Medical device intelligent management system and method based on Internet of Things monitoring

Abstract

The present invention provides an intelligent management system and method for medical devices based on Internet of Things monitoring. The system includes an Internet of Things monitoring middle platform, an identity acquisition module, an Internet of Things tag recognition module, a device status recognition module, an association and binding module, and a data uploading module. The identity acquisition module acquires user identity information. The Internet of Things tag recognition module recognizes the Internet of Things tag of the target medical device to obtain the inbound and outbound information of the target medical device. The device status recognition module acquires the original device image of the target medical device at the time of warehousing, and obtains the status information of the target medical device based on the original device image. The association and binding module associates and binds the user identity information, the inbound and outbound information, and the status information to obtain the device usage record information of the target medical device. The data uploading module uploads the device usage record information to the blockchain for storage based on the user identity information. The present invention improves the accuracy of inventory data and the accuracy of status management of medical devices.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to an intelligent management system for medical devices based on Internet of Things monitoring. Background Art

[0002] Medical devices play a crucial role in modern medicine, and their management is crucial for ensuring medical quality, patient safety, and hospital operation efficiency.

[0003] Currently, the management of medical devices is mainly achieved through manual management methods. That is, for the incoming and outgoing inventory, usage records, etc. of medical devices, it still relies on manual paper records or simple spreadsheet entries. However, with the increase in incoming and outgoing inventory and usage records, manual entry is prone to human errors, such as data entry errors, missing records, etc., resulting in inaccurate inventory data of medical devices. When a medical device is returned to the warehouse after use, for the status of the medical device after being taken out and used, it is mainly recorded based on the judgment of doctors' experience. However, during the use process, the medical device may be subjected to improper operations (such as excessive bending, collision) and generate tiny damages that are difficult to detect with the naked eye, resulting in inaccurate status management of the medical device. Summary of the Invention

[0004] The present invention provides an intelligent management system and method for medical devices based on Internet of Things monitoring, aiming to improve the accuracy of inventory data and status management of medical devices.

[0005] In a first aspect, the present invention provides an intelligent management system for medical devices based on Internet of Things monitoring, including an Internet of Things monitoring middleware, an identity collection module, an Internet of Things tag identification module, a device status identification module, an association binding module, and a data blockchain module; the Internet of Things monitoring middleware is respectively connected to the identity collection module, the Internet of Things tag identification module, the device status identification module, the association binding module, and the data blockchain module to manage each module;

[0006] The Internet of Things monitoring middleware is used to respond to the outgoing request and the incoming request of the target medical device;

[0007] The identity collection module is used to collect user identity information;

[0008] The Internet of Things tag identification module is used to identify the Internet of Things tag of the target medical device to obtain the incoming and outgoing inventory information of the target medical device;

[0009] The device status identification module is used to collect the original device image of the target medical device when it is put into storage, and obtain the status information of the target medical device based on the original device image;

[0010] The associated binding module is used to associate and bind the user identity information, the inbound and outbound information, and the status information to obtain the device usage record information of the target medical device;

[0011] The data uploading module is used to upload the device usage record information to the blockchain for storage based on the user identity information.

[0012] In a second aspect, the present invention also provides an intelligent management method for medical devices based on Internet of Things monitoring, which is applied to the intelligent management system for medical devices based on Internet of Things monitoring described in the first aspect. The intelligent management method for medical devices based on Internet of Things monitoring includes:

[0013] In response to the outbound request of the target medical device, collect the user identity information and identify the Internet of Things tag of the target medical device to obtain the outbound information of the target medical device;

[0014] In response to the inbound request of the target medical device, identify the Internet of Things tag of the target medical device to obtain the inbound information of the target medical device;

[0015] Collect the original device image of the target medical device at the time of inbound, and obtain the status information of the target medical device based on the original device image;

[0016] Associate and bind the user identity information, the outbound information, the inbound information, and the status information to obtain the device usage record information of the target medical device;

[0017] Upload the device usage record information to the blockchain for storage based on the user identity information.

[0018] According to the intelligent management method for medical devices based on Internet of Things monitoring provided by the embodiments of the present invention, the device types of the target medical device include diagnostic type, treatment type, and monitoring type;

[0019] The collection of the original device image of the target medical device at the time of inbound includes:

[0020] If the device type is the diagnostic type, collect the multi-peak gray level histogram of the target medical device at the time of inbound as the original device image; if the device type is the treatment type, collect the skewed gray level histogram of the target medical device at the time of inbound as the original device image; if the device type is the monitoring type, collect the single-peak gray level histogram of the target medical device at the time of inbound as the original device image;

[0021] The obtaining of the status information of the target medical device based on the original device image includes:

[0022] Obtain the target gray pixel threshold of the original instrument image;

[0023] Segment the original instrument image based on the target gray pixel threshold to obtain the foreground image and background image of the original instrument image;

[0024] Eliminate the background image in the original instrument image to obtain the target instrument image;

[0025] Input the target instrument image into the defect detection model to obtain the defect detection result output by the defect detection model; the defect detection model is trained based on the sample image and its corresponding defect label;

[0026] Determine the status information of the target medical device based on the defect detection result.

