Electronic invoice information verification method, device, terminal and storage medium

Abstract

The present invention relates to the field of electronic invoice detection technology, and discloses an electronic invoice information verification method, device, terminal and storage medium. The method comprises obtaining electronic invoice data; performing repeatability detection according to the electronic invoice data, judging whether there is intersection in the electronic invoice data, and generating and storing intersection data when it is judged that there is intersection; grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list; calculating the invoicing rate similarity of the sub-data list according to the invoicing rate; judging whether there is abnormality in the invoicing behavior of the sub-data list according to the invoicing rate similarity and the intersection data; generating early warning prompt information when it is judged that there is abnormality in the invoicing behavior, so that the supervision system can provide feedback and investigation according to the early warning prompt information. The method can detect repeated invoicing behavior and abnormal invoicing behavior in the invoicing process, and improve the accuracy of invoice verification.

Description

Technical Field

[0001] The present invention relates to the field of electronic invoice detection technology, and in particular to an electronic invoice information verification method, device, terminal and storage medium. Background Art

[0002] At present, the existing electronic invoice anomaly detection technology mainly generates a transaction hash value based on the user's invoice application. The transaction hash value is used to verify the integrity of the invoice application. When the hash values ​​of other transactions in the block are abnormal, the anomaly can be detected in time according to the transaction hash value. And through the binding relationship between the hash value of the invoice transaction and the characteristic value of the invoice transaction, when the characteristic values ​​of other invoice transactions in the block are abnormal, the anomaly can be detected in time according to the hash value of the invoice transaction. However, the existing technology fails to detect the behavior of repeated invoicing during the invoicing process, and the phenomenon of repeated invoice issuance during the invoicing process reduces the efficiency of invoice management and the credibility of invoices. Summary of the invention

[0003] The present invention provides an electronic invoice information verification method, device, terminal and storage medium, which can detect repeated invoice issuance behavior and abnormal invoice issuance behavior during the invoice issuance process, thereby improving the accuracy of invoice verification and the efficiency of invoice management.

[0004] In a first aspect, in order to solve the above technical problems, the present invention provides an electronic invoice information verification method, comprising:

[0005] Acquire electronic invoice data; wherein the electronic invoice data includes invoice code, invoice number and invoicing time;

[0006] Performing a repeatability check based on the electronic invoice data to determine whether the electronic invoice data is crossed, and generating and storing crossed data when it is determined that there is crossed;

[0007] Grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list;

[0008] According to the billing rate, calculating the billing rate similarity of the sub-data list;

[0009] Judging whether there is an abnormality in the billing behavior of the sub-data list according to the billing rate similarity and the cross data;

[0010] When it is determined that the invoicing behavior is abnormal, an early warning prompt information is generated, so that the supervision system can provide feedback and conduct investigation based on the early warning prompt information.

[0011] Preferably, grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list includes:

[0012] The invoicing time in the electronic invoice data is grouped to obtain a time sub-data list; wherein the time sub-data list includes a first time sub-data list and a second time sub-data list;

[0013] According to the time sub-data list, the billing rate of the first time sub-data list and the billing rate of the second time sub-data list are calculated;

[0014] Grouping the invoice codes in the electronic invoice data to obtain a code sub-data list; wherein the code sub-data list includes a first code sub-data list and a second code sub-data list;

[0015] According to the calculation of the code sub-data list, the billing rate of the first code sub-data list and the billing rate of the second code sub-data list are obtained.

[0016] Preferably, the invoicing rate is specifically: the ratio of the invoicing quantity of the set invoicing unit to the total invoicing quantity of all invoicing units in the sub-data list within the set invoicing time.

[0017] Preferably, the calculation formula of the billing rate similarity is:

[0018]

[0019]

[0020] In the formula, is the time billing rate similarity, is the code billing rate similarity, is the billing rate of the first code sub-data list, The billing rate for the second code sub-data list, is the billing rate of the first sub-data list, The billing rate of the second time sub-data list.

[0021] Preferably, judging whether there is an abnormality in the billing behavior of the sub-data list according to the billing rate similarity and the cross data includes:

[0022] It is determined whether the similarity of the billing rate of the code sub-data list is less than a first threshold value. When it is determined that the similarity of the billing rate is less than the first threshold value, it is determined that the billing behavior in the code sub-data list is abnormal.

[0023] Preferably, judging whether the invoicing behavior of the sub-data list is abnormal based on the invoicing rate similarity and the cross data further includes:

[0024] It is determined whether the similarity of the billing rate of the time sub-data list is greater than a second threshold value. When it is determined that the similarity of the billing rate is greater than the second threshold value, it is determined that the billing behavior in the time sub-data list is abnormal.

