Bill risk analysis method, apparatus and device, and storage medium

Abstract

The embodiment of the invention provides a bill risk analysis method and device, equipment and a storage medium. The bill risk analysis method comprises the following steps: identifying a to-be-analyzed bill, and determining a bill surface element corresponding to the to-be-analyzed bill based on the type of a label in bill surface data of the identified to-be-analyzed bill; obtaining an early warning rule based on the bill surface element, and judging whether the to-be-analyzed bill has a preset risk of the early warning rule according to the early warning rule; wherein the early warning rules comprise ticket face early warning rules corresponding to ticket face elements and associated early warning rules corresponding to associated elements obtained based on the ticket face elements; and if the to-be-analyzed bill has the preset risk of the early warning rule, displaying the preset risk. According to the embodiment of the invention, the risk of the to-be-analyzed bill is automatically identified and pre-warned, and the management efficiency of the to-be-analyzed bill is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of artificial intelligence technology, and in particular to a bill risk analysis method, device, equipment and storage medium. Background Art

[0002] Invoices are issued by sellers or service providers to prove the transaction of goods sales or service provision. In modern economic activities, invoices play an indispensable role as financial vouchers. They are not only the basis for corporate financial management and tax declaration, but also an important basis for audit and supervision. They play a vital role in corporate financial management, tax declaration, audit supervision and other aspects. With the rapid development of digital technology and the increasingly complex business environment, it has become crucial to analyze the risks of invoices.

[0003] Traditional bill risk analysis methods mainly rely on manual work, which is not only inefficient but also easily affected by human factors, leading to an increased risk of misjudgment and missed judgment. Summary of the invention

[0004] In view of this, embodiments of the present application provide a bill risk analysis method, apparatus, device and storage medium to at least partially solve the above problems.

[0005] According to a first aspect of an embodiment of the present application, a bill risk analysis method is provided, comprising:

[0006] Identify the bill to be analyzed, and confirm the bill face element corresponding to the bill to be analyzed based on the type of the tag in the bill face data identified;

[0007] Acquire warning rules based on the face elements, and determine whether the to-be-analyzed bill has a preset risk of the warning rules according to the warning rules; wherein the warning rules include face warning rules corresponding to the face elements and associated warning rules corresponding to associated elements obtained based on the face elements;

[0008] If the bill to be analyzed has the preset risk of the early warning rule, the preset risk will be displayed.

[0009] In an optional embodiment, the association element is obtained by the following steps:

[0010] Calculate the similarity between the bill face data and the sample associated data by using fuzzy matching to obtain candidate associated data of the bill to be analyzed;

[0011] The ticket data is subjected to association rule mining by association rule mining, and the association data of the ticket to be analyzed is confirmed in the candidate association data according to the mining result, so as to obtain the association elements of different element types corresponding to the association data.

[0012] In an optional embodiment, it also includes:

[0013] The ticket data and the ticket elements are classified and stored according to the corresponding relationship, and the associated data and the associated elements are classified and stored according to the corresponding relationship.

[0014] In an optional embodiment, judging whether the bill to be analyzed has a preset risk of the warning rule according to the warning rule,

[0015] include:

[0016] Based on the ticket face warning rule, determine whether the ticket face data of the to-be-analyzed bill has the preset risk of the ticket face warning rule, and / or, based on the association warning rule, determine whether the association data of the to-be-analyzed bill has the preset risk of the association warning rule.

[0017] In an optional embodiment, it also includes:

[0018] Selecting a target warning rule from the warning rules;

[0019] For all the bills to be analyzed, it is determined whether all the bills to be analyzed have the preset risks of the target warning rule according to the target warning rule.

[0020] In an optional embodiment, the step of identifying the bill to be analyzed includes:

[0021] The bill to be analyzed is identified by optical character recognition.

[0022] In an optional embodiment, it also includes:

[0023] If the bill to be analyzed has the preset risk of the early warning rule, the preset risk is displayed in a data visualization form.

