Medical product business information review method, device, electronic equipment and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for reviewing business information of medical products, relating to the field of information detection technology. The method includes: identifying the business information to be reviewed to obtain unit text areas and corresponding unit text content; performing clarity detection on each unit text area to obtain a comprehensive clarity detection result for the business information to be reviewed; when the comprehensive clarity detection result of the business information to be reviewed is clear, querying the reference text content corresponding to each unit text content based on the identity identifier contained in each unit text content; performing consistency detection on each unit text content and the corresponding reference text content; and determining the review result of the business information to be reviewed based on the consistency detection result of the unit text content. The technical solution of this invention improves the review efficiency and accuracy of business information of medical product providers, and can ensure the operational stability of medical product business platforms.

Description

Technical Field

[0001] This invention relates to the field of information detection technology, and in particular to a method, apparatus, electronic device, and storage medium for reviewing business information of medical products. Background Technology

[0002] Medical product providers are required to provide business information to the medical product distribution platform. The platform will review the provider's business information when the provider first joins the platform or when the platform reaches its review period.

[0003] Currently, the review of business information of medical product providers is mainly conducted manually. However, due to the large number of medical product providers on the medical product business platform and the large amount of business information involved, as well as the need for periodic review of the business information of medical product providers, the review efficiency is low, and it is easy to miss some information, making it difficult to ensure the operational stability of the medical product business platform. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for reviewing business information of medical product providers. It enables automatic review of business information of medical product providers, improves the efficiency and accuracy of review, and ensures the operational stability of the medical product business platform.

[0005] According to one aspect of the present invention, a method for reviewing the business information of medical products is provided, the method comprising:

[0006] Obtain the business information pending review;

[0007] The business data to be reviewed is identified to obtain at least one unit text area and the unit text content corresponding to the unit text area;

[0008] The clarity of the text areas in each unit is tested to obtain the overall clarity test results of the business documents to be reviewed;

[0009] When the overall clarity test result of the business documents to be reviewed is clear, the reference text content corresponding to the text content of each unit is queried according to the identity identifier contained in the text content of each unit.

[0010] A consistency check is performed on the text content of each unit and the corresponding reference text content;

[0011] Based on the consistency detection results of the text content of the unit, the review result of the business information to be reviewed is determined.

[0012] According to another aspect of the present invention, a medical product business information verification device is provided, the device comprising:

[0013] The business data acquisition module is used to acquire business data to be reviewed.

[0014] The unit text region recognition module is used to recognize the business data to be reviewed and obtain at least one unit text region and the unit text content corresponding to the unit text region.

[0015] The comprehensive clarity detection module is used to perform clarity detection on the text areas of each unit to obtain the comprehensive clarity detection result of the business documents to be reviewed;

[0016] The reference text content query module is used to query the reference text content corresponding to each unit text content based on the identity identifier contained in the text content of each unit when the overall clarity detection result of the business materials to be reviewed is clear.

[0017] The text content consistency detection module is used to perform consistency detection on the text content of each unit and the corresponding reference text content;

[0018] The audit result determination module is used to determine the audit result of the business documents to be audited based on the consistency detection result of the text content of the unit.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the medical product business information review method according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the medical product business data review method according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the medical product business data review method according to any embodiment of the present invention.

[0025] The technical solution of this invention identifies the business documents to be reviewed, obtaining at least one unit text area and the corresponding unit text content. Clarity detection is performed on each unit text area to obtain a comprehensive clarity detection result for the business documents to be reviewed. When the comprehensive clarity detection result of the business documents to be reviewed is clear, the reference text content corresponding to each unit text content is queried based on the identity identifier contained in each unit text content. Consistency detection is performed on each unit text content and its corresponding reference text content. Based on the consistency detection result of the unit text content, the review result of the business documents to be reviewed is determined. This achieves automatic review of the business documents of medical product providers from both text clarity and content consistency perspectives, improving the review efficiency and accuracy of the business documents of medical product providers and ensuring the operational stability of the medical product business platform.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart of a method for reviewing business information of medical products according to Embodiment 1 of the present invention;

[0029] Figure 2 This is a flowchart of a method for reviewing business information of medical products according to Embodiment 2 of the present invention;

[0030] Figure 3 This is a flowchart of a method for reviewing business information of medical products according to Embodiment 2 of the present invention;

[0031] Figure 4 This is a schematic diagram of the structure of a medical product business information verification device according to Embodiment 3 of the present invention;

[0032] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the medical product business data review method of this invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] Example 1

[0036] Figure 1 This is a flowchart illustrating a method for reviewing medical product business information according to Embodiment 1 of the present invention. This embodiment of the invention is applicable to situations involving the review of medical product business information on a medical product business platform. The method can be executed by a medical product business information review device, which can be implemented in hardware and / or software and can be configured in an electronic device that performs the function of reviewing medical product business information.