[0025] Preferably, after judging whether the billing behavior of the sub-data list is abnormal according to the billing rate similarity and the cross data, the method further includes:

[0026] Further determining whether the abnormal invoicing unit is the same as the invoicing unit in the cross data; when the abnormal invoicing unit is the same as the invoicing unit in the cross data, determining that duplicate invoices exist, and generating an abnormal list;

[0027] Adding the invoicing quantity of each invoicing unit in the abnormal list at all invoicing times to obtain the abnormal data quantity;

[0028] The abnormal data volume is compared with a third threshold value. When the abnormal data volume is less than the third threshold value, it is determined that the abnormal data volume is related to data collection abnormality; when the abnormal data volume is greater than the third threshold value, it is determined that the abnormal data volume is related to abnormal invoicing behavior.

[0029] In a second aspect, the present invention provides an electronic invoice information verification device, comprising:

[0030] A data acquisition module, used to acquire electronic invoice data;

[0031] A cross detection module, used to perform a repeatability detection based on the electronic invoice data to determine whether the electronic invoice data has a crossover, and when it is determined that there is a crossover, generate and store crossover data;

[0032] A data grouping module, used for grouping the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list;

[0033] A similarity calculation module, used for calculating the similarity of the billing rate of the sub-data list according to the billing rate;

[0034] A behavior detection module, used for judging whether the invoicing behavior of the sub-data list is abnormal according to the invoicing rate similarity and the cross data;

[0035] The warning generation module is used to generate warning prompt information when it is determined that the invoicing behavior is abnormal, so that the supervision system can provide feedback and investigation based on the warning prompt information.

[0036] In a third aspect, the present invention also provides a terminal comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned electronic invoice information verification methods when executing the computer program.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the electronic invoice information verification methods described above.

[0038] Compared with the prior art, the present invention has the following beneficial effects: the embodiment of the present invention provides an electronic invoice information verification method, device, terminal and storage medium. The method includes: obtaining electronic invoice data; wherein the electronic invoice data includes an invoice code, an invoice number and an invoice time; performing a repeatability test based on the electronic invoice data to determine whether the electronic invoice data has an intersection, and when it is determined that there is an intersection, generating and storing the intersection data; grouping the electronic invoice data to obtain a sub-data list, and calculating the invoice rate of the sub-data list; calculating the invoice rate similarity of the sub-data list based on the invoice rate; determining whether the invoice behavior of the sub-data list is abnormal based on the invoice rate similarity and the intersection data; when it is determined that the invoice behavior is abnormal, generating an early warning prompt information so that the supervision system can provide feedback and investigation based on the early warning prompt information.

[0039] In the present invention, the method first obtains electronic invoice data including invoice code, invoice number and invoicing time to lay the foundation for subsequent verification. Then, through repeatability detection, the method can effectively identify and record repeated invoices, thereby avoiding the problem of duplicate invoices. In addition, the method also includes grouping the electronic invoice data, calculating the invoicing rates of different groups, and comparing the similarities of these invoicing rates, which helps to reveal the pattern and frequency of invoicing behavior, and then identify abnormal invoicing behavior patterns. When it is detected that the similarity of different invoicing rates is greater than or less than a preset threshold or there is cross data, the method will determine whether there is an abnormality in the invoicing behavior, and generate a warning prompt message after confirming the abnormality. In summary, the method can detect repeated invoicing behavior and abnormal invoicing behavior in the invoicing process, and improve the accuracy of invoice verification and the efficiency of invoice management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of the electronic invoice information verification method provided by the first embodiment of the present invention;

[0041] Figure 2It is a schematic diagram of the structure of the electronic invoice information verification device provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Reference Figure 1 The first embodiment of the present invention provides an electronic invoice information verification method, comprising the following steps:

[0044] S11, obtaining electronic invoice data.

[0045] S12, performing a repeatability check based on the electronic invoice data to determine whether there is any intersection in the electronic invoice data, and generating and storing intersection data when it is determined that there is any intersection.

[0046] S13, grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list.

[0047] S14, calculating the similarity of the billing rates of the sub-data lists according to the billing rates.

[0048] S15, judging whether there is any abnormality in the billing behavior of the sub-data list according to the billing rate similarity and the cross data.

[0049] S16, when it is determined that the invoicing behavior is abnormal, an early warning prompt information is generated, so that the supervision system can provide feedback and conduct investigation according to the early warning prompt information.

[0050] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0051] In step S11, the electronic invoice data is obtained. It is worth noting that the acquisition of electronic invoice data can be: interface call, if the invoice data is stored in an online database or provided through an API interface, these interfaces can be called programmatically to obtain the data. This usually requires network programming knowledge and understanding of API documents; data import, if there is an electronic file of the electronic invoice, such as PDF or OFD format, the corresponding reader or library can be used to parse the file content and extract the invoice data, and for structured data files, such as electronic invoices in XML or JSON format, these files can be directly read and parsed to obtain the required data; scanning and OCR technology, use a scanner to scan the paper invoice into an electronic image, and then use optical character recognition (OCR) technology to convert the text in the image into machine-readable data.