[0024] According to a second aspect of an embodiment of the present application, there is provided a bill risk analysis device, comprising:

[0025] An identification unit, used for identifying the bill to be analyzed, and confirming the bill face element corresponding to the bill to be analyzed based on the type of the tag in the bill face data identified by the identification unit;

[0026] A judgment unit, configured to obtain a warning rule based on the face element of the ticket, and judge whether the to-be-analyzed ticket has a preset risk of the warning rule according to the warning rule; wherein the warning rule includes a face warning rule corresponding to the face element of the ticket, and an associated warning rule corresponding to an associated element obtained based on the face element of the ticket;

[0027] The display unit is used to display the preset risk when the judgment unit judges that the bill to be analyzed has the preset risk of the early warning rule.

[0028] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, a method as described in any one of the first aspects is implemented.

[0029] According to a fourth aspect of an embodiment of the present application, a computer storage medium is provided, which is configured to store computer program instructions, wherein the computer program instructions are used to execute any one of the methods according to the first aspect.

[0030] According to the solution provided in the embodiment of the present application, the face value elements of the bill to be analyzed are confirmed based on the tag type, which helps to accurately match the face value data of the bill to be analyzed with the face value elements; early warning rules are obtained based on the face value elements, and it is determined according to the early warning rules whether the bill to be analyzed has the preset risks of the early warning rules, and the risks of the bill to be analyzed are automatically identified and warned, which improves the risk management efficiency of the bill to be analyzed, reduces the cost of manual review, and helps to reduce the risks caused by non-compliance of the bill to be analyzed; if the bill to be analyzed has the preset risks of the early warning rules, the preset risks will be displayed, which helps enterprises better understand and respond to risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0032] Figure 1 The figure is a schematic diagram of an exemplary all-electric invoice;

[0033] Figure 2 A flowchart of a bill risk analysis method according to an embodiment of the present application;

[0034] Figure 3 is a structural diagram of a bill risk analysis device according to an embodiment of the present application;

[0035] Figure 4 This is an exemplary preset risk display diagram according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0037] In modern economic activities, invoices, as financial vouchers, play an indispensable role. If invoices are improperly issued, such as incorrect information, unclear invoices, etc., it will lead to a series of problems, affect the financial management of the enterprise, and bring a series of economic losses. Therefore, the invoice review work should be strengthened to promptly discover and correct the errors and problems in invoice issuance.

[0038] The fully digitalized electronic invoice is referred to as the all-electronic invoice. It is a new invoice with the same legal effect as the paper invoice. The all-electronic invoice does not exist in paper form, does not need to be supported by a medium, and does not require an application for use. Instead, the face information of the paper invoice is fully digitized, which has effectively promoted the digital transformation and upgrading of enterprises. An exemplary all-electronic invoice face diagram is shown below: Figure 1 shown.

[0039] The specific implementation of the embodiment of the present application is further explained below in conjunction with the accompanying drawings of the embodiment of the present application.

[0040] Figure 2 A flowchart showing a method for analyzing bill risk according to an embodiment of the present application is shown. Figure 2 As shown, a bill risk analysis method according to an embodiment of the present application includes the following steps:

[0041] Step S102: Identify the bill to be analyzed, and confirm the bill face elements corresponding to the bill to be analyzed based on the identified tag type in the bill face data of the bill to be analyzed.

[0042] The bill collector receives the bill to be analyzed and identifies the bill to be analyzed on a personal computer or mobile terminal. In one feasible method, optical character recognition (OCR) is used to identify the bill to be analyzed. Specifically, the image of the bill to be analyzed is preprocessed to improve the accuracy of recognition, including: cropping to remove the background in the image that is not related to the bill to be analyzed, removing noise and interference in the image, adjusting the image direction, and enhancing the contrast to make the text and other contents in the image clearer. The image of the bill to be analyzed after preprocessing is recognized by optical character recognition, and the text features in the image are automatically analyzed and converted into editable text information, thereby obtaining the face data of the bill to be analyzed. Optical character recognition can quickly and accurately identify various text information on the bill to be analyzed, reducing the need for manual input, thereby reducing the manpower cost of the enterprise and the subsequent correction cost caused by incorrect input of the bill information to be analyzed.