[0037] Medical product providers are required to provide operating documents to the medical product distribution platform. The platform reviews these documents upon a provider's initial registration or upon reaching the required review period. The clarity of the documents is a crucial indicator for approval. Reaching the required review period for drug or medical device providers signifies that the provider has registered and the platform has conducted an initial review of their qualifications. However, changes in identity (e.g., changes in personnel or company names) and business scope are possible. To ensure the accuracy of the review and the platform's operational stability, the platform conducts periodic reviews of the provider's qualifications. These reviews can be conducted at specific time intervals, such as twice, three times, four times, or quarterly.

[0038] Currently, the review of business documents for medical product providers is primarily conducted manually. However, due to the large number of medical product providers and the vast amount of business documents involved in medical product distribution platforms, coupled with the need for periodic reviews, the review efficiency is low, and omissions are common, making it difficult to guarantee the operational stability of the medical product distribution platform. Ensuring the operational stability of a medical product distribution platform can be understood as requiring periodic audits by the auditing party, including random checks on the business qualifications of the medical products offered by the platform. If inconsistencies in business qualifications are detected, penalties may be imposed on both the medical product distribution platform and the relevant medical product providers for that specific medical product.

[0039] See Figure 1 The methods for reviewing the business information of medical products shown include:

[0040] S110. Obtain the business information to be reviewed.

[0041] The business information to be audited can be information related to the operation provided by the medical product provider to the medical product operation platform. This information is used to demonstrate the provider's eligibility to operate on the platform. For example, medical products include pharmaceuticals or medical devices. The business information to be audited can also include the provider's identity and operating authority. The identity document identifies the provider, such as a copy of their ID card, business license, or power of attorney. Operating authority indicates whether the provider is authorized to operate medical products. For example, operating authority includes the scope of business and the validity period of the license. The scope of business indicates the range of medical products the provider can operate. For example, the scope of business may include the treatment scope of the business license and a special drug operating license. The treatment scope of the business license indicates the provider's authority to operate conventional medical products. A special drug operating license indicates the provider's authority to operate special drugs. Optionally, the business information to be audited can be in the form of images or PDF (Portable Document Format).

[0042] In an optional embodiment of the present invention, the business information to be audited includes initial business information or periodic audit information.

[0043] Initial registration documents refer to the business-related materials provided by medical supply providers when they join a medical supply business platform. Periodic review documents refer to the business-related materials that the medical supply platform needs to review when the review cycle for medical product providers is reached. Compared to the review of medical product business documents at other times, the workload for initial registration documents and periodic review documents is greater and the review efficiency is lower; therefore, this solution is more effective.

[0044] This solution automates the review of medical product providers' initial or periodic review documents by specifying the business information to be reviewed.

[0045] Specifically, you can obtain the pending business information uploaded by the medical product provider to the medical product business platform.

[0046] S120. Identify the business data to be reviewed to obtain at least one unit text area and the unit text content corresponding to the unit text area.

[0047] The unit text area can be the area occupied by text of a certain content category in the business documents to be reviewed. For example, the unit text area can be the area occupied by a single line of text in the business documents to be reviewed, or the area occupied by multiple blocks of text exceeding a preset interval within a single line of the business documents to be reviewed. Optionally, the unit text area can be represented by the vertex coordinates of the area. For example, the unit text area can be a rectangular area; the coordinates of the four vertices of the rectangle can be used to represent the unit text area. The unit text content can be the specific content of the text within the unit text area.

[0048] Specifically, an OCR (Optical Character Recognition) algorithm can be used to recognize the business documents to be reviewed, and obtain at least one unit text area and the unit text content corresponding to the unit text area.

[0049] S130. Perform clarity testing on the text areas of each unit to obtain the comprehensive clarity test results of the business documents to be reviewed.

[0050] The overall clarity test results of the business documents to be reviewed can be used to characterize the overall clarity of the documents. For example, the overall clarity test results of the business documents to be reviewed may include clear or unclear.

[0051] Specifically, the Laplace algorithm can be used to calculate the sharpness of individual text regions, obtaining the unit sharpness of each region. The unit sharpnesses of each text region can then be combined, for example, by weighted summation or averaging, to obtain the overall sharpness of the business documents to be reviewed. This overall sharpness can then be compared to a preset overall sharpness threshold. If the overall sharpness of the business documents to be reviewed is greater than or equal to the preset threshold, the overall sharpness test result is considered clear; if the overall sharpness is less than the threshold, the overall sharpness test result is considered unclear. The overall sharpness characterizes the overall clarity of the text contained in the business documents to be reviewed.

