A qualification approval method, device, equipment and storage medium

Abstract

The embodiment of the present invention discloses a qualification approval method, device, equipment and storage medium. It relates to automatic programming technology, and the method includes obtaining preset qualification approval information input by a user for a qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image; performing qualification review according to the qualification document elements identified in the preset qualification image and the preset qualification text information; if the qualification document elements successfully match the preset qualification text information, it is determined that the qualification application is approved. The technical solution of this embodiment can approve unstructured qualification images to realize automated qualification approval.

Description

Technical Field

[0001] The embodiments of the present invention relate to automatic programming technology, and more particularly to a qualification approval method, device, equipment and storage medium. Background Art

[0002] Some business systems require users to apply for qualifications before allowing other functions to be used, and then the system administrator will confirm and approve the qualifications. Such systems that include approval business require applicants to upload images of certificates issued by the management department and the applicant's ID card, and then enter basic information, and then submit them for approval by the administrator.

[0003] At present, the approval trigger of some systems is that after the applicant submits the application, the applicant notifies the authorized approver to conduct manual verification and approval. Therefore, from the perspective of process approval, the existing process approval requires human participation, and the authorized approver subjectively judges the legality and validity of the qualifications. The existing automatic approval tools have a single input element, that is, the input element is mainly structured data, which is stored in the workflow or approval information database. It is insufficient for situations where unstructured multimedia information such as user-related certificates and qualification scans needs to be entered. Therefore, its usage scenario is single and cannot meet the above-mentioned qualification approval needs. The existing automated approval system is suitable for the information entered by the user as structured data, while the qualification business approval system has the following characteristics: (1) Qualification application is a rigid demand, that is, the user must first apply for qualifications before using other functions of the business system; (2) The business volume of qualification application is large. The user base determines the large business volume of qualification application and approval, and the application submitted by the user is very complex; (3) The approval manpower is insufficient. Manual approval is repetitive and time-consuming. In order to ensure the continuity of approval, it is necessary to arrange special personnel for approval, which is a waste of expensive manpower. Due to these practical reasons, the process cannot be processed in time and may be blocked. For example, if a process has a strong timeliness requirement, if the approver fails to approve it in time, it may have a negative impact on the company's business. Summary of the invention

[0004] The embodiments of the present invention provide a qualification approval method, device, equipment and storage medium to implement the approval of unstructured qualification images and realize automated qualification approval.

[0005] In a first aspect, an embodiment of the present invention provides a qualification approval method, including:

[0006] Acquire preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image;

[0007] Conducting qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0008] If the qualification document elements successfully match the preset qualification text information, it is determined that the qualification application is approved.

[0009] In a second aspect, an embodiment of the present invention further provides a qualification approval device, including:

[0010] A qualification approval information acquisition module is used to acquire preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image;

[0011] A qualification review module, used to conduct qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0012] The approval module is used to determine whether the qualification application is approved if the qualification document elements match the preset qualification text information successfully.

[0013] In a third aspect, an embodiment of the present invention further provides a qualification approval device, the qualification approval device comprising:

[0014] one or more processors;

[0015] A memory for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the qualification approval method provided by any embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a qualification approval method as provided in any embodiment of the present invention.

[0018] The embodiment of the present invention identifies the qualification document elements in the qualification image and performs qualification approval on unstructured data such as the image, thereby solving the problem that the existing qualification approval tool does not support images for input elements, and the manual review is inefficient and consumes a lot of human resources, thereby realizing automated qualification approval and improving the efficiency of qualification approval. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a qualification approval method in Embodiment 1 of the present invention;

[0020] Figure 2 It is a flow chart of a qualification approval method in Embodiment 2 of the present invention;

[0021] Figure 3 It is a flow chart of a qualification approval method in Embodiment 3 of the present invention;

[0022] Figure 4 It is a structural diagram of a qualification approval device in Embodiment 4 of the present invention;

[0023] Figure 5 It is a structural diagram of a qualification approval device in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0025] Embodiment 1

[0026] Figure 1 This is a flowchart of a qualification approval method provided in the first embodiment of the present invention. This embodiment can be applied to the situation in which the qualification approval information input by the user is reviewed after the user applies for the qualification in the business system. The method can be executed by a qualification approval device, which can be implemented by hardware and / or software and can generally be integrated into the qualification approval device, such as a server. The qualification approval method specifically includes the following steps:

[0027] Step 110: Obtaining preset qualification approval information input by the user for the qualification application;

[0028] Among them, the preset qualification approval information includes preset qualification text information and preset qualification images. When a user applies for qualifications, he can enter the relevant preset qualification approval information in the qualification approval system interface. The preset qualification approval information is the certificate information related to the user. Some business systems require users to apply for qualifications before allowing the use of other functions. This type of system that includes approval business requires applicants to upload certificate information. This certificate information can include preset qualification images and preset qualification text information. The preset qualification image is the certificate image required for the qualification application, such as a scanned image of a certificate issued by the management department, a scanned image of the applicant's identity document, and then the user enters the text information related to the qualification application, that is, the information of the above-mentioned certificate, such as the information number, issuing agency, issuance time and validity period covered by the certificate, etc.

[0029] Step 120: Perform qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0030] Among them, the preset qualification approval information input by the user for the qualification application can be input into the qualification approval engine, which is based on a preset series of parameters, with the user's input information as input and the approval result as output. The qualification document elements can be identified from the preset qualification image based on optical character recognition (OCR), and the qualification document elements can be some relevant information of the certificate, such as the information number, issuing authority, issuing time and validity period covered by the certificate. Recognition parameters (Image Recognition Parameters, IRP) can be pre-set. The parameters that need to be input when using OCR for image recognition constitute the image recognition model to facilitate accurate and efficient identification of certificates issued by government departments, user's ID card information, etc. The approval parameters of qualification approval: (Approve and Refuse Parameters, ARP) can also be pre-set. During automated approval, based on the approval parameters, the recognition result is used as input, and the authentication information of the government department or authority is called to verify whether the information entered by the user is true.

[0031] After verifying the authenticity of the information entered by the user, the qualification document elements are compared with the preset qualification text information to see if they are consistent. Only if the qualification document elements are consistent with the preset qualification text information can the qualification approval be passed.

[0032] Step 130: If the qualification document elements successfully match the preset qualification text information, it is determined that the qualification application is approved.

[0033] Among them, the successful matching of the qualification document elements with the preset qualification text information means that the qualification document elements are consistent with the preset qualification text information, and the confidence of the qualification document elements needs to be greater than the preset confidence threshold. According to the preset recognition algorithm in the recognition parameters, for example, the Tesseract algorithm is specified to recognize the text in the picture; the information number, issuing authority, issuance time and validity period covered by the certificate are obtained through regular expressions, and the recognition result will return the confidence of each information recognition at the same time; according to the certificate number identified in the picture, the authenticity of the certificate file can be queried in the official system, and according to the query results, it can be known whether the certificate has expired or invalid; if there is a mismatch during the verification process, the application will be rejected; the same identification of the text in the ID card picture is performed on the ID card information, and the ID card number, issuing authority, issuance time and validity period covered by the ID card are obtained through regular expressions, and the authenticity of the ID card is queried; finally, the basic information of the identified ID card and the basic information of the certificate are compared with the preset qualification text information entered by the user in the interface. It is approved when it is completely matched and the confidence is greater than the confidence threshold.

[0034] The technical solution of this embodiment, by identifying the qualification document elements in the qualification image, performs qualification approval on unstructured data such as images, solves the problem that the existing qualification approval tools do not support images for input elements, and the manual review is inefficient and consumes a lot of human resources, thereby realizing automated qualification approval and improving the efficiency of qualification approval.

[0035] Embodiment 2

[0036] Figure 2 This is a flowchart of a qualification approval method provided in Embodiment 2 of the present invention. This embodiment is further refined on the basis of the above technical solution. After the qualification review is conducted based on the qualification document elements identified in the preset qualification image and the preset qualification text information, it also includes: if the qualification document elements fail to match the preset qualification text information, notifying the preset administrator for manual review. The qualification approval method provided in this embodiment specifically includes:

[0037] Step 210: Obtaining preset qualification approval information input by the user for the qualification application;

[0038] Step 220: Perform qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0039] Step 230: If the qualification document elements successfully match the preset qualification text information, it is determined that the qualification application is approved.

[0040] Step 240: If the qualification document elements fail to match the preset qualification text information, notify the preset administrator for manual review.

[0041] Among them, the existing automatic approval tools lack an escape route, that is, they lack remedial measures and rely entirely on the automated approval system. When there are situations in the system where approval is impossible or other exceptional circumstances exist, there is a lack of an escape route for manual intervention and approval. Whether the match between the qualification document element and the preset qualification text information is successful or unsuccessful depends on whether the qualification document element is consistent with the preset qualification text information and whether the confidence in identifying the qualification document element is greater than a preset confidence threshold. It is understandable that the order in which steps 230 and 240 are executed is not limited.