[0043] The formats of the bills to be analyzed include: PDF (Portable Document Format), OFD (Open Fixed-layout Document), XML (Extensible Markup Language), etc.

[0044] Taking all-electronic invoices as an example, optical character recognition is used to identify all-electronic invoices, and the invoice data obtained includes: QR code content, label type, invoice number content, invoice date content, purchaser's name content, purchaser's taxpayer identification number content, seller's name content, seller's taxpayer identification number content, item name content, tax rate content, total price and tax (uppercase and lowercase) content, remarks content, invoice issuer content, etc.

[0045] Among them, the QR code, label, invoice number, invoice date, etc. are the face elements of the all-electric invoice. The face elements are the basic items of the all-electric invoice. The specific content of the face elements constitutes the face data of the all-electric invoice. There is a corresponding relationship between the face data and the face elements. For example, the specific label type of the all-electric invoice corresponds to the label in the face elements. The elementization of the all-electric invoice makes the content of the all-electric invoice more flexible, the data more useful, and more conducive to the collection of information about the all-electric invoice.

[0046] Furthermore, the invoice elements include: basic elements, specific elements and additional elements. Among them, basic elements refer to the necessary elements that are uniformly set for all all-electric invoices, such as project name, invoice number, etc. Specific elements refer to the elements corresponding to specific industries or scenarios, such as the construction service location, construction project name, etc. corresponding to the construction service industry, or the departure point, arrival point, etc. corresponding to the cargo transportation service industry. Additional elements are elements that taxpayers add according to their needs, mainly including adding elements in the remarks column of the all-electric invoice.

[0047] Among them, the role of the label is to identify the key information of the all-electric invoice, such as the type, purpose, and status. The label types of all-electric invoices include: taxpayer management, invoice management, tax management, and risk management. Specifically, the taxpayer management labels include: general taxpayers, small-scale taxpayers, and refined oil taxpayers, which are helpful for the classification and management of taxpayers; the invoice management labels include: construction service invoices, rare earth invoices, agricultural product purchase invoices, etc., which help the tax authorities to classify and process invoices and strengthen the supervision of invoices; the tax management labels include: vehicle purchase tax, deed tax, etc., which can reflect the tax types and tax preferential policies involved in all-electric invoices; the risk management labels include: abnormal vouchers, suspicious invoices, and refined oil abnormal labels, which are used to identify all-electric invoices that may be risky. By identifying the labels, the required all-electric invoices can be quickly screened out and classified and supervised.

[0048] After identifying the face data of the bill to be analyzed, according to the type of label in the face data of the bill to be analyzed, for example, real estate sales, the face elements corresponding to the bill to be analyzed are confirmed according to the label type of real estate sales, including: basic elements such as project name, invoice number, property certificate / real estate certificate number, area unit and other specific elements, and additional elements added by the taxpayer as needed. Furthermore, in a feasible way, the face data and face elements are classified and stored according to the corresponding relationship, thereby improving the management efficiency of face data, and can quickly locate specific face data, while helping to ensure the accuracy and consistency of face data and reduce errors and omissions in face data.

[0049] In one feasible manner, based on the face data of the bill to be analyzed, associated data is obtained that is not directly displayed on the face of the bill to be analyzed but is directly associated with the bill to be analyzed, and both the face data and the associated data indicate the specific content of a certain element related to the bill to be analyzed.

[0050] When the face data of the bill to be analyzed is not standardized or complete, such as when there are spelling errors or missing data, it is impossible to obtain accurate related data by direct and precise matching. Therefore, in a feasible way, when the face data of the bill to be analyzed is not standardized or complete, the face data of the bill to be analyzed is obtained, and the face data is first preprocessed, including: removing irrelevant information, supplementing missing values, etc. Specifically, it includes: removing unimportant information such as instructions, and supplementing missing values ​​by using mean filling, interpolation, etc. to ensure the accuracy of the face data.