[0027] According to the intelligent management method of medical devices based on Internet of Things monitoring provided by the embodiments of the present invention, the obtaining of the target gray pixel threshold of the original instrument image includes:

[0028] For the target medical device of the diagnosis type, segment the original instrument image based on each peak in the original instrument image to obtain a plurality of instrument sub-images; each of the instrument sub-images represents a sub-image corresponding to a peak;

[0029] For the first instrument sub-image with the maximum peak value, use the pixel point corresponding to the peak in the first instrument sub-image as the center and a first size range as the sliding window to obtain the first pixel point; determine the first gray pixel threshold based on the gray pixel value of the first pixel point;

[0030] For the second instrument sub-image with the minimum peak value, use the pixel point corresponding to the peak in the second instrument sub-image as the center and a second size range as the sliding window to obtain the second pixel point; determine the second gray pixel threshold based on the gray pixel value of the second pixel point;

[0031] For the third instrument sub-image other than the first instrument sub-image and the second instrument sub-image, use the pixel point corresponding to the peak in the third instrument sub-image as the center and a third size range as the sliding window to obtain the third pixel point; determine the third gray pixel threshold based on the gray pixel value of the third pixel point;

[0032] Determine the target gray pixel threshold based on the first gray pixel threshold, the second gray pixel threshold, and the third gray pixel threshold; the first size range is greater than the third size range, and the third size range is greater than the second size range.

[0033] For the intelligent management method of medical devices based on Internet of Things monitoring provided by an embodiment of the present invention, obtaining the target gray pixel threshold of the original device image includes:

[0034] For the target medical device of the treatment type, segment the original device image according to a preset area size to obtain a plurality of first image areas;

[0035] Determine the second image area based on the pixel density of each of the first image areas;

[0036] Based on the gray pixel values corresponding to the pixel points in each of the second image areas, determine the gray pixel threshold of each of the second image areas;

[0037] Determine the target gray pixel threshold based on the gray pixel thresholds of each of the second image areas.

[0038] For the intelligent management method of medical devices based on Internet of Things monitoring provided by an embodiment of the present invention, obtaining the target gray pixel threshold of the original device image includes:

[0039] For the target medical device of the monitoring type, take each pixel point corresponding to the quarter peak in the original device image as the center, and the first preset radius as the diffusion radius to obtain the fourth pixel points; determine the fourth gray pixel threshold based on the gray pixel values of the fourth pixel points;

[0040] Take each pixel point corresponding to the half peak in the original device image as the center, and the second preset radius as the diffusion radius to obtain the fifth pixel points; determine the fifth gray pixel threshold based on the gray pixel values of the fifth pixel points;

[0041] Take each pixel point corresponding to the three-quarter peak in the original device image as the center, and the third preset radius as the diffusion radius to obtain the sixth pixel points; determine the sixth gray pixel threshold based on the gray pixel values of the sixth pixel points;

[0042] Based on the fourth gray pixel threshold, the fifth gray pixel threshold, and the sixth gray pixel threshold, determine the target gray pixel threshold; the first preset radius is less than the second preset radius, and the second preset radius is less than the third preset radius.

[0043] For the intelligent management method of medical devices based on Internet of Things monitoring provided by an embodiment of the present invention, storing the device usage record information on the blockchain based on the user identity information includes:

[0044] Perform a hashing operation on the information of the instrument usage record to obtain a structure hash value; the structure hash value includes a first hash value corresponding to the user identity information, a second hash value corresponding to the outbound information, a third hash value corresponding to the inbound information, and a fourth hash value corresponding to the status information;

[0045] Generate an initial record structure based on the instrument usage record information and the structure hash value;

[0046] Query in the blockchain based on the first hash value to obtain the hash tree corresponding to the user identity information in the blockchain; the hash tree includes a root node, a parent node, and child nodes;

[0047] Encrypt the user identity information based on the root hash value of the root node, and generate a first target record structure based on the encrypted user identity information and the initial record structure;

[0048] Store the first target record structure into the hash tree based on the structure hash value.

[0049] According to the intelligent management method of medical devices based on Internet of Things monitoring provided by the embodiments of the present invention, storing the first target record structure into the hash tree based on the structure hash value includes:

[0050] Traverse in the hash tree with the fourth hash value as the first traversal index to obtain the parent node of the first target record structure in the hash tree;

[0051] Traverse in the child nodes of the parent node with the second hash value and the third hash value as the second traversal index to obtain the target child node in the parent node;

[0052] Concatenate the first target record structure with the second target record structure in the target child node and store it into the target child node.

[0053] In a third aspect, the present invention further provides an electronic device, including: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby implementing the intelligent management method of medical devices based on Internet of Things monitoring as described in any one of the above.

[0054] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium, in which a computer software program is stored, and when the computer software program is executed by a processor, the intelligent management method of medical devices based on Internet of Things monitoring as described in any one of the above is implemented.

