coordinate system, the area of ​​the distribution region enclosed by the bill distribution curve and the preset distribution curve is calculated, and the area of ​​the preset curve enclosed by the preset distribution curve and the horizontal axis of the coordinate system is determined.

[0046] Calculate the distribution area: 1.77 cm 2 The preset curve area is 80.21cm 2The area ratio is 2.2%, which is greater than or equal to the first preset area ratio of 2.1% and less than the second preset area ratio of 3.9%. The generated bill is determined to be unqualified. Based on the label data, it is determined whether the preset area ratio meets the standard. The social security payment label data corresponding to the insured persons in each label column in that month are summed to obtain the total label. The difference between the total label 158692 and the preset label total 123435 is calculated. The total label difference is 35257, and the total label difference is greater than zero. It is determined that the preset area ratio does not meet the standard. The label is calculated. The ratio of the total difference 35257 to the preset label sum 123435 is 28.6%, which is less than or equal to the first preset total ratio 32.6%. The preset area ratio is increased to 1.12 times of the initial preset area ratio. After the preset area ratio is increased, the generated bill is re-evaluated based on the area ratio. The first preset area ratio is increased to 2.352%. The area ratio of 2.2% is less than the first preset area ratio of 2.352%. The generated bill is judged to be qualified, and the judgment of the generated bill is completed. Example 3

[0047] The relevant data on the social security payment details of 26 insured employees within the company for which bills need to be generated in August are selected to obtain a distribution curve of insured employees-social security payment bills within that month, and the social security payment situation of the insured employees within the company within that month is analyzed. The process of generating a bill distribution curve based on the relevant data on social security payment details is the same as that in Example 1, and the process of selecting data in the training set for learning to generate a preset distribution curve is the same as that in Example 1. The generated bill distribution curve and the preset distribution curve are superimposed on the same coordinate system, the area of ​​the distribution area enclosed by the bill distribution curve and the preset distribution curve is calculated, and the area of ​​the preset curve enclosed by the preset distribution curve and the horizontal axis of the coordinate system is determined.

[0048] Calculate the distribution area: 5.85 cm 2 With the preset curve area of ​​80.13cm 2The ratio of the area ratio is 7.3%, which is greater than or equal to the second preset area ratio of 3.9%, and the generated bill is determined to be unqualified. The difference between the area ratio of 7.3% and the second preset area ratio of 3.9% is calculated. The area ratio difference is 3.4%, which is less than or equal to the first preset area ratio difference of 12.9%. When the label data is extracted, the recognition of the label data does not meet the standard. The label columns in the preset distribution curve and the bill distribution curve are counted, and the preset item values ​​of each label column in the preset distribution curve and the actual item values ​​of each label column in the bill distribution curve are determined. The absolute value of the difference between each preset item value and each actual item value is calculated as the item deviation value, and the ratio of each item deviation value to each preset item value is calculated as the item deviation ratio. The average value of the item deviation ratio is obtained, and the deviation average value is 30.07%, which is less than or equal to the second preset deviation average value of 52% and greater than the first preset deviation average value of 16%. The noise reduction ratio is increased to 1.089 times the initial noise reduction ratio. Example 4

[0049] The relevant data on the social security payment details of 26 insured employees within the company for which bills need to be generated in December are selected to obtain a distribution curve of insured employees-social security payment bills within that month, and the social security payment situation of the insured employees within the company within that month is analyzed. The process of generating a bill distribution curve based on the relevant data on social security payment details is the same as that in Example 1, and the process of selecting data in the training set for learning to generate a preset distribution curve is the same as that in Example 1. The generated bill distribution curve and the preset distribution curve are superimposed on the same coordinate system, the area of ​​the distribution region enclosed by the bill distribution curve and the preset distribution curve is calculated, and the area of ​​the preset curve enclosed by the preset distribution curve and the horizontal axis of the coordinate system is determined.

