A physical examination report verification method, device, equipment and medium

Abstract

The present invention relates to the field of information processing technology, and provides a physical examination report verification method, device, equipment and medium, which can receive a physical examination report and perform text extraction on the physical examination report to obtain the physical examination report text information; the physical examination report text information is compared with the corresponding physical examination package content for consistency; when the physical examination report text information and the corresponding physical examination package content are compared for consistency, the department summary and the final examination conclusion in the physical examination report text information are matched for text similarity; the user information in the physical examination report text information is verified with the user information reserved during the user's physical examination; when the user information in the physical examination report text information is verified with the user information reserved during the user's physical examination, the physical examination report is transferred to the user end. The present invention can automatically match physical examination reports, improve operational efficiency, reduce the error rate caused by human participation, reduce operational manpower costs, and avoid mis-sending reports.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a physical examination report verification method, device, equipment and medium. Background Art

[0002] With the development of social economy, the improvement of people's living standards and the continuous improvement of the basic medical security system for urban and rural residents, people's medical needs are increasing, especially the demand for physical examination services is becoming more and more serious. Physical examination report refers to a document with a certain format generated based on the data of physical examination and reaction. Physical examination report is an important data for physical examination users to intuitively understand their own health status.

[0003] However, the existing physical examination report generation and circulation process has the following problems:

[0004] 1. During the generation process of the physical examination report, there may be errors in the report generation due to system problems, such as duplicate content, blank pages, mismatched user information, etc. This will not only affect the user experience, but also mismatched user information may lead to the mis-sending of the report.

[0005] 2. System problems cause reports to be sent to other users by mistake, which not only increases the risk of privacy of reports, but also causes users to misunderstand their own conditions when they receive reports from others by mistake. In serious cases, this can lead to wrong medication, wrong medical treatment, emotional instability, etc., leading to an increase in user complaints;

[0006] 3. Human error by doctors leads to erroneous final examination conclusions. Users will first check the final examination conclusions of their own reports because they are more intuitive and clear. If an erroneous conclusion is reached, users will also misunderstand their own condition.

[0007] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0008] The purpose of the present invention is to provide a physical examination report verification method, device, equipment and medium, thereby overcoming one or more problems caused by the limitations and defects of the relevant technology at least to a certain extent.

[0009] To achieve the above-mentioned purpose and other related purposes, the present invention provides a physical examination report verification method, comprising:

[0010] Receiving a physical examination report, and performing text extraction on the physical examination report to obtain text information of the physical examination report;

[0011] Performing a consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and a consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content;

[0012] When the consistency comparison between the physical examination report text information and the corresponding physical examination package content is passed, the department summary and the final examination conclusion in the physical examination report text information are matched for text similarity;

[0013] When the department summary and the final examination conclusion in the physical examination report text information match, verifying the user information in the physical examination report text information with the user information reserved during the user's physical examination;

[0014] When the user information in the text information of the physical examination report is verified with the user information reserved during the user's physical examination, the physical examination report is transferred to the user end.

[0015] In one embodiment of the present invention, before the consistency comparison between the physical examination report text information and the corresponding physical examination package content is performed, a step of performing error detection on the physical examination report text information is also included.

[0016] In one embodiment of the present invention, the step of comparing the consistency of the medical examination report text information with the corresponding medical examination package content includes:

[0017] Segmenting the physical examination report text information to obtain department segmentation information of each department, each of the department segmentation information corresponds to a department name in the physical examination report text information;

[0018] Performing a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content to obtain a first matching degree;

[0019] When the first matching degree is greater than or equal to a first preset threshold, the department segmentation information of each department is re-segmented to obtain item segmentation information of each physical examination item, each item segmentation information corresponds to a physical examination item name in the physical examination report text information;

[0020] Performing a consistency comparison between the names of the physical examination items in the physical examination report text information and the names of the physical examination items in the physical examination package content to obtain a second matching degree;

[0021] When the second matching degree is greater than or equal to a second preset threshold, a step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report is performed.

[0022] In an embodiment of the present invention, the first preset threshold is greater than the second preset threshold.

[0023] In one embodiment of the present invention, the step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report includes:

[0024] Extracting the corresponding department summaries of each department from the department segmentation information of each department and performing splicing and integration to obtain department summary integration data;

[0025] Extracting the final examination conclusion from the text information of the physical examination report;

[0026] Performing text similarity matching between the department summary integrated data and the final inspection conclusion;

[0027] When the department summary integrated data matches the final examination conclusion, a step of verifying the user information in the physical examination report text information with the user information reserved during the user's physical examination is performed.

[0028] In one embodiment of the present invention, the physical examination report verification method further includes:

[0029] When the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content fails, a first type of manual review is performed;

[0030] When the department summary and the final examination conclusion in the text information of the physical examination report do not match, a first type of manual review is performed.

[0031] In one embodiment of the present invention, the physical examination report verification method further includes:

[0032] When the user information in the medical examination report text information fails to pass the verification with the user information reserved during the user's medical examination, a second type of manual review is performed;

[0033] After passing the second type of manual review, the verification and collection process will begin.

[0034] In order to achieve the above-mentioned object and other related objects, the present invention also provides a physical examination report verification device, the physical examination report verification device comprising:

[0035] A text extraction unit, used for receiving a physical examination report and performing text extraction on the physical examination report to obtain text information of the physical examination report;

[0036] A first matching unit is used to perform consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content;

[0037] A second matching unit is used to perform text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report when the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content is passed;

[0038] A user information verification unit, used to verify the user information in the physical examination report text information with the user information reserved during the user's physical examination when the department summary in the physical examination report text information matches the final examination conclusion;

[0039] The transfer unit is used to transfer the physical examination report to the user end when the user information in the physical examination report text information is verified with the user information reserved during the user physical examination.

