An information processing method for a physical examination intelligent main examination system based on knowledge base
Through the intelligent main examination system of physical examination based on the knowledge base, the historical physical examination report data is processed and integrated, and standard physical examination reports are generated, which solves the problem of doctors' work burden and low reliability during the physical examination report processing, and achieves more efficient and reliable physical examination report processing.
Patent Information
- Application Number
- CN202510067586.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-16
- Publication Date
- 2025-05-09
- Estimated Expiration
- 2045-01-16
AI Technical Summary
During the data processing of existing physical examination reports, doctors need to perform a lot of repetition and mechanical work, which can easily lead to problems such as fatigue, typos, missed diagnosis, and the credibility of past physical examination reports is unknown, which is a risk as a reference.
Using a knowledge base-based intelligent main examination system for physical examinations, obtaining historical physical examination report data sets, extracting and training scoring models, generating standard physical examination reports, and constructing a knowledge base to provide doctors with reliable historical data references.
It reduces the work burden of doctors, improves the reliability of physical examination reports, avoids reference errors, and enhances the accuracy and efficiency of physical examination results.
Smart Images
Figure CN119479977B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information processing, and in particular to an information processing method of a knowledge base-based intelligent physical examination system. Background Art
[0002] Physical examination is the process of testing and measuring the human body's morphological structure and functional development level. The main purpose of physical examination is to understand one's own physical condition and promptly discover potential diseases or health risks so as to take preventive and therapeutic measures as soon as possible. Through physical examination, you can grasp various indicators of your body, so as to know whether your body is in a healthy state, and provide guidance for adjusting your personal living habits.
[0003] The physical examination report is a summary of the physical examination results, usually issued by a medical institution or professional physical examination center after completing a series of physical examination items. It contains the basic information of the person being examined, the measurement results of various physical examination indicators, the doctor's evaluation and suggestions, etc. Some of the data in the physical examination report are direct test parameter results, and some conclusions require the doctor to enter after comprehensive analysis and judgment of the data. However, this is a lot of repetitive and mechanical work for doctors, which is easy to cause fatigue, and the probability of typos, extra words, missing words, missed diagnoses, prevention and treatment recommendations, etc. is also greatly increased. Using similar past physical examination reports as a reference can alleviate this problem to a large extent. However, there are many past physical examination reports and their credibility is unknown, so there are certain risks in using them as a reference. Summary of the invention
[0004] In view of some of the above-mentioned defects in the prior art, the technical problem to be solved by the present invention is to provide an information processing method for a physical examination intelligent main inspection system based on a knowledge base, aiming to provide doctors with reliable historical data references through the knowledge base to reduce the workload of doctors.
[0005] To achieve the above object, the present invention provides an information processing method for a physical examination intelligent main examination system based on a knowledge base, the method comprising:
[0006] Step S1, obtaining a historical physical examination report data set, collecting a first conclusion word for a first preset disease in each historical physical examination report in the historical physical examination report data set; obtaining a first initial score corresponding to the historical physical examination report for the first preset disease according to each first conclusion word; wherein the historical physical examination report is a report whose credibility is greater than a threshold credibility;
[0007] Step S2, extracting the first feature of each of the historical physical examination reports in the historical physical examination report data set for the first preset disease; inputting the first feature and the first initial score corresponding to it into a first training model for training to obtain a first scoring model;
[0008] Step S3, re-inputting the historical physical examination report data set into the first scoring model to obtain a first corrected score for each of the historical physical examination reports for a first preset disease; wherein the first corrected score is positively correlated with the severity of the first preset disease;
[0009] Step S4: according to the first correction score corresponding to each of the historical physical examination reports, using a clustering algorithm to divide each of the historical physical examination reports into a plurality of critical levels; extracting similar features of the historical physical examination reports corresponding to the first preset disease in each of the critical levels; generating a standard physical examination report corresponding to the first preset disease for each of the critical levels according to the similar features, and constructing a first knowledge base according to the standard physical examination reports; wherein the standard physical examination report at least includes a standard conclusion word and a standard detection parameter for the first preset disease;
[0010] Step S5, obtain the current physical examination report to be evaluated; compare and match the current physical examination report with each of the standard physical examination reports in the first knowledge base, obtain the standard physical examination report with the highest similarity to the current physical examination report, output and display the standard physical examination report corresponding to the current physical examination report; the standard physical examination report is used to provide a reference for doctors to conduct physical examinations.