[0042] Optionally, if the qualification document element fails to match the preset qualification text information, notifying a preset administrator for manual review includes:

[0043] If the qualification document element completely matches the content of the preset qualification text information, and the confidence level of the qualification document element identified from the preset qualification image is less than the confidence level threshold, notify the preset administrator to conduct manual review;

[0044] If the qualification document element does not completely match the preset qualification text information content, and the confidence level of the qualification document element identified from the preset qualification image is greater than the confidence level threshold, the preset administrator is notified for manual review.

[0045] Optionally, if the qualification document element completely matches the preset qualification text information content, and the confidence of identifying the qualification document element from the preset qualification image is less than a threshold, after notifying the preset administrator for manual review, the method further includes:

[0046] If the manual review is passed, the confidence threshold is reduced by a preset adjustment amount.

[0047] Among them, if the manual review is passed, it means that the confidence threshold is set too high and the approval is too strict. Therefore, after the approval result of this manual intervention is fed back to the approval engine, the approval engine will reduce the confidence threshold in the approval parameters.

[0048] Optionally, if the qualification document element does not completely match the preset qualification text information content, and the confidence level of the qualification document element identified from the preset qualification image is greater than the confidence level threshold, after notifying the preset administrator for manual review, the method further includes:

[0049] If the manual review fails, the confidence threshold is increased by a preset adjustment amount.

[0050] Among them, if the manual review fails, it means that the confidence threshold is set too low and the approval is too loose. Therefore, after the approval result of this manual intervention is fed back to the approval engine, the approval engine will increase the confidence threshold in the approval parameters.

[0051] Optionally, before performing qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information, the method further includes:

[0052] Compare the image file size of the preset qualification image with a preset file size threshold, and eliminate the preset qualification image whose image file size is smaller than the preset file size threshold; and / or,

[0053] Determine the clarity of the preset qualification image based on a preset clarity algorithm, and remove the preset qualification image whose clarity does not meet the clarity condition; and / or,

[0054] According to the qualification document elements and the corresponding document validity identification resources, the preset qualification images that do not meet the preset document validity conditions are eliminated.

[0055] Among them, the recognition parameters can include the direction of the detected image, including horizontal and vertical, the detected language, which can be Chinese by default, the OCR confidence, and the recognition algorithm: this parameter is used to recognize the algorithm of text information in the image. The mainstream choices include: Tesseract / AipOcr / KNN to implement OCR.

[0056] The approval parameters are composed of a series of thresholds and judgment conditions. Since the relevant files in the application form will be stored on the server for manual review and later log tracking, their clarity and file size need to be considered. Since the clarity of an image is an important indicator for measuring the quality of an image, it can better correspond to people's subjective feelings. Low image clarity shows that the image is blurry. The approval parameters include the qualification file size threshold, the qualification file clarity evaluation function, such as gradient function, grayscale variance function, energy gradient function, entropy function and quadratic fuzzy algorithm, etc., the ID card file size threshold, the ID card file clarity evaluation function, the function type can be the same as the qualification file clarity evaluation function, whether to open the recommendation code green approval, this parameter indicates that the applicant has entered the internal recommendation code. If the recommendation code is turned on during the review, the green approval channel can be used. The system directly registers and approves, the expedited approval form, and the user's level.

[0057] After the user enters the application form information and submits it to the approval engine, the automatic approval process can begin. After the approval begins, the image can be pre-processed.

[0058] (1) Based on recognition parameters, such as specifying the recognition algorithm as "secondary blur algorithm" to detect whether the file is blurred, the application form with blur will be directly rejected. The principle of secondary blur: If an image is already blurred, then blurring it again will not change the high-frequency component much; but if the original image is clear, blurring it once will change the high-frequency component a lot. It is essentially a clarity algorithm based on secondary blur.

[0059] (2) Obtain the size of the image file and compare it with the file size threshold in the approval parameters. If it does not meet the threshold, the application will be rejected directly.

[0060] (3) Query the authenticity and validity of the certificate and ID card based on the qualification document elements, and eliminate the preset qualification images that do not meet the preset document validity conditions, such as forged, expired and invalid certificates.