[0052] S140. When the overall clarity test result of the business documents to be reviewed is clear, the reference text content corresponding to the text content of each unit shall be queried based on the identity identifier contained in the text content of each unit.

[0053] The reference text content can be pre-stored in this device to verify the correctness of the unit's text content. All reference text content corresponding to the same identity can be stored uniformly in this device.

[0054] Specifically, when the overall clarity test result of the business documents to be reviewed is clear, the reference text content corresponding to the identity identifier contained in the text content of each unit can be queried, thereby obtaining the reference text content corresponding to the text content of each unit.

[0055] S150. Perform consistency checks on the text content of each unit and the corresponding reference text content.

[0056] Specifically, the text content of each unit and its corresponding reference text content can be vectorized to obtain text content vectors for each unit and their corresponding reference text content. The unit similarity can then be calculated between these vectors. Each unit's similarity can be compared to a preset similarity threshold. If the similarity of all units is greater than or equal to the preset threshold, the text content of each unit is determined to be consistent with its corresponding reference text content; if the similarity of any unit is less than the preset threshold, the text content of each unit is determined to be inconsistent with its corresponding reference text content. For example, the preset similarity threshold can be 100%.

[0057] Optionally, when it is determined that the text content of each unit is inconsistent with the corresponding reference text content, the medical product operation platform will send an information change prompt to the medical product provider to remind the medical product provider to update the operation information in a timely manner.

[0058] Optionally, if it is determined that the text content of each unit is inconsistent with the corresponding reference text content, and the text content of the unit with inconsistent positioning is the business scope, the medical product operation platform will issue a non-compliant business scope warning to the medical product provider to prompt the medical product provider to handle the corresponding medical products.

[0059] S160. Based on the consistency test results of the unit text content, determine the audit results of the business data to be audited.

[0060] The review results of pending business documents can be characterized by two dimensions: clarity and content consistency. For example, the review results can include "approved" and "unapproved".

[0061] Specifically, if the consistency test result of the unit text content is consistent with the corresponding reference text content, the audit result of the business documents to be audited is determined to be approved; if the consistency test result of the unit text content is inconsistent with the corresponding reference text content, the audit result of the business documents to be audited is determined to be unapproved.

[0062] The technical solution of this invention identifies the business documents to be reviewed, obtaining at least one unit text area and the corresponding unit text content. Clarity detection is performed on each unit text area to obtain a comprehensive clarity detection result for the business documents to be reviewed. When the comprehensive clarity detection result of the business documents to be reviewed is clear, the reference text content corresponding to each unit text content is queried based on the identity identifier contained in each unit text content. Consistency detection is performed on each unit text content and its corresponding reference text content. Based on the consistency detection result of the unit text content, the review result of the business documents to be reviewed is determined. This achieves automatic review of the business documents of medical product providers from both text clarity and content consistency perspectives, improving the review efficiency and accuracy of the business documents of medical product providers and ensuring the operational stability of the medical product business platform.

[0063] Example 2

[0064] Figure 2 This is a flowchart of a method for reviewing business information of medical products provided in Embodiment 2 of the present invention. Based on the above embodiments, this invention further specifies the process of "identifying the business information to be reviewed and obtaining at least one unit text area and the corresponding unit text content" as "identifying the business information to be reviewed and obtaining the largest effective text area, at least one unit text area, and the corresponding unit text content." It also specifies the process of "performing clarity detection on each unit text area to obtain the overall clarity detection result of the business information to be reviewed" as "calculating the clarity of the largest effective text area to obtain its average clarity; calculating the clarity of each unit text area to obtain its average clarity; combining the average clarity of the largest effective text area and the unit clarity of each unit text area to obtain the overall clarity of the business information to be reviewed; obtaining a preset overall clarity threshold and comparing the overall clarity of the business information to be reviewed with the preset overall clarity threshold to obtain the overall clarity detection result of the business information to be reviewed." This invention introduces the concepts of the largest effective text area and average clarity, considering the overall clarity of medical supply business information, further improving the accuracy of clarity detection for medical supply business information, thereby improving the accuracy of reviewing medical supply business information. It should be noted that for parts not described in detail in the embodiments of the present invention, please refer to the descriptions in other embodiments.

[0065] See Figure 2 The methods for reviewing the business information of medical products shown include:

[0066] S210. Obtain the business information to be reviewed.

[0067] S220. Identify the business data to be reviewed to obtain the largest effective text area, at least one unit text area, and the unit text content corresponding to the unit text area.

