Intelligent information verification method and device, electronic equipment and storage medium

Abstract

The invention discloses an information intelligent verification method and device, and the method comprises the steps: obtaining document information, converting the document information into table data, and enabling the table data to comprise original data and an original calculation result; matching the original data with the data model formula in the first database; if the matching is successful, obtaining a first calculation result of the original data according to a data model formula in the first database; the data model formula in the first database is a common data model formula imported in an initialization manner; if the matching fails, matching the original data with a data model formula in a second database, and obtaining a second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by using auxiliary calculation. According to the intelligent information verification method and device provided by the invention, the information verification result is obtained through auxiliary calculation, and the information accuracy is greatly improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing, and in particular to an information intelligent verification method and device. Background Art

[0002] At present, the contents filled in the declaration materials of many financial institutions are text materials submitted by third parties. The commonly used intelligent systems are mainly to verify the text content in the materials. However, there is no way to verify the accuracy of the table data in the materials, and whether the calculation formula used for the table data complies with industry standards cannot be verified.

[0003] Therefore, it is necessary to provide an intelligent information verification method and device to solve the above problems. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an intelligent information verification method and device, which obtains information verification results through auxiliary calculations, thereby greatly improving the accuracy of the information.

[0005] According to one aspect of the present invention, there is provided a method for intelligent information verification, the method comprising:

[0006] Acquire document information, and convert the document information into table data, wherein the table data includes original data and original calculation results;

[0007] Matching the original data with a data model formula in a first database;

[0008] If the original data and the data model formula in the first database match successfully, a first calculation result of the original data is obtained according to the data model formula in the first database; the data model formula in the first database is a commonly used data model formula imported for initialization;

[0009] If the original data and the data model formula in the first database fail to match, the original data and the data model formula in the second database are matched, and a second calculation result of the original data is obtained according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation;

[0010] The first calculation result or the second calculation result is compared with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it means that the original calculation result is accurate. If the first calculation result or the second calculation result is inconsistent with the original calculation result, it means that the original calculation result is wrong.

[0011] Preferably, converting the document information into tabular data includes identifying the document information through an OCR system and an intelligent recognition system.

[0012] Preferably, the auxiliary calculation is to generate a data model formula based on fuzzy matching between the original data and the original calculation result.

[0013] Preferably, the auxiliary calculation includes setting an input result set and an output result set, and the input result set and the output result set are represented by the following Zadeh representation:

[0014]

[0015] Among them, μ 1 Represents an element, x 1 represents the degree of membership to the set A.

[0016] Preferably, a verification result set and an original data set are defined, and the verification result set is compared with the input result set, and the verification result set is defined according to preset rules; the verification result set is used to exclude multiple groups of results obtained from the original data set.

[0017] Preferably, the values ​​obtained from each of the above arrays are subjected to intersection processing to exclude repeated values, and then subjected to union processing to be sorted according to the combination.

[0018] Preferably, the degree of membership is calculated by the following formula:

[0019] μA∧B=min(μA,μB)

[0020] Among them, A represents the original calculation result set, B represents the output result set, the smaller the membership degree, the closer to the correct result, and the formula with the smallest membership degree is selected as the data model formula obtained by auxiliary calculation.

[0021] According to another aspect of the present invention, there is provided an information intelligent verification device, the device comprising:

[0022] A document information acquisition module, which is used to acquire document information and convert the document information into table data, wherein the table data includes original data and original calculation results;

[0023] An original data matching module, which is used to match the original data with a data model formula in a first database;

[0024] A first calculation result acquisition module, which is used to obtain a first calculation result of the original data according to the data model formula in the first database when the original data and the data model formula in the first database are matched successfully; the data model formula in the first database is a commonly used data model formula imported for initialization;

[0025] A second calculation result acquisition module, which is used to match the original data with the data model formula in the second database when the original data and the data model formula in the first database fail to match, and obtain a second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation;

[0026] A calculation result comparison module is used to compare the first calculation result or the second calculation result with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it means that the original calculation result is accurate; if the first calculation result or the second calculation result is inconsistent with the original calculation result, it means that the original calculation result is wrong.

[0027] The present application discloses an intelligent information verification method and device, which obtains document information, converts the document information into tabular data, wherein the tabular data includes original data and original calculation results; matches the original data with a data model formula in a first database; if the original data and the data model formula in the first database are successfully matched, a first calculation result of the original data is obtained according to the data model formula in the first database; the data model formula in the first database is a commonly used data model formula imported for initialization; if the original data and the data model formula in the first database fail to match, the original data and the data model formula in the second database are matched, and a second calculation result of the original data is obtained according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation; compares the first calculation result or the second calculation result with the original calculation result, and if the first calculation result or the second calculation result is consistent with the original calculation result, it indicates that the original calculation result is accurate, and if the first calculation result or the second calculation result is inconsistent with the original calculation result, it indicates that the original calculation result is wrong, and the information verification result is obtained by auxiliary calculation, which greatly improves the accuracy of the information. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present invention, not all embodiments. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0029] Figure 1 is a flow chart of an information intelligent verification method according to an embodiment of the present invention;

[0030] Figure 2 is a module schematic diagram of an information intelligent verification device according to an embodiment of the present invention;

[0031] Figure 3 FIG. 4 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. According to 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.

