Remote gynecological treatment system

Abstract

The invention discloses a remote gynecological treatment system, which relates to the field of medicine, solves the problem of poor inquiry effect of the existing remote gynecological treatment system, and comprises a data acquisition module which is used for respectively acquiring patient symptom acquisition data, affected area image data and a plurality of target treatment records to obtain remote treatment acquisition data, the privacy processing module is used for carrying out privacy analysis and encryption on the image data of the affected area according to the remote treatment collection data to obtain image encryption data of the affected area, and the data analysis module is used for automatically analyzing the remote treatment collection data to obtain a platform patient generality analysis coefficient and a historical treatment generality analysis coefficient. And the remote treatment module is used for carrying out remote treatment on the target patient according to the automatic treatment analysis data, and the remote gynecological treatment system is applicable and high in gynecological treatment result accuracy.

Description

Technical Field

[0001] The present invention belongs to the field of medicine and relates to data analysis technology, and specifically relates to a remote gynecological diagnosis system. Background Art

[0002] When the existing remote gynecological diagnosis system conducts remote gynecological diagnosis on patients, the following specific defects exist: The existing remote gynecological diagnosis system cannot identify and encrypt the privacy parts of the affected area images, which easily leads to insufficient protection of patients' personal information and medical records, and there is a risk of privacy leakage; The existing remote gynecological diagnosis system cannot automatically analyze the common symptoms between the clinical symptoms of the patient and the historical cases in the diagnosis system, nor can it automatically analyze the common symptoms between the clinical symptoms of the patient and the patient's historical diagnosis symptoms, which easily leads to the lack of accuracy and applicability of the diagnosis results.

[0003] Therefore, we propose a remote gynecological diagnosis system. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a remote gynecological diagnosis system, aiming to improve the accuracy of remote gynecological diagnosis results and the applicability of the remote gynecological diagnosis system.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions: A remote gynecological diagnosis system includes: A data acquisition module: used to respectively obtain patient symptom acquisition data, affected area image data, and multiple target diagnosis records to obtain remote diagnosis acquisition data; A privacy processing module: used to perform privacy analysis on the affected area image data according to the remote diagnosis acquisition data, divide the affected area images into the first type of gynecological affected area images and the second type of gynecological affected area images according to the analysis results, and perform privacy encryption on the second type of affected area images to obtain encrypted affected area image data; A data analysis module: used to obtain multiple symptom comparison patients, perform symptom commonality analysis on the target patient and each symptom comparison patient through the remote diagnosis acquisition data to obtain a platform patient commonality analysis coefficient, perform time commonality analysis on the target patient and the onset symptoms in each target diagnosis record respectively to obtain a historical diagnosis commonality analysis coefficient, and define the historical diagnosis commonality analysis coefficient and the platform patient commonality analysis coefficient as diagnosis automatic analysis data; A remote diagnosis module: used to perform remote diagnosis on the target patient according to the diagnosis automatic analysis data.

[0006] Furthermore, the data acquisition module obtains the remote diagnosis acquisition data as follows: Collect symptoms from the patient to obtain patient symptom collection data; Obtain the affected area images corresponding to each affected part of the target patient to obtain affected area image data; Obtain the historical medical records of the target patient, and mark the records of the historical medical records due to the chief complaint of the target patient's visit as target visit records; Name several target visit records existing in the historical medical records in chronological order as the S1 target visit record to the Sm target visit record; Define the S1 target visit record to the Sm target visit record, the affected area image data, and the patient symptom collection data as remote visit collection data.

[0007] Furthermore, the data collection module obtains the patient symptom collection data as follows: Obtain the chief complaint of the target patient through the consultation dialog box to obtain the chief complaint of the target patient's visit; Obtain the time value when the patient's chief complaint appears through the consultation dialog box to obtain the first symptom characteristic time point, mark the time value corresponding to the current moment as the second symptom characteristic time point, and mark the time period between the first symptom characteristic time point and the second symptom characteristic time point as the patient symptom monitoring period; Obtain the clinical symptoms that appear in the target patient during the patient symptom monitoring period to obtain the Z1 clinical symptom to the Zc clinical symptom; Obtain the time value when the Z1 clinical symptom first appears in the target patient to obtain the Z1 symptom onset time value, obtain the time value when the Z2 clinical symptom first appears in the target patient to obtain the Z2 symptom onset time value, and so on, obtain the time value when the Zc clinical symptom first appears in the target patient to obtain the Zc symptom onset time value; Define the chief complaint of the target patient's visit, the Z1 clinical symptom to the Zc clinical symptom, and the Z1 symptom onset time value to the Zc symptom onset time value as the patient symptom collection data.

[0008] Furthermore, the privacy processing module obtains the encrypted data of the affected area images as follows: Obtain the remote visit collection data, and obtain the affected area image data according to the remote visit collection data; Conduct privacy analysis on the affected area image data, and divide it into the first type of gynecological affected area image and the second type of gynecological affected area image according to the analysis results; Specifically as follows: Obtain the affected area images corresponding to each affected part according to the affected area image data to obtain multiple affected area images; Use the data crawler technology to crawl several gynecological affected area images with the gynecological affected area image as the keyword; Divide the obtained several gynecological lesion area images into first-type gynecological lesion area images and second-type gynecological lesion area images to obtain gynecological lesion area image labeling data; Create a gynecological lesion area image recognition model using the gynecological lesion area image labeling data; Use the gynecological lesion area image recognition model to divide the lesion area images into first-type gynecological lesion area images and second-type gynecological lesion area images, and use an encryption algorithm to perform privacy encryption on the second-type lesion area images to obtain encrypted lesion area image data.