[0011] Optionally, step S5 includes:
[0012] Obtaining the current physical examination report to be evaluated; obtaining, based on the current physical examination report, current detection parameters for the first preset disease in the current physical examination report;
[0013] The current detection parameters are compared and matched with the standard detection parameters of each standard physical examination report in the first knowledge base to obtain the standard physical examination report with the highest similarity; wherein the standard conclusion word corresponding to the standard physical examination report with the highest similarity is used as an evaluation reference for the current physical examination report for the first preset disease.
[0014] Optionally, obtaining a historical physical examination report data set in step S1 includes:
[0015] Obtaining a physical examination report that has been reviewed by a credible expert and / or a physical examination report that has been subsequently verified by pathology as the historical physical examination report; wherein the physical examination report that has been subsequently verified by pathology is a physical examination report in which the subsequent symptoms of the corresponding patient are consistent with the corresponding conclusion words in the physical examination report;
[0016] The historical physical examination reports are integrated to generate the historical physical examination report data set.
[0017] Optionally, after step S5, the method further includes:
[0018] Extracting the standard conclusion word for the first preset disease from the standard physical examination report that has the highest similarity to the current physical examination report;
[0019] The standard conclusion word is sent to the user end as an evaluation reference of the current physical examination report for the first preset disease.
[0020] Optionally, in step S2, extracting the first feature of each of the historical physical examination reports in the historical physical examination report data set for the first preset disease includes:
[0021] Obtaining a first detection parameter for the first preset disease in each of the historical physical examination reports;
[0022] The first feature of each of the historical physical examination reports for the first preset disease is extracted according to the first detection parameter.
[0023] Optionally, the method further includes:
[0024] Repeat steps S1-S4 to obtain a first knowledge base corresponding to multiple diseases;
[0025] The physical examination reports to be evaluated are sequentially input into each of the first knowledge bases for comparison and matching to obtain the standard physical examination reports with the highest similarity; wherein the standard physical examination reports with the highest similarity are used as references for corresponding diseases.
[0026] Optionally, the step S5 further includes:
[0027] According to the current physical examination report, obtaining current detection parameters for the first preset disease in the current physical examination report;
[0028] Determine whether the current detection parameter is within the first threshold range. If so, determine that the current detection parameter of the current physical examination report is normally entered; if not, determine that the current detection parameter of the current physical examination report is abnormally entered, and issue an alarm; wherein the alarm is used to prompt the staff to re-enter the parameter.
[0029] Optionally, in step S1, obtaining a first initial score corresponding to the historical physical examination report for the first preset disease according to each of the first conclusion words includes:
[0030] Performing semantic analysis on each of the first conclusion words to obtain the severity of the first conclusion word with respect to the first preset disease;
[0031] According to the severity, a first initial score of the historical physical examination report for the first preset disease is obtained.
[0032] Optionally, after obtaining the current physical examination report to be evaluated in step S5, the method further includes:
[0033] According to the physical examination report template, identify various test parameters in the current physical examination report;
[0034] Determine whether there are any input errors in each detection parameter. If so, issue an alarm to allow the staff to re-enter the parameters; if not, continue to work normally.