[0052] Specifically, the electronic invoice data includes an invoice code, an invoice number and an invoicing time. Among them, the invoice code is a code used to uniquely identify an invoice to ensure the uniqueness of each invoice. It usually includes the region code, year, industry category code, invoice type identification and a serial number, which helps to quickly identify the source and type of the invoice. The invoice number is a supplement to the invoice code and is another important number used to identify the invoice. This number is usually generated sequentially and can reflect the number of invoices issued by the invoicing party within a set time period. The invoicing time refers to the specific date and time when the invoice is issued. In the present invention, due to the uniqueness of the invoice code and number, the system can prevent the same invoice from being issued repeatedly by checking whether the same code and number already exist in the database. The invoicing time can also be used to determine whether the same invoice is issued repeatedly.

[0053] In step S12, a repeatability test is performed based on the electronic invoice data to determine whether the electronic invoice data is cross-linked. When it is determined that there is cross-linking, cross-linking data is generated and stored. Specifically, the main purpose of repeatability detection is to identify whether there is the same or similar invoice data, which usually involves comparing key information such as invoice code, invoice number and invoicing time. In the detection process, various algorithms or technologies, such as hash functions, data fingerprints, similarity calculations, etc., can be used to identify repeated or similar invoice data. After detecting repeated or similar invoice data, it is necessary to further determine whether these data are cross-linked, that is, whether they belong to repeated invoicing behaviors of different invoicing units or different time periods. The determination of cross-linking data usually needs to comprehensively consider multiple factors, such as invoicing units, invoicing time, amount, commodity or service information, etc., to determine whether there is abnormal invoicing behavior. When it is determined that there is cross-linking data, these data need to be generated and stored for subsequent analysis and processing. The storage of cross-linking data can use a database, a file system or other storage medium, and the security, integrity and accessibility of the data need to be ensured. It is worth noting that the cross-linking data will be used in subsequent steps to further determine whether the collected data is abnormal or the invoicing behavior is abnormal.

[0054] In step S13, the electronic invoice data is grouped to obtain a sub-data list, and the invoicing rate of the sub-data list is calculated.

[0055] Preferably, the grouping of the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list includes: grouping the invoicing time in the electronic invoice data to obtain a time sub-data list; wherein the time sub-data list includes a first time sub-data list and a second time sub-data list; and calculating according to the time sub-data list to obtain the invoicing rate of the first time sub-data list and the invoicing rate of the second time sub-data list.

[0056] Preferably, the grouping of the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list also includes: grouping the invoice codes in the electronic invoice data to obtain a code sub-data list; wherein the code sub-data list includes a first code sub-data list and a second code sub-data list; and calculating according to the code sub-data list to obtain the invoicing rate of the first code sub-data list and the invoicing rate of the second code sub-data list.

[0057] Preferably, the invoicing rate is specifically: the ratio of the invoicing quantity of the set invoicing unit to the total invoicing quantity of all invoicing units in the sub-data list within the set invoicing time.

[0058] Specifically, the collected electronic invoice data is grouped according to the set standards. In the present invention, the grouping standard can be the invoice code or the invoicing time. Such grouping helps to analyze the invoice data with similar characteristics separately in the subsequent steps. If grouped by the invoicing time, a list of electronic invoice data in different time periods can be obtained, such as the first time sub-data list and the second time sub-data list. This grouping method is convenient for analyzing the invoicing volume in different time periods and identifying the distribution characteristics of the invoicing behavior in time. If grouped by invoice code, a list of electronic invoice data with different invoice codes can be obtained, such as the first code sub-data list and the second code sub-data list. The invoice code usually contains information such as the source area and industry category of the invoice, so the invoice can be classified according to the code.

[0059] Specifically, after completing the grouping, the invoicing rate of each sub-data list needs to be calculated. The invoicing rate is used to measure the invoicing situation of the invoicing unit within a set time period or invoice code range. The invoicing rate refers to the ratio of the invoicing volume of the set invoicing unit to the total invoicing volume of all invoicing units in a certain sub-data list. For example, assuming a sub-data list within a time period, in which a total of 100 invoices are issued, and a specific invoicing unit has issued 20 invoices, then the invoicing rate of this invoicing unit in this time period is 20%. In this way, the invoicing rate of different units in a specific time period can be calculated. This invoicing rate can be used for further analysis, such as determining whether there is abnormal invoicing behavior.