[0009] Furthermore, the data analysis module obtains the automatic diagnosis analysis data as follows: Obtain remote diagnosis collection data, and obtain S1 target diagnosis records to Sm target diagnosis records, lesion area image data, and patient symptom collection data according to the remote diagnosis collection data; Obtain the target patient's chief complaint for diagnosis, Z1 clinical symptoms to Zc clinical symptoms, and Z1 symptom onset time values to Zc symptom onset time values according to the patient symptom collection data; Conduct a common symptom analysis between the target patient and the historical diagnosed patients in the diagnosis platform to obtain the platform patient common analysis coefficient corresponding to the target patient; Conduct a common symptom analysis between the target patient and the onset symptoms in S1 target diagnosis records to Sm target diagnosis records respectively to obtain the historical diagnosis common analysis coefficient; Define the historical diagnosis common analysis coefficient and the platform patient common analysis coefficient as the automatic diagnosis analysis data.

[0010] Furthermore, the data analysis module obtains the platform patient common analysis coefficient as follows: Obtain the historical diagnosed data of the diagnosis platform, select several patients with the same chief complaint for diagnosis as the symptom comparison patients according to the historical diagnosed data of the diagnosis platform to obtain multiple symptom comparison patients, and randomly select a sample symptom comparison patient from the multiple symptom comparison patients; Conduct a common analysis of the symptom onset time between the sample symptom patient and the target patient to obtain the sample symptom analysis coefficient; Obtain the symptom common analysis coefficients corresponding to each symptom comparison patient respectively to obtain multiple symptom common analysis coefficients, and calculate the average of the obtained multiple symptom common analysis coefficients to obtain the platform patient common analysis coefficient.

[0011] Furthermore, the data analysis module obtains the sample symptom analysis coefficient as follows: According to the time value of the onset of Z1 symptom to the time value of the onset of Zc symptom, mark the time point when the B1 clinical symptom first occurs in the target patient as the first symptom monitoring time point, mark the time point corresponding to the current moment as the second symptom monitoring time point, and mark the period between the first symptom monitoring time point and the second symptom monitoring time point as the B1 symptom monitoring period; Select several natural symptom monitoring periods within the B1 symptom monitoring period, and name the selected several natural symptom monitoring periods as the M1 monitoring natural period to the Mp monitoring natural period in chronological order; In the M1 monitoring natural period, obtain the onset period of the B1 clinical symptom to get the M1 symptom onset sub-period. In the M2 monitoring natural period, obtain the onset period of the B1 clinical symptom to get the M2 symptom onset sub-period, and so on. In the Mp monitoring natural period, obtain the onset period of the B1 clinical symptom to get the Mp symptom onset sub-period; Obtain the B1 symptom monitoring period corresponding to the sample symptom comparison patient, and select several natural symptom monitoring periods within its corresponding B1 symptom monitoring period. Name the selected several natural symptom monitoring periods as the Y1 monitoring natural period to the Yp monitoring natural period in chronological order; In the Y1 monitoring natural period, obtain the onset period of the B1 clinical symptom to get the Y1 symptom onset sub-period. In the Y2 monitoring natural period, obtain the onset period of the B1 clinical symptom to get the Y2 symptom onset sub-period, and so on. In the Yp monitoring natural period, obtain the onset period of the B1 clinical symptom to get the Yp symptom onset sub-period; Obtain the overlapping duration of the B1 clinical symptom in the M1 monitoring natural period and the Y1 monitoring natural period to get the M1 symptom overlapping duration; Obtain the overlapping duration of the B1 clinical symptom in the M2 monitoring natural period and the Y2 monitoring natural period to get the M2 symptom overlapping duration. Obtain the overlapping duration of the B1 clinical symptom in the M3 monitoring natural period and the Y3 monitoring natural period to get the M3 symptom overlapping duration, and so on. Obtain the overlapping duration of the B1 clinical symptom in the Mp monitoring natural period and the Yp monitoring natural period to get the Mp symptom overlapping duration; Obtain the average daily overlapping duration of B1 symptom to Bz symptom and the daily overlapping variance of B1 symptom to Bz symptom, and calculate to obtain the symptom commonality analysis coefficient corresponding to the sample symptom comparison patient; Calculate the average daily overlapping duration of B1 symptom to Bz symptom and the daily overlapping variance of B1 symptom to Bz symptom to obtain the symptom commonality analysis coefficient corresponding to the sample symptom comparison patient, and name it the sample symptom commonality analysis coefficient; Calculate the sample symptom analysis coefficient, and the specific formula is as follows: ; Among them, Ygx is the sample symptom analysis coefficient, Csci is the average daily overlap duration of Bi symptoms, Cfci is the daily overlap variance of Bi symptoms, and z is the numerical value corresponding to the symptoms with consistent comparison.

