Standardized blood pressure measurement process control system and implementation method thereof

Abstract

The present invention discloses a standardized blood pressure measurement process control system and its implementation method, the process control system includes a blood pressure measurement process control device and a built-in control module, the blood pressure measurement process control device includes a computer body, a display screen, a control switch and an electronic blood pressure monitor, the electronic blood pressure monitor is installed in the body of the blood pressure measurement process control device by a fixed mechanism. The present invention controls the electronic blood pressure monitor through the built-in control modules, realizes a set of blood pressure measurements for a patient (bilateral synchronization), automatically completes the binding and output of the patient's identity information and blood pressure measurement results, generates a blood pressure measurement report sheet containing complete information, reduces the measurement procedure errors caused by human factors while reducing the work intensity of medical personnel, and improves the reliability of the measurement results and records.

Description

[Technical field]

[0001] The present invention relates to the technical field of blood pressure measurement process control, in particular to a standardized blood pressure measurement process control system and its implementation method. [Background technology]

[0002] In modern medicine, electronic blood pressure monitors are mainly used to measure the blood pressure of the human body, but the arbitrariness in the measurement process of traditional manually controlled electronic blood pressure monitors is particularly large, and for the same subject, the blood pressure measurement results of different medical staff are quite different, and there are obvious measurement procedure errors. In addition, there are also defects in the data collection and management of the measurement results. For example, the electronic blood pressure monitor itself only has the function of blood pressure measurement, and does not have the function of inputting and binding the identity information of the person being measured, and medical staff usually need to manually record the identity information of the subject when using it, which is easy to make mistakes and also increases the workload of medical staff. In addition, even if the electronic blood pressure monitor has a data storage function, the measurement data can only be stored in chronological order, and the input of the identity information of the subject needs to be completed manually. When there are many subjects, the identity information of the subject is easily confused with the blood pressure measurement data, and the blood pressure data of the subject may be confused with the blood pressure data of other subjects. Summary of the Invention

[0003] To address the above problems, the present invention provides a process control system for standardized blood pressure measurement, which controls an electronic blood pressure monitor to realize a set of standardized blood pressure measurements for a patient (bilateral synchronization), automatically completes the binding and output of the patient's identity information and blood pressure measurement results, reduces the workload of medical personnel, reduces measurement procedure errors caused by human factors, and improves the reliability of measurement results and records.

[0004] In order to achieve the above objectives, the present invention adopts the following technical solutions. A standardized blood pressure measurement process control system comprising a blood pressure measurement process control device and a built-in control module, the blood pressure measurement process control device comprising a computer body, a display screen, a control switch and an electronic blood pressure meter, the computer body for controlling the whole measurement process and displaying and outputting the results, the display screen for performing human-machine interaction and displaying the measurement results, the control switch for controlling the on and off of the electronic blood pressure meter, the electronic blood pressure meter for performing blood pressure measurement, and installed inside the blood pressure measurement process control device through a fixed structure; The control module includes an information collection module, an image sharpness checking module, a data processing module, and a blood pressure measurement process control module. The information collection module is for taking pictures of a user's identification card information and each measurement result on the display panel of the electronic blood pressure meter, and sending the collected images to the image sharpness checking module. The image sharpness checking module is for performing a sharpness check on the collected images, and sending images that pass the check to the data processing module. The data processing module includes an image pre-processing module, a character detection module, a character recognition module, and a regular expression filtering module. The image pre-processing module is for cropping the certificate image according to specifications and correcting the captured image of the electronic blood pressure meter display panel. The character detection module and the character recognition module are for detecting and recognizing character information in the certificate image and the blood pressure measurement result image. The regular expression filtering module is for extracting and filling important information from the text by specifying corresponding regular expression filtering criteria, calculating the average value and difference of the blood pressure measurement values, and integrating the user's identification information and the blood pressure measurement results, and displaying them on a display screen.

[0005] Furthermore, to replace the conventional manual start button, a control command signal for the control switch is periodically sent by the built-in program of the signal collection module, and a virtual switch is driven by an I / O control card connected to the USB interface.