[0060] In general, through grouping operations, electronic invoice data can be structured to facilitate subsequent analysis. Different grouping methods (such as by time or code) help analyze invoicing behavior from different angles. Calculating the invoicing rate can help discover the pattern and distribution of invoicing behavior. For example, some units may issue a large number of invoices in a certain period of time, or issue an abnormally large number of invoices within a certain invoice code range. The calculation of the invoicing rate is the core data in the subsequent steps. In step S14, the system will calculate the similarity based on the invoicing rates of different sub-data lists to determine whether there are any abnormalities in the invoicing behavior of these data lists. Therefore, accurate calculation of the invoicing rate is the basis for detecting abnormal invoicing behavior.

[0061] In step S14, the similarity of the billing rates of the sub-data lists is calculated according to the billing rates. Preferably, the calculation formula of the similarity of the billing rates is:

[0062]

[0063]

[0064] In the formula, is the time billing rate similarity, is the code billing rate similarity, is the billing rate of the first code sub-data list, The billing rate for the second code sub-data list, is the billing rate of the first sub-data list, The billing rate of the second time sub-data list.

[0065] Specifically, step S14 is to perform similarity calculation on the invoicing rates of the grouped sub-data lists, the main purpose of which is to compare the invoicing rates of different sub-data lists, so as to determine whether there are abnormal differences between them.

[0066] Specifically, through similarity calculation, it can be found whether the invoicing behaviors between different sub-data lists (such as time periods or invoice code groups) are similar. If the similarity of the invoice code grouping is high, it means that the invoicing behaviors of these data lists are consistent and are judged to be normal; if the similarity is low, there may be abnormal invoicing behaviors. If the similarity of the invoice time grouping is high, it means that the invoicing behaviors of these data lists are abnormal; if the similarity is low, it means that the invoicing behaviors of these data lists are consistent and are judged to be normal. This step is particularly used to discover that some units may exhibit abnormal invoicing behaviors under certain time periods or set codes, such as sudden large-scale invoicing or too low invoicing.

[0067] Obviously, the conditions required to judge the similarity of invoice code groups and the similarity of invoice time groups are different, which will be reflected in the conditional judgment of subsequent steps, but both can help the system detect abnormal invoicing behaviors in different dimensions.

[0068] In step S15, it is determined whether there is any abnormality in the billing behavior of the sub-data list according to the billing rate similarity and the cross data.

[0069] Preferably, judging whether there is any abnormality in the issuing behavior of the sub-data list based on the issuing rate similarity and the cross data includes: judging whether the issuing rate similarity of the code sub-data list is less than a first threshold value; when it is judged that the issuing rate similarity is less than the first threshold value, it is judged that there is any abnormality in the issuing behavior within the code sub-data list.

[0070] Preferably, judging whether there is any abnormality in the invoicing behavior of the sub-data list based on the invoicing rate similarity and the cross data also includes: judging whether the invoicing rate similarity of the time sub-data list is greater than a second threshold; when it is judged that the invoicing rate similarity is greater than the second threshold, it is judged that there is any abnormality in the invoicing behavior in the time sub-data list.

[0071] It is worth noting that the meaning of invoice code grouping similarity is different from the meaning of invoice time grouping similarity.

[0072] Among them, in the meaning of the similarity of invoice code groups, the high similarity of invoice code groups means that the invoicing behaviors in different invoice code groups are very similar. For example, the number and frequency of invoice issuance in different industries, regions or types are basically the same. This usually indicates that the invoicing behavior is normal and there is no obvious abnormality. This consistency shows that the invoicing units under each invoice code are normal in operation. If the similarity of invoice code groups is low, it means that there are large differences in the invoicing behaviors between groups of different invoice codes. For example, the unit invoicing volume under some invoice codes is much higher than that of other invoice code ranges. This may mean that the set invoice code has abnormalities in the invoicing behavior.

[0073] In the meaning of the invoice time grouping similarity, contrary to the invoice code grouping similarity, high or low similarity of invoice time grouping has different meanings. If the similarity of invoice time grouping is very high, it means that the invoicing behavior in different time periods is very consistent. This situation is usually abnormal, because in the real business environment, the invoicing volume in different time periods will naturally fluctuate due to seasons, business volume changes, etc. If the similarity is too high, it may mean that abnormal invoicing behavior occurs in the system. Low similarity of invoice time grouping means that there are natural fluctuations in invoicing behavior in different time periods, which in turn indicates compliance with normal invoicing behavior. For example, a large business volume in a certain time period leads to an increase in invoicing volume, while a small business volume in another time period leads to a decrease in invoicing volume. This fluctuation is in line with normal market behavior and business laws, and is therefore not considered abnormal.