[0012] Furthermore, the data analysis obtains the average daily overlap duration and the daily overlap variance of symptoms, specifically as follows: Calculate the average of the overlap durations of M1 symptoms to Mp symptoms to obtain the average daily overlap duration of B1 clinical symptoms in the target patient's body and the body of the patient compared with the sample symptoms, and name it the average daily overlap duration of B1 symptoms; Calculate the variance of the overlap durations of M1 symptoms to Mp symptoms to obtain the daily overlap duration variance of B1 clinical symptoms in the target patient's body and the body of the patient compared with the sample symptoms, and name it the daily overlap variance of B1 symptoms; Conduct a commonality analysis of the onset time periods of B2 clinical symptoms to Bz clinical symptoms respectively to obtain the average daily overlap durations of B2 symptoms to Bz symptoms and the daily overlap variances of B2 symptoms to Bz symptoms.

[0013] Furthermore, the data analysis module obtains the overlap duration of M1 symptoms, specifically as follows: In the existing rectangular coordinate system, mark the time range corresponding to the natural symptom monitoring period as the ordinate, and mark the M1 monitoring natural period and the Y1 monitoring natural period as the abscissa to obtain the first-period plane coordinate system. In the first-period plane coordinate system, create the time range corresponding to the M1 monitoring natural period as the M1 symptom period histogram column, and create the time range corresponding to the Y1 monitoring natural period as the Y1 symptom period histogram column; Fill the time range corresponding to the M1 symptom onset sub-period into the M1 symptom period histogram column to obtain the M1 symptom period filled histogram column, and fill the time range corresponding to the Y1 symptom onset sub-period into the Y1 symptom period histogram column to obtain the Y1 symptom period filled histogram column; Obtain the overlapping time length of the filled areas in the M1 symptom period filled histogram column and the Y1 symptom period filled histogram column on the coordinate Y-axis to obtain the overlap duration of B1 clinical symptoms in the M1 monitoring natural period and the Y1 monitoring natural period, and name it the overlap duration of M1 symptoms.

[0014] Furthermore, the remote medical treatment module conducts remote medical treatment for the target patient, specifically as follows: Obtain the encrypted data of the affected area image; Obtain the automatically analyzed data of the medical visit, and respectively obtain the historical medical visit common analysis coefficient and the platform patient common analysis coefficient according to the automatically analyzed data of the medical visit; Calculate the remote recommendation coefficient by using the historical medical visit common analysis coefficient and the platform patient common analysis coefficient; Calculate the remote medical visit recommendation coefficient. The specific formula is as follows: ; Among them, Ytj is the remote medical visit recommendation coefficient, Lgx is the historical medical visit common analysis coefficient, and Pgx is the platform patient common analysis coefficient; Respectively obtain the thresholds of the remote medical visit recommendation coefficient, compare the remote medical visit recommendation coefficient with the thresholds of the remote medical visit recommendation coefficient, and divide the target patients into first-type medical visit patients and second-type medical visit patients according to the comparison results; Specifically as follows: Respectively obtain the thresholds of the historical medical visit common analysis coefficient and the platform patient common analysis coefficient; Calculate the threshold of the remote recommendation coefficient by using the thresholds of the historical medical visit common analysis coefficient and the platform patient common analysis coefficient; Calculate the threshold of the remote medical visit recommendation coefficient. The specific formula is as follows: ; Among them, Ytjy is the threshold of the remote medical visit recommendation coefficient, Lgxy is the threshold of the historical medical visit common analysis coefficient, and Pgxy is the threshold of the platform patient common analysis coefficient; If the remote medical visit recommendation coefficient is greater than or equal to the threshold of the remote medical visit recommendation coefficient, divide the target patient into first-type medical visit patients; If the remote medical visit recommendation coefficient is less than the threshold of the remote medical visit recommendation coefficient, divide the target patient into second-type medical visit patients; When the target patient is a first-type medical visit patient, the remote medical visit platform automatically makes an offline medical appointment for the target patient; When the target patient is a second-type medical visit patient, the remote medical visit platform automatically assigns an online doctor to the target patient and pushes the encrypted data of the affected area image to the online doctor.

[0015] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are: 1. By identifying the privacy parts of the affected area image and encrypting the identified privacy part images, the present invention can fully protect the personal information and medical records of patients, thereby reducing the risk of privacy leakage; 2. The present invention automatically analyzes the common symptoms between the clinical symptoms presented by the patient and the historical cases in the medical treatment system, and also analyzes the common symptoms between the clinical symptoms presented by the patient and the patient's historical medical treatment symptoms, and provides medical treatment guidance for the patient according to the analysis results, which can improve the accuracy and efficiency of remote gynecological medical treatment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 is the overall system block diagram of the present invention; Figure 2 is the schematic diagram of the M1 symptom time period histogram of the present invention; Figure 3 is the schematic diagram of the filled M1 symptom time period histogram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0019] Embodiment 1 Please refer to Figure 1 , the present invention provides a technical solution: a remote gynecological medical treatment system, including a data acquisition module, a privacy processing module, a data analysis module, a remote medical treatment module and a server. The data acquisition module, the privacy processing module, the data analysis module and the remote medical treatment module are respectively connected to the server, and the server controls the data acquisition module, the privacy processing module, the data analysis module and the remote medical treatment module respectively; The data acquisition module respectively obtains patient symptom acquisition data, affected area image data and a plurality of target medical treatment records to obtain remote medical treatment acquisition data; Specifically as follows: Symptoms of the patient are collected to obtain patient symptom acquisition data; Specifically as follows: The medical treatment chief complaint corresponding to the target patient is obtained through the medical treatment dialog box to obtain the target patient medical treatment chief complaint; It should be noted here that: In this application, the target patient involved here is specifically the patient served by the remote gynecological medical treatment system at the current moment; In this application, the medical treatment chief complaint involved here is specifically the main problem or discomfort symptom expressed by the target patient in the medical treatment dialog box; Obtain the time value when the patient's chief complaint of seeking medical treatment appears through the medical treatment dialog box, obtain the first symptom characteristic time point, mark the time value corresponding to the current moment as the second symptom characteristic time point, and mark the time period between the first symptom characteristic time point and the second symptom characteristic time point as the patient symptom monitoring period; Obtain the clinical symptoms that the target patient has during the patient symptom monitoring period, and obtain the Z1 clinical symptom to the Zc clinical symptom; It should be noted here that: In this application, Z involved here is the identifier corresponding to the clinical symptom, and c involved here is the numerical value of the number of clinical symptoms corresponding to the target patient, and c is an integer greater than 0.