[0051] After data preprocessing, fuzzy matching is used to calculate the similarity between the face data and the sample associated data; wherein the sample associated data is known associated data, for example, the sample associated data is a known tax classification code. Based on the similarity between the face data and the sample associated data, associated data with a similarity higher than a preset value are preliminarily screened out from the sample associated data to form candidate associated data for the bill to be analyzed. Specifically, the fuzzy matching algorithms include: cosine similarity, Jaccard similarity, semantic similarity, etc., which are selected based on the actual face data.

[0052] Furthermore, in a feasible method, association rule mining is performed on the ticket data by association rule mining, for example, April algorithm is used to mine the ticket data, and frequent item sets and association rules are found in the ticket data. According to the frequent item sets and association rules in the mining results, for example, a certain frequent item set, the associated data related to the frequent item set is screened out in the candidate associated data. Combining fuzzy matching with association rule mining, the candidate associated data is updated and optimized, and the associated data of the bill to be analyzed is obtained in the candidate associated data to obtain the associated elements of different element types corresponding to the associated data. Therefore, by combining fuzzy matching with association rule mining, fuzzy matching makes the association rule mining more tolerant to the ticket data. In the case of irregular or incomplete ticket data, the associated data corresponding to the ticket data is mined, which improves the accuracy of the associated elements obtained based on the ticket elements, and further expands the scope of the bill risk analysis and improves the accuracy of the bill risk analysis.

[0053] Among them, the associated elements do not directly constitute the bills to be analyzed, and the specific content of the associated elements constitutes the associated data of the bills to be analyzed. There is a direct correspondence between the associated data and the associated elements. For example, the specific tax classification code content of the all-electric invoice corresponds to the tax classification code in the associated elements. Further, in a feasible way, the associated data and the associated elements are classified and stored according to the corresponding relationship, thereby improving the management efficiency of the associated data, and can quickly locate specific associated data, while helping to ensure the accuracy and consistency of the associated data and reduce errors and omissions in the associated data.

[0054] Step S104: Acquire warning rules based on the face value of the bill, and determine whether the bill to be analyzed has the preset risk of the warning rules according to the warning rules.

[0055] The warning rules include the ticket warning rules corresponding to the ticket elements, and the associated warning rules corresponding to the associated elements obtained based on the ticket elements. Specifically, in one feasible manner, obtaining the warning rules based on the ticket elements includes obtaining the ticket warning rules corresponding to the ticket elements based on the ticket elements, obtaining the associated elements based on the ticket elements, and further obtaining the associated warning rules corresponding to the associated elements.

[0056] In order to identify the risks of the bills to be analyzed, warning rules are preset for various bill elements and related elements, so as to judge whether the bill data of the bill to be analyzed has the preset risks of the bill warning rules based on the warning rules, and / or, judge whether the related data has the preset risks of the related warning rules based on the related warning rules. The scope of risk analysis is expanded to the bill data and related data, and the risks of the bills to be analyzed are automatically identified and warned in combination with the warning rules, which improves the risk management efficiency of the bills to be analyzed, reduces the cost of manual review, and helps to reduce the risks caused by non-compliance of the bills to be analyzed.

[0057] In one feasible method, for each ticket element and associated element, the preset risk of each ticket element and associated element is statistically generated by means of big data statistics. Furthermore, based on different regions and different industries, early warning rules are set for each risk. Specifically, thresholds of ticket elements and associated elements of different element types are set, and judgments are made according to the thresholds. Each early warning rule makes judgments on at least one element type, thereby judging whether the bill to be analyzed has the preset risk of the early warning rule according to the early warning rule.

[0058] The following is a specific example to describe how to determine whether the bill to be analyzed has the preset risks of the warning rules based on the warning rules.