[0061] The technical solution of this embodiment sets up an escape route, which can be used as a remedial measure. By releasing manpower from the approval work through the qualification approval engine, the qualification approval is not overly dependent on the automated approval system. For situations that cannot be approved or are exceptional in the system, manual intervention approval is carried out.

[0062] Embodiment 3

[0063] Figure 3 This is a flow chart of a qualification approval method provided in Embodiment 3 of the present invention. This embodiment is further refined on the basis of the above technical solution. The qualification approval method provided in this embodiment also includes:

[0064] Step 310: sampling from the application forms approved within a preset time period according to the positive sampling ratio to obtain a sample of the approved application forms;

[0065] Step 320: sampling from the application forms that have not been approved within the preset time period according to the negative sampling ratio to obtain a sample of application forms that have not been approved;

[0066] Step 330: providing the approved application form sample and the unapproved application form sample to an administrator for manual review;

[0067] Step 340: Adjust the preset parameters in the qualification approval process according to the manual review results provided by the administrator.

[0068] Among them, the sample library for sampling can select the approved application forms within a period of time, including the application forms that have been approved and those that have been rejected. The positive sampling ratio can be the sampling ratio for the application forms that have been approved when the administrator reviews them, and the negative sampling ratio can be the sampling ratio for the application forms that have been rejected when the administrator reviews them. The positive sampling ratio and the negative sampling ratio can be preset and can also be modified by the administrator. Batch random sampling, followed by manual review and verification, optimize the feedback and adjust the recognition parameters and approval parameters based on the manual review results fed back by the administrator. The manual review results can be an evaluation of whether the audit results are reasonable after the sampling review. Multiple administrators can perform manual review and verification, and then summarize the manual review results. According to the review results, adjust the approval parameters and recognition parameters set during initialization.

[0069] The technical solution of this embodiment adds a feedback mechanism. Since the approval of some businesses does require manual definition and cannot be completely automated, a manual intervention mechanism should be added to the system to manually review the correctness of the automated review. Especially when the system is initialized, it is necessary to correct the parameters in the approval engine in a timely manner through certain manual intervention. After the system has been running for a period of time, the credibility of the system's automated approval converges to a higher level.

[0070] Embodiment 4

[0071] Figure 4 This is a schematic diagram of the structure of a qualification approval device provided in Embodiment 4 of the present invention. The qualification approval device provided in this embodiment specifically includes:

[0072] The qualification approval information acquisition module 410 is used to acquire the preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image;

[0073] The qualification review module 420 is used to perform qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0074] The approval module 430 is used to determine whether the qualification application is approved if the qualification document elements match the preset qualification text information successfully.

[0075] By identifying the qualification document elements in the qualification images, the qualification approval is carried out on the unstructured data such as images, so as to solve the problems that the existing qualification approval tools do not support images for input elements, and the manual review is inefficient and consumes a lot of human resources. Automated qualification approval is realized to improve the efficiency of qualification approval.

[0076] Optionally, the qualification approval device also includes:

[0077] The manual review intervention module is used to notify the preset administrator to perform manual review after the qualification review is performed on the qualification document elements identified in the preset qualification image and the preset qualification text information if the qualification document elements fail to match the preset qualification text information.

[0078] Optionally, the manual review intervention module includes:

[0079] A first manual review intervention unit is used to notify the preset administrator to conduct manual review if the qualification document element completely matches the preset qualification text information content and the confidence of the qualification document element identified from the preset qualification image is less than the confidence threshold; or

[0080] The second manual review intervention unit is used to notify the preset administrator to perform manual review if the qualification document element does not completely match the preset qualification text information content and the confidence of the qualification document element identified from the preset qualification image is less than the confidence threshold.

[0081] Optionally, the manual review intervention module further includes:

[0082] The first confidence threshold adjustment unit is used to, if the qualification document element completely matches the preset qualification text information content and the confidence of the qualification document element identified from the preset qualification image is less than the threshold, notify the preset administrator for manual review, and if the manual review is passed, reduce the confidence threshold according to the preset adjustment range.

[0083] Optionally, the manual review intervention module further includes:

[0084] The second confidence threshold adjustment unit is used to, if the qualification document element does not completely match the preset qualification text information content, and the confidence of the qualification document element identified from the preset qualification image is less than the confidence threshold, notify the preset administrator for manual review, and if the manual review fails, reduce the confidence threshold by a preset adjustment range.