[0074] In general, the similarity calculation of invoice code groups is to see whether the invoicing behavior is similar across codes (such as industries or regions). Typically, the invoicing behavior of different codes may be different, so if the similarity is too high, it may mean that the behavior between these codes is not different, but abnormal. The similarity calculation of invoice time groups is to analyze whether the invoicing behavior is consistent across different time periods. Invoicing volume in different time periods usually fluctuates, so if the similarity of time groups is too high, it means that the invoicing behavior in these time periods is too consistent, which may indicate abnormal behavior.

[0075] Specifically, the first threshold is used to determine whether there is an abnormality in the similarity of the billing rates between different invoice code groups. Generally, the setting of the first threshold needs to consider the following factors: historical data analysis, by analyzing the normal billing behavior in the past, find the natural fluctuation range of the similarity between different invoice code groups. For example, under most normal operations, the similarity of the billing rates of code groups usually fluctuates within a certain range, and this range can be used as the basis for determining the threshold. Statistical model, using statistical methods (such as standard deviation, variance, etc.) to quantify the normal fluctuation range of the billing behavior between different code groups. Assuming that the billing behavior of different industries or regions varies greatly under normal circumstances, a statistical distribution can be used to model (such as Gaussian distribution), and then a percentile (such as 5% or 95%) is used as the first threshold. Specifically, it is assumed that through historical data analysis, it is found that the similarity of the billing rates between different invoice code groups is mostly concentrated in the range of 60% to 90%. If the similarity is lower than 60%, it may indicate that the billing behavior of these code groups is abnormal, so 60% can be set as the first threshold. That is, if the similarity of the code groups is less than 60%, the system will consider that there are problems with the billing behavior in these invoice codes.

[0076] Specifically, the second threshold is used to determine the similarity of the billing rate in different time periods, with the purpose of detecting abnormal billing behavior in time. The following factors need to be considered to determine this threshold: Seasonal and cyclical fluctuations: The billing volume of different industries in different time periods may fluctuate due to seasonal or cyclical factors. Therefore, these natural fluctuation factors must be considered when setting the threshold. Historical billing data, by analyzing past billing data, identify the similarity range of time period grouping under normal circumstances. For example, through data analysis, it is found that the similarity of billing rates between different time periods usually fluctuates between 30% and 70%, so this range can be used as a reference for the second threshold. Anomaly detection methods, statistical anomaly detection methods such as z-score (standard score) or IQR (interquartile range) can be used to determine the similarity outside the normal range. When the similarity of billing rates in a certain time period deviates from the average level by more than a certain degree, it can be considered that there is an anomaly, and the critical value of this deviation is the second threshold. Specifically, it is assumed that through data analysis, it is known that the similarity of billing rates in different time periods fluctuates between 40% and 80% under normal circumstances. When the similarity is higher than 80%, it means that the billing behavior is too consistent, so 80% can be set as the second threshold. In other words, if the similarity of the billing rate of the time grouping is higher than 80%, the system will consider the billing behavior in these time periods to be abnormal.

[0077] In the present invention, the first threshold is used for the similarity of the billing rate of the invoice code group, and the setting method is usually based on the normal fluctuation range of different industries or regions. A value lower than this threshold may indicate abnormal billing behavior. The second threshold is used for the similarity of the billing rate of the invoice time group, and the setting method is based on the fluctuation pattern over time. A value higher than this threshold may indicate abnormal billing behavior. These two thresholds are determined by historical data analysis, statistical models, etc., so as to help the system identify abnormal billing behavior under different groups.

[0078] Preferably, after judging whether there is an abnormality in the invoicing behavior of the sub-data list according to the invoicing rate similarity and the cross data, it also includes: further judging whether the abnormal invoicing unit is the same as the invoicing unit in the cross data, when the abnormal invoicing unit is the same as the invoicing unit in the cross data, it is judged that there is duplicate invoice issuance, and an abnormal list is generated; the invoicing volume of each invoicing unit in the abnormal list at all invoicing times is added to obtain the abnormal data volume; the abnormal data volume is compared with a third threshold value, when the abnormal data volume is less than the third threshold value, it is judged that the abnormal data volume is related to data collection abnormality; when the abnormal data volume is greater than the third threshold value, it is judged that the abnormal data volume is related to abnormal invoicing behavior.

[0079] Specifically, in the previous steps, the system has identified possible abnormal invoicing behaviors through invoicing rate similarity calculation and cross-data. This step is to further verify the specific nature of the abnormal behavior. Abnormal invoicing units refer to invoicing units that behave abnormally within certain time periods or code ranges, as detected by similarity analysis or other methods. The invoicing units in the cross-data are the invoicing units involved in the invoice cross-behavior (possibly repeated invoicing) identified by repeatability detection. If the abnormal invoicing unit is the same unit as the invoicing unit in the cross-data, the system can confirm that these units have repeated invoicing behavior. Once repeated invoicing is confirmed, the system will generate an exception list containing all unit information that has repeated invoicing behavior.