[0059] For example, the first early warning rule is obtained based on the tax classification code in the associated elements of the company's all-electric invoice, and the first early warning rule is used to determine whether the all-electric invoice has the preset risk of the first early warning rule. Specifically, the preset risk of the first early warning rule is: "There are sensitive items in the input items."

[0060] Specifically, the first early warning rule includes: summarizing the invoice amounts of the enterprise's input invoices for 12 months according to the tax classification code; first determine whether the tax classification code corresponding to the invoice exists in the enterprise's input invoices for 12 months: the tax classification code with the first five digits being 10802, for example, 1080201000000000000 for pig iron, or the tax classification code with the first seven digits being 1080306, for example, 1080306010000000000 for alumina, or the tax classification code with the first nine digits being 108 For example, the tax classification code of 031101 is 1080311010100000000 for gold ore (including associated gold), or the tax classification code with the first five digits as 10201 is 10201, for example, 1020100000000000000 for coal mining products. If it exists, it is further judged whether the total amount of invoices with the above tax classification codes is greater than one million yuan. If it is greater, it is judged according to the first early warning rule that the enterprise has the preset risk corresponding to the first early warning rule "there are sensitive items in the input items".

[0061] For another example, the second warning rule is obtained based on the label in the face element of the company's all-electric invoice, and the second warning rule is used to determine whether the all-electric invoice has the preset risk of the second warning rule. Specifically, the preset risk of the second warning rule is: "There may be a risk of legal disputes."

[0062] Specifically, the second warning rule includes: when the label type of the all-electric invoice is real estate operating lease, select the valid invoices from the company's 12-month sales invoices; determine whether the tax classification code in the valid sales invoices contains 304050202000000000 corresponding to real estate operating lease, or 3040502020100000000 corresponding to residential operating lease services, or 3040502020101000000 corresponding to public housing rental, or 3040502020102000000 corresponding to individual rental housing, or 3040502020199000000 corresponding to other housing rental services, or 3040502020199000000 corresponding to vehicle parking services. 0200000000, or 3040502020400000000 for commercial premises operating leasing services, or 3040502029900000000 for other real estate operating leasing services, or 3040502029901000000 for military surplus property leasing services, or 3040502029902000000 for other real estate operating leasing services; if it exists, then further determine whether the remarks column of the invoice with the above tax classification code includes the words "* city * district (county, city)". If not, then judge according to the second early warning rule that the enterprise has the preset risk corresponding to the second early warning rule "possible risk of legal disputes".

[0063] In one feasible method, multiple bills to be analyzed are analyzed in batches to see whether they meet the preset risk of a certain early warning rule. Specifically, a target early warning rule is selected from the early warning rules to determine whether multiple bills to be analyzed meet the preset risk of the target early warning rule. In this way, a flexible judgment can be made on batches of bills to be analyzed. Enterprises can uniformly analyze whether the selected bills to be analyzed meet a certain specific risk, which helps enterprises understand their own financial status and operating conditions and provides strong support for financial management and decision-making.

[0064] Step S106: If the bill to be analyzed has a preset risk of the early warning rule, the preset risk is displayed.

[0065] After identifying the preset risks of the early warning rules for the bills to be analyzed, displaying the early warning risks will help to more intuitively understand the risk content and its impact.

[0066] In one feasible approach, if the bill to be analyzed has a preset risk in the early warning rule, the preset risk is combined with the bill elements and bill data in the early warning rule, and / or the associated elements and associated data in the form of data visualization. For example, the preset risk is displayed in the form of a chart, a map, a dashboard, etc. By selecting an appropriate display form, the preset risk can be displayed more intuitively, which helps enterprises better understand and deal with risks.

[0067] Chart forms include line charts, bar charts, radar charts, etc., map forms include heat maps, area maps, etc. Dashboards can comprehensively display multiple indicators and data, and usually contain multiple widgets, such as charts, counters, progress bars, etc.

[0068] In one feasible method, after judging that the enterprise has the preset risk corresponding to the first early warning rule, "there are sensitive items in the input items", based on the first early warning rule, Figure 4 As shown, the preset risks are displayed in the form of a pie chart, combined with the project name, invoice total amount and amount ratio.