[0020] Obtain the time value when the Z1 clinical symptom first appears in the target patient to obtain the Z1 symptom onset time value, obtain the time value when the Z2 clinical symptom first appears in the target patient to obtain the Z2 symptom onset time value, and so on, obtain the time value when the Zc clinical symptom first appears in the target patient to obtain the Zc symptom onset time value; Define the patient's chief complaint of seeking medical treatment, the Z1 clinical symptom to the Zc clinical symptom, and the Z1 symptom onset time value to the Zc symptom onset time value as the patient symptom collection data; Obtain the affected area image corresponding to each affected part of the target patient to obtain the affected area image data; It should be noted here that: The target patient involved here specifically refers to a patient who can independently provide the affected area image. If the patient cannot independently provide the affected area image, the patient does not belong to the target patient in this application; In specific implementation, the specific diseases corresponding to the target patient include but are not limited to vulvovaginitis, condyloma acuminata, and Bartholin gland inflammation. The specific diseases corresponding to non-target patients include but are not limited to endometriosis, uterine fibroids, and ovarian cysts.

[0021] Obtain the historical medical treatment records corresponding to the target patient, and mark the records of seeking medical treatment due to the patient's chief complaint of seeking medical treatment in the historical medical treatment records as the target medical treatment records; Name the several target medical treatment records existing in the historical medical treatment records in chronological order as the S1 target medical treatment record to the Sm target medical treatment record; It should be noted here that: In this application, there are multiple target medical treatment records for the target patient involved here; In this application, S involved here is the identifier corresponding to the target medical treatment record, and m is the numerical value corresponding to the number of target medical treatment records; Define the S1 target medical record to the Sm target medical record, the affected area image data, and the patient symptom collection data as the remote medical visit collection data; The data collection module obtains the remote medical visit collection data and transports it to the privacy processing module and the data analysis module; The privacy processing module performs privacy analysis and encryption on the affected area image data according to the remote medical visit collection data to obtain the encrypted affected area image data; Specifically as follows: Obtain the remote medical visit collection data, and obtain the affected area image data according to the remote medical visit collection data; Perform privacy analysis on the affected area image data, and divide it into the first type of gynecological affected area image and the second type of gynecological affected area image according to the analysis results; Specifically as follows: Obtain the affected area image corresponding to each disease location according to the affected area image data respectively to obtain multiple affected area images; Use data crawling technology to crawl several gynecological affected area images with the gynecological affected area image as the keyword; Divide the obtained several gynecological affected area images into the first type of gynecological affected area image and the second type of gynecological affected area image to obtain the gynecological affected area image marking data; It should be noted here that: In this application, the first type of gynecological affected area image involved here is the human body's conventional affected area image, the second type of affected area image involved here is the human body's privacy affected area image, and the human body's privacy affected area image involved here includes but is not limited to external genital images, internal genital images, and breast images; Divide the gynecological affected area image marking data into the gynecological affected area image training set and the gynecological affected area image test set according to the image training and test ratio; It should be noted here that the ratio of the number of gynecological affected area images in the gynecological affected area image training set and the gynecological affected area image test set is 8:2: Create an image recognition model through an existing artificial intelligence platform, and use the gynecological affected area image training set to train the image recognition model until each medical gynecological affected area image in the gynecological affected area image training set has been trained on the image recognition model once; Use the gynecological affected area image test set to test the image recognition model and obtain the recognition accuracy rate. If the recognition accuracy rate is greater than or equal to the target recognition accuracy rate, the training of the image recognition model is completed to obtain the gynecological affected area image recognition model. If the recognition accuracy rate is less than the target recognition accuracy rate, continue to use the gynecological affected area image training set to train the image recognition model until the recognition accuracy rate is greater than or equal to the target recognition accuracy rate; The gynecological affected area image recognition model is used to divide the affected area image into the first type of gynecological affected area image and the second type of gynecological affected area image, and the encryption algorithm is used to perform privacy encryption on the second type of affected area image to obtain the encrypted data of the affected area image; It should be noted here that: The encryption algorithm involved here is the AES symmetric encryption algorithm.