[0040] To achieve the above-mentioned object and other related objects, the present invention further provides an electronic device, the electronic device comprising:

[0041] a memory storing at least one instruction; and

[0042] The processor executes the instructions stored in the memory to implement the above-mentioned physical examination report verification method.

[0043] To achieve the above-mentioned purpose and other related purposes, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned physical examination report verification method.

[0044] The physical examination report verification method, device, equipment and medium of the present invention can intelligently check the matching degree between the physical examination report content and the corresponding physical examination package content and the matching degree between the department summary in the physical examination report and the final examination conclusion, thereby reducing the error rate caused by human participation and reducing the operating manpower cost.

[0045] The physical examination report verification method, device, equipment and medium of the present invention can detect low-level errors (duplicate content, blank pages and garbled characters) and other errors in the physical examination report.

[0046] The physical examination report verification method, device, equipment and medium of the present invention can reduce the scenarios where the system generates report errors and increase the accuracy of the report.

[0047] The physical examination report verification method, device, equipment and medium of the present invention can intelligently verify the user information reserved during the user's physical examination and the user information in the physical examination report when the verified physical examination report is transferred to the user end, avoid sending it to the wrong user, better protect user privacy, and reduce user complaints.

[0048] The physical examination report verification method, device, equipment and medium of the present invention can automatically match physical examination reports and improve operational efficiency.

[0049] The physical examination report verification method, device, equipment and medium of the present invention basically do not affect the report verification result even after the report template is updated, and have high accuracy and compatibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of a preferred embodiment of the physical examination report verification method of the present invention is shown.

[0051] Figure 2 A sub-step flow chart of step S30 of a preferred embodiment of the physical examination report verification method of the present invention is shown.

[0052] Figure 3 A functional module diagram of a preferred embodiment of the physical examination report verification device of the present invention is shown.

[0053] Figure 4 A schematic diagram of the structure of an electronic device for implementing a preferred embodiment of the method for verifying a physical examination report of the present invention is shown. DETAILED DESCRIPTION

[0054] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0055] See also Figure 1-4 It should be noted that the illustrations provided in this embodiment are only used to illustrate the basic concept of the present invention in a schematic manner, and the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0056] Figure 1 A flow chart of a preferred embodiment of the physical examination report verification method of the present invention is shown.

[0057] The physical examination report verification method is applied to one or more electronic devices, which are devices that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and their hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0058] The electronic device may be any electronic product that can perform human-computer interaction with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistant (PDA), a game console, an interactive network television (IPTV), a smart wearable device, etc.

[0059] The electronic device may also include a network device and / or a user device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud consisting of a large number of hosts or network servers based on cloud computing.

[0060] The network where the electronic device is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (VPN), etc.

[0061] The following will be combined Figure 1 The physical examination report verification method of the present invention is described in detail.

[0062] First, execute step S10, receive the physical examination report, and extract the text of the physical examination report to obtain the physical examination report text information. The physical examination report text information may include user information, department name, physical examination item name, physical examination item test results, department summary, final examination conclusion and other information.

[0063] In this embodiment, the physical examination report is provided by the physical examination institution. After the physical examination report verification device receives the physical examination report sent by the physical examination structure, it can automatically trigger (of course, it can also be manually triggered) the physical examination report verification process. When extracting text from the physical examination report, the corresponding text extraction process is used to extract text according to the file format of the physical examination report to obtain the text information of the physical examination report. The file format can be, for example, PDF format, jpeg, png and other image formats, or word format.

[0064] For example: for physical examination reports in PDF format, you can use the open source, Java-based Apache PDFbox tool library that supports PDF document generation to extract the text information of the entire user's physical examination report or a page in the report; for physical examination reports in image formats such as jpeg and png, you can use OCR technology to extract the text information of the user's physical examination report; for physical examination reports in word format, you can use poi, poi-ooxml or poi-scratchpad framework to extract text information in the user's physical examination report.

[0065] Then, step S20 is executed to perform error detection on the text information of the physical examination report.

[0066] In this embodiment, error detection is to perform error detection on the extracted data of each page of the physical examination report, such as blank pages, repeated content, and garbled characters. For example, when the extracted data of a page in the physical examination report does not have any content, the page is considered to be a blank page; when the extracted data of a page in the physical examination report is consistent with the extracted data of a page before the page, the page is considered to have repeated content; when the extracted text in the physical examination report is not within the Unicode encoding range: 4E00-9FA5 (Chinese), 30-39 (numbers), 61-7a and 41-5a (uppercase and lowercase English), it is considered to be garbled characters.

[0067] If the above-mentioned errors are detected in the text information of the physical examination report, a first type of manual review is performed. When there are no errors in the text information of the physical examination report, step S30 is executed.

[0068] Among them, the first type of manual review refers to the transfer of the physical examination report to the user end after the review is passed. If the review fails, the physical examination report will be returned to the original physical examination structure, and the original physical examination institution needs to provide a new physical examination report that meets the requirements and re-verify the process.

[0069] By performing error detection on the text information of the physical examination report, errors in the generated physical examination report caused by system problems can be reduced, thereby increasing the accuracy of the report.

[0070] Next, execute step S30 to perform a consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and a consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content.