[0069] In one feasible manner, a bill risk analysis method of an embodiment of the present application is combined with a system of an enterprise, etc., or combined with an external platform outside the financial field, etc. to directly generate vouchers, reports, etc., which helps the enterprise understand its own financial status and operating conditions.

[0070] Therefore, according to a bill risk analysis method of an embodiment of the present application, the face value elements of the bill to be analyzed are confirmed based on the label type, which helps to accurately match the face value data of the bill to be analyzed with the face value elements; early warning rules are obtained based on the face value elements, and it is determined according to the early warning rules whether the bill to be analyzed has the preset risks of the early warning rules, and the risks of the bill to be analyzed are automatically identified and warned, which improves the risk management efficiency of the bill to be analyzed, reduces the cost of manual review, and helps to reduce the risks caused by non-compliance of the bill to be analyzed; if the bill to be analyzed has the preset risks of the early warning rules, the preset risks will be displayed, which helps enterprises better understand and deal with risks.

[0071] See also Figure 3 As shown, the embodiment of the present application also provides a bill risk analysis device, including:

[0072] The identification unit is used to identify the bill to be analyzed, and confirm the bill face element corresponding to the bill to be analyzed based on the type of the label in the bill face data of the identified bill to be analyzed.

[0073] In one feasible manner, based on the face data of the bill to be analyzed, associated data that is not directly displayed on the face of the bill to be analyzed but is directly associated with the bill to be analyzed is obtained to obtain associated elements of different element types corresponding to the associated data. Both the face data and the associated data indicate the specific content of an element related to the bill to be analyzed.

[0074] The judgment unit is used to obtain warning rules based on the face elements of the bill and judge whether the bill to be analyzed has the preset risk of the warning rules according to the warning rules.

[0075] The warning rules include the ticket warning rules corresponding to the ticket elements, and the associated warning rules corresponding to the associated elements obtained based on the ticket elements. Specifically, in one feasible manner, obtaining the warning rules based on the ticket elements includes obtaining the ticket warning rules corresponding to the ticket elements based on the ticket elements, obtaining the associated elements based on the ticket elements, and further obtaining the associated warning rules corresponding to the associated elements.

[0076] In order to identify the risks of the bills to be analyzed, early warning rules are preset for various bill elements and related elements, so as to judge the bill data of the bill to be analyzed and / or whether the related data has the preset risks of the early warning rules according to the early warning rules. The scope of risk analysis is expanded to the bill data and related data, and the risks of the bills to be analyzed are automatically identified and warned in combination with the early warning rules, which improves the risk management efficiency of the bills to be analyzed, reduces the cost of manual review, and helps to reduce the risks caused by non-compliance of the bills to be analyzed.

[0077] The display unit is used to display the preset risk when the judgment unit judges that the bill to be analyzed has the preset risk of the early warning rule.

[0078] In one feasible approach, if the bill to be analyzed has a preset risk in the early warning rule, the preset risk is combined with the bill elements and bill data in the early warning rule, and / or the associated elements and associated data in the form of data visualization. For example, the preset risk is displayed in the form of a chart, a map, a dashboard, etc. By selecting an appropriate display form, the preset risk can be displayed more intuitively, which helps enterprises better understand and deal with risks.

[0079] The information interaction, execution process, etc. between the units in the above-mentioned device are based on the same concept as the embodiment of the method of the present application. For specific contents, please refer to the description in the embodiment of the method of the present application, and will not be repeated here.

[0080] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a bill risk analysis method in any embodiment of the present invention is implemented.

[0081] The present application also provides a computer storage medium configured to store computer program instructions for executing the method described in any of the above method embodiments. The computer storage medium includes, but is not limited to, a compact disc read-only memory (CD-ROM), a random access memory (RAM), a floppy disk, a hard disk, or a magneto-optical disk.