[0006] Specifically, the implementation method based on the above-mentioned standardized blood pressure measurement process control system includes: Step S1, system environment configuration: placing the blood pressure measurement process control device on a horizontal table, connecting it to a power source, turning on the power switch of the combined device, and putting the control system into a standby state; Step S2, identity information collection: the user places his / her identity card or medical insurance card at the designated photo-taking position, and controls the camera through the information collection module to take and sample the user's identity card information; the collected photos are inspected through the image sharpness inspection module; and the photos that pass the inspection are sent to the data processing module to generate an identity information list; Step S3, data collection and processing: after the identity information is successfully collected, the blood pressure measurement control module controls the electronic blood pressure monitor to complete the blood pressure measurement for the user; the information collection module controls the camera to sample the data displayed on the electronic blood pressure monitor display panel every time; the data processing module recognizes and extracts the sampled data, and further calculates the average value and difference of the blood pressure measurement results, and obtains a blood pressure measurement result list; Step S4, integration, printing, and uploading of measurement report: The data processing module includes a step of integrating the identification information list generated in step S2 with the blood pressure measurement result list in step S3, displaying them on the display screen, and uploading and storing them in the hospital's HIS system or cloud server.

[0007] Furthermore, the collection of identity information in step S2 is specifically as follows: Step S21, certificate image collection: the user places the ID card or medical insurance card at the designated photo-taking position, and the information collection module controls the camera to take a photo, and the image sharpness check module checks the image sharpness. If the pixel value of the collected certificate image is less than the set threshold of 1080x960, an error message is returned, and the user is prompted to take a photo again and sample; if the pixel value of the collected certificate image is equal to or greater than the set threshold of 1080x960, step S32 is executed; Step S22, certificate image processing: the image pre-processing module uniformly crops the certificate image collected in step S31 into an image with an aspect ratio of 3:2, and performs grayscale processing; Step S23, certificate image recognition: using a character detection module and a character recognition module to detect and recognize the character information in the processed certificate image, and perform regular expression filtering to obtain the character recognition result of the image; Step S24, storing and binding certificate information: According to the character recognition result obtained in step S33, the user's name, gender, and age information are saved to generate an identity information list, which is bound to the subsequent blood pressure measurement result list, and then a blood pressure measurement report is output.

[0008] The aforementioned data collection and processing specifically: Step S31, display panel image collection: the information collection module controls the camera to collect the image of the electronic blood pressure monitor display panel at the specified position, and transmits it to the data processing module after being inspected and passed by the image sharpness inspection module; Step S32, panel image correction: the image pre-processing module further performs corner point detection and affine transformation on the collected image to implement image correction; Step S33, symbol segmentation, recognition and result calculation: the character detection module and the character recognition module complete the independent segmentation of the symbols in the corrected image, perform symbol recognition on the independently segmented image using a threading method, extract important information in the recognized text by the regular expression filtering module, and calculate the average value and difference of the blood pressure measurement values.

[0009] Furthermore, in step S23, using a character detection module and a character recognition module to detect and recognize character information in the certificate image, Character detection: using DBnet network to implement character detection, outputting image text segmentation result by the network based on segmentation method, converting the segmentation result image into a binary image using a preset threshold T, inserting the image binarization operation into the network for joint optimization, making the network adaptively predict the threshold value of each pixel in the image through 4 or more sampling operations, training the certificate information model using ICPR dataset, parsing and storing the text in a list, and performing recognition after training; Character recognition: Select CRNN+CTC to implement the recognition algorithm, extract character sequence features based on convolutional features by extracting features, select GRU with smaller computational cost, use Mobilenet for CNN, zoom the image of the image to a size of 32x640x32 under the condition of fixed aspect ratio, and become 1x8x512 after passing through CNN, set T=8 for LSTM, input the features into LSTM, in the actual recognition, consider the overlap, interruption and different intervals of the text, output the results using CTC, predict the spaces in the text by using the forward-backward algorithm of HMM according to the artificially specified space symbol, and finally enumerate all possible results to output the recognized character information.