[0055] Fifth aspect, the present invention further provides a computer program product, including a computer program, which when executed by a processor implements the intelligent management method of medical devices based on Internet of Things monitoring as described in any one of the above.

[0056] The intelligent management system of medical devices based on Internet of Things monitoring provided by the embodiments of the present invention automatically records the inbound and outbound information of target medical devices when they are in and out of the warehouse through the Internet of Things tag recognition module, without manual entry, thus avoiding human errors caused by manual entry and improving the accuracy of inventory data of medical devices. At the same time, the original device image of the target medical device when it is put into the warehouse is collected through the device status recognition module, and the status information of the target medical device is recognized based on the original device image. The device image can better highlight the detailed features of the target medical device. Therefore, it can accurately identify the minor damages that are difficult to be found by the naked eye, and improve the accuracy of the status management of medical devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is the structural diagram of the intelligent management system of medical devices based on Internet of Things monitoring provided by the present invention;

[0058] Figure 2 is the flowchart of the intelligent management method of medical devices based on Internet of Things monitoring provided by the present invention;

[0059] Figure 3 is the embodiment diagram of the electronic device provided by the embodiments of the present invention;

[0060] Figure 4 is the embodiment diagram of the computer-readable storage medium provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0062] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0063] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without the use of these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0064] Optionally, refer to Figure 1 as shown in Figure 1 is a structural diagram of the intelligent management system for medical devices based on Internet of Things monitoring provided by the present invention. The intelligent management system for medical devices based on Internet of Things monitoring includes an Internet of Things monitoring middle platform, an identity acquisition module, an Internet of Things tag recognition module, a device status recognition module, an association binding module, and a data uploading module. In the embodiments of the present invention, the Internet of Things monitoring middle platform is respectively connected to the identity acquisition module, the Internet of Things tag recognition module, the device status recognition module, the association binding module, and the data uploading module to manage each module.

[0065] Optionally, when users (such as doctors, nurses, etc.) use medical devices, they need to trigger an outbound request on the interactive screen of the intelligent management system for medical devices. When returning medical devices, they need to trigger an inbound request on the interactive screen of the intelligent management system for medical devices.

[0066] Furthermore, in the embodiments of the present invention, each medical device has its corresponding Internet of Things tag on its surface. Among them, the Internet of Things tags are such as near-field communication (NFC) tags, radio frequency identification (RFID) tags, Bluetooth low energy (BLE) tags, etc. The Internet of Things tags contain the basic information of the medical devices, and the basic information includes information such as device model, device specification, production batch, purchase date, device type, etc. At the same time, it is necessary to register the Internet of Things tags of the medical devices and the information such as device model, device specification, production batch, purchase date, device type, etc. contained therein into the intelligent management system for medical devices.

[0067] Furthermore, after the user triggers an outbound request for a target medical device on the interactive screen of the intelligent management system for medical devices, the Internet of Things monitoring middle platform responds to the outbound request of the target medical device and controls the identity acquisition module to collect the user identity information. Among them, the user identity information includes information such as user identity ID, user name, user department, user work permit, etc.

[0068] Further, the IoT tag recognition module recognizes the IoT tag of the target medical device to obtain the outbound information of the target medical device, where the outbound information includes information such as the outbound time, outbound handler, device name, device type, device serial number, etc.

[0069] Further, after the user triggers an inbound request for the target medical device on the interaction screen of the medical device intelligent management system, the IoT monitoring middleware responds to the inbound request of the target medical device, controls the IoT tag recognition module to recognize the IoT tag of the target medical device, and obtains the inbound information of the target medical device, where the inbound information includes information such as the inbound time, inbound inspector, device name, device type, device serial number, etc.

[0070] Further, when the IoT monitoring middleware responds to the inbound request of the target medical device, it is necessary to control the device status recognition module to collect the original device image of the target medical device at the time of inbound, where the original device image is the grayscale image of the target medical device. The device status recognition module obtains the status information of the target medical device according to the original device image, where the status information represents the integrity of the target medical device.

[0071] Further, the association and binding module associates and binds the user identity information, inbound and outbound information, and status information to obtain the device usage record information of the target medical device, where the association and binding rules are set according to the actual situation, or can be determined according to the type of the target medical device in combination with the mapping table in the system.

[0072] Further, the data uploading module uploads the device usage record information to the blockchain for storage according to the user identity information.

[0073] In the embodiment of the present invention, the IoT tag recognition module automatically records the inbound and outbound information of the target medical device during inbound and outbound, without manual entry, thus avoiding human errors caused by manual entry and improving the accuracy of the inventory data of medical devices. At the same time, the device status recognition module collects the original device image of the target medical device at the time of inbound, and based on the original device image, the status information of the target medical device is recognized. The device image can better highlight the detailed features of the target medical device. Therefore, it can accurately identify minor damages that are difficult to detect by the naked eye, improving the accuracy of the status management of medical devices.