[0022] The data analysis module automatically analyzes the data collected from remote consultations to obtain the common analysis coefficient of platform patients and the common analysis coefficient of historical consultations, and obtains the automatically analyzed data of consultations; Specifically as follows: Obtain the data collected from remote consultations, and obtain the S1 target consultation record to the Sm target consultation record, the affected area image data, and the patient symptom collection data according to the data collected from remote consultations; Obtain the main complaint of the target patient's consultation, the Z1 clinical symptom to the Zc clinical symptom, and the Z1 symptom onset time value to the Zc symptom onset time value according to the patient symptom collection data; Perform symptom commonality analysis on the target patient and the historical admitted patients in the consultation platform to obtain the common analysis coefficient of platform patients corresponding to the target patient; Specifically as follows: Obtain the historical admitted data of the consultation platform, and select several patients with the same main complaint of the target patient's consultation as the symptom comparison patients according to the historical admitted data of the consultation platform to obtain multiple symptom comparison patients, and randomly select a sample symptom comparison patient from the multiple symptom comparison patients; Name the obtained multiple consistent comparison symptoms as the B1 clinical symptom to the Bz clinical symptom respectively; It should be noted here that: In this application, B involved here is the identifier corresponding to the consistent comparison symptom, z is the quantity value corresponding to the consistent comparison symptom, and z is an integer greater than 0; Perform commonality analysis on the onset time of the B1 clinical symptom between the target patient and the sample symptom comparison patient to obtain the average daily overlap duration of the B1 symptom and the daily overlap variance of the B1 symptom; Specifically as follows: Mark the time point when the B1 clinical symptom first occurs in the target patient as the first symptom monitoring time point according to the Z1 symptom onset time value to the Zc symptom onset time value, mark the time point corresponding to the current moment as the second symptom monitoring time point, and mark the time period between the first symptom monitoring time point and the second symptom monitoring time point as the B1 symptom monitoring period; Select several natural symptom monitoring time periods within the B1 symptom monitoring period, and name the selected several natural symptom monitoring time periods as the M1 monitoring natural time period to the Mp monitoring natural time period in chronological order; It should be noted here that: In this application, the specific natural period monitored by M1 here is the first complete natural date after the first symptom monitoring time point. The specific complete natural date involved here is from 0:00 to 24:00 of a date after the first symptom monitoring time point; In this application, M involved here is an identifier corresponding to the natural period of symptom monitoring of the target patient, p is the corresponding numerical value of the natural period of symptom monitoring, and p is an integer greater than 0; During the natural period monitored by M1, obtain the onset period of the B1 clinical symptom to get the M1 symptom onset sub-period. During the natural period monitored by M2, obtain the onset period of the B1 clinical symptom to get the M2 symptom onset sub-period, and so on. During the natural period monitored by Mp, obtain the onset period of the B1 clinical symptom to get the Mp symptom onset sub-period; It should be noted here that: In this application, there can be multiple M1 symptom onset periods to Mp symptom onset periods involved here; Obtain the B1 symptom monitoring cycle corresponding to the sample symptom comparison patient, and select several natural periods of symptom monitoring within its corresponding B1 symptom monitoring cycle. Name the selected several natural periods of symptom monitoring in chronological order as the Y1 natural monitoring period to the Yp natural monitoring period; It should be noted here that: In this application, Y involved here is an identifier corresponding to the natural period of symptom monitoring of the sample symptom comparison patient, and p is the corresponding numerical value of the natural period of symptom monitoring; During the Y1 natural monitoring period, obtain the onset period of the B1 clinical symptom to get the Y1 symptom onset sub-period. During the Y2 natural monitoring period, obtain the onset period of the B1 clinical symptom to get the Y2 symptom onset sub-period, and so on. During the Yp natural monitoring period, obtain the onset period of the B1 clinical symptom to get the Yp symptom onset sub-period; It should be noted here that: In this application, there can be multiple Y1 symptom onset periods to Yp symptom onset periods involved here; Obtain the overlapping duration of the B1 clinical symptom in the M1 natural monitoring period and the Y1 natural monitoring period to get the M1 symptom overlapping duration; Specifically as follows: Please refer to Figure 2, in the existing rectangular coordinate system, mark the time range corresponding to the natural period of symptom monitoring as the ordinate, and mark the natural period of M1 monitoring and the natural period of Y1 monitoring as the abscissa to obtain the first-period plane coordinate system. In the first-period plane coordinate system, create a histogram of the M1 symptom period for the time range corresponding to the natural period of M1 monitoring, and create a histogram of the Y1 symptom period for the time range corresponding to the natural period of Y1 monitoring; Please refer to Figure 3 , fill the histogram of the M1 symptom period with the time range corresponding to the M1 symptom onset sub-period to obtain a filled histogram of the M1 symptom period, and fill the histogram of the Y1 symptom period with the time range corresponding to the Y1 symptom onset sub-period to obtain a filled histogram of the Y1 symptom period; Obtain the overlapping time length of the filled areas of the filled histogram of