[0010] JPEG0007671551000001.jpg101170

[0011] The beneficial effects of the present invention are as follows: 1. According to the process control system of standard blood pressure measurement of the present invention, by controlling the electronic sphygmomanometer, a set of standardized (bilateral synchronous) blood pressure measurements for patients can be realized under the control of a set program, and more comprehensive information can be obtained while reducing measurement procedure errors caused by human factors, improving the reliability of the measurement results, and helping doctors make more reasonable decisions on the subsequent diagnosis and treatment of hypertension patients. 2. According to the implementation method of the standard blood pressure measurement process control system of the present invention, the binding and output of the patient's identity information and blood pressure measurement results can be automatically completed, providing a convenient and reliable standardized blood pressure measurement process control means and corresponding data management function, and reducing the workload of medical personnel. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a structural block diagram of the standardized bimanual / ankle synchronous blood pressure measurement system of the present invention. [Diagram 2] FIG. 2 is a flow chart of the standardized bimanual / ankle synchronous blood pressure measurement method of the present invention. [Diagram 3] FIG. 3 is a flow chart of information interaction in an embodiment of the present invention. [Figure 4] FIG. 4 is a flow chart of image processing in an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] In order to allow those skilled in the art to better understand the technical solutions in the present disclosure, the technical solutions in the embodiments of the present disclosure are clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, and are not all of the embodiments.

[0014] As shown in FIG. 1, a standardized blood pressure measurement process control system includes a blood pressure measurement process control device and a built-in control module, the blood pressure measurement process control device includes a computer body, a display screen, a control switch and an electronic blood pressure meter, the computer body is for controlling the entire measurement process and displaying and outputting the results, the display screen is for performing human-machine interaction and displaying the measurement results, the control switch is for controlling the on and off of the electronic blood pressure meter, and the electronic blood pressure meter is for performing blood pressure measurement, and is installed inside the blood pressure measurement process control device through a fixed structure; The control module includes an information collection module, an image sharpness checking module, a data processing module, and a blood pressure measurement process control module. The information collection module is for taking pictures of a user's identification card information and each measurement result on the display panel of the electronic blood pressure meter, and sending the collected images to the image sharpness checking module. The image sharpness checking module is for performing a sharpness check on the collected images, and sending images that pass the check to the data processing module. The data processing module includes an image pre-processing module, a character detection module, a character recognition module, and a regular expression filtering module. The image pre-processing module is for cropping the certificate image according to specifications and correcting the captured image of the electronic blood pressure meter display panel. The character detection module and the character recognition module are for detecting and recognizing character information in the certificate image and the blood pressure measurement result image. The regular expression filtering module is for extracting and filling important information from the text by specifying corresponding regular expression filtering criteria, calculating the average value and difference of the blood pressure measurement values, and integrating the user's identification information and the blood pressure measurement results, and displaying them on a display screen.

[0015] Specifically, to replace the conventional manual start button, a control command signal for the control switch is periodically sent by the built-in program of the signal collection module, and a virtual switch is driven by an I / O control card connected to the USB interface.

[0016] In addition, as shown in FIG. 2 to FIG. 4, the present embodiment also provides an implementation method based on the above-mentioned standardized blood pressure measurement process control system, which includes: Step S1, system environment configuration: placing the blood pressure measurement process control device on a horizontal table, connecting it to a power source, turning on the power switch of the combined device, and putting the control system into a standby state; Step S2, identity information collection: the user places his / her identity card or medical insurance card at a designated photographing position, and the information collection module controls the camera to photograph and sample the user's identity card information; the collected photos are inspected by the image sharpness inspection module; and the photos that pass the inspection are sent to the data processing module to generate an identity information list; Step S3, data collection and processing: after the identity information is successfully collected, the blood pressure measurement control module controls the electronic blood pressure monitor to complete the blood pressure measurement for the user; the information collection module controls the camera to sample the data displayed on the electronic blood pressure monitor display panel every time; the data processing module recognizes and extracts the sampled data, and further calculates the average value and difference of the blood pressure measurement results, and obtains a blood pressure measurement result list; Step S4, integration, printing, and uploading of measurement report: The data processing module includes a step of integrating the identification information list generated in step S2 with the blood pressure measurement result list in step S3, displaying them on the display screen, and uploading and storing them in the hospital's HIS system or cloud server.