[0068] The maximum effective text area can be the area containing text remaining after cropping the white borders without text from the business documents to be reviewed. Generating the maximum effective text area can be understood as removing areas without text or indistinguishable from the background, i.e., removing areas that do not require clarity assessment. For example, the business documents to be reviewed could be scaled-down versions of an identity document. The maximum effective text area can be the actual area occupied by the identity document within the business documents to be reviewed. Another example is a power of attorney. The maximum effective text area can be the smallest rectangular area that can select all the text in the power of attorney; that is, the effective text area excluding page margins. Yet another example is a scaled-down version of a business license. The maximum effective text area can include the actual area occupied by the business license within the business documents to be reviewed, or a further cropped result of the actual area occupied by the business license within the business documents to be reviewed. This can be understood as follows: when the business license is a color document, the maximum effective text area can be the actual area occupied by the business license within the business documents to be reviewed. When the business license is a black and white document, the maximum effective text area can be a further cropped result of the actual area occupied by the business license within the business documents to be reviewed. For example, the largest effective text region can be represented by the vertex coordinates of the region.

[0069] Specifically, edge detection algorithms can be used to crop the business documents to be reviewed, obtaining the largest effective text area. OCR algorithms can be used to recognize the business documents to be reviewed, obtaining at least one unit of text area and the corresponding text content for each unit. For example, edge detection algorithms can include the Sobel edge detection algorithm (a first-derivative-based edge detection method), the Roberts edge detection algorithm (a cross-differential algorithm), or the Canny edge detection algorithm (a classic edge detection method), etc.

[0070] In an optional embodiment of the present invention, after obtaining the maximum effective text area, at least one unit text area, and the unit text content corresponding to the unit text area, the method further includes: detecting and removing the official seal area within the maximum effective text area.

[0071] Based on the experimental results of technical personnel, it is evident that official seals may affect the accuracy of average clarity detection for the largest effective text area, thereby impacting the accuracy of clarity detection for medical product business documents. The official seal area can be the area occupied by the official seal in the business documents to be audited.

[0072] Specifically, after obtaining the largest effective text region, at least one unit text region, and the unit text content corresponding to the unit text region, a seal recognition algorithm can be used to identify the business documents to be reviewed, thus obtaining the seal region. The seal region can be removed from the largest effective text region. For example, the seal recognition algorithm can be a pre-trained seal recognition model.

[0073] This solution introduces the detection of the official seal area. By removing the official seal area from the largest effective text area, the accuracy of the clarity detection of medical product business documents can be improved, thereby improving the accuracy of the review of medical product business documents.

[0074] S230. Calculate the sharpness of the largest effective text area to obtain the average sharpness of the largest effective text area.

[0075] Average clarity represents the sharpness of the largest effective text area. It provides a comprehensive overview of the clarity of the business documents being audited. A higher average clarity indicates a sharper largest effective text area, while a lower average clarity indicates a less sharp largest effective text area.

[0076] Specifically, the Laplace algorithm can be used to calculate the sharpness of the largest effective text region and obtain the average sharpness of the largest effective text region.

[0077] S240. Calculate the clarity of each unit text area to obtain the unit clarity of each unit text area.

[0078] Unit sharpness refers to the clarity of text within a unit text area. Unit sharpness characterizes the clarity of a single group of text from a local perspective. It can be understood that higher unit sharpness means clearer text within the unit text area; lower unit sharpness means less clear text within the unit text area.

[0079] Specifically, the Laplace algorithm can be used to calculate the sharpness of individual text regions, thus obtaining the sharpness of each individual text region.

[0080] S250. The average clarity of the largest effective text area and the unit clarity of each unit text area are combined to obtain the overall clarity of the business data to be audited.

[0081] Overall clarity can be characterized from two dimensions: the overall image and the overall text.

[0082] Specifically, the overall clarity of the business documents to be reviewed can be obtained by weighted summing of the average clarity of the largest effective text area and the average clarity of each unit text area.

[0083] Optionally, the average clarity of each text region can be calculated. A weighted sum of the average clarity of the largest effective text region and the average clarity of each text region can be obtained to determine the overall clarity of the business documents to be reviewed.

[0084] For example, the overall clarity of the business information to be audited can be calculated using the following formula:

[0085] Average sharpness = Laplacian algorithm value of the largest effective text region;

[0086] Average unit sharpness = sum(Laplacian algorithm value of unit text region) / number of unit text regions;

[0087] Overall sharpness = 0.6 * average sharpness + 0.4 * average unit sharpness;

[0088] In the formula, the Laplacian algorithm value of the largest effective text region is the result of the sharpness calculation of the largest effective text region using the Laplacian algorithm; the Laplacian algorithm value of the unit text region is the result of the sharpness calculation of the unit text region using the Laplacian algorithm; 0.6 is the weight of the average sharpness; and 0.4 is the weight of the average sharpness of the unit.

[0089] S260. Obtain the preset overall clarity threshold, and compare the overall clarity of the business documents to be reviewed with the preset overall clarity threshold to obtain the overall clarity detection result of the business documents to be reviewed.