[0085] Optionally, the qualification approval device also includes:

[0086] A first qualification image screening module is used to compare the image file size of the preset qualification image with a preset file size threshold before conducting qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information, and eliminate the preset qualification image whose image file size is smaller than the preset file size threshold; and / or,

[0087] A second qualification image screening module is used to determine the clarity of the preset qualification image based on a preset clarity algorithm, and to remove the preset qualification image whose clarity does not meet the clarity condition; and / or,

[0088] The third qualification image screening module is used to identify resources based on the qualification document elements and corresponding document validity, and eliminate the preset qualification images that do not meet the preset document validity conditions.

[0089] Optionally, the qualification approval device also includes:

[0090] The first sampling module is used to sample the approved application forms in a preset time period according to a positive sampling ratio to obtain a sample of the approved application forms;

[0091] A second sampling module is used to sample application forms that have not been approved within the preset time period according to a negative sampling ratio to obtain a sample of application forms that have not been approved;

[0092] A sample review module, used to provide the approved application form sample and the unapproved application form sample to an administrator for manual review;

[0093] The parameter adjustment module is used to adjust the preset parameters in the qualification approval according to the manual review results fed back by the administrator.

[0094] The qualification approval device provided in the embodiment of the present invention can execute the qualification approval method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0095] Embodiment 5

[0096] Figure 5 A schematic diagram of the structure of a qualification approval device provided in Embodiment 5 of the present invention is shown in FIG. Figure 5 As shown, the qualification approval device includes a processor 510, a memory 520, an input device 530 and an output device 540; the number of the processor 510 in the qualification approval device can be one or more. Figure 5 A processor 510 is taken as an example; the processor 510, the memory 520, the input device 530 and the output device 540 in the qualification approval device can be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0097] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the qualification approval method in the embodiment of the present invention (for example, the qualification approval information acquisition module 410, the qualification review module 420 and the approval module 430 in the qualification approval device). The processor 510 executes various functional applications and data processing of the qualification approval device by running the software programs, instructions and modules stored in the memory 520, that is, implements the above-mentioned qualification approval method.

[0098] The memory 520 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 520 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include a memory remotely arranged relative to the processor 510, and these remote memories may be connected to the qualification approval device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] The input device 530 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the qualification approval device. The output device 540 may include a display device such as a display screen.

[0100] Embodiment 6

[0101] Embodiment 6 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to execute a qualification approval method when executed by a computer processor, including:

[0102] Acquire preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image;

[0103] Conducting qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information;

[0104] If the qualification document elements successfully match the preset qualification text information, it is determined that the qualification application is approved.

[0105] Of course, the storage medium containing computer executable instructions provided in an embodiment of the present invention is not limited to the method operations described above, and the computer executable instructions can also execute related operations in the qualification approval method provided in any embodiment of the present invention.

[0106] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0107] It is worth noting that in the embodiment of the above-mentioned qualification approval device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0108] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A qualification approval method, characterized in that: include: Acquire preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image; Conducting qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information; If the qualification document element successfully matches the preset qualification text information, it is determined that the qualification application is approved; the qualification document element successfully matches the preset qualification text information means that the qualification document element is consistent with the preset qualification text information and the confidence of the qualification document element is greater than the preset confidence threshold; If the qualification document elements fail to match the preset qualification text information, notify the preset administrator for manual review; If the qualification document element fails to match the preset qualification text information, notifying the preset administrator for manual review includes: If the qualification document element completely matches the content of the preset qualification text information, and the confidence level of the qualification document element identified from the preset qualification image is less than the confidence level threshold, notify the preset administrator to conduct manual review; If the qualification document element does not completely match the content of the preset qualification text information, and the confidence level of the qualification document element identified from the preset qualification image is greater than the confidence level threshold, notify the preset administrator to conduct manual review; Wherein, if the qualification document element completely matches the preset qualification text information content, and the confidence of identifying the qualification document element from the preset qualification image is less than a threshold, after notifying the preset administrator for manual review, it also includes: If the manual review is passed, it means that the confidence threshold is set too high, and the confidence threshold is reduced according to the preset adjustment range; Wherein, if the qualification document element does not completely match the content of the preset qualification text information, and the confidence of identifying the qualification document element from the preset qualification image is greater than the confidence threshold, after notifying the preset administrator for manual review, it also includes: If the manual review fails, it means that the confidence threshold is set too small, and the confidence threshold is increased according to the preset adjustment range.