[0035] Beneficial effects of the present invention: 1. The present invention obtains a historical physical examination report data set, collects the first conclusion words of each historical physical examination report in the historical physical examination report data set for a first preset disease; obtains the first initial score of the corresponding historical physical examination report for the first preset disease according to each first conclusion word; extracts the first feature of each historical physical examination report in the historical physical examination report data set for the first preset disease; inputs the first feature and its corresponding first initial score into the first training model for training to obtain a first scoring model; re-inputs the historical physical examination report data set into the first scoring model to obtain the first corrected score of each historical physical examination report for the first preset disease. The first scoring model of the present invention is trained using historical physical examination reports with a credibility greater than a threshold credibility. The high-credibility training data enables the first scoring model to discard some data with deviations during the training process, so that the credibility of the score output by the obtained first scoring model is improved; the first scoring model with high credibility corrects the score of the re-input historical physical examination report on the first preset disease, so that the score has a higher credibility, and then the standard physical examination report referenced by the doctor has a higher credibility, thereby avoiding reference errors and making the conclusion of the physical examination doctor more reliable. 2. The present invention uses a clustering algorithm to divide each historical physical examination report into multiple critical levels according to the first correction score corresponding to each historical physical examination report; extracts similar features of the historical physical examination report corresponding to the first preset disease in each critical level; generates a standard physical examination report corresponding to the first preset disease for each critical level according to the similar features, and constructs a first knowledge base based on the standard physical examination report. The present invention integrates many historical physical examination reports in the above manner, reduces reference data, avoids excessive time required for matching and comparison, and improves efficiency; at the same time, due to clustering, the characteristics of the original historical physical examination report are still integrated to ensure credibility.
[0036] In summary, the present invention provides doctors with reliable historical data references through the knowledge base, reduces the workload of physical examination doctors, and increases the reliability of the conclusions given by physical examination doctors. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 It is a flowchart of an information processing method of a knowledge base-based physical examination intelligent main examination system provided by a specific embodiment of the present invention. DETAILED DESCRIPTION
[0038] The present invention discloses an information processing method for a physical examination intelligent main inspection system based on a knowledge base. Those skilled in the art can refer to the content of this article and appropriately improve the technical details for implementation. It should be particularly noted that all similar replacements and modifications are obvious to those skilled in the art, and they are all considered to be included in the present invention. The methods and applications of the present invention have been described through preferred embodiments, and relevant personnel can obviously modify or appropriately change and combine the methods and applications described herein without departing from the content, spirit and scope of the present invention to implement and apply the technology of the present invention.
[0039] The applicant has found through research that the physical examination report is a summary of the physical examination results, usually issued by a medical institution or a professional physical examination center after completing a series of physical examination items. It contains the basic information of the person being examined, the measurement results of various physical examination indicators, the doctor's evaluation and suggestions, etc. Some of the data in the physical examination report are direct test parameter results, and some conclusions require the doctor to input them after comprehensive analysis and judgment of the data. However, this is a lot of repetitive and mechanical work for doctors, which is easy to cause fatigue, and the probability of typos, extra words, missing words, missed diagnoses, prevention and treatment recommendations, etc. is also greatly increased. This problem can be alleviated to a large extent by using similar past physical examination reports as a reference. However, there are many past physical examination reports and their credibility is unknown, so there is a certain risk in using them as a reference.
[0040] Therefore, the embodiment of the present invention provides an information processing method of a physical examination intelligent main inspection system based on a knowledge base, such as Figure 1 As shown, the method includes:
[0041] Step S1, obtaining a historical physical examination report data set, collecting first conclusion words for a first preset disease in each historical physical examination report in the historical physical examination report data set; obtaining a first initial score for the first preset disease in the corresponding historical physical examination report according to each first conclusion word.
[0042] Among them, the historical physical examination report is a report whose credibility is greater than the threshold credibility.
[0043] It should be noted that the threshold credibility is generally high. Therefore, when the credibility of all historical physical examination reports in the historical physical examination report data set is greater than the threshold credibility, it means that only a few data in many historical physical examination reports will be biased, and most of the other data are reliable data. Therefore, the model trained by the majority of reliable data is also reliable, and the data re-evaluated by it has improved reliability.
[0044] In this specific embodiment, step S1 obtains a historical physical examination report data set, including:
[0045] Obtain a physical examination report that has been reviewed by a credible expert and / or verified by subsequent pathology as a historical physical examination report; a physical examination report that has been verified by subsequent pathology is a physical examination report in which the subsequent symptoms of the corresponding patient are consistent with the corresponding conclusion words in the physical examination report;
[0046] Integrate historical physical examination reports to generate a historical physical examination report data set.
[0047] It should be noted that physical examination reports that have been reviewed by credible experts and / or verified by subsequent pathology are more credible than general physical examination reports.