[0090] The preset overall clarity threshold can serve as a reference value for the overall clarity of the business documents to be reviewed. For example, the preset overall clarity threshold can be 500. Based on experimental results from technical personnel, the detection accuracy with a preset overall clarity threshold of 500 is 95%.

[0091] Specifically, a preset overall clarity threshold can be retrieved from the device's storage. The overall clarity of the business documents to be reviewed can be compared with the preset overall clarity threshold. If the overall clarity of the business documents to be reviewed is greater than or equal to the preset overall clarity threshold, the overall clarity test result of the business documents to be reviewed is clear; if the overall clarity of the business documents to be reviewed is less than the preset overall clarity threshold, the overall clarity test result of the business documents to be reviewed is unclear.

[0092] S270. When the overall clarity test result of the business documents to be reviewed is clear, the reference text content corresponding to the text content of each unit shall be queried based on the identity identifier contained in the text content of each unit.

[0093] S280. Perform consistency checks on the text content of each unit and the corresponding reference text content.

[0094] S290. Based on the consistency test results of the unit text content, determine the audit results of the business data to be audited.

[0095] The technical solution of this invention introduces the maximum effective text area and average clarity, taking into account the overall clarity of medical supply business materials, further improving the accuracy of clarity detection for medical supply business materials, thereby improving the accuracy of review of medical supply business materials.

[0096] In an optional embodiment of the present invention, after obtaining the business information to be reviewed, the method further includes: detecting the template type of the business information to be reviewed; when the template type of the business information to be reviewed is detected, detecting at least one key text region of the business information to be reviewed; calculating the unit key clarity of each key text region; combining the unit key clarity of each key text region to obtain the key clarity of each key text region; obtaining a preset key clarity threshold, and comparing the key clarity of each key text region with the preset key clarity threshold to obtain the key clarity detection result of the business information to be reviewed; after obtaining the comprehensive clarity detection result of the business information to be reviewed, the method further includes: when the comprehensive clarity detection result of the business information to be reviewed is unclear or the key clarity detection result of the key text region of the business information to be reviewed is unclear, determining that the business information to be reviewed is unclear.

[0097] The template type of the business documents to be reviewed can be used to represent the category of the business documents to be reviewed. Key text areas can be relatively important text areas in the business documents to be reviewed, such as the specific content corresponding to identity identifiers and business permissions. The template type of the business documents to be reviewed has corresponding key text areas. For example, key text areas can be represented by the vertex coordinates of the area. Optionally, the template type of the business documents to be reviewed is associated with the vertex coordinates of each corresponding key text area and stored in a database. Unit key clarity can be the clarity of the text in a single key text area. Unit key clarity can further represent the clarity of key text from a local perspective. The higher the key clarity, the clearer the text within the key text area; the lower the key clarity, the less clear the text within the key text area. Key clarity can be used to represent the overall clarity of the key text contained in the business documents to be reviewed. For example, key clarity can be the average value of the unit key clarity of each key text area. The preset key clarity threshold can be a reference detection value for the key clarity of the business documents to be reviewed. For example, the preset key clarity threshold can be a value between 600 and 1000. The key clarity test results for the business documents to be reviewed can include whether they are clear or unclear.

[0098] Specifically, a template detection algorithm can be used to identify the template type of the business documents to be reviewed. For example, the template detection algorithm can be a template detection model. The business documents to be reviewed can be input into the template detection model, which outputs the reference template type and corresponding reference confidence level. The maximum value of the reference confidence level can be compared with a preset confidence threshold. If the maximum value of the reference confidence level is less than the preset confidence threshold, it is determined that no template type for the business documents to be reviewed was found. If the reference confidence level is greater than or equal to the preset confidence threshold, the reference template type corresponding to the maximum value of the reference confidence level is determined as the template type for the business documents to be reviewed. For example, the preset confidence threshold can be 0.8. Optionally, the business documents to be reviewed can be input into the template detection model, which outputs the reference template type and corresponding reference confidence level, as well as at least one key text region corresponding to each reference template type. The Laplace algorithm can be used to calculate the sharpness of the key text regions to obtain the unit key sharpness of the key text regions. The key clarity of each key text region can be weighted and summed to obtain the key clarity of each key text region. The key clarity of each key text region in the business documents to be reviewed can be compared with a preset key clarity threshold. If the key clarity of each key text region in the business documents to be reviewed is greater than or equal to the preset key clarity threshold, the key clarity detection result of the key text regions in the business documents to be reviewed is clear; if the key clarity of each key text region in the business documents to be reviewed is less than the preset key clarity threshold, the key clarity detection result of the key text regions in the business documents to be reviewed is unclear.