[0017] Furthermore, the collection of identity information in step S2 is specifically as follows: Step S21, certificate image collection: the user places the ID card or medical insurance card at the designated photo-taking position, and the information collection module controls the camera to take a photo, and the image sharpness check module checks the image sharpness. If the pixel value of the collected certificate image is less than the set threshold of 1080x960, an error message is returned, and the user is prompted to take a photo again and sample; if the pixel value of the collected certificate image is equal to or greater than the set threshold of 1080x960, step S32 is executed; Step S22, certificate image processing: the image pre-processing module uniformly crops the certificate image collected in step S31 into an image with an aspect ratio of 3:2, and performs grayscale processing; Step S23, certificate image recognition: using a character detection module and a character recognition module to detect and recognize character information in the processed certificate image, and perform regular expression filtering to obtain a character recognition result of the image; Step S24, storing and binding certificate information: According to the character recognition result obtained in step S33, the user's name, gender, and age information are saved to generate an identity information list, which is bound to the subsequent blood pressure measurement result list, and then a blood pressure measurement report is output.

[0018] The aforementioned data collection and processing specifically: Step S31, display panel image collection: the information collection module controls the camera to collect the picture of the electronic blood pressure monitor display panel at the specified position, and transmits it to the data processing module after being inspected and passed by the image sharpness inspection module; Step S32, panel image correction: the image pre-processing module further performs corner point detection and affine transformation on the collected image to implement image correction; Step S33, symbol segmentation, recognition and result calculation: the character detection module and the character recognition module complete the independent segmentation of the symbols in the corrected image, perform symbol recognition on the independently segmented image using a threading method, extract important information in the recognized text by the regular expression filtering module, and calculate the average value and difference of the blood pressure measurement values.

[0019] Furthermore, in step S23, detecting and recognizing character information in the certificate image using a character detection module and a character recognition module, Character detection: using DBnet network to implement character detection, outputting image text segmentation result by the network based on segmentation method, converting the segmentation result image into a binary image using a preset threshold T, inserting the image binarization operation into the network for joint optimization, making the network adaptively predict the threshold value of each pixel in the image through 4 or more sampling operations, training the certificate information model using ICPR dataset, parsing and storing the text in a list, and performing recognition after training; Character recognition: Select CRNN+CTC to implement the recognition algorithm, extract character sequence features based on convolutional features by extracting features, select GRU with smaller computational cost, use Mobilenet for CNN, zoom the image of the image to a size of 32x640x32 under the condition of fixed aspect ratio, and become 1x8x512 after passing through CNN, set T=8 for LSTM, input the features into LSTM, in the actual recognition, consider the overlap, interruption and different intervals of the text, output the results using CTC, predict the spaces in the text by using the forward-backward algorithm of HMM according to the artificially specified space symbol, and finally enumerate all possible results to output the recognized character information.

[0020] JPEG0007671551000002.jpg92170

[0021] Although the preferred embodiments of the present invention have been described in detail above, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or alternatives without departing from the spirit of the present invention, and these equivalent modifications or alternatives are included in the scope defined by the claims of this application.

Claims

1. A standardized blood pressure measurement process control system, comprising a blood pressure measurement process control device and a built-in control module, wherein the blood pressure measurement process control device comprises a control module, a display screen, a control switch and an electronic blood pressure meter, the control module is for controlling the whole measurement process and displaying and outputting the result, the display screen is for performing human-machine interaction and displaying the measurement result, the control switch is for controlling the on and off of the electronic blood pressure meter, the electronic blood pressure meter is for implementing blood pressure measurement, and is installed inside the blood pressure measurement process control device by a fixed structure; The control module includes an information collection module, an image sharpness inspection module, a data processing module, and a blood pressure measurement process control module. The information collection module is for capturing user's identification card information and electronic blood pressure meter display panel information for each time, and sending the collected images to the image sharpness inspection module. The image sharpness inspection module is for performing a sharpness inspection on the collected images, and sending the images that pass the inspection to the data processing module. The data processing module includes an image pre-processing module, a character detection module, a character recognition module, and a regular expression filtering module. The image pre-processing module is for cropping the certificate image according to specifications and correcting the captured image of the electronic blood pressure meter display panel. The character detection module and the character recognition module are for filtering the certificate image and the blood pressure measurement information. a data processing module for recognizing and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image, the data processing module for detecting and detecting the text information in the result image,