[0074] Optionally, referring to Figure 2 , Figure 2 is the flowchart of the medical device intelligent management method based on IoT monitoring provided by the present invention. In the embodiment of the present invention, the execution subject of the medical device intelligent management method based on IoT monitoring is the medical device management system. Therefore, the medical device intelligent management method based on IoT monitoring includes:

[0075] Step 10: In response to the outbound request of the target medical device, collect the user identity information and identify the Internet of Things (IoT) tag of the target medical device to obtain the outbound information of the target medical device.

[0076] Optionally, when using a medical device, the user needs to trigger an outbound request on the interactive screen of the medical device management system. When returning a medical device, the user needs to trigger an inbound request on the interactive screen of the medical device management system. Further, in the embodiments of the present invention, each medical device has its corresponding IoT tag on its surface. The IoT tag can be, for example, a Near Field Communication (NFC) tag, a Radio Frequency Identification (RFID) tag, a Bluetooth Low Energy (BLE) tag, etc. The IoT tag contains the basic information of the medical device, and the basic information includes information such as device model, device specification, production batch, purchase date, device type, etc.

[0077] Optionally, it is necessary to register the IoT tag of the medical device and the information such as device model, device specification, production batch, purchase date, device type, etc. contained therein into the medical device management system.

[0078] Therefore, after the user triggers an outbound request for the target medical device on the interactive screen of the medical device management system, in response to the outbound request of the target medical device, collect the user identity information. The user identity information includes information such as user identity ID, user name, user department, user work permit, etc.

[0079] Further, the medical device management system identifies the IoT tag of the target medical device to obtain the outbound information of the target medical device. The outbound information includes information such as outbound time, outbound handler, device name, device type, device number, etc.

[0080] Step 20: In response to the inbound request of the target medical device, identify the IoT tag of the target medical device to obtain the inbound information of the target medical device.

[0081] Further, after the user triggers an inbound request for the target medical device on the interactive screen of the medical device management system, in response to the inbound request of the target medical device, identify the IoT tag of the target medical device to obtain the inbound information of the target medical device. The inbound information includes information such as inbound time, inbound inspector, device name, device type, device number, etc.

[0082] Step 30: Collect the original device image of the target medical device at the time of inbound, and obtain the status information of the target medical device based on the original device image.

[0083] Further, when the medical device management system responds to the warehousing request of the target medical device, it needs to collect the original device image of the target medical device at the time of warehousing. Among them, the original device image is the grayscale image of the target medical device. Further, the medical device management system obtains the status information of the target medical device according to the original device image. Among them, the status information characterizes the integrity of the target medical device, specifically as described in steps 301 to 305.

[0084] Step 40: Associate and bind the user identity information, outbound information, inbound information, and status information to obtain the device usage record information of the target medical device.

[0085] Further, the medical device management system associates and binds the user identity information, outbound information, inbound information, and status information to obtain the device usage record information of the target medical device. Among them, the association and binding rules are set according to the actual situation, and can also be determined according to the type of the target medical device in combination with the mapping table in the system. For example, the association and binding rule is to bind according to the order of user identity information - outbound / inbound information and status information.

[0086] Therefore, in one embodiment, the device usage record information of the target medical device can be expressed as device usage record information R = {U, O, I, S}, where U represents the user identity information, O represents the outbound information, I represents the inbound information, and S represents the status information.

[0087] Step 50: Based on the user identity information, upload the device usage record information to the blockchain for storage.

[0088] Further, the medical device management system uploads the device usage record information to the blockchain for storage according to the user identity information, specifically as described in steps 501 to 505.

[0089] In the embodiment of the present invention, the Internet of Things tag automatically records the inbound and outbound information of the target medical device during inbound and outbound, without manual entry, thus avoiding human errors caused by manual entry and improving the accuracy of the inventory data of medical devices. At the same time, by collecting the original device image of the target medical device at the time of warehousing and identifying the status information of the target medical device based on the original device image, since the device image can better highlight the detailed features of the target medical device, therefore, it can accurately identify tiny damages that are difficult to detect by the naked eye, improving the accuracy of the status management of medical devices.

[0090] In one embodiment, the device types of the target medical devices include diagnostic types, treatment types, and monitoring types. Among them, diagnostic medical devices such as ultrasonic diagnostic instruments, magnetic resonance imaging devices, computed tomography scanners, etc.; treatment medical devices such as laser therapy devices, microwave therapy devices, surgical instruments, etc.; monitoring medical devices such as wearable heart rate monitors, pulse oximeters, cardiac pacemakers, etc.

[0091] Furthermore, in order to ensure the accuracy of the status information of the target medical devices, for target medical devices of different device types, the original device images of the target medical devices at the time of warehousing are collected in different collection methods, where the collection methods include multi-modal gray-level histograms, skewed gray-level histograms, and unimodal gray-level histograms.

[0092] Among them, since diagnostic medical devices often have complex internal structures and components made of various different materials. For example, in an ultrasonic diagnostic instrument, it has a probe (containing various different acoustic materials and electronic components), a signal processing circuit, a display module, etc. Therefore, for target medical devices of the diagnostic device type, the multi-modal gray-level histogram of the target medical device at the time of warehousing is collected as the original device image.