[0071] like Figure 2As shown, the step of comparing the consistency of the physical examination report text information with the corresponding physical examination package content further includes:

[0072] Step S31, segmenting the physical examination report text information to obtain department segmentation information of each department, each of the department segmentation information corresponds to a department name in the physical examination report text information;

[0073] Step S32: performing a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content to obtain a first matching degree;

[0074] Step S33: when the first matching degree is greater than or equal to the first preset threshold, the department segmentation information of each department is re-segmented to obtain the detailed segmentation information of each physical examination item, each of which corresponds to a physical examination item name in the physical examination report text information, and when the first matching degree is less than the first preset threshold, it means that the consistency comparison between the physical examination report text information and the corresponding physical examination package content fails, and a first type of manual review is required;

[0075] Step S34: performing a consistency comparison between the names of the physical examination items in the physical examination report text information and the names of the physical examination items in the physical examination package content to obtain a second matching degree.

[0076] When the second matching degree is greater than or equal to the second preset threshold, that is, when the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content is passed, step S40 needs to be executed; when the second matching degree is less than the second preset threshold, it means that the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content is not passed, and the first type of manual review is required.

[0077] As can be seen from the above, in this embodiment, when the first matching degree is greater than or equal to the first preset threshold, and when the second matching degree is greater than or equal to the second preset threshold, it means that the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content has passed, and step S40 needs to be performed. When the first matching degree is less than the first preset threshold, or the second matching degree is less than the second preset threshold, that is, when the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content has failed, a first type of manual review is required.

[0078] It should be noted that the first matching degree and the second matching degree can be customized according to actual needs, and the present invention is not limited thereto.

[0079] In the present invention, each physical examination report corresponds to a physical examination order of the user. The physical examination order is generated after the user makes an appointment. The order records which physical examination package the user has reserved at that time. The physical examination package corresponding to the physical examination report can be obtained according to the physical examination order information. The content of the physical examination package, that is, the test items in the physical examination package, corresponds to each department and physical examination item data, which is provided in advance by the physical examination institution and maintained and stored in the physical examination report verification device in advance; and in the physical examination report of the physical examination institution, there are test results corresponding to the department and physical examination items.

[0080] For example, in order to accurately segment the text information of the physical examination report and obtain the department segmentation information of each department and the detailed segmentation information of each physical examination item, the physical examination report verification device has pre-summarized 102 department names (such as: general examination, internal medicine, surgery, ENT, gynecology, blood routine, blood sugar, urine routine, etc.), 827 physical examination item names (such as: height, weight, systolic blood pressure, diastolic blood pressure, pulse, body mass index, waist circumference, hip circumference, waist-to-hip ratio, body fat percentage, etc.). The 102 department names and 827 item names cover 4.7 million report data.

[0081] According to the 102 department names and using regular expressions, the physical examination report text information is segmented starting with the first department name that matches these department names and ending with the second department name, and so on, to obtain the department segmentation information of each department, wherein each of the department segmentation information corresponds to a department name in the physical examination report text information. By obtaining the department name in the physical examination report text information according to the department segmentation information of each department, the problem of repeated extraction of the same department name in the physical examination report text information can be avoided.

[0082] The consistency comparison of the department names in the physical examination report text information and the department names in the physical examination package content is performed to obtain a first matching degree in the following manner: construct a first set and a second set, the first set is composed of all department names in the physical examination report text information, and the second set is composed of all department names in the physical examination package content; obtain department names belonging to the first set but not belonging to the second set and department names belonging to the second set but not belonging to the first set to form a third set; calculate the first matching degree according to the following formula,

[0083] The first matching degree = 1-(the number of department names in the third set / the number of department names in the second set).

[0084] When the first matching degree is less than 95%, the above-mentioned first type of manual review will be performed, wherein 95% is used as the first preset threshold.

[0085] When the first matching degree is greater than or equal to 95%, the segmented information of each department is re-segmented according to the 827 item names and regular expressions to obtain the item segmentation information of each physical examination item, and each item segmentation information corresponds to a physical examination item name in the physical examination report text information.

[0086] By obtaining the names of the physical examination items in the physical examination report text information in accordance with the item segmentation information of each physical examination item, the problem of repeated extraction of the same physical examination item name in the physical examination report text information can be avoided.

[0087] The consistency comparison between the names of the physical examination items in the physical examination report text information and the names of the departments in the physical examination package content to obtain the second matching degree can be performed in the following manner: construct a fourth set and a fifth set, the fourth set consisting of all the names of the physical examination items in the physical examination report text information, and the fifth set consisting of all the names of the physical examination items in the physical examination package content; obtain the names of the physical examination items that belong to the fourth set but not to the fifth set and the names of the physical examination items that belong to the fifth set but not to the fourth set to form a sixth set; calculate the second matching degree according to the following formula,

[0088] The second matching degree = 1-(the number of names of physical examination items in the sixth set / the number of names of physical examination items in the fifth set).

[0089] When the second matching degree is less than 90%, the above-mentioned first type of manual review will be performed, wherein 90% serves as the second preset threshold.

[0090] When the second matching degree is greater than or equal to 90%, the step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report is performed, that is, step S40.

[0091] It should be noted that the second preset threshold here is smaller than the first preset threshold mainly because it takes into account the possibility that the user undergoing the physical examination may have additional physical examination items at the physical examination site.

[0092] By comparing the consistency of the text information of the physical examination report with the corresponding physical examination package content, errors in the generated physical examination report caused by system problems or human problems can be reduced, and the accuracy of the report can be increased.

[0093] Next, step S40 is executed to perform text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report.

[0094] The step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report further includes:

[0095] Extracting the corresponding department summaries of each department from the department segmentation information of each department and performing splicing and integration to obtain department summary integration data;

[0096] Extracting the final examination conclusion from the text information of the physical examination report;

[0097] Performing text similarity matching between the department summary integrated data and the final inspection conclusion;

[0098] When the department summary integrated data matches the final examination conclusion, step S50 is executed. When the department summary in the physical examination report text information does not match the final examination conclusion, a first type of manual review is performed.