[0033] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0034] In view of the problems existing in the prior art, an embodiment of the present invention provides an intelligent information verification method and device, which obtains information verification results through auxiliary calculations, thereby greatly improving the accuracy of information.

[0035] Figure 1 is a flow chart of an information intelligent verification method according to an embodiment of the present invention, such as Figure 1 As shown, an embodiment of the present invention provides an intelligent information verification method, the method comprising:

[0036] S101: Acquire document information, and convert the document information into table data, where the table data includes original data and original calculation results;

[0037] S102: Matching the original data with a data model formula in a first database;

[0038] S103: If the original data matches successfully with the data model formula in the first database, then obtain the first calculation result of the original data according to the data model formula in the first database; the data model formula in the first database is a commonly used data model formula imported during initialization.

[0039] S104: If the original data fails to match with the data model formula in the first database, then match the original data with the data model formula in the second database, and obtain the second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by using auxiliary calculation.

[0040] S105: Compare the first calculation result or the second calculation result with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it indicates that the original calculation result is accurate; if the first calculation result or the second calculation result is inconsistent with the original calculation result, it indicates that the original calculation result is incorrect.

[0041] Specifically, for example, the original data can be a + b + c = n. If the original data matches successfully with the data model formula in the first database, then obtain the first calculation results of the original data according to the data model formula in the first database, a1 + b1 + c1 = n1; a2 + b2 + c2 = n2.

[0042] At this time, set the original data as multiple arrays:

[0043] {a a1 a2.....an}

[0044] {b b1 b2.....bn}

[0045] {c c1 c2.....cn}

[0046] {n n1 n2.....nn}

[0047] Perform an intersection operation on the values obtained from each of the above arrays to exclude duplicate values. Then perform a union operation. For example: after performing an intersection operation on the values obtained from the above multiple arrays and excluding duplicate values, the array obtained after performing a union operation is {a, b1, c2, nn}.

[0048] In a specific implementation, converting the document information into tabular data includes recognizing the document information through an ocr (Optical Character Recognition) system and an intelligent recognition system.

[0049] In a specific implementation, the auxiliary calculation is to generate a data model formula based on fuzzy matching between the original data and the original calculation result.

[0050] In a specific implementation, the auxiliary calculation includes setting an input result set and an output result set, and the input result set and the output result set are represented by the following Zadeh representation:

[0051]

[0052] Among them, μ 1 Represents an element, x 1 represents the degree of membership to the set A.

[0053] In a specific implementation, a verification result set and an original data set are defined, and the verification result set and the input result set are compared. The verification result set is defined according to preset rules; the verification result set is used to exclude multiple groups of results obtained from the original data set.

[0054] In a specific implementation, the values ​​obtained from each of the above arrays are subjected to intersection processing, duplicate values ​​are excluded, and then union processing is performed and sorted according to the combination.

[0055] For example, it can be {a, b1, c2, nn}, multiple combinations.

[0056] In a specific implementation, the membership degree is calculated by the following formula:

[0057] μA∧B=min(μA,μB)

[0058] Among them, A represents the original calculation result set, B represents the output result set, the smaller the membership degree, the closer to the correct result, and the formula with the smallest membership degree is selected as the data model formula obtained by auxiliary calculation.

[0059] Figure 2 is a schematic diagram of a module of an information intelligent verification device according to an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an intelligent information verification device, the device comprising:

[0060] A document information acquisition module 21, which is used to acquire document information and convert the document information into table data, wherein the table data includes original data and original calculation results;

[0061] An original data matching module 22, which is used to match the original data with a data model formula in a first database;

[0062] A first calculation result acquisition module 23, which is used to obtain a first calculation result of the original data according to the data model formula in the first database when the original data and the data model formula in the first database are matched successfully; the data model formula in the first database is a commonly used data model formula imported for initialization;

[0063] A second calculation result acquisition module 24 is configured to match the original data with the data model formula in the second database when the original data fails to match the data model formula in the first database, and obtain a second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation;

[0064] The calculation result comparison module 25 is used to compare the first calculation result or the second calculation result with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it means that the original calculation result is accurate; if the first calculation result or the second calculation result is inconsistent with the original calculation result, it means that the original calculation result is wrong.