[0080] Specifically, the third threshold is used to distinguish whether the abnormal behavior is caused by data collection problems or by real invoicing behavior anomalies. When the amount of abnormal data is calculated, the system will compare this value with the preset third threshold. Through this comparison, the system can further classify abnormal behaviors: If the amount of abnormal data is relatively small, it means that these abnormal behaviors may be caused by data collection anomalies. Data collection anomalies may include erroneous records or duplicate records caused by errors in data input, transmission or storage, rather than real invoicing behavior anomalies. If the amount of abnormal data is large, it means that these units do have significant invoicing behavior anomalies, that is, the units have abnormal invoicing behaviors in actual operations, such as large-scale invoicing or repeated invoicing in a short period of time.

[0081] In the present invention, the role of the third threshold is to help the system distinguish the nature of data anomalies and avoid misjudgment. Usually, the setting of the third threshold needs to be based on historical data. For example, if under normal circumstances, the invoice volume rarely exceeds a certain set value, then this value can be used as a reference standard for the third threshold. This comparison process ensures that the system will not generate too many false alarms due to small-scale data anomalies, and can accurately identify the real problem units.

[0082] In step S16, when it is determined that the invoicing behavior is abnormal, early warning information is generated so that the supervision system can provide feedback and conduct investigation based on the early warning information.

[0083] Specifically, the early warning information is a notification or warning automatically generated by the system when abnormal invoicing behavior is detected. The early warning content can include: which invoicing units' behaviors are marked as abnormal; the type of abnormal behavior (such as repeated invoicing, abnormally high invoicing volume, etc.); specific abnormal data (such as invoicing volume exceeding the threshold, unreasonable time distribution of invoicing behavior, etc.); the time period when the abnormality occurred and the relevant invoice code and other information. With this information, the supervision system can quickly understand the nature and scale of the abnormality and decide whether further measures need to be taken, such as data review, on-site investigation or invoice cancellation.

[0084] The following describes the working process of the present invention by taking a relatively common scenario as an example. The working process is as follows:

[0085] Obtain a large amount of electronic invoice data. Invoice data includes invoice code, invoice number, invoice time, invoice amount, and information about the invoicing company. The system performs a preliminary duplication check on the invoice data to determine whether any company has repeatedly issued the same invoice or submitted invoices with the same invoice number and code in the same time period. If the system detects that an invoice is issued repeatedly, it will generate and store relevant cross-data for subsequent processing. For example, a company issued the same invoice twice in a short period of time. The system groups the invoice data according to two dimensions: according to the invoice code (industry, region) and the invoice time. Group by invoice code: The system will classify invoices corresponding to different invoice codes, such as invoices from different regions and industries will be classified into different sub-data lists. Group by invoice time: The system groups invoice data according to time (such as quarterly, monthly), and analyzes the invoicing situation in each time period. For each sub-data list, the system calculates the invoicing rate, that is, the ratio of the number of invoices issued by each company in a sub-data list to the total invoicing volume of all companies in the list. For example, the system can calculate the proportion of invoices issued in a certain industry or region within a set time. The system calculates similarity based on the invoicing rates of different groups, and compares whether the invoicing behaviors are consistent in different time periods or different invoice codes (such as regions, industries). Invoice code similarity: The system compares whether there are large differences in the invoicing rates of different industries or regions. Usually, the invoicing behaviors of different industries or regions will be different. If the similarity is too high, it may mean that there are abnormalities in the invoicing behaviors of these industries or regions. Invoice time similarity: The system compares the invoicing behaviors of the same industry or region in different time periods. If the invoicing behaviors within the time group are too consistent (the similarity is too high), there may be anomalies. If the invoice code similarity of certain industries or regions is too low, it indicates that the invoicing behaviors of these industries or regions are abnormally different. If the invoicing similarity within a certain time period is too high, it indicates that there may be abnormalities in these invoices, such as duplicate invoicing. The system also combines previous cross-data to further determine whether there are companies that have duplicate invoicing or abnormal invoicing behaviors. After detecting abnormal invoicing behavior, the system will generate an early warning prompt message to report which companies or regions have problems with invoicing behavior.

[0086] In summary, the present invention provides an electronic invoice information verification method, including: obtaining electronic invoice data; wherein the electronic invoice data includes an invoice code, an invoice number and an invoicing time; performing a repeatability check based on the electronic invoice data to determine whether the electronic invoice data has any intersection, and when it is determined that there is an intersection, generating and storing intersection data; grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list; based on the invoicing rate, calculating the invoicing rate similarity of the sub-data list; based on the invoicing rate similarity and the intersection data, determining whether the invoicing behavior of the sub-data list is abnormal; when it is determined that the invoicing behavior is abnormal, generating early warning prompt information, so that the supervision system can provide feedback and investigation based on the early warning prompt information.