[0099] As an example, in the department segmentation information of each department, there will be a conclusion (that is, department summary) at the end of the content, but because the corresponding text of each institution's report is different, the following regular expression can be used:

[0100] ((Department)?(Summary|Conclusion)|Inspection|Test)(Result|Findings)|Preliminary opinion).*

[0101] The department summary of each department is extracted and integrated into department summary integrated data.

[0102] The final inspection conclusion can be obtained through the following regular expression:

[0103] ((Physical examination)?Results|(Final examination)?Conclusion|(Main)?Positive results (and|and)(Suggestions|Abnormal conditions)|Analysis of physical examination results and expert health guidance|(Physical examination conclusion and)?Health suggestions|Interpretation of abnormal indicators|Summary of positive results|Health suggestions|(General examination)?Summary analysis|Conclusions and suggestions).*

[0104] Extracted from the text information of the physical examination report.

[0105] The department summary integrated data and the final inspection conclusion can be compared for text similarity using the Levenshtein distance algorithm to obtain the matching degree between the two (calculated by edit distance / character length). When the matching degree is greater than or equal to 80% (custom configuration can be performed according to actual needs), step S50 is executed. When the matching degree is less than 80%, the first type of manual review is performed. It is understandable that the Jaccard similarity algorithm, simhash similarity algorithm, Bm25 similarity algorithm, and word vector average cosine similarity algorithm can also be used to match the text similarity between the department summary integrated data and the final inspection conclusion.

[0106] By detecting the matching degree between the department summary and the final examination conclusion in the text information of the physical examination report, the error in the final examination conclusion caused by human errors of doctors can be reduced, and the accuracy of the report can be increased.

[0107] Next, step S50 is executed to verify the user information in the text information of the physical examination report with the user information reserved during the physical examination.

[0108] In this embodiment, regular rules are first used to extract user information from the text information of the physical examination report, and then the user information entered by the user when making an appointment and placing an order is compared with the user information in the physical examination report. If they are consistent, the physical examination report is transferred to the user end. If they are inconsistent, a second type of manual review is performed.

[0109] Among them, the second type of manual review means: after the review is passed, the verification and collection process will begin. If the review fails, the physical examination report will be returned to the original physical examination structure, and the original physical examination institution will need to provide a new physical examination report that meets the requirements and re-go through the verification process.

[0110] As an example, user information may include name, gender, ID number, age, mobile phone number, etc., and the method of extracting it from the text information of the physical examination report is as follows:

[0111] 1. Name:

[0112] Due to the particularity of physical examination reports, names generally begin with honorifics and are also marked with the "name" positioning word. The following regular expression can be used for extraction:

[0113] (?<=Dear).*(?=Sir|Ms.|(You|Hello))|(?<=Name[::]).*.

[0114] 2. Gender

[0115] Gender is relatively fixed, usually written as male or female, and also needs to be considered as a honorific. In addition, the "name" positioning word will also be marked. The following regular expression can be used for extraction:

[0116] Male|Female|Mr.|Gentleman|Lady|(?<=gender[::]).*.

[0117] 3. Certificate Number

[0118] The document number is generally an ID card, passport, Hong Kong, Macau and Taiwan pass, etc., which can be extracted using the following regular expression:

[0119] (?<=document number[::]).*|(?<=identity card[::]).*|(?<=document number[::]).*|(?<=identity card number[::]).*|(?<=passport[::]).*|(?<=Hong Kong, Macau and Taiwan Pass[::]).*|(?<=Hong Kong and Macau Pass[::]).*.

[0120] In addition, some institutions will directly display the certificate number without a positioning word. If the above expression cannot extract it, you can consider directly matching the number:

[0121] The ID card can be represented by the following regular expression:

[0122] [1-9]\d{5}[1-9]\d{3}((0[1-9])|(1[0-2]))((0[1-9])|([1-2]\d)|(3[0-1]))((\d{4})|(\d{3}[Xx]));

[0123] The following regular expression can be used for the Hong Kong, Macau and Taiwan Pass:

[0124] (W|C|T|H|M|w|c|t|h|m)\d{8};

[0125] Due to the uncertainty of the letter + letter composition of the passport, it is necessary to judge based on the English name and positioning word.

[0126] 4. Age

[0127] Age can be located using the word "age". XX years old may also appear. The following regular expression can be used to extract it:

[0128] (?<=age[::]).*(?=years old)|\d.*(?=years old).

[0129] 5. Mobile phone number

[0130] Mobile phone numbers can be extracted using the positioning words "mobile phone number" and "contact information" using the following regular expressions:

[0131] (?<=mobile phone[::])\d{11}|(?<=mobile phone number[::])\d{11}|(?<=contact information[::])\d{11}.

[0132] At present, some institutions will also directly display the mobile phone number without a positioning word. If the above regular expression cannot be found, you can consider directly matching the form of numbers. The regular expression is as follows:

[0133] 1[3-9]\d{9},

[0134] If the area code is required, the regular expression is as follows:

[0135] \+\(?\d{2}\)?1[3-9]\d{9}.

[0136] Since not all five items of information are displayed in the physical examination report of all physical examination institutions, but at least the name and ID number will be included, if one of the name and ID number cannot be extracted, a second type of manual review is required.

[0137] When comparing, if one item in the user information is incorrect, a second type of manual review is also required, in which the comparison item uses the user information filled in by the user when making an appointment and placing an order.

[0138] Next, step S60 is executed to transfer the physical examination report to the user end or enter the verification and collection process.

[0139] Specifically, when the user information in the text information of the physical examination report is verified with the user information reserved during the user's physical examination, the physical examination report is transferred to the user end.