[0099] For example, the critical sharpness of each key text region can be calculated using the following formula:

[0100] Key clarity = sum(Laplacian algorithm value of key text region) / number of key text regions;

[0101] In the formula, the Laplacian algorithm value of the key text region is the result of the sharpness calculation of the key text region using the Laplacian algorithm, that is, the unit key sharpness.

[0102] This solution detects the template type of the business documents to be reviewed. Upon detecting the template type, it introduces a key text area detection method in addition to the maximum effective text area and unit text area. Furthermore, it calculates key clarity based on average clarity and unit clarity. If the overall clarity detection result of the business documents to be reviewed is unclear, or if the key clarity detection result of the key text area is unclear, the business documents to be reviewed are determined to be unclear. Comparatively, the clarity of key text within a key text area is more important than the clarity of text within a unit text area. Therefore, based on the unit clarity detection of unit text areas, a key text clarity detection process is added to the key text area, taking into account the clarity of key text in medical supply business documents, further improving the accuracy of clarity detection for medical supply business documents, thereby improving the accuracy of the review of medical supply business documents.

[0103] Figure 3 This is a flowchart illustrating the method for reviewing business information for medical products. Based on the above embodiments, Figure 3 This is a preferred embodiment of the present invention. See also: Figure 3 The methods for presenting information on the operation of medical products include:

[0104] S310. Obtain the business information to be reviewed and check the template type of the business information to be reviewed.

[0105] S320. When no template type of the business documents to be reviewed is detected, a general processing procedure is adopted to check the business documents to be reviewed and obtain the comprehensive clarity test results of the business documents to be reviewed.

[0106] The general processing flow may include: identifying the business data to be reviewed to obtain the largest effective text area, at least one unit text area, and the unit text content corresponding to each unit text area; using the Laplace algorithm to calculate the average clarity of the largest effective text area; using the Laplace algorithm to identify each unit text area to obtain the unit clarity of each unit text area; calculating the average unit clarity of each unit text area; weighted summing the average clarity of the largest effective text area and the average unit clarity of each unit text area to obtain the overall clarity of the business data to be reviewed; comparing the overall clarity of the business data to be reviewed with a preset overall clarity threshold; if the overall clarity of the business data to be reviewed is greater than or equal to the preset overall clarity threshold, the overall clarity detection result of the business data to be reviewed is clear; if the overall clarity of the business data to be reviewed is less than the preset overall clarity threshold, the overall clarity detection result of the business data to be reviewed is unclear.

[0107] S330. When a template type for the business documents to be reviewed is detected, a general processing flow is used to review the business documents to be reviewed, and a comprehensive clarity review result is obtained. At the same time, a key text area processing flow is used to review the business documents to be reviewed, and a key clarity review result is obtained. Based on the comprehensive clarity review result and the key clarity review result, the comprehensive clarity review result of the business documents to be reviewed is updated.

[0108] The key text region processing flow may include: when a template type of the business documents to be reviewed is detected, detecting at least one key text region in the business documents to be reviewed; calculating the unit key clarity of each key text region; combining the unit key clarity of each key text region to obtain the key clarity of each key text region; obtaining a preset key clarity threshold, and comparing the key clarity of each key text region with the preset key clarity threshold to obtain the key clarity detection result of the business documents to be reviewed.

[0109] Specifically, when the overall clarity test result of the business documents to be reviewed is clear and the key clarity test result of the key text area of ​​the business documents to be reviewed is clear, the overall clarity of the business documents to be reviewed is updated to clear; when the overall clarity test result of the business documents to be reviewed is unclear or the key clarity test result of the key text area of ​​the business documents to be reviewed is unclear, the overall clarity of the business documents to be reviewed is updated to unclear.

[0110] Optionally, if the overall clarity of the business documents to be reviewed is found to be unclear, feedback can be sent to the medical product business platform to prompt the platform to manually review the clarity of the documents.

[0111] S340. Perform a consistency check on the unit text content and the corresponding reference text content of the business data to be audited, and obtain the consistency check result of the business data to be audited.

[0112] The reference text content can be pre-stored in the database.

[0113] S350. Based on the comprehensive clarity test results and consistency test results of the business documents to be audited, determine the audit results of the business documents to be audited.

[0114] Specifically, if the consistency test result of the unit text content and the overall clarity test result of the business documents to be reviewed are clear and the text content of each unit is consistent with the corresponding reference text content, the review result of the business documents to be reviewed is determined to be approved; if the consistency test result of the unit text content is inconsistent with the corresponding reference text content or the overall clarity test result of the business documents to be reviewed is unclear, the review result of the business documents to be reviewed is determined to be unapproved.

[0115] This solution can improve the efficiency of reviewing business information for medical products, thereby increasing the approval rate.