[0050] Calculate the distribution area: 16.23 cm 2 With the preset curve area of ​​80.37cm 2The area ratio is 20.2%, which is greater than or equal to the second preset area ratio of 3.9%. The generated bill is determined to be unqualified. The difference between the area ratio of 20.2% and the second preset area ratio of 3.9% is calculated. The area ratio difference is 16.3%, which is greater than the first preset area ratio difference of 12.9% and less than or equal to the second preset area ratio difference of 36.7%. The number of label columns is counted. The total number of label columns is 26, which is less than or equal to the preset total number of label columns of 229. The bill distribution curve and the preset distribution curve are overlapped to determine the overlap curve length of the overlapped part of the bill distribution curve and the preset distribution curve. The ratio of the overlap curve length of 10.17 cm to the total curve length of 10.2 cm of the preset distribution curve is calculated. The overlap curve ratio is 99.7%, which is greater than the preset overlap curve ratio. The value is 99.3%, which determines that the generation process of the bill distribution curve does not meet the standard, and makes a longitudinal correction to the bill distribution curve. Taking the preset distribution curve as the benchmark, the bill distribution curve and the preset distribution curve are scanned for overlap, and the overlap degree of the scan when the data points of the bill distribution curve and the preset distribution curve at each label column are overlapped are determined in turn, and the label column with the largest overlap degree is determined, and the obtained label column is recorded as the benchmark label column, which is the 9th one. Based on the 9th benchmark label column, the bill distribution curve is moved to overlap with the preset distribution curve to complete the longitudinal correction.

[0051] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A bill generation method, characterized in that: include: Store the relevant data for generating bills in the data column; Select a label column in the data column based on the requirement and extract label data; Converting and integrating the extracted label data; Generate a bill distribution curve based on the processed label data, and form a preset distribution curve by learning the data in the training set; Superimposing the generated bill distribution curve and the preset distribution curve into the same coordinate system; Calculating the area of ​​a distribution region enclosed by the bill distribution curve and the preset distribution curve; Making a determination on the generated bill based on the area of ​​the distribution region; Generate corresponding processing instructions based on the judgment results, or, completing the determination of the generated bill; The determination includes determining whether the generated bill is qualified and determining the reason for not being qualified; The operating parameters in the bill generation process are re-determined based on the received processing instruction.

2. The bill generation method according to claim 1, characterized in that: The process of determining the generated bill based on the area of ​​the distribution area includes: Determining a preset curve area enclosed by the preset distribution curve and the abscissa axis of the coordinate system; Calculating the ratio of the distribution area to the preset curve area, and recording the obtained ratio as the area ratio; When the area ratio of the region is less than the area ratio of the first preset region, the generated bill is determined to be qualified, and the determination of the generated bill is completed; When the area ratio of the region is greater than or equal to the area ratio of the first preset region and less than the area ratio of the second preset region, the generated bill is determined to be unqualified, and whether the area ratio of the preset distribution region meets the standard is determined based on the tag data; When the area ratio of the region is greater than or equal to the area ratio of the second preset region, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio.

3. The bill generation method according to claim 2, characterized in that: The process of determining whether the area ratio of the preset area meets the standard based on the tag data includes: Sum the data of the tag data in each of the tag columns to obtain the tag sum; Calculate the difference between the label sum and the preset label sum, and record the obtained difference as the label sum difference; When the tag sum difference is greater than zero, it is determined that the preset area ratio does not meet the standard, and the preset area ratio is corrected based on the tag sum difference; When the difference in the total of the labels is less than or equal to zero, it is determined that the area ratio of the preset region meets the standard, the generated bill is unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region.

4. The bill generation method according to claim 3, characterized in that: The process of correcting the area ratio of the preset area based on the tag sum difference includes: Calculate the ratio of the label sum difference to the preset label sum, and record the obtained ratio as the sum ratio; The area ratio of the preset region is increased based on the total ratio, and the increase in the area ratio of the preset region is proportional to the total ratio.