[0140] When the user information in the physical examination report text information fails to pass the verification with the user information reserved during the user's physical examination, a second type of manual review is performed. After the second type of manual review passes, the verification and collection process begins.

[0141] After entering the collection process, users must enter their own user information (such as ID number) and compare it with the user information reserved in advance at the medical examination institution before they can view their own report. By adding a collection process to reports with poor information matching, users can conduct a second check to reduce risks.

[0142] It should be noted that in order to further ensure the security of the data, the data models involved can also be deployed on the blockchain to prevent the data from being maliciously tampered with.

[0143] It should be noted that the step division of the above methods is only for clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they contain the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0144] like Figure 3 As shown, it is a functional module diagram of a preferred embodiment of the physical examination report verification device of the present invention. The physical examination report verification device includes: a text extraction unit 111, an error detection unit 112, a first matching unit 113, a second matching unit 114, an information verification unit 115, a report circulation unit 116, a manual review unit 117 and a collection verification unit 118. The module / unit referred to in the present invention refers to a series of computer program segments that can be executed by the processor 13 and can complete fixed functions, which are stored in the memory 12.

[0145] The text extraction unit 111 is used to receive the physical examination report and extract the text of the physical examination report to obtain the physical examination report text information. The physical examination report text information may include user information, department name, physical examination item name, physical examination item test results, department summary, final examination conclusion and other information.

[0146] The physical examination report is provided by the physical examination institution. After the physical examination report verification device receives the physical examination report sent by the physical examination structure, it can automatically trigger (of course, it can also be manually triggered) the physical examination report verification process. When the text extraction unit 111 extracts the text of the physical examination report, it uses the corresponding text extraction process to extract the text according to the file format of the physical examination report to obtain the text information of the physical examination report. The file format can be, for example, PDF format, jpeg, png and other image formats, or word format.

[0147] For example: for physical examination reports in PDF format, you can use the open source, Java-based Apache PDFbox tool library that supports PDF document generation to extract the text information of the entire user's physical examination report or a page in the report; for physical examination reports in image formats such as jpeg and png, you can use OCR technology to extract the text information of the user's physical examination report; for physical examination reports in word format, you can use poi, poi-ooxml or poi-scratchpad framework to extract text information in the user's physical examination report.

[0148] The error detection unit 112 is used to perform error detection on the text information of the physical examination report, wherein the error detection is to perform error detection such as blank pages, repeated content and garbled characters on the extracted data of each page of the physical examination report.

[0149] For example, when the extracted data of a page in the physical examination report contains no content, the page is considered to be a blank page; when the extracted data of a page in the physical examination report is consistent with the extracted data of a page before the page, the page is considered to have duplicate content; when the extracted text in the physical examination report is not within the Unicode encoding range of 4E00-9FA5 (Chinese), 30-39 (numbers), 61-7a and 41-5a (uppercase and lowercase English), it is considered to be garbled.

[0150] If the error detection unit 112 detects that the medical examination report text information has the above-mentioned error, it will transfer to the manual review unit 117 for the first type of manual review. When the error detection unit 112 does not detect an error from the medical examination report text information, it will transfer to the first matching unit 113.

[0151] Among them, the first type of manual review refers to the transfer of the physical examination report to the user end after the review is passed. If the review fails, the physical examination report will be returned to the original physical examination structure, and the original physical examination institution needs to provide a new physical examination report that meets the requirements and re-verify the process.

[0152] By performing error detection on the text information of the physical examination report, errors in the generated physical examination report caused by system problems can be reduced, thereby increasing the accuracy of the report.

[0153] The first matching unit 113 is used to perform a consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and a consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content.

[0154] Specifically, the first matching unit 113 first segments the physical examination report text information to obtain department segmentation information of each department, and each of the department segmentation information corresponds to a department name in the physical examination report text information; then, a consistency comparison is performed between the department name in the physical examination report text information and the department name in the physical examination package content to obtain a first matching degree. When the first matching degree is greater than or equal to a first preset threshold, the department segmentation information of each department is re-segmented to obtain item segmentation information of each physical examination item, and each of the item segmentation information corresponds to a physical examination item name in the physical examination report text information; finally, a consistency comparison is performed between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content to obtain a second matching degree. When the second matching degree is greater than or equal to a second preset threshold, transfer to the second matching unit 114.

[0155] The first matching unit 113 is also used to transfer to the manual review unit 117 for a first type of manual review when the consistency comparison between the physical examination report text information and the corresponding physical examination package content fails, wherein the failure of the consistency comparison between the physical examination report text information and the corresponding physical examination package content means that the first matching degree is less than a first preset threshold, or the second matching degree is less than a second preset threshold.

[0156] It should be noted that the first matching degree and the second matching degree can be customized according to actual needs, and the present invention is not limited thereto.

[0157] In the present invention, each physical examination report corresponds to a physical examination order of the user. The physical examination order is generated after the user makes an appointment. The order records which physical examination package the user has reserved at that time. The physical examination package corresponding to the physical examination report can be obtained according to the physical examination order information. The content of the physical examination package, that is, the test items in the physical examination package, corresponds to each department and physical examination item data, which is provided in advance by the physical examination institution and maintained and stored in the physical examination report verification device in advance; and in the physical examination report of the physical examination institution, there are test results corresponding to the department and physical examination items.

[0158] For example, in order to accurately segment the text information of the physical examination report and obtain the department segmentation information of each department and the detailed segmentation information of each physical examination item, the physical examination report verification device has pre-summarized 102 department names (such as: general examination, internal medicine, surgery, ENT, gynecology, blood routine, blood sugar, urine routine, etc.), 827 physical examination item names (such as: height, weight, systolic blood pressure, diastolic blood pressure, pulse, body mass index, waist circumference, hip circumference, waist-to-hip ratio, body fat percentage, etc.). The 102 department names and 827 item names cover 4.7 million report data.