[0048] In this specific embodiment, in step S1, obtaining a first initial score for a first preset disease in a corresponding historical physical examination report according to each first conclusion word includes:
[0049] Performing semantic analysis on each first conclusion word to obtain the severity of the first conclusion word for the first preset disease;
[0050] A first initial score for a first predetermined disease from a historical physical examination report is obtained according to severity.
[0051] It should be noted that the score can be divided into 1-100 points, among which 1 point is the lowest and represents the mildest first preset disease, and 100 points is the highest and represents the most serious first preset disease.
[0052] Step S2: extracting the first feature of each historical physical examination report in the historical physical examination report data set for the first preset disease; inputting the first feature and its corresponding first initial score into a first training model for training to obtain a first scoring model.
[0053] It should be noted that the machine learning of the embodiment of the present invention uses the first initial score as the label training corresponding to the first feature, so that the first scoring model can output the corresponding score according to the input physical examination report. And because the training data used in the embodiment of the present invention has high credibility, even if there are a few data with deviated credibility, it is difficult to affect the accuracy of the final training model. Therefore, based on this point, the embodiment of the present invention uses the first scoring model obtained by training to re-score each historical physical examination report in the historical physical examination report data set to obtain a more accurate first correction score.
[0054] In this specific embodiment, step S2 extracts the first feature of each historical physical examination report for the first preset disease in the historical physical examination report data set, including:
[0055] Obtaining a first detection parameter for a first preset disease in each historical physical examination report;
[0056] According to the first detection parameter, a first feature of each historical physical examination report for a first preset disease is extracted.
[0057] Step S3: re-input the historical physical examination report data set into the first scoring model to obtain a first corrected score for each historical physical examination report for the first preset disease.
[0058] Among them, the first adjusted score is positively correlated with the severity of the first preset disease.
[0059] Step S4: Based on the first correction score corresponding to each historical physical examination report, a clustering algorithm is used to divide each historical physical examination report into multiple critical levels; similar features of the historical physical examination report corresponding to each critical level for the first preset disease are extracted respectively; based on the similar features, a standard physical examination report corresponding to the first preset disease for each critical level is generated, and a first knowledge base is constructed based on the standard physical examination report.
[0060] The standard physical examination report includes at least a standard conclusion word and standard detection parameters for the first preset disease.
[0061] It should be noted that the scoring in the embodiment of the present invention is used to cluster reports with similar severity of the first preset disease to generate standard physical examination reports for each category. In future references, only the standard physical examination report needs to be called for comparison, and there is no need to find a report similar to the current physical examination report from many historical physical examination reports. This reduces the workload of data comparison and avoids the impact caused by errors in the conclusion words of historical physical examination reports.
[0062] Step S5, obtain the current physical examination report to be evaluated; compare and match the current physical examination report with each standard physical examination report in the first knowledge base, obtain the standard physical examination report with the highest similarity to the current physical examination report, output and display the standard physical examination report corresponding to the current physical examination report; the standard physical examination report is used to provide a reference for the doctor's physical examination.
[0063] In this specific embodiment, step S5 includes:
[0064] Obtaining a current physical examination report to be evaluated; obtaining, based on the current physical examination report, current detection parameters for a first preset disease in the current physical examination report;
[0065] The current detection parameters are compared and matched with the standard detection parameters of each standard physical examination report in the first knowledge base to obtain the standard physical examination report with the highest similarity; wherein the standard conclusion words corresponding to the standard physical examination report with the highest similarity are used as a reference for evaluating the current physical examination report for the first preset disease.
[0066] It should be noted that the embodiment of the present invention uses a standard physical examination report for reference, and a standard physical examination report has only one critical level, which greatly reduces the comparison and matching time.
[0067] In this specific embodiment, after step S5, the method further includes:
[0068] Extract the standard conclusion words for the first preset disease from the standard physical examination report that is most similar to the current physical examination report;
[0069] The standard conclusion word is sent to the user end as an evaluation reference for the first preset disease in the current physical examination report.
[0070] It should be noted that the standard conclusion word is the reference given by the physical examination doctor for the conclusion word of the current physical examination report.