[0087] In the present invention, the method first obtains electronic invoice data including invoice code, invoice number and invoicing time to lay the foundation for subsequent verification. Then, through repeatability detection, the method can effectively identify and record repeated invoices, thereby avoiding the problem of duplicate invoices. In addition, the method also includes grouping the electronic invoice data, calculating the invoicing rates of different groups, and comparing the similarities of these invoicing rates, which helps to reveal the pattern and frequency of invoicing behavior, and then identify abnormal invoicing behavior patterns. When it is detected that the similarity of different invoicing rates is greater than or less than a preset threshold or there is cross data, the method will determine whether there is an abnormality in the invoicing behavior, and generate a warning prompt message after confirming the abnormality. In summary, the method can detect repeated invoicing behavior and abnormal invoicing behavior in the invoicing process, and improve the accuracy of invoice verification and the efficiency of invoice management.

[0088] Reference Figure 2 The second embodiment of the present invention provides an electronic invoice information verification device, comprising:

[0089] A data acquisition module, used to acquire electronic invoice data;

[0090] A cross detection module, used to perform a repeatability detection based on the electronic invoice data to determine whether the electronic invoice data has a crossover, and when it is determined that there is a crossover, generate and store crossover data;

[0091] A data grouping module, used for grouping the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list;

[0092] A similarity calculation module, used for calculating the similarity of the billing rate of the sub-data list according to the billing rate;

[0093] A behavior detection module, used for judging whether the invoicing behavior of the sub-data list is abnormal according to the invoicing rate similarity and the cross data;

[0094] The warning generation module is used to generate warning prompt information when it is determined that the invoicing behavior is abnormal, so that the supervision system can provide feedback and investigation based on the warning prompt information.

[0095] In an optional implementation, the data grouping module is specifically used to:

[0096] The invoicing time in the electronic invoice data is grouped to obtain a time sub-data list; wherein the time sub-data list includes a first time sub-data list and a second time sub-data list;

[0097] According to the time sub-data list, the billing rate of the first time sub-data list and the billing rate of the second time sub-data list are calculated;

[0098] Grouping the invoice codes in the electronic invoice data to obtain a code sub-data list; wherein the code sub-data list includes a first code sub-data list and a second code sub-data list;

[0099] According to the calculation of the code sub-data list, the billing rate of the first code sub-data list and the billing rate of the second code sub-data list are obtained.

[0100] In an optional implementation, the behavior detection module is specifically used to:

[0101] It is determined whether the similarity of the billing rate of the code sub-data list is less than a first threshold value. When it is determined that the similarity of the billing rate is less than the first threshold value, it is determined that the billing behavior in the code sub-data list is abnormal.

[0102] In an optional implementation, the behavior detection module is specifically used to:

[0103] It is determined whether the similarity of the billing rate of the time sub-data list is greater than a second threshold value. When it is determined that the similarity of the billing rate is greater than the second threshold value, it is determined that the billing behavior in the time sub-data list is abnormal.

[0104] In an optional implementation, the behavior detection module is specifically used to:

[0105] Further determining whether the abnormal invoicing unit is the same as the invoicing unit in the cross data; when the abnormal invoicing unit is the same as the invoicing unit in the cross data, determining that duplicate invoices exist, and generating an abnormal list;

[0106] Adding the invoicing quantity of each invoicing unit in the abnormal list at all invoicing times to obtain the abnormal data quantity;

[0107] The abnormal data volume is compared with a third threshold value. When the abnormal data volume is less than the third threshold value, it is determined that the abnormal data volume is related to data collection abnormality; when the abnormal data volume is greater than the third threshold value, it is determined that the abnormal data volume is related to abnormal invoicing behavior.

[0108] It should be noted that an electronic invoice information verification device provided in an embodiment of the present invention is used to execute all the process steps of an electronic invoice information verification method in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0109] The embodiment of the present invention further provides a terminal. The terminal includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as an electronic invoice information verification method program. When the processor executes the computer program, the steps in the above-mentioned electronic invoice information verification method embodiments are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the behavior detection module.

[0110] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing set functions, which are used to describe the execution process of the computer program in the terminal.

[0111] The terminal may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of the terminal and do not constitute a limitation on the terminal. The terminal may include more or fewer components than the above, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0112] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal, and various interfaces and lines are used to connect various parts of the entire terminal.