[0065] Figure 3 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 3 As shown, an electronic device 300 provided in this embodiment includes: a processor 301 and a memory 302; wherein:

[0066] The memory 302 is used to store computer programs, and the memory may also be a flash memory.

[0067] The processor 301 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0068] Optionally, the memory 302 may be independent or integrated with the processor 401 .

[0069] When the memory 302 is a device independent of the processor 301, the electronic device 300 may further include:

[0070] The bus 303 is used to connect the memory 302 and the processor 301 .

[0071] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the above-mentioned various implementation modes.

[0072] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program so that the electronic device implements the methods provided in the above various embodiments.

[0073] In summary, the present application discloses an intelligent information verification method and device, which obtains document information, converts the document information into tabular data, wherein the tabular data includes original data and original calculation results; matches the original data with a data model formula in a first database; if the original data and the data model formula in the first database match successfully, obtains a first calculation result of the original data according to the data model formula in the first database; the data model formula in the first database is a commonly used data model formula imported for initialization; if the original data and the data model formula in the first database fail to match, match the original data with the data model formula in the second database, and obtain a second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained using auxiliary calculation; compares the first calculation result or the second calculation result with the original calculation result, and if the first calculation result or the second calculation result is consistent with the original calculation result, it indicates that the original calculation result is accurate, and if the first calculation result or the second calculation result is inconsistent with the original calculation result, it indicates that the original calculation result is wrong, and the information verification result is obtained by auxiliary calculation, which greatly improves the accuracy of the information.

[0074] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the claims.

[0075] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An intelligent information verification method, characterized in that: The method comprises: Acquire document information, and convert the document information into table data, wherein the table data includes original data and original calculation results; Matching the original data with a data model formula in a first database; If the original data and the data model formula in the first database match successfully, a first calculation result of the original data is obtained according to the data model formula in the first database; the data model formula in the first database is a commonly used data model formula imported for initialization; If the original data and the data model formula in the first database fail to match, the original data and the data model formula in the second database are matched, and a second calculation result of the original data is obtained according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation; The first calculation result or the second calculation result is compared with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it means that the original calculation result is accurate. If the first calculation result or the second calculation result is inconsistent with the original calculation result, it means that the original calculation result is wrong.

2. The information intelligent verification method according to claim 1, characterized in that: Converting the document information into table data includes identifying the document information through an OCR system and an intelligent recognition system.

3. The information intelligent verification method according to claim 1, characterized in that: The auxiliary calculation is to generate a data model formula based on fuzzy matching between the original data and the original calculation result.

4. The information intelligent verification method according to claim 3 is characterized in that: The auxiliary calculation includes setting an input result set and an output result set; Defining the original data and the original calculation results according to the business attributes to obtain multiple groups of data critical values; The input result set is obtained by a set of fuzzy calculations, and the input result set is a set of arrays; Constraining the input result set to obtain the output result set, wherein the output result set is a critical array; The input result set and the output result set are represented by the following Zadeh notation: Among them, μ1 represents the element and x1 represents the membership to the set A.

5. The information intelligent verification method according to claim 4, characterized in that: A verification result set and an original data set are defined, and the verification result set is compared with the input result set. The verification result set is defined according to preset rules; the verification result set is used to exclude multiple groups of results obtained from the original data set.

6. The information intelligent verification method according to claim 5, characterized in that: The values ​​obtained from each of the above arrays are processed for intersection, duplicate values ​​are excluded, and then processed for union, and sorted according to the combination.

7. The information intelligent verification method according to claim 6, characterized in that: The membership degree is calculated by the following formula: μA∧B=min(μA,μB) Among them, A represents the original calculation result set, B represents the output result set, the smaller the membership degree, the closer to the correct result, and the formula with the smallest membership degree is selected as the data model formula obtained by auxiliary calculation.

8. An intelligent information verification device, characterized in that: The device comprises: A document information acquisition module, which is used to acquire document information and convert the document information into table data, wherein the table data includes original data and original calculation results; An original data matching module, which is used to match the original data with a data model formula in a first database; A first calculation result acquisition module, which is used to obtain a first calculation result of the original data according to the data model formula in the first database when the original data and the data model formula in the first database are matched successfully; the data model formula in the first database is a commonly used data model formula imported for initialization; A second calculation result acquisition module, which is used to match the original data with the data model formula in the second database when the original data and the data model formula in the first database fail to match, and obtain a second calculation result of the original data according to the data model formula in the second database; the data model formula in the second database is a data model formula obtained by auxiliary calculation; A calculation result comparison module is used to compare the first calculation result or the second calculation result with the original calculation result. If the first calculation result or the second calculation result is consistent with the original calculation result, it means that the original calculation result is accurate; if the first calculation result or the second calculation result is inconsistent with the original calculation result, it means that the original calculation result is wrong.

9. An electronic device, characterized in that: include: processor; as well as, A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images