[0082] It should be pointed out that, according to the needs of implementation, the various components / steps described in the embodiments of the present application can be split into more components / steps, or two or more components / steps or partial operations of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present application.

[0083] The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk or magneto-optical disk), or implemented as a computer code originally stored in a remote recording medium or a non-temporary machine-readable medium downloaded through a network and stored in a local recording medium, so that the method described herein can be stored in such software processing on a recording medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware (such as an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA)). It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component (e.g., a random access memory (RAM), a read-only memory (ROM), a flash memory, etc.) that can store or receive software or computer code, and when the software or computer code is accessed and executed by a computer, a processor or hardware, the method described herein is implemented. In addition, when a general-purpose computer accesses the code for implementing the method shown here, the execution of the code converts the general-purpose computer into a dedicated computer for executing the method shown here.

[0084] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for specific applications, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0085] The above implementation methods are only used to illustrate the embodiments of the present application, and are not limitations on the embodiments of the present application. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the embodiments of the present application. Therefore, all equivalent technical solutions also belong to the scope of the embodiments of the present application. The scope of patent protection of the embodiments of the present application should be limited by the claims.

Claims

1. A bill risk analysis method, characterized in that: include: Identify the bill to be analyzed, and confirm the bill face element corresponding to the bill to be analyzed based on the type of the tag in the bill face data identified; Acquire warning rules based on the face elements, and judge whether the to-be-analyzed bill has a preset risk of the warning rules according to the warning rules; wherein the warning rules include face warning rules corresponding to the face elements, and associated warning rules corresponding to associated elements obtained based on the face elements; If the bill to be analyzed has the preset risk of the early warning rule, the preset risk will be displayed.

2. The method according to claim 1, characterized in that: The association elements are obtained by the following steps: Calculate the similarity between the bill face data and the sample associated data by using fuzzy matching to obtain candidate associated data of the bill to be analyzed; The ticket data is subjected to association rule mining by association rule mining, and the associated data of the ticket to be analyzed is confirmed in the candidate associated data according to the mining result, so as to obtain the associated elements of different element types corresponding to the associated data.

3. The method according to claim 2, characterized in that Also includes: The ticket data and the ticket elements are classified and stored according to the corresponding relationship, and the associated data and the associated elements are classified and stored according to the corresponding relationship.

4. The method according to claim 2, characterized in that: The step of judging whether the bill to be analyzed has a preset risk according to the early warning rule according to the early warning rule, include: Based on the ticket face warning rule, determine whether the ticket face data of the to-be-analyzed bill has the preset risk of the ticket face warning rule, and / or, based on the association warning rule, determine whether the association data of the to-be-analyzed bill has the preset risk of the association warning rule.

5. The method according to claim 1, characterized in that Also includes: Selecting a target warning rule from the warning rules; For all the bills to be analyzed, it is determined whether all the bills to be analyzed have the preset risks of the target warning rule according to the target warning rule.

6. The method according to claim 1, characterized in that The step of identifying the bill to be analyzed includes: The bill to be analyzed is identified by optical character recognition.

7. The method according to claim 1, characterized in that Also includes: If the bill to be analyzed has the preset risk of the early warning rule, the preset risk is displayed in a data visualization form.

8. A bill risk analysis device, characterized in that: include: An identification unit, used for identifying the bill to be analyzed, and confirming the bill face element corresponding to the bill to be analyzed based on the type of the tag in the bill face data identified by the identification unit; A judgment unit, configured to obtain a warning rule based on the face element of the ticket, and judge whether the to-be-analyzed ticket has a preset risk of the warning rule according to the warning rule; wherein the warning rule includes a face warning rule corresponding to the face element of the ticket, and an associated warning rule corresponding to an associated element obtained based on the face element of the ticket; The display unit is used to display the preset risk when the judgment unit judges that the bill to be analyzed has the preset risk of the early warning rule.

9. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer storage medium, characterized in that: The device is configured to store computer program instructions for executing the method according to any one of claims 1 to 7.

Images