[0116] Example 3

[0117] Figure 4 This is a schematic diagram of a medical product business information verification device provided in Embodiment 3 of the present invention. This embodiment of the invention is applicable to the verification of medical product business information on a medical product business platform. The device can execute a medical product business information verification method and can be implemented in hardware and / or software. The device can be configured in an electronic device that carries the function of verifying medical product business information.

[0118] See Figure 4 The medical product business data verification device shown includes: a business data acquisition module 410, a unit text region recognition module 420, a comprehensive clarity detection module 430, a reference text content query module 440, a text content consistency detection module 450, and a verification result determination module 460. The system includes: a business data acquisition module 410 for acquiring business data to be reviewed; a unit text region recognition module 420 for recognizing the business data to be reviewed to obtain at least one unit text region and the corresponding unit text content; a comprehensive clarity detection module 430 for performing clarity detection on each unit text region to obtain a comprehensive clarity detection result for the business data to be reviewed; a reference text content query module 440 for querying the reference text content corresponding to each unit text content based on the identity identifier contained in each unit text content when the comprehensive clarity detection result of the business data to be reviewed is clear; a text content consistency detection module 450 for performing consistency detection on each unit text content and the corresponding reference text content; and a review result determination module 460 for determining the review result of the business data to be reviewed based on the consistency detection result of the unit text content.

[0119] The technical solution of this invention identifies the business documents to be reviewed, obtaining at least one unit text area and the corresponding unit text content. Clarity detection is performed on each unit text area to obtain a comprehensive clarity detection result for the business documents to be reviewed. When the comprehensive clarity detection result of the business documents to be reviewed is clear, the reference text content corresponding to each unit text content is queried based on the identity identifier contained in each unit text content. Consistency detection is performed on each unit text content and its corresponding reference text content. Based on the consistency detection result of the unit text content, the review result of the business documents to be reviewed is determined. This achieves automatic review of the business documents of medical product providers from both text clarity and content consistency perspectives, improving the review efficiency and accuracy of the business documents of medical product providers and ensuring the operational stability of the medical product business platform.

[0120] In an optional embodiment of the present invention, the unit text region recognition module includes: a maximum effective text region recognition unit, used to recognize the business information to be reviewed, and obtain a maximum effective text region, at least one unit text region, and unit text content corresponding to the unit text region; the comprehensive clarity detection module includes: an average clarity calculation unit, used to calculate the clarity of the maximum effective text region, and obtain the average clarity of the maximum effective text region; a unit clarity calculation unit, used to calculate the clarity of each unit text region, and obtain the unit clarity of each unit text region; a comprehensive clarity calculation unit, used to combine the average clarity of the maximum effective text region and the unit clarity of each unit text region, and obtain the comprehensive clarity of the business information to be reviewed; and a comprehensive clarity detection unit, used to compare the comprehensive clarity of the business information to be reviewed with a preset comprehensive clarity threshold, and obtain the comprehensive clarity detection result of the business information to be reviewed.

[0121] In an optional embodiment of the present invention, the device further includes: a template type detection module, configured to detect the template type of the business data to be reviewed after obtaining the business data to be reviewed; a key text region detection module, configured to detect at least one key text region of the business data to be reviewed when the template type of the business data to be reviewed is detected; a unit key clarity calculation module, configured to calculate the unit key clarity of each key text region; a key clarity calculation module, configured to integrate the unit key clarity of each key text region to obtain the key clarity of each key text region; a key clarity detection module, configured to obtain a preset key clarity threshold and compare the key clarity of each key text region with the preset key clarity threshold to obtain the key clarity detection result of the business data to be reviewed; and a review result determination module, further including: a review result determination unit, configured to determine that the business data to be reviewed is unclear when the overall clarity detection result of the business data to be reviewed is unclear or the key clarity detection result of the key text region of the business data to be reviewed is unclear after obtaining the overall clarity detection result of the business data to be reviewed.

[0122] In an optional embodiment of the present invention, the device further includes: a seal text region removal module, used to detect and remove the seal text region in each of the unit text regions after obtaining at least one unit text region and the unit text content corresponding to the unit text region.

[0123] In an optional embodiment of the present invention, the operating data to be audited includes initial operating data or periodic operating data.

[0124] The medical product business data verification device provided in this embodiment of the invention can execute the medical product business data verification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0125] In the technical solutions of this invention, the acquisition, storage, and application of business information to be reviewed, preset comprehensive clarity threshold, and preset key clarity threshold, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0126] Example 4

[0127] Figure 5A schematic diagram of an electronic device 500 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0128] like Figure 5 As shown, the electronic device 500 includes at least one processor 501 and a memory, such as a read-only memory (ROM) 502 or a random access memory (RAM) 503, communicatively connected to the at least one processor 501. The memory stores computer programs executable by the at least one processor. The processor 501 can perform various appropriate actions and processes based on the computer program stored in the ROM 502 or loaded into the RAM 503 from storage unit 508. The RAM 503 can also store various programs and data required for the operation of the electronic device 500. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0129] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0130] Processor 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 501 performs the various methods and processes described above, such as the methods for reviewing business information for medical products.