[0093] Since treatment medical devices usually have one or several key functional components. For example, the laser emission module of a medical laser therapy device is the core component, and other components play auxiliary or supporting roles. Therefore, for target medical devices of the treatment device type, the skewed gray-level histogram of the target medical device at the time of warehousing is collected as the original device image.

[0094] Since the structures and materials of monitoring medical devices are usually relatively simple. For example, a wearable heart rate monitor is mainly composed of a housing (usually made of a single material such as plastic), a sensor (mostly a certain specific type of biosensor), and a simple circuit. Therefore, for target medical devices of the monitoring device type, the unimodal gray-level histogram of the target medical device at the time of warehousing is collected as the original device image.

[0095] In one embodiment, the descriptions of steps 301 to 305 include:

[0096] Step 301, obtain the target gray pixel threshold of the original device image.

[0097] Optionally, the medical device management system obtains the target gray pixel threshold of the original device image. Among them, for target medical devices of different device types, the method of obtaining their original device images is different, specifically as described in steps 3011 to 30113.

[0098] Step 302: Segment the original instrument image based on the target gray pixel threshold to obtain the foreground image and background image of the original instrument image.

[0099] Further, guided by the target gray pixel threshold, the medical device management system takes the pixel points in the original instrument image with gray pixel values less than the target gray pixel threshold as background pixel points, and the pixel points with gray pixel values greater than or equal to the target gray pixel threshold as foreground pixel points, and segments the original instrument image to obtain the foreground image and background image of the original instrument image. Among them, the foreground image is the image composed of foreground pixel points, and the background image is the image composed of background pixel points.

[0100] Step 303: Remove the background image in the original instrument image to obtain the target instrument image.

[0101] Step 304: Input the target instrument image into the defect detection model to obtain the defect detection result output by the defect detection model.

[0102] Optionally, the defect detection model is embedded in the medical device management system of the embodiment of the present invention. Among them, the defect detection model is obtained by training a preset neural network based on the sample image and its corresponding defect label. The preset neural network model can be a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), etc.

[0103] Further, the medical device management system removes the background image in the original instrument image and only retains the foreground image in the original instrument image to obtain the target instrument image. Further, the medical device management system inputs the target instrument image into the defect detection model to obtain the defect detection result output by the defect detection model. Among them, the defect detection result includes the defect type and the probability value of the defect type.

[0104] Step 305: Determine the status information of the target medical device based on the defect detection result.

[0105] Further, the medical device management system determines the defect type and the probability value of the defect type in the defect detection result, and determines the status information of the target medical device according to the defect type and the probability value of the defect type. In one embodiment, when the probability value is less than 0.1, it indicates that the defect type is normal; when the probability value is greater than or equal to 0.1 and less than 0.3, it indicates that the defect type is slightly damaged and repairable; when the probability value is greater than or equal to 0.3, it indicates that the defect type is severely damaged and irreparable.

[0106] In one embodiment, if the defect detection result is that there is no defect, the status information of the target medical device is that there is no damage. If the defect detection result is a scratch type and the probability value of the scratch type is 0.08, the status information of the target medical device is normal. If the defect detection result is a hole type and the probability value of the hole type is 0.5, the status information of the target medical device is severely damaged and irreparable.

[0107] In the embodiment of the present invention, by collecting the original device image of the target medical device when it is warehoused and identifying the status information of the target medical device based on the original device image. Since the device image can better highlight the detailed features of the target medical device, it can accurately identify the tiny damages that are difficult to be found by the naked eye, improving the accuracy of the status management of the medical device.

[0108] In one embodiment, for the target medical device of the diagnosis type, obtaining the target gray pixel threshold of the original device image includes steps 3011 to 3015:

[0109] Step 3011, perform image segmentation on the original device image based on each peak in the original device image to obtain a plurality of device sub-images.

[0110] Specifically, since there are multiple peaks in the original device image, the medical device management system performs image segmentation on the original device image according to each peak in the original device image to obtain a plurality of device sub-images. That is to say, each device sub-image represents the sub-image corresponding to a peak. The specific analysis is as follows:

[0111] In one embodiment, the original device image is I(x, y), where (x, y) represents the coordinates in the original device image. The peaks can be determined by a preset peak detection algorithm (such as the peak detection filter method, wavelet transform method, etc.). Therefore, after peak detection, the set of n peaks of the original device image is P = {p1, p2,..., p n}, where each peak p i (i = 1, 2,..., n) has its corresponding coordinate, peak value size and other information. Perform segmentation on the original device image through the peaks to obtain a set of n device sub-images as I sub = {I1, I2,..., I n}, where each device sub-image I j (j = 1, 2,..., n) corresponds to the sub-image of a peak.

[0112] Step 3012, for the first device sub-image with the maximum peak value, take the pixel point corresponding to the peak in the first device sub-image as the center and the first size range as the sliding window to obtain the first pixel point; determine the first gray pixel threshold based on the gray pixel value of the first pixel point.