[0159] The first matching unit 113 will segment the physical examination report text information according to the 102 department names and using regular expressions, starting with the first department name that matches these department names, ending with the second department name, and so on, to obtain department segmentation information for each department, wherein each of the department segmentation information corresponds to a department name in the physical examination report text information. By obtaining the department name in the physical examination report text information according to the department segmentation information of each department, the problem of repeated extraction of the same department name in the physical examination report text information can be avoided.

[0160] The consistency comparison of the department names in the physical examination report text information and the department names in the physical examination package content is performed to obtain a first matching degree in the following manner: construct a first set and a second set, the first set is composed of all department names in the physical examination report text information, and the second set is composed of all department names in the physical examination package content; obtain department names belonging to the first set but not belonging to the second set and department names belonging to the second set but not belonging to the first set to form a third set; calculate the first matching degree according to the following formula,

[0161] The first matching degree = 1-(the number of department names in the third set / the number of department names in the second set).

[0162] When the first matching degree is less than 95%, the process is transferred to the manual review unit 117 for a first type of manual review, wherein 95% is used as a first preset threshold.

[0163] When the first matching degree is greater than or equal to 95%, the first matching unit 113 re-segments the segmented information of each department according to the 827 item names and uses regular expressions to obtain the item segmentation information of each physical examination item, and each item segmentation information corresponds to a physical examination item name in the physical examination report text information.

[0164] By obtaining the names of the physical examination items in the physical examination report text information in accordance with the item segmentation information of each physical examination item, the problem of repeated extraction of the same physical examination item name in the physical examination report text information can be avoided.

[0165] The names of the physical examination items in the physical examination report text information and the names of the physical examination items in the physical examination package content are compared for consistency to obtain the second matching degree in the following manner: construct a fourth set and a fifth set, the fourth set consisting of all the names of the physical examination items in the physical examination report text information, and the fifth set consisting of all the names of the physical examination items in the physical examination package content; obtain the names of the physical examination items that belong to the fourth set but not to the fifth set and the names of the physical examination items that belong to the fifth set but not to the fourth set to form a sixth set; calculate the second matching degree according to the following formula,

[0166] The second matching degree = 1-(the number of names of physical examination items in the sixth set / the number of names of physical examination items in the fifth set).

[0167] When the second matching degree is less than 90%, the process goes to the manual review unit 117 for a first type of manual review, wherein 90% is used as a second preset threshold.

[0168] When the second matching degree is greater than or equal to 90%, the process goes to the second matching unit 114 to detect the matching degree between the department summary and the final examination conclusion in the text information of the physical examination report.

[0169] It should be noted that the second preset threshold here is smaller than the first preset threshold mainly because it takes into account the possibility that the user undergoing the physical examination may have additional physical examination items at the physical examination site.

[0170] By performing text similarity matching on the department name and physical examination item name in the physical examination report text information with the department name and physical examination item name in the corresponding physical examination package content, errors in the generated physical examination report caused by system problems or human problems can be reduced, thereby increasing the accuracy of the report.

[0171] The second matching unit 114 is used to perform text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report.

[0172] Specifically, the second matching unit 114 first extracts the corresponding department summaries of each department from the department segmentation information of each department and performs splicing and integration to obtain department summary integration data; then extracts the final inspection conclusion from the physical examination report text information; then performs text similarity matching on the department summary integration data and the final inspection conclusion; finally, when the department summary integration data matches the final inspection conclusion, it goes to the information verification unit 115; when the department summary and the final inspection conclusion in the physical examination report text information do not match, it goes to the manual review unit 117 for the first type of manual review.

[0173] As an example, in the department segmentation information of each department, there will be a conclusion (that is, department summary) at the end of the content, but because the corresponding text of each institution's report is different, the following regular expression can be used:

[0174] ((Department)?(Summary|Conclusion)|Inspection|Test)(Result|Findings)|Preliminary opinion).*

[0175] The department summary of each department is extracted and integrated into department summary integrated data.

[0176] The final inspection conclusion can be obtained through the following regular expression:

[0177] ((Physical examination)?Results|(Final examination)?Conclusion|(Main)?Positive results (and|and)(Suggestions|Abnormal conditions)|Analysis of physical examination results and expert health guidance|(Physical examination conclusion and)?Health suggestions|Interpretation of abnormal indicators|Summary of positive results|Health suggestions|(General examination)?Summary analysis|Conclusions and suggestions).*

[0178] Extracted from the text information of the physical examination report.

[0179] The department summary integrated data and the final inspection conclusion can be compared for text similarity using the Levenshtein distance algorithm to obtain the matching degree between the two (calculated by edit distance / character length). When the matching degree is greater than or equal to 80% (customizable according to actual needs), it is transferred to the information verification unit 115. When the matching degree is less than 80%, it is transferred to the manual review unit 117 for the first type of manual review. It is understandable that the Jaccard similarity algorithm, the simhash similarity algorithm, the Bm25 similarity algorithm, and the word vector average cosine similarity algorithm can also be used to match the text similarity between the department summary integrated data and the final inspection conclusion.

[0180] By performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report, it is possible to reduce the possibility of human errors by doctors leading to errors in the final examination conclusion and increase the accuracy of the report.

[0181] The information verification unit 115 is used to verify the user information in the physical examination report text information with the user information reserved during the user's physical examination.