the M1 symptom period and the filled histogram of the Y1 symptom period on the Y-axis of the coordinate to obtain the overlapping duration of the B1 clinical symptoms in the natural period of M1 monitoring and the natural period of Y1 monitoring, and name it the M1 symptom overlapping duration; Obtain the overlapping duration of the B1 clinical symptoms in the natural period of M2 monitoring and the natural period of Y2 monitoring to obtain the M2 symptom overlapping duration, obtain the overlapping duration of the B1 clinical symptoms in the natural period of M3 monitoring and the natural period of Y3 monitoring to obtain the M3 symptom overlapping duration, and so on, obtain the overlapping duration of the B1 clinical symptoms in the natural period of Mp monitoring and the natural period of Yp monitoring to obtain the Mp symptom overlapping duration; Calculate the average of the M1 symptom overlapping duration to the Mp symptom overlapping duration to obtain the average daily overlapping duration of the B1 clinical symptoms in the target patient's body and the sample symptom comparison patient's body, and name it the B1 symptom average daily overlapping duration; Calculate the variance of the M1 symptom overlapping duration to the Mp symptom overlapping duration to obtain the variance of the daily overlapping duration of the B1 clinical symptoms in the target patient's body and the sample symptom comparison patient's body, and name it the B1 symptom daily overlapping variance; Conduct a commonality analysis of the onset periods of the B2 clinical symptoms to the Bz clinical symptoms respectively to obtain the B2 symptom average daily overlapping duration to the Bz symptom average daily overlapping duration and the B2 symptom daily overlapping variance to the Bz symptom daily overlapping variance; Calculate the symptom commonality analysis coefficient corresponding to the sample symptom comparison patient from the B1 symptom average daily overlapping duration to the Bz symptom average daily overlapping duration and the B1 symptom daily overlapping variance to the Bz symptom daily overlapping variance, and name it the sample symptom commonality analysis coefficient; Calculate the sample symptom analysis coefficient, and the specific formula is as follows: ; Among them, Ygx is the sample symptom analysis coefficient, Csci is the average daily overlap duration of Bi symptoms, Cfci is the daily overlap variance of Bi symptoms, and z is the numerical value corresponding to the symptoms with consistent comparison; It should be noted here that: In this application, the average daily overlap duration of Bi symptoms involved here can be the average daily overlap duration of any one symptom from the average daily overlap duration of B1 symptoms to the average daily overlap duration of Bz symptoms, and the daily overlap variance of Bi symptoms involved here can be the daily overlap variance of any one symptom from the daily overlap variance of B1 symptoms to the daily overlap variance of Bz symptoms; Repeat the process of obtaining the symptom commonality analysis coefficient corresponding to the sample symptom comparison patient, obtain the symptom commonality analysis coefficient corresponding to each symptom comparison patient respectively, obtain multiple symptom commonality analysis coefficients, and calculate the average of the obtained multiple symptom commonality analysis coefficients to obtain the platform patient commonality analysis coefficient; Repeat the process of obtaining the platform patient commonality analysis coefficient, and conduct commonality analysis on the onset symptoms of the target patient with the S1 target medical record to the Sm target medical record respectively to obtain the historical medical record commonality analysis coefficient; It should be noted here that: In this application, the process of obtaining the historical patient commonality analysis coefficient here is the same as the process of obtaining the platform patient commonality analysis coefficient. Here, each target medical record from the S1 target medical record to the Sm target medical record is regarded as a symptom comparison patient; Define the historical medical record commonality analysis coefficient and the platform patient commonality analysis coefficient as the medical record automatic analysis data; The data analysis module obtains the medical record automatic analysis data and transmits it to the remote medical record module; The remote medical record module conducts remote medical treatment on the target patient according to the medical record automatic analysis data; Specifically as follows: Obtain the encrypted data of the affected area image; Obtain the medical record automatic analysis data, and respectively obtain the historical medical record commonality analysis coefficient and the platform patient commonality analysis coefficient according to the medical record automatic analysis data; Calculate the remote recommendation coefficient by calculating the historical medical record commonality analysis coefficient and the platform patient commonality analysis coefficient; Calculate the remote medical treatment recommendation coefficient, and the specific formula is as follows: ; Among them, Ytj is the remote medical treatment recommendation coefficient, Lgx is the historical medical record commonality analysis coefficient, and Pgx is the platform patient commonality analysis coefficient; Obtain the remote consultation recommendation coefficient thresholds respectively, compare the remote consultation recommendation coefficient with the remote consultation recommendation coefficient thresholds numerically, and divide the target patients into first-type consultation patients and second-type consultation patients according to the comparison results; Specifically as follows: Obtain the historical consultation commonality analysis coefficient threshold and the platform patient commonality analysis coefficient threshold respectively; It should be noted here that: The historical consultation commonality analysis coefficient threshold and the platform patient commonality analysis coefficient threshold involved here are the maximum historical consultation commonality analysis coefficient and the maximum platform patient commonality analysis coefficient corresponding to the second-type consultation patients respectively.