2. The method for implementing the process control system for standardized blood pressure measurement includes: Step S1, system environment configuration: placing the blood pressure measurement process control device on a horizontal table, connecting it to a power source, turning on the power switch of the combined device, and putting the control system into a standby state; Step S2, identity information collection: the user places his / her identity card or medical insurance card at a designated photographing position, and the information collection module controls the camera to photograph and sample the user's identity card information; the collected photos are inspected by the image sharpness inspection module; and the photos that pass the inspection are sent to the data processing module to generate an identity information list; Step S3, data collection and processing: after the identity information is successfully collected, the blood pressure measurement control module controls the electronic blood pressure monitor to complete one set of blood pressure measurements for the user; the information collection module controls the camera to sample the data displayed on the electronic blood pressure monitor display panel every time; the data processing module recognizes and extracts the sampled data, and further calculates the average value and difference of the blood pressure measurement results, and obtains a blood pressure measurement result list; Step S4: Integrating, printing and uploading the measurement report: the data processing module includes a step of integrating the identification information list generated in step S2 with the blood pressure measurement result list in step S3, and then displaying the results on the display screen and uploading them to the hospital's HIS system or cloud server for storage. The process control system for standardized blood pressure measurement according to claim 1, characterized in that:

3. In step S2, the identity information is collected as follows: Step S21, certificate image collection: the user places the ID card or medical insurance card at the designated photo-taking position, and the information collection module controls the camera to take a photo, and the image sharpness check module checks the image sharpness. If the pixel value of the collected certificate image is less than the set threshold of 1080x960, an error message is returned, and the user is prompted to take a photo again and sample; if the pixel value of the collected certificate image is equal to or greater than the set threshold of 1080x960, step S32 is executed; Step S22, certificate image processing: the image pre-processing module uniformly crops the certificate image collected in step S31 into an image with an aspect ratio of 3:2, and performs grayscale processing; Step S23: certificate image recognition: using a character detection module and a character recognition module to detect and recognize character information in the processed certificate image, and perform regular expression filtering to obtain a character recognition result of the image; Step S24: storing and binding certificate information: according to the character recognition result obtained in step S33, storing the user's name, gender, and age information to generate an identity information list, binding it with the subsequent blood pressure measurement result list, and then outputting a blood pressure measurement report. The process control system for standardized blood pressure measurement according to claim 2, further comprising:

4. In step S3, data collection and processing is specifically performed as follows: Step S31, display panel image collection: the information collection module controls the camera to collect a picture of the electronic blood pressure monitor display panel at a specified position, and transmits the picture to the data processing module after being inspected and passed by the image sharpness inspection module; Step S32, panel image correction: the image pre-processing module further performs corner point detection and affine transformation on the collected image to implement image correction; The process control system of standardized blood pressure measurement according to claim 2, characterized in that the process control system includes the steps of: step S33, symbol segmentation, recognition and result calculation: the character detection module and the character recognition module complete the independent segmentation of the symbol in the corrected image, and using a threading method to perform symbol recognition on the independently segmented image, extracting important information in the recognized text by a regular expression filtering module, and calculating the average value and difference of the blood pressure measurement value.

5. In step S23, using a character detection module and a character recognition module to detect and recognize character information in the certificate image, Character detection: using DBnet network to implement character detection, outputting image text segmentation result by the network based on segmentation method, converting the segmentation result image into a binary image using a preset threshold T, inserting the image binarization operation into the network for joint optimization, making the network adaptively predict the threshold value of each pixel in the image through 4 or more sampling operations, training the certificate information model using ICPR dataset, parsing and storing the text into a list, and performing recognition after training; Character recognition: Select CRNN+CTC to implement the recognition algorithm; extract character sequence features based on convolution features by extracting features; select GRU with smaller computational cost; use Mobilenet for CNN; zoom the image of the image to a size of 32x640x32 under the condition of fixed aspect ratio, and become 1x8x512 after passing through CNN; set T=8 for LSTM; input the features into LSTM; in the actual recognition, consider the overlap, interruption and different intervals of the text, and use CTC to output the results; predict the blank space in the text by using the forward-backward algorithm of HMM according to the artificially designated blank symbol; and finally enumerate all possible results to output the recognized character information.

6.

Images