[0113] Optionally, the first size range in the embodiments of the present invention is greater than the third size range, and the third size range is greater than the second size range. In one embodiment, the first size range is, for example, 6*6, the second size range is, for example, 3*3, and the third size range is, for example, 5*5, etc.

[0114] Further, for the first instrument sub-image of the maximum peak value, the medical device management system acquires the pixel points corresponding to the peaks in the first instrument sub-image, and takes the pixel points corresponding to the peaks in the first instrument sub-image as the center and the first size range as the sliding window to acquire the first pixel points.

[0115] Further, the medical device management system determines a first gray pixel threshold according to the gray pixel values of the first pixel points. The specific analysis process is as follows: The first instrument sub-image is I max , and the coordinates of the pixel points corresponding to the peaks are (x max , y max ). The first size range is set as W1*H1 (representing the width and height of the sliding window), then the set P1 of m first pixel points within the sliding window can be determined by the following method:

[0116]

[0117] Further, after acquiring the set of the first pixel points, the set of the gray pixel values of the m first pixel points is G1 = {g 11 , g 12 ,..., g 1m}, where g 1m represents the gray pixel value of the m-th first pixel point. The first gray pixel threshold calculated according to the gray pixel values of the m first pixel points is as follows:

[0118]

[0119] where T1 represents the first gray pixel threshold, g 1i represents the gray pixel value of the i-th first pixel point, w(g 1i ) represents the weight coefficient corresponding to the gray pixel value of the i-th first pixel point, e represents the base of the exponential function, α represents a preset adjustment parameter, represents the mean value of the gray pixel values of the m first pixel points.

[0120] Step 3013, for the second instrument sub-image of the minimum peak value, take the pixel points corresponding to the peaks in the second instrument sub-image as the center and the second size range as the sliding window to acquire the second pixel points; determine a second gray pixel threshold based on the gray pixel values of the second pixel points.

[0121] Further, for the second instrument sub-image with the minimum peak value, the medical device management system obtains the pixel points corresponding to the peaks in the second instrument sub-image, and takes the pixel points corresponding to the peaks in the second instrument sub-image as the center and the second size range as the sliding window to obtain the second pixel points.

[0122] Further, the medical device management system determines the second gray pixel threshold based on the gray pixel values of the second pixel points. The specific analysis process is as follows: The second instrument sub-image is I min , and the pixel point coordinates corresponding to the peak are (x min , y min ). The second size range is set as W2*H2, and the set P2 of k second pixel points within the sliding window can be determined by the following method:

[0123]

[0124] Further, after obtaining the set of second pixel points, the set of gray pixel values of the k second pixel points is G2 = {g 21 , g 22 ,..., g 2k}, where g 2k represents the gray pixel value of the k-th second pixel point. The second gray pixel threshold is calculated based on the gray pixel values of the k second pixel points. The formula is as follows:

[0125]

[0126] Among them, T2 represents the second gray pixel threshold, g 2i represents the gray pixel value of the i-th second pixel point; C 2i represents the local contrast of the i-th second pixel point, and the size of its surrounding neighborhood is r; N r (g 2i ) represents the set of neighborhood pixel points with a radius of r for the i-th second pixel point, (x', y') represents the coordinates corresponding to any pixel point in the set of neighborhood pixel points, and g 2(x',y') represents the gray pixel value corresponding to the pixel point (x', y'), and |N r (g 2i )| represents the sum of the gray pixel values of all pixel points in the set of neighborhood pixel points.

[0127] Step 3014: For the third instrument sub-image other than the first instrument sub-image and the second instrument sub-image, take the pixel points corresponding to the peaks in the third instrument sub-image as the center and the third size range as the sliding window to obtain the third pixel points; determine the third gray pixel threshold based on the gray pixel values of the third pixel points.

[0128] Optionally, the third instrument sub-image in the embodiments of the present invention is an instrument sub-image other than the first instrument sub-image and the second instrument sub-image, that is, the third instrument sub-image is an instrument sub-image whose peak value is between the maximum peak value and the minimum peak value. The third size range includes a first target size range and a second target size range, and the first target size range is larger than the second target size range.

[0129] Therefore, the medical device management system determines the peak difference according to the maximum peak value and the minimum peak value.

[0130] Further, for the first target instrument sub-image in the third instrument sub-image, the peak value of the first target instrument sub-image is greater than or equal to the peak difference. The medical device management system acquires the pixel points corresponding to the peak in the first target instrument sub-image, and takes the pixel points corresponding to the peak in the first target instrument sub-image as the center and the first target size range as the sliding window to acquire the first target pixel points. Further, the medical device management system calculates the average value of the gray pixel values corresponding to all the first target pixel points to obtain the first target gray pixel threshold of the first target instrument sub-image.

[0131] Further, for the second target instrument sub-image in the third instrument sub-image, the peak value of the second target instrument sub-image is less than the peak difference. The medical device management system acquires the pixel points corresponding to the peak in the second target instrument sub-image, and takes the pixel points corresponding to the peak in the second target instrument sub-image as the center and the second target size range as the sliding window to acquire the second target pixel points. Further, the medical device management system calculates the average value of the gray pixel values corresponding to all the second target pixel points to obtain the second target gray pixel threshold of the second target instrument sub-image.