[0182] Specifically, the information verification unit 115 first uses regular rules to extract the user information in the physical examination report text information, and then compares the user information when the user makes an appointment and places an order with the user information in the physical examination report. If they are consistent, it will be transferred to the report circulation unit 116 to transfer the physical examination report to the user end through the report circulation unit 116. If they are inconsistent, it will be transferred to the manual review unit 117 for a second type of manual review.

[0183] As an example, user information may include name, gender, ID number, age, mobile phone number, etc., and the method of extracting it from the text information of the physical examination report is as follows:

[0184] 1. Name:

[0185] Due to the particularity of physical examination reports, names generally begin with honorifics and are also marked with the "name" positioning word. The following regular expression can be used for extraction:

[0186] (?<=Dear).*(?=Sir|Ms.|(You|Hello))|(?<=Name[::]).*.

[0187] 2. Gender

[0188] Gender is relatively fixed, usually written as male or female, and also needs to be considered as a honorific. In addition, the "name" positioning word will also be marked. The following regular expression can be used for extraction:

[0189] Male|Female|Mr.|Gentleman|Lady|(?<=gender[::]).*.

[0190] 3. Certificate Number

[0191] The document number is generally an ID card, passport, Hong Kong, Macau and Taiwan pass, etc., which can be extracted using the following regular expression:

[0192] (?<=document number[::]).*|(?<=identity card[::]).*|(?<=document number[::]).*|(?<=identity card number[::]).*|(?<=passport[::]).*|(?<=Hong Kong, Macau and Taiwan Pass[::]).*|(?<=Hong Kong and Macau Pass[::]).*.

[0193] In addition, some institutions will directly display the certificate number without a positioning word. If the above expression cannot extract it, you can consider directly matching the number:

[0194] The ID card can be represented by the following regular expression:

[0195] [1-9]\d{5}[1-9]\d{3}((0[1-9])|(1[0-2]))((0[1-9])|([1-2]\d)|(3[0-1]))((\d{4})|(\d{3}[Xx]));

[0196] The following regular expression can be used for the Hong Kong, Macau and Taiwan Pass:

[0197] (W|C|T|H|M|w|c|t|h|m)\d{8};

[0198] Due to the uncertainty of the letter + letter composition of the passport, it is necessary to judge based on the English name and positioning word.

[0199] 4. Age

[0200] Age can be located using the word "age". XX years old may also appear. The following regular expression can be used to extract it:

[0201] (?<=age[::]).*(?=years old)|\d.*(?=years old).

[0202] 5. Mobile phone number

[0203] Mobile phone numbers can be extracted using the positioning words "mobile phone number" and "contact information" using the following regular expressions:

[0204] (?<=mobile phone[::])\d{11}|(?<=mobile phone number[::])\d{11}|(?<=contact information[::])\d{11}.

[0205] At present, some institutions will also directly display the mobile phone number without a positioning word. If the above regular expression cannot be found, you can consider directly matching the form of numbers. The regular expression is as follows:

[0206] 1[3-9]\d{9},

[0207] If the area code is required, the regular expression is as follows:

[0208] \+\(?\d{2}\)?1[3-9]\d{9}.

[0209] Since not all five items of information are displayed in the physical examination report of all physical examination institutions, but at least the name and ID number will be included, if one of the name and ID number cannot be extracted, a second type of manual review is required.

[0210] During the comparison, if one item in the user information is incorrect, it is also necessary to transfer to the manual review unit 117 for the second type of manual review, wherein the comparison item uses the user information filled in by the user when making an appointment and placing an order.

[0211] The report transfer unit 116 is used to transfer the physical examination report to the user end or to the verification and collection unit 118 for processing when the user information in the physical examination report text information is verified with the user information reserved during the user's physical examination. Specifically, when the user information in the physical examination report text information is verified with the user information reserved during the user's physical examination, the physical examination report is transferred to the user end.

[0212] Specifically, the report circulation unit 116 is used to transfer the report to the manual review unit 117 for a second type of manual review when the user information in the physical examination report text information fails to pass the verification with the user information reserved during the user physical examination. After the second type of manual review passes, the report circulation unit 116 is transferred to the verification and collection unit 118 for processing.

[0213] The manual review unit 117 is used to execute the first type of manual review process and the second type of manual review process.

[0214] The verification and collection unit 118 is used to enter the collection process. After entering the collection process, the user must enter his or her user information (such as ID number) and compare it with the user information reserved in advance at the physical examination institution before the physical examination before viewing his or her report. By adding a collection process to the report with a low information match, the user can check it twice to reduce the risk.

[0215] It should be noted that in order to further ensure the security of the data, the data models involved can also be deployed on the blockchain to prevent the data from being maliciously tampered with.

[0216] It should be noted that the physical examination report verification device of this embodiment is a device corresponding to the above-mentioned physical examination report verification method, and the functional modules / units in the physical examination report verification device may correspond to the corresponding steps in the physical examination report verification method. The physical examination report verification device of this embodiment can be implemented in conjunction with the physical examination report verification method.

[0217] like Figure 4 , which is a schematic diagram of the structure of an electronic device of a preferred embodiment of the present invention for implementing the method for verifying a physical examination report.

[0218] The electronic device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a program for verifying a physical examination report.

[0219] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 can also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of a text recognition program based on direction detection, etc., but can also be used to temporarily store data that has been output or is to be output.

[0220] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect the various components of the entire electronic device 1, and executes or executes the programs or modules stored in the memory 12 (for example, executing the medical examination report verification program, etc.), and calls the data stored in the memory 12 to execute various functions of the electronic device 1 and process data.

[0221] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned physical examination report verification method embodiment, for example Figure 1 Steps shown.