5. The bill generation method according to claim 4, characterized in that: After the preset area ratio is increased, the process of re-determining the generated bill based on the area ratio includes: When the area ratio of the region is less than the area ratio of the first preset region, the generated bill is determined to be qualified, and the determination of the generated bill is completed; When the area ratio of the region is greater than or equal to the area ratio of the first preset region, the generated bill is determined to be unqualified, and the reason why the generated bill is unqualified is determined based on the area ratio of the region.

6. The bill generation method according to claim 5, characterized in that: The process of determining the reason why the generated bill is unqualified based on the area ratio includes: Calculating the difference between the area ratio of the region and the area ratio of the second preset region, and recording the obtained difference as the area ratio difference of the region; When the area ratio difference is less than or equal to the first preset area ratio difference, the generated bill is determined to be unqualified because the identification of the label data does not meet the standard when the label data is extracted, and the noise reduction factor of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve; When the area ratio difference is greater than the first preset area ratio difference and less than or equal to the second preset area ratio difference, determining the reason why the generated bill is unqualified based on the tag column; When the regional area ratio difference is greater than the second preset regional area ratio difference, the reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

7. The bill generation method according to claim 6, characterized in that: The process of correcting the noise reduction ratio of the tag data based on the superimposed bill distribution curve and the preset distribution curve includes: Separately counting the label columns in the preset distribution curve and the bill distribution curve; Determine the preset item value of each of the label columns in the preset distribution curve, and the actual item value of each of the label columns in the bill distribution curve; Calculating the absolute value of the difference between each of the preset item values ​​and each of the corresponding actual item values, and recording the obtained absolute value of the difference as the item deviation value; Calculate the ratio of each item deviation value to the corresponding preset item value, and record the obtained ratio as the item deviation ratio; Calculate the average value of the deviation ratios of the items, and record the average value as the deviation average value; The noise reduction factor of the label data is increased based on the deviation average value, and the increase of the noise reduction factor is proportional to the deviation average value.

8. The bill generation method according to claim 6, characterized in that: The process of determining the reason why the generated bill is unqualified based on the tag column includes: Counting the number of the tag columns, and recording the obtained number as the total number of tag columns; When the total number of label columns is greater than the preset total number of label columns, the reason for determining that the generated bill is unqualified is that the identification of the label data during the extraction of the label data does not meet the standard, and the noise reduction ratio of the label data is corrected based on the superimposed bill distribution curve and the preset distribution curve; When the total number of the label columns is less than or equal to the preset total number of the label columns, the reason why the generated bill is unqualified is determined based on the bill distribution curve and the preset distribution curve.

9. The bill generation method according to claim 8, characterized in that: The process of determining the reason why the generated bill is unqualified based on the bill distribution curve and the preset distribution curve includes: Overlapping the bill distribution curve with the preset distribution curve; Determining the overlap curve length of the overlapped portion of the bill distribution curve and the preset distribution curve; Calculating the ratio of the length of the coincidence curve to the total length of the preset distribution curve, and recording the obtained ratio as the coincidence curve ratio; When the coincidence curve ratio is less than or equal to the preset coincidence curve ratio, it is determined that the training set used to form the preset distribution curve does not meet the standard, and a notification that the training set needs to be optimized is issued; When the coincidence curve ratio is greater than the preset coincidence curve ratio, it is determined that the generation process of the bill distribution curve does not meet the standard, and the bill distribution curve is vertically corrected.

10. The bill generation method according to claim 9, characterized in that: The process of vertically correcting the bill distribution curve includes: Based on the preset distribution curve, the bill distribution curve is scanned to overlap with the preset distribution curve; sequentially determining the overlap degree of the bill distribution curve and the preset distribution curve when the data points at each of the label columns overlap; Determine the label column when the overlap degree is the largest, and record the obtained label column as a reference label column; The bill distribution curve is moved based on the reference label column to complete the vertical correction.

Images