[0023] Calculate the remote recommendation coefficient threshold from the historical consultation commonality analysis coefficient threshold and the platform patient commonality analysis coefficient threshold; Calculate the remote consultation recommendation coefficient threshold, and the specific formula is as follows: ; Among them, Ytjy is the remote consultation recommendation coefficient threshold, Lgxy is the historical consultation commonality analysis coefficient threshold, and Pgxy is the platform patient commonality analysis coefficient threshold; If the remote consultation recommendation coefficient is greater than or equal to the remote consultation recommendation coefficient threshold, then divide the target patients into first-type consultation patients; If the remote consultation recommendation coefficient is less than the remote consultation recommendation coefficient threshold, then divide the target patients into second-type consultation patients; When the target patients are first-type consultation patients, the remote consultation platform automatically makes an offline consultation appointment for the target patients; When the target patients are second-type consultation patients, the remote consultation platform automatically assigns online doctors to the target patients and pushes the encrypted data of the affected area images to the online doctors.

[0024] In this application, if there are corresponding calculation formulas, the above calculation formulas are all calculated by taking the numerical values without dimensions. For the coefficients such as weight coefficients and proportionality coefficients in the formulas, the magnitudes set are for obtaining a result value by quantifying each parameter. Regarding the magnitudes of the weight coefficients and proportionality coefficients, as long as the proportional relationship between the parameters and the result value is not affected.

[0025] The above-disclosed preferred embodiments of the present invention are only used to help illustrate the present invention. The preferred embodiments do not elaborate on all details, nor do they limit the present invention to only the specific implementation manners. Obviously, according to the content of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments to better explain the principle and practical application of the present invention, so that those skilled in the relevant technical fields can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A remote gynecological consultation system, characterized in that, Including: Data acquisition module: used to separately obtain patient symptom acquisition data, affected area image data, and multiple target medical record, so as to obtain remote medical treatment acquisition data; Privacy processing module: used to perform privacy analysis on the affected area image data according to the remote medical treatment acquisition data, divide the affected area images into the first type of gynecological affected area images and the second type of gynecological affected area images, and perform privacy encryption on the second type of affected area images to obtain encrypted affected area image data; Data analysis module: obtain multiple symptom comparison patients, perform symptom commonality analysis on the target patient and each symptom comparison patient through the remote medical treatment acquisition data to obtain the platform patient commonality analysis coefficient, perform time commonality analysis on the target patient and the onset symptoms in each target medical record respectively to obtain the historical medical treatment commonality analysis coefficient, and define the historical medical treatment commonality analysis coefficient and the platform patient commonality analysis coefficient as the medical treatment automatic analysis data; Remote medical treatment module: used to perform remote medical treatment on the target patient according to the medical treatment automatic analysis data.

2. The remote gynecological consultation system according to claim 1, characterized in that, Obtain the remote medical treatment acquisition data, specifically as follows: Collect symptoms of the patient to obtain patient symptom acquisition data, and obtain the affected area image data corresponding to each affected area of the target patient; Obtain the historical medical records corresponding to the target patient, record the chief complaints of the target patient during the medical treatment in the historical medical records, and name them as the S1 target medical record to the Sm target medical record in chronological order; Define the S1 target medical record to the Sm target medical record, the affected area image data, and the patient symptom acquisition data as the remote medical treatment acquisition data.

3. The remote gynecological consultation system according to claim 2, wherein Obtain the patient symptom acquisition data, specifically as follows: Obtain the chief complaint of the target patient through the medical treatment dialog box to obtain the chief complaint of the target patient; Mark a patient symptom monitoring period, and obtain the clinical symptoms that the target patient presents during the patient symptom monitoring period to obtain the Z1 clinical symptom to the Zc clinical symptom; Separate obtain the time values when the Z1 clinical symptom to the Zc clinical symptom first appear in the target patient to obtain the Z1 symptom onset time value to the Zc symptom onset time value; Define the chief complaint of the target patient, the Z1 clinical symptom to the Zc clinical symptom, and the Z1 symptom onset time value to the Zc symptom onset time value as the patient symptom acquisition data.

4. The remote gynecological consultation system according to claim 1, characterized in that, Obtain the encrypted affected area image data, specifically as follows: Obtain the remote medical treatment acquisition data, and obtain the affected area image data according to the remote medical treatment acquisition data; Perform privacy analysis on the affected area image data, and divide it into the first type of gynecological affected area images and the second type of gynecological affected area images according to the analysis results; Specifically as follows: Separate obtain the affected area images corresponding to each affected area according to the affected area image data to obtain multiple affected area images; Use data crawling technology to crawl a number of gynecological affected area images with the gynecological affected area images as keywords; Divide the obtained number of gynecological affected area images into the first type of gynecological affected area images and the second type of gynecological affected area images to obtain gynecological affected area image marking data; Use the gynecological affected area image marking data to create a gynecological affected area image recognition model; The affected area images are divided into the first type of gynecological affected area images and the second type of gynecological affected area images using a gynecological affected area image recognition model, and the second type of affected area images are privately encrypted using an encryption algorithm to obtain encrypted data of the affected area images.

5. A remote gynecological consultation system according to claim 1, characterized in that, Obtain the automatic visit analysis data as follows: Obtain the remote visit collection data, and obtain the S1 target visit record to the Sm target visit record, the affected area image data, and the patient symptom collection data according to the remote visit collection data; Obtain the target patient's visit chief complaint, the Z1 clinical symptoms to the Zc clinical symptoms, and the Z1 symptom onset time value to the Zc symptom onset time value according to the patient symptom collection data; Conduct a symptom commonality analysis between the target patient and the historical admitted patients in the consultation platform to obtain the platform patient commonality analysis coefficient corresponding to the target patient; Conduct a commonality analysis on the onset symptoms between the Z1 clinical symptoms to the Zc clinical symptoms and the S1 target visit record to the Sm target visit record to obtain the historical visit commonality analysis coefficient; Define the historical visit commonality analysis coefficient and the platform patient commonality analysis coefficient as the automatic visit analysis data.