[0132] Further, the medical device management system determines the first target gray pixel threshold and the second target gray pixel threshold as the third gray pixel threshold.

[0133] Step 3015, determine the target gray pixel threshold based on the first gray pixel threshold, the second gray pixel threshold, and the third gray pixel threshold.

[0134] Further, the medical device management system calculates according to the first gray pixel threshold, the second gray pixel threshold, the first target gray pixel threshold, the second target gray pixel threshold and their corresponding weight coefficients to obtain the target gray pixel threshold. The specific calculation formula is as follows:

[0135] T(Gray)=T1*w1+T2*w2+T 31 *w 31 +T 32 *w 32 ;

[0136] w1 + w2 + w3 + w4 = 1;

[0137] Wherein, T(Gray) represents the target gray pixel threshold, T 31 represents the first target gray pixel threshold, T 32 represents the second target gray pixel threshold, w1, w2, w 31 , w 32 represents the weight coefficient.

[0138] In the embodiment of the present invention, for the target medical device of the diagnosis type, the target gray pixel threshold can be accurately obtained. Therefore, the target device image can be obtained according to the target gray pixel threshold subsequently, so that the state information of the target medical device can be accurately identified, and the accuracy of the state management of the medical device is improved.

[0139] In one embodiment, for the target medical device of the treatment type, obtaining the target gray pixel threshold of the original device image includes steps 3016 to 3019:

[0140] Step 3016, segment the original device image according to the preset region size to obtain a plurality of first image regions.

[0141] Specifically, since there are different pixel densities in the original device image, the medical device management system segments the original device image according to the preset region size to obtain a plurality of first image regions. Among them, the preset region size is set according to the actual situation, and the specific analysis is as follows:

[0142] In one embodiment, the original device image is I(x, y), where the size of the original device image is M*N (M is the number of pixels in the height direction, and N is the number of pixels in the width direction), and the preset region size is Z*C (Z is the segmentation size in the height direction, and C is the segmentation size in the width direction). Therefore, the number of first image regions obtained by segmenting the original device image I(x, y) is:

[0143] Wherein, represents rounding down.

[0144] For the i-th first image region I 1i , its coordinate range can be expressed as from L1 to L2, where:

[0145] Wherein, % represents the modulo operation.

[0146]

[0147] Step 3017, determine the second image region based on the pixel density of each first image region.

[0148] Furthermore, the medical device management system determines a second image region based on the pixel density of each first image region. The specific analysis process is as follows:

[0149] For each first image region I 1i , calculate its pixel density D i . In one embodiment, the total number of pixels in each first image region I 1i is P 1i . Calculate the pixel density D 1i of each first image region I i using the following specific formula:

[0150]

[0151] where d ij represents the density contribution value of each pixel point (x 1i , y j ) in the first image region I j within the entire first image region I 1i . K(x, y) represents a two-dimensional Gaussian kernel function, σ represents the standard deviation of the Gaussian kernel, and e represents the base of the exponential function.

[0152] Furthermore, the medical device management system compares the pixel density D i of each first image region with a density threshold θ. If the pixel density is greater than or equal to the density threshold θ, the first image region corresponding to this pixel density is determined as the second image region I 2k (here k is equal to the number of pixel densities that are greater than or equal to the density threshold θ).

[0153] Step 3018: Determine the grayscale pixel threshold for each second image region based on the grayscale pixel values corresponding to the pixel points in each second image region.

[0154] Furthermore, the medical device management system determines the grayscale pixel threshold for each second image region according to the grayscale pixel values corresponding to the pixel points in each second image region. The specific analysis process is as follows:

[0155] For each second image region I 2k , obtain the number H 2k (g) of pixel points with a grayscale pixel value of g, where g represents the grayscale pixel value, usually in the range of 0 - 255. The specific calculation formula is as follows:

[0156]

[0157] H total (t) = H in(t) + H between (t);

[0158]

[0159] wherein, T 2k represents the gray pixel threshold in each second image region, represents the t value that maximizes H total (t); H total (t) represents the total entropy, t represents the temporary threshold variable, H between (t) represents the between-class entropy, H in (t) represents the within-class entropy, P 2k (g) represents the probability of a pixel point with a gray value of g in the second image region I 2k .

[0160] Step 3019, determine the target gray pixel threshold based on the gray pixel threshold of each second image region.

[0161] Furthermore, the medical device management system determines the target gray pixel threshold according to the gray pixel threshold of each second image region. The specific analysis process is as follows:

[0162] Obtain the number n2 of second image regions. For the gray pixel threshold T 2k of each second image region, determine the corresponding weight value according to its region size and the number of pixel points. The specific calculation formula is:

[0163]

[0164] wherein, w 2k represents the weight value of the gray pixel threshold of each second image region, S 2k represents the area of each second image region (calculated by the number of pixel points); S total represents the total number of pixel points, P 2k represents the total number of pixel points in each second image region.