2. The method according to claim 1, characterized in that Before performing qualification review according to the qualification document elements identified in the preset qualification image and the preset qualification text information, the method further includes: Compare the image file size of the preset qualification image with a preset file size threshold, and eliminate the preset qualification image whose image file size is smaller than the preset file size threshold; and / or, Determine the clarity of the preset qualification image based on a preset clarity algorithm, and remove the preset qualification image whose clarity does not meet the clarity condition; and / or, According to the qualification document elements and the corresponding document validity identification resources, the preset qualification images that do not meet the preset document validity conditions are eliminated.

3. The method according to any one of claims 1 to 2, characterized in that: Also includes: Sampling the approved application forms within a preset time period according to the positive sampling ratio to obtain a sample of approved application forms; Sampling from the application forms that have not been approved within the preset time period according to the negative sampling ratio to obtain a sample of application forms that have not been approved; Providing the approved application form sample and the unapproved application form sample to the administrator for manual review; Adjust the preset parameters in the qualification approval process based on the manual review results provided by the administrator.

4. A qualification approval device, characterized in that: include: A qualification approval information acquisition module is used to acquire preset qualification approval information input by the user for the qualification application; wherein the preset qualification approval information includes preset qualification text information and preset qualification image; A qualification review module, used to conduct qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information; An approval module is used to determine that the qualification application is approved if the qualification document element successfully matches the preset qualification text information; the qualification document element successfully matches the preset qualification text information means that the qualification document element is consistent with the preset qualification text information and the confidence of the qualification document element is greater than a preset confidence threshold; A manual review intervention module, used for notifying a preset administrator to conduct manual review if the qualification document elements and the preset qualification text information fail to match after the qualification review is conducted based on the qualification document elements identified in the preset qualification image and the preset qualification text information; Wherein, the manual review intervention module includes: A first manual review intervention unit, configured to notify the preset administrator to conduct manual review if the qualification document element completely matches the preset qualification text information content and the confidence level of the qualification document element identified from the preset qualification image is less than a confidence level threshold; A second manual review intervention unit, configured to notify the preset administrator to conduct manual review if the qualification document element does not completely match the preset qualification text information content and the confidence level of the qualification document element identified from the preset qualification image is greater than the confidence level threshold; Correspondingly, the manual review intervention module also includes: A first confidence threshold adjustment unit is used to, if the qualification document element completely matches the preset qualification text information content, and the confidence of the qualification document element identified from the preset qualification image is less than the threshold, notify the preset administrator to conduct manual review, if the manual review is passed, it means that the confidence threshold is set too large, and reduce the confidence threshold according to the preset adjustment range; The second confidence threshold adjustment unit is used to notify the preset administrator for manual review if the qualification document element does not completely match the preset qualification text information content, and the confidence of the qualification document element identified from the preset qualification image is greater than the confidence threshold. If the manual review fails, it means that the confidence threshold is set too small, and the confidence threshold is increased according to the preset adjustment range.

5. The device according to claim 4, characterized in that Also includes: A first qualification image screening module is used to compare the image file size of the preset qualification image with a preset file size threshold before conducting qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information, and eliminate the preset qualification image whose image file size is smaller than the preset file size threshold; and / or, A second qualification image screening module is used to determine the clarity of the preset qualification image based on a preset clarity algorithm before conducting a qualification review based on the qualification document elements identified in the preset qualification image and the preset qualification text information, and to eliminate the preset qualification image whose clarity does not meet the clarity condition; and / or, The third qualification image screening module is used to eliminate the preset qualification images that do not meet the preset document validity conditions based on the qualification document elements identified in the preset qualification image and the preset qualification text information before conducting qualification review.

6. The device according to any one of claims 4 to 5, characterized in that: Also includes: The first sampling module is used to sample the application forms approved within a preset time period according to a positive sampling ratio to obtain a sample of the approved application forms; A second sampling module is used to sample application forms that have not been approved within the preset time period according to a negative sampling ratio to obtain a sample of application forms that have not been approved; A sample review module, used to provide the approved application form sample and the unapproved application form sample to an administrator for manual review; The parameter adjustment module is used to adjust the preset parameters in the qualification approval according to the manual review results fed back by the administrator.

7. A qualification approval device, characterized in that: The qualification approval equipment includes: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the qualification approval method as described in any one of claims 1-3.

8. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the qualification approval method as described in any one of claims 1 to 3 when executed by a computer processor.

Images