[0071] In this specific embodiment, step S5 also includes:
[0072] According to the current physical examination report, obtaining current detection parameters for the first preset disease in the current physical examination report;
[0073] Determine whether the current detection parameters are within the first threshold range. If so, determine that the current detection parameters of the current physical examination report are normally entered; if not, determine that the current detection parameters of the current physical examination report are abnormally entered, and issue an alarm; wherein the alarm is used to prompt the staff to re-enter the parameters.
[0074] In this specific embodiment, after obtaining the current physical examination report to be evaluated in step S5, the method further includes:
[0075] According to the physical examination report template, identify the various test parameters in the current physical examination report;
[0076] Determine whether there are any input errors in each detection parameter. If so, issue an alarm to allow the staff to re-enter the parameters; if not, continue to work normally.
[0077] It should be noted that input errors will seriously affect the normal working process, so they should be discovered in time and re-entered correctly.
[0078] In this specific embodiment, the method further includes:
[0079] Repeat steps S1-S4 to obtain a first knowledge base corresponding to multiple diseases;
[0080] The physical examination reports to be evaluated are sequentially input into each first knowledge base for comparison and matching to obtain each standard physical examination report with the highest similarity; wherein each standard physical examination report with the highest similarity is used as a reference for the corresponding disease.
[0081] It should be noted that the physical examination parameters corresponding to different diseases are not the same, so the corresponding first knowledge base is needed for reference.
[0082] The embodiment of the present invention obtains a historical physical examination report data set, collects the first conclusion words of each historical physical examination report in the historical physical examination report data set for a first preset disease; obtains the first initial score of the corresponding historical physical examination report for the first preset disease according to each first conclusion word; extracts the first feature of each historical physical examination report in the historical physical examination report data set for the first preset disease; inputs the first feature and its corresponding first initial score into the first training model for training to obtain a first scoring model; re-inputs the historical physical examination report data set into the first scoring model to obtain the first corrected score of each historical physical examination report for the first preset disease. The first scoring model of the embodiment of the present invention is trained using historical physical examination reports with a credibility greater than a threshold credibility. The high-credibility training data causes the first scoring model to discard some data with deviations during the training process, so that the credibility of the score output by the obtained first scoring model is improved; the first scoring model with high credibility corrects the score of the re-input historical physical examination report on the first preset disease to make the score have a higher credibility, thereby making the standard physical examination report referenced by the doctor have a higher credibility, thereby avoiding reference errors and making the conclusion of the physical examination doctor more reliable.
[0083] The embodiment of the present invention uses a clustering algorithm to divide each historical physical examination report into multiple critical levels according to the first correction score corresponding to each historical physical examination report; extracts similar features of the historical physical examination report corresponding to each critical level for the first preset disease; generates a standard physical examination report corresponding to the first preset disease for each critical level according to the similar features, and constructs a first knowledge base based on the standard physical examination report. The embodiment of the present invention integrates many historical physical examination reports in the above manner, reduces reference data, avoids excessive time required for matching and comparison, and improves efficiency; at the same time, due to clustering, the characteristics of the original historical physical examination report are still integrated to ensure credibility.
[0084] In summary, the embodiment of the present invention provides doctors with reliable historical data references through the knowledge base, reduces the workload of physical examination doctors, and increases the reliability of the conclusion words given by physical examination doctors.