[0165] Furthermore, according to the gray pixel threshold T 2k of each second image region and its corresponding weight value w 2k , calculate the target gray pixel threshold T(Gray). The specific formula is as follows:

[0166]

[0167] In an embodiment of the present invention, for a target medical device of a treatment type, the target gray pixel threshold can be accurately obtained. Therefore, the target device image can be obtained according to the target gray pixel threshold subsequently, so that the state information of the target medical device can be accurately identified, and the accuracy of the state management of the medical device is improved.

[0168] In one embodiment, for a target medical device of a monitoring type, obtaining the target gray pixel threshold of the original device image includes steps 30110 to 30113:

[0169] Step 30110: Taking each pixel point corresponding to a quarter of the peak value in the original device image as the center and the first preset radius as the diffusion radius, obtaining the fourth pixel points; determining the fourth gray pixel threshold based on the gray pixel values of the fourth pixel points;

[0170] Step 30111: Taking each pixel point corresponding to a half of the peak value in the original device image as the center and the second preset radius as the diffusion radius, obtaining the fifth pixel points; determining the fifth gray pixel threshold based on the gray pixel values of the fifth pixel points;

[0171] Step 30112: Taking each pixel point corresponding to three - quarters of the peak value in the original device image as the center and the third preset radius as the diffusion radius, obtaining the sixth pixel points; determining the sixth gray pixel threshold based on the gray pixel values of the sixth pixel points;

[0172] Step 30113: Determining the target gray pixel threshold based on the fourth gray pixel threshold, the fifth gray pixel threshold, and the sixth gray pixel threshold.

[0173] In an embodiment of the present invention, the first preset radius is less than the second preset radius, and the second preset radius is less than the third preset radius. In one embodiment, for example, the first preset radius r1 = 3, the second preset radius r2 = 5, and the third preset radius r3 = 6.

[0174] Specifically, the medical device management system takes each pixel point corresponding to a quarter of the peak value in the original device image as the center and the first preset radius as the diffusion radius, obtains the fourth pixel points, and performs an average calculation based on the gray pixel values of each fourth pixel point to obtain the fourth gray pixel threshold.

[0175] Further, the medical device management system takes each pixel point corresponding to a half of the peak value in the original device image as the center and the second preset radius as the diffusion radius, obtains the fifth pixel points, and performs an average calculation based on the gray pixel values of each fifth pixel point to obtain the fifth gray pixel threshold.

[0176] Further, the medical device management system takes each pixel point corresponding to three - quarters of the peak value in the original device image as the center and the third preset radius as the diffusion radius to obtain the sixth pixel points, and calculates the average value based on the gray - scale pixel values of each sixth pixel point to obtain the sixth gray - scale pixel threshold.

[0177] Further, the medical device management system performs weighted calculation according to the fourth gray - scale pixel threshold, the fifth gray - scale pixel threshold, the sixth gray - scale pixel threshold and their corresponding weight coefficients to obtain the target gray - scale pixel threshold. The specific calculation formula is as follows:

[0178] T(Gray)=T4*w4+T5*w5+T6*w6;

[0179] w4 + 2w5 + 2w6=1;

[0180] Wherein, T(Gray) represents the target gray - scale pixel threshold, T4 represents the fourth gray - scale pixel threshold, T5 represents the fifth gray - scale pixel threshold, T6 represents the sixth gray - scale pixel threshold, and w4, w5, w6 represent the weight coefficients.

[0181] The embodiment of the present invention can accurately obtain the target gray - scale pixel threshold for the target medical device of the monitoring type. Therefore, the target device image can be obtained according to the target gray - scale pixel threshold subsequently, so that the state information of the target medical device can be accurately identified, and the accuracy of the state management of the medical device is improved.

[0182] In one embodiment, the descriptions of steps 501 to 505 are as follows:

[0183] Step 501: Perform a hash operation on the device usage record information to obtain a structure hash value.

[0184] Step 502: Generate an initial record structure based on the device usage record information and the structure hash value.

[0185] Specifically, the device usage record information can be expressed as R = {U, O, I, S}, where U represents user identity information, O represents outbound information, I represents inbound information, and S represents status information.

[0186] Further, in order to ensure the integrity and verifiability of data in the embodiment of the present invention, the medical device management system performs a hash operation on the device usage record information to obtain the structure hash value corresponding to the device usage record information. Therefore, the structure hash value includes the first hash value corresponding to the user identity information, the second hash value corresponding to the outbound information, the third hash value corresponding to the inbound information, and the fourth hash value corresponding to the status information. In one embodiment, the hash operation process is as follows: The first hash value h U = Hash(U), the second hash value h O= Hash(O), the third hash value h I = Hash(I), the fourth hash value h S = Hash(S), where Hash() represents a hash function, such as the SHA-256 hash algorithm.

[0187] Further, the medical device management system concatenates the device usage record information and the structure hash value to generate an initial record structure