[0222] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a text extraction unit 111, an error detection module 112, a first matching unit 113, a second matching unit 114, an information verification unit 115, a report circulation unit 116, a manual review unit 117, and a collection verification unit 118.

[0223] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, and includes a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the physical examination report verification method described in each embodiment of the present invention.

[0224] The blockchain referred to in this invention is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, platform product service layer, and application service layer.

[0225] The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one arrow is used in the figure, but it does not mean that there is only one bus or one type of bus. The bus is configured to realize the connection and communication between the memory 12 and at least one processor 13, etc.

[0226] The physical examination report verification method, device, equipment and medium of the present invention can intelligently check the matching degree between the content of the physical examination report and the corresponding physical examination package content, and the matching degree between the department summary and the final examination conclusion in the physical examination report, reduce the error rate caused by human participation, and reduce the operating labor cost. The physical examination report verification method, device, equipment and medium of the embodiment of the present invention can detect low-level errors (duplicate content, blank pages and garbled characters) and other errors in the physical examination report, reduce the scenario of the system generating report errors, and increase the accuracy of the report. The physical examination report verification method, device, equipment and medium of the embodiment of the present invention can intelligently verify the user information reserved during the user's physical examination and the user information in the physical examination report when the verified physical examination report is transferred to the user end, avoid sending to the wrong user, better protect the privacy of users, and reduce user complaints. The physical examination report verification method, device, equipment and medium of the embodiment of the present invention can automatically match the physical examination report, improve operational efficiency, reduce the error rate caused by human participation, and reduce operational labor costs. The physical examination report verification method, device, equipment and medium of the embodiments of the present invention basically do not affect the report verification result even if the report template is updated, and have high accuracy and compatibility.

[0227] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0228] The above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for verifying a physical examination report, characterized in that: include: Receiving a physical examination report, and performing text extraction on the physical examination report to obtain text information of the physical examination report; Performing a consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and a consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content; When the consistency comparison between the physical examination report text information and the corresponding physical examination package content is passed, the department summary and the final examination conclusion in the physical examination report text information are matched for text similarity; When the department summary and the final examination conclusion in the physical examination report text information match, verifying the user information in the physical examination report text information with the user information reserved during the user's physical examination; When the user information in the text information of the physical examination report is verified with the user information reserved during the user's physical examination, the physical examination report is transferred to the user end.

2. The method for verifying a physical examination report according to claim 1, characterized in that: Before the consistency comparison between the physical examination report text information and the corresponding physical examination package content is performed, the step of performing error detection on the physical examination report text information is also included, wherein the error detection is to detect blank pages, repeated content and garbled characters in the physical examination report text information.

3. The method for verifying a physical examination report according to claim 1, characterized in that: The step of comparing the consistency of the medical examination report text information with the corresponding medical examination package content includes: Segmenting the physical examination report text information to obtain department segmentation information of each department, each of the department segmentation information corresponds to a department name in the physical examination report text information; Performing a consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content to obtain a first matching degree; When the first matching degree is greater than or equal to a first preset threshold, the department segmentation information of each department is re-segmented to obtain item segmentation information of each physical examination item, each item segmentation information corresponds to a physical examination item name in the physical examination report text information; Performing a consistency comparison between the names of the physical examination items in the physical examination report text information and the names of the physical examination items in the physical examination package content to obtain a second matching degree; When the second matching degree is greater than or equal to a second preset threshold, a step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report is performed.

4. The method for verifying a physical examination report according to claim 3, characterized in that: The first preset threshold is greater than the second preset threshold.

5. The method for verifying a physical examination report according to claim 3, characterized in that: The step of performing text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report includes: Extracting the corresponding department summaries of each department from the department segmentation information of each department and performing splicing and integration to obtain department summary integration data; Extracting the final examination conclusion from the text information of the physical examination report; Performing text similarity matching between the department summary integrated data and the final inspection conclusion; When the department summary integrated data matches the final examination conclusion, a step of verifying the user information in the physical examination report text information with the user information reserved during the user's physical examination is performed.

6. The method for verifying a physical examination report according to claim 1, characterized in that: The physical examination report verification method also includes: When the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content fails, a first type of manual review is performed; When the department summary and the final examination conclusion in the text information of the physical examination report do not match, a first type of manual review is performed.

7. The method for verifying a physical examination report according to claim 1, characterized in that: The physical examination report verification method also includes: When the user information in the medical examination report text information fails to pass the verification with the user information reserved during the user's medical examination, a second type of manual review is performed; After passing the second type of manual review, the verification and collection process will begin.

8. A physical examination report verification device, characterized in that: The physical examination report verification device comprises: A text extraction unit, used for receiving a physical examination report and performing text extraction on the physical examination report to obtain text information of the physical examination report; A first matching unit is used to perform consistency comparison between the physical examination report text information and the corresponding physical examination package content, wherein the consistency comparison includes: consistency comparison between the department name in the physical examination report text information and the department name in the physical examination package content, and consistency comparison between the physical examination item name in the physical examination report text information and the physical examination item name in the physical examination package content; A second matching unit is used to perform text similarity matching on the department summary and the final examination conclusion in the text information of the physical examination report when the consistency comparison between the text information of the physical examination report and the corresponding physical examination package content is passed; A user information verification unit, used to verify the user information in the physical examination report text information with the user information reserved during the user's physical examination when the department summary in the physical examination report text information matches the final examination conclusion; The transfer unit is used to transfer the physical examination report to the user end when the user information in the physical examination report text information is verified with the user information reserved during the user physical examination.

9. An electronic device, characterized in that: The electronic device comprises: a memory storing at least one instruction; and A processor executes instructions stored in the memory to implement the physical examination report verification method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the physical examination report verification method according to any one of claims 1 to 7.

Images