6. The remote gynecological consultation system according to claim 5, characterized in that, Obtain the platform patient commonality analysis coefficient as follows: Obtain the historical admitted data of the consultation platform, select multiple symptom comparison patients according to the historical admitted data of the consultation platform, and randomly select a sample symptom comparison patient; Conduct a commonality analysis on the symptom onset time between the sample symptom patient and the target patient to obtain the sample symptom analysis coefficient; Obtain the symptom commonality analysis coefficients corresponding to each symptom comparison patient respectively, obtain multiple symptom commonality analysis coefficients, and calculate the average value to obtain the platform patient commonality analysis coefficient.

7. The remote gynecological consultation system according to claim 6, characterized in that, Obtain the sample symptom analysis coefficient as follows: Mark the B1 symptom monitoring period corresponding to the target patient, select the M1 monitoring natural time period to the Mp monitoring natural time period within the B1 symptom monitoring period, and obtain the onset time period of the B1 clinical symptom during the monitoring natural time period to obtain the M1 symptom onset sub-time period to the Mp symptom onset sub-time period; Obtain the B1 symptom monitoring period corresponding to the sample symptom comparison patient, and select the Y1 monitoring natural time period to the Yp monitoring natural time period within the B1 symptom monitoring period; During the Y1 monitoring natural time period to the Yp monitoring natural time period, obtain the onset time period of the B1 clinical symptom respectively to obtain the Y1 symptom onset sub-time period to the Yp symptom onset sub-time period; Obtain the overlapping duration of the B1 clinical symptom in the M1 monitoring natural time period and the Y1 monitoring natural time period to obtain the M1 symptom overlapping duration, and so on, to obtain the Mp symptom overlapping duration; Obtain the average daily overlapping duration of the B1 symptom to the Bz symptom and the daily overlapping variance of the B1 symptom to the Bz symptom, and calculate Ygx for the sample symptom analysis coefficient; The details are as follows: ; Among them, Csci is the average daily overlapping duration of the Bi symptom, Cfci is the daily overlapping variance of the Bi symptom, and z is the numerical value of the number of symptoms with consistent comparison.

8. The remote gynecological consultation system according to claim 7, wherein, Obtain the average daily overlapping duration of the symptom and the daily overlapping variance of the symptom as follows: Calculate the average value of the M1 symptom overlapping duration to the Mp symptom overlapping duration to obtain the average daily overlapping duration of the B1 symptom; Calculate the variance from the overlapping duration of M1 symptoms to the overlapping duration of Mp symptoms to obtain the daily overlapping variance of B1 symptoms; Conduct a commonality analysis of the onset time periods for each of the clinical symptoms from B2 to Bz, obtaining the average daily overlapping durations of the B2 to Bz symptoms and the daily overlapping variances of the B2 to Bz symptoms.

9. The remote gynecological consultation system according to claim 7, characterized in that Obtain the overlapping duration of M1 symptoms as follows: In a Cartesian coordinate system, mark the time range corresponding to the natural symptom monitoring period as the ordinate, and mark the natural monitoring periods of M1 and Y1 as the abscissa to obtain the first-period plane coordinate system. In this first-period plane coordinate system, create a histogram column for the M1 symptom period using the time range corresponding to the natural monitoring period of M1, and create a histogram column for the Y1 symptom period using the time range corresponding to the natural monitoring period of Y1; Fill the histogram column of the M1 symptom period with the time range corresponding to the M1 symptom onset sub-period to obtain the filled histogram column of the M1 symptom period, and fill the histogram column of the Y1 symptom period with the time range corresponding to the Y1 symptom onset sub-period to obtain the filled histogram column of the Y1 symptom period; Obtain the overlapping time length on the Y-axis coordinate of the filled areas in the filled histogram column of the M1 symptom period and the filled histogram column of the Y1 symptom period to obtain the overlapping duration of M1 symptoms.

10. A remote gynecological consultation system according to claim 1, characterized in that, The remote consultation for the target patient is as follows: Obtain the encrypted data of the affected area image; Obtain the automatic consultation analysis data, and respectively obtain the historical consultation commonality analysis coefficient and the platform patient commonality analysis coefficient based on the automatic consultation analysis data; Calculate the remote recommendation coefficient from the historical consultation commonality analysis coefficient Lgx and the platform patient commonality analysis coefficient Pgx, and obtain the threshold of the remote recommendation coefficient; If the remote consultation recommendation coefficient is greater than or equal to the remote consultation recommendation coefficient threshold, classify the target patient as a first-type consultation patient. If the remote consultation recommendation coefficient is less than the remote consultation recommendation coefficient threshold, classify the target patient as a second-type consultation patient; When the target patient is a first-type consultation patient, the remote consultation platform automatically makes an offline consultation appointment for the target patient; When the target patient is a second-type consultation patient, the remote consultation platform automatically assigns an online doctor to the target patient and pushes the encrypted data of the affected area image to the online doctor.

Images