[0113] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0114] Wherein, if the module / unit integrated in the terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0115] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0116] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An electronic invoice information verification method, characterized in that: include: Acquire electronic invoice data; wherein the electronic invoice data includes invoice code, invoice number and invoicing time; Performing a repeatability check based on the electronic invoice data to determine whether the electronic invoice data is crossed, and generating and storing crossed data when it is determined that there is crossed; Grouping the electronic invoice data to obtain a sub-data list, and calculating the invoicing rate of the sub-data list; According to the billing rate, calculating the billing rate similarity of the sub-data list; Judging whether there is an abnormality in the billing behavior of the sub-data list according to the billing rate similarity and the cross data; When it is determined that the invoicing behavior is abnormal, an early warning prompt information is generated, so that the supervision system can provide feedback and conduct investigation based on the early warning prompt information; The invoicing rate is specifically: the ratio of the invoicing quantity of the set invoicing unit to the total invoicing quantity of all invoicing units in the sub-data list within the set invoicing time; The calculation formula of the invoice rate similarity is: , In the formula, is the time billing rate similarity, is the code billing rate similarity, is the billing rate of the first code sub-data list, The billing rate for the second code sub-data list, is the billing rate of the first sub-data list, The billing rate of the second time sub-data list.

2. The electronic invoice information verification method according to claim 1, characterized in that: The step of grouping the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list includes: The invoicing time in the electronic invoice data is grouped to obtain a time sub-data list; wherein the time sub-data list includes a first time sub-data list and a second time sub-data list; According to the time sub-data list, the billing rate of the first time sub-data list and the billing rate of the second time sub-data list are calculated; Grouping the invoice codes in the electronic invoice data to obtain a code sub-data list; wherein the code sub-data list includes a first code sub-data list and a second code sub-data list; According to the calculation of the code sub-data list, the billing rate of the first code sub-data list and the billing rate of the second code sub-data list are obtained.

3. The electronic invoice information verification method according to claim 2, characterized in that: The determining, based on the invoicing rate similarity and the cross data, whether the invoicing behavior of the sub-data list is abnormal includes: It is determined whether the similarity of the billing rate of the code sub-data list is less than a first threshold value. When it is determined that the similarity of the billing rate is less than the first threshold value, it is determined that the billing behavior in the code sub-data list is abnormal.

4. The electronic invoice information verification method according to claim 2, characterized in that: The determining, based on the billing rate similarity and the cross data, whether the billing behavior of the sub-data list is abnormal, further includes: It is determined whether the similarity of the billing rate of the time sub-data list is greater than a second threshold value. When it is determined that the similarity of the billing rate is greater than the second threshold value, it is determined that the billing behavior in the time sub-data list is abnormal.

5. The electronic invoice information verification method according to claim 1, characterized in that: After judging whether the billing behavior of the sub-data list is abnormal according to the billing rate similarity and the cross data, the method further includes: Further determining whether the abnormal invoicing unit is the same as the invoicing unit in the cross data; when the abnormal invoicing unit is the same as the invoicing unit in the cross data, determining that duplicate invoices exist, and generating an abnormal list; Adding the invoicing quantity of each invoicing unit in the abnormal list at all invoicing times to obtain the abnormal data quantity; The abnormal data volume is compared with a third threshold value. When the abnormal data volume is less than the third threshold value, it is determined that the abnormal data volume is related to data collection abnormality; when the abnormal data volume is greater than the third threshold value, it is determined that the abnormal data volume is related to abnormal invoicing behavior.

6. An electronic invoice information verification device, characterized in that: include: A data acquisition module, used to acquire electronic invoice data; A cross detection module, used to perform a repeatability detection based on the electronic invoice data to determine whether the electronic invoice data has a crossover, and when it is determined that there is a crossover, generate and store crossover data; A data grouping module, used for grouping the electronic invoice data to obtain a sub-data list and calculating the invoicing rate of the sub-data list; A similarity calculation module, used for calculating the similarity of the billing rate of the sub-data list according to the billing rate; A behavior detection module, used for judging whether the invoicing behavior of the sub-data list is abnormal according to the invoicing rate similarity and the cross data; An early warning generation module is used to generate early warning prompt information when it is determined that the invoicing behavior is abnormal, so that the supervision system can provide feedback and conduct investigation based on the early warning prompt information; The invoicing rate is specifically: the ratio of the invoicing quantity of the set invoicing unit to the total invoicing quantity of all invoicing units in the sub-data list within the set invoicing time; The calculation formula of the invoice rate similarity is: , In the formula, is the time billing rate similarity, is the code billing rate similarity, is the billing rate of the first code sub-data list, The billing rate for the second code sub-data list, is the billing rate of the first sub-data list, The billing rate of the second time sub-data list.

7. A terminal, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the electronic invoice information verification method as claimed in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the electronic invoice information verification method according to any one of claims 1 to 5.

Images