[0131] In some embodiments, the medical product business information verification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by processor 501, one or more steps of the medical product business information verification method described above may be performed. Alternatively, in other embodiments, processor 501 may be configured to perform the medical product business information verification method by any other suitable means (e.g., by means of firmware).

[0132] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0133] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0134] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0136] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0137] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0138] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0139] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for reviewing the business information of medical products, characterized in that, The method includes: Obtain the business information pending review; The template type of the business documents to be reviewed is checked; When the template type of the business documents to be reviewed is detected, at least one key text area of ​​the business documents to be reviewed is detected; Calculate the unit key clarity of each of the key text regions; The key clarity of each key text region is obtained by combining the unit key clarity of each key text region. A preset key clarity threshold is obtained, and the key clarity of each key text region is compared with the preset key clarity threshold to obtain the key clarity detection result of the business documents to be reviewed; The business data to be reviewed is identified to obtain the largest effective text area, at least one unit text area, and the unit text content corresponding to the unit text area; The sharpness of the largest effective text region is calculated to obtain the average sharpness of the largest effective text region. Calculate the clarity of each unit text region to obtain the unit clarity of each unit text region; The overall clarity of the business documents to be reviewed is obtained by combining the average clarity of the largest effective text region and the unit clarity of each unit text region. A preset overall clarity threshold is obtained, and the overall clarity of the business information to be reviewed is compared with the preset overall clarity threshold to obtain the overall clarity detection result of the business information to be reviewed; If the overall clarity test result of the business documents to be reviewed is unclear or the key clarity test result of the key text area of ​​the business documents to be reviewed is unclear, the business documents to be reviewed are determined to be unclear. When the overall clarity test result of the business documents to be reviewed is clear, the reference text content corresponding to the text content of each unit is queried according to the identity identifier contained in the text content of each unit. A consistency check is performed on the text content of each unit and the corresponding reference text content; Based on the consistency detection results of the text content of the unit, the review result of the business information to be reviewed is determined.

2. The method according to claim 1, characterized in that, After obtaining the maximum effective text region, at least one unit text region, and the unit text content corresponding to the unit text region, the method further includes: Within the largest valid text area, detect and remove the official seal area.

3. The method according to claim 1, characterized in that, The business data to be audited includes initial business data or periodic business data.

4. A device for verifying the business information of medical products, characterized in that, The device includes: The business data acquisition module is used to acquire business data to be reviewed. The template type detection module is used to detect the template type of the business documents to be reviewed; The key text region detection module is used to detect at least one key text region of the business materials to be reviewed when the template type of the business materials to be reviewed is detected; The unit key clarity calculation module is used to calculate the unit key clarity of each of the key text regions. The key clarity calculation module is used to integrate the unit key clarity of each key text region to obtain the key clarity of each key text region. The key clarity detection module is used to obtain a preset key clarity threshold and compare the key clarity of each key text region with the preset key clarity threshold to obtain the key clarity detection result of the business documents to be reviewed. The maximum effective text region recognition unit is used to recognize the business information to be reviewed, and obtain the maximum effective text region, at least one unit text region, and the unit text content corresponding to the unit text region; An average sharpness calculation unit is used to calculate the sharpness of the largest effective text region and obtain the average sharpness of the largest effective text region. The unit sharpness calculation unit is used to calculate the sharpness of each unit text region to obtain the unit sharpness of each unit text region. The overall clarity calculation unit is used to combine the average clarity of the largest effective text region and the unit clarity of each unit text region to obtain the overall clarity of the business data to be reviewed. The overall clarity detection unit is used to compare the overall clarity of the business materials to be reviewed with a preset overall clarity threshold to obtain the overall clarity detection result of the business materials to be reviewed. The audit result determination unit is used to determine that the business materials to be audited are unclear when the overall clarity detection result of the business materials to be audited is unclear or the key clarity detection result of the key text area of ​​the business materials to be audited is unclear. The reference text content query module is used to query the reference text content corresponding to each unit text content based on the identity identifier contained in the text content of each unit when the overall clarity detection result of the business materials to be reviewed is clear. The text content consistency detection module is used to perform consistency detection on the text content of each unit and the corresponding reference text content; The audit result determination module is used to determine the audit result of the business documents to be audited based on the consistency detection result of the text content of the unit.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the medical product business data review method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the medical product business data review method according to any one of claims 1-3.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the medical product business data review method according to any one of claims 1-3.

Images