[0085] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0086] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0087] The above are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims
1. An information processing method for a physical examination intelligent main examination system based on a knowledge base, characterized in that: The method comprises: Step S1, obtaining a historical physical examination report data set, collecting a first conclusion word for a first preset disease in each historical physical examination report in the historical physical examination report data set; obtaining a first initial score corresponding to the historical physical examination report for the first preset disease according to each first conclusion word; wherein the historical physical examination report is a report whose credibility is greater than a threshold credibility; Step S2, extracting the first feature of each of the historical physical examination reports in the historical physical examination report data set for the first preset disease; inputting the first feature and the first initial score corresponding to it into a first training model for training to obtain a first scoring model; Step S3, re-inputting the historical physical examination report data set into the first scoring model to obtain a first corrected score for each of the historical physical examination reports for a first preset disease; wherein the first corrected score is positively correlated with the severity of the first preset disease; Step S4: according to the first correction score corresponding to each of the historical physical examination reports, using a clustering algorithm to divide each of the historical physical examination reports into a plurality of critical levels; extracting similar features of the historical physical examination reports corresponding to the first preset disease in each of the critical levels; generating a standard physical examination report corresponding to the first preset disease for each of the critical levels according to the similar features, and constructing a first knowledge base according to the standard physical examination reports; wherein the standard physical examination report at least includes a standard conclusion word and a standard detection parameter for the first preset disease; Step S5, obtain the current physical examination report to be evaluated; compare and match the current physical examination report with each of the standard physical examination reports in the first knowledge base, obtain the standard physical examination report with the highest similarity to the current physical examination report, output and display the standard physical examination report corresponding to the current physical examination report; the standard physical examination report is used to provide a reference for doctors to conduct physical examinations.
2. The information processing method of the knowledge base-based intelligent physical examination system according to claim 1 is characterized in that: The step S5 comprises: Obtaining the current physical examination report to be evaluated; obtaining, based on the current physical examination report, current detection parameters for the first preset disease in the current physical examination report; The current detection parameters are compared and matched with the standard detection parameters of each standard physical examination report in the first knowledge base to obtain the standard physical examination report with the highest similarity; wherein the standard conclusion word corresponding to the standard physical examination report with the highest similarity is used as an evaluation reference for the current physical examination report for the first preset disease.
3. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: The historical physical examination report data set obtained in step S1 includes: Obtaining a physical examination report that has been reviewed by a credible expert and / or a physical examination report that has been subsequently verified by pathology as the historical physical examination report; wherein the physical examination report that has been subsequently verified by pathology is a physical examination report in which the subsequent symptoms of the corresponding patient are consistent with the corresponding conclusion words in the physical examination report; The historical physical examination reports are integrated to generate the historical physical examination report data set.
4. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: After step S5, the method further includes: Extracting the standard conclusion word for the first preset disease from the standard physical examination report that has the highest similarity to the current physical examination report; The standard conclusion word is sent to the user end as an evaluation reference of the current physical examination report for the first preset disease.
5. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: The step S2 extracts the first feature of each of the historical physical examination reports in the historical physical examination report data set for the first preset disease, including: Obtaining a first detection parameter for the first preset disease in each of the historical physical examination reports; The first feature of each of the historical physical examination reports for the first preset disease is extracted according to the first detection parameter.
6. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: The method further comprises: Repeat steps S1-S4 to obtain a first knowledge base corresponding to multiple diseases; The physical examination reports to be evaluated are sequentially input into each of the first knowledge bases for comparison and matching to obtain the standard physical examination reports with the highest similarity; wherein the standard physical examination reports with the highest similarity are used as references for corresponding diseases.
7. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: The step S5 also includes: According to the current physical examination report, obtaining current detection parameters for the first preset disease in the current physical examination report; Determine whether the current detection parameter is within the first threshold range. If so, determine that the current detection parameter of the current physical examination report is normally entered; if not, determine that the current detection parameter of the current physical examination report is abnormally entered, and issue an alarm; wherein the alarm is used to prompt the staff to re-enter the parameter.
8. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: In step S1, obtaining a first initial score for the first preset disease in the historical physical examination report according to each of the first conclusion words includes: Performing semantic analysis on each of the first conclusion words to obtain the severity of the first conclusion word with respect to the first preset disease; According to the severity, a first initial score of the historical physical examination report for the first preset disease is obtained.
9. The information processing method of the knowledge-based intelligent physical examination system according to claim 1 is characterized in that: After obtaining the current physical examination report to be evaluated in step S5, the method further includes: According to the physical examination report template, identify various test parameters in the current physical examination report; Determine whether there are any input errors in each detection parameter. If so, issue an alarm to allow the staff to re-enter the parameters; if not, continue to work normally.
Citation Information
Patent Citations
Auxiliary diagnosis method and apparatus, and construction apparatus, analysis apparatus and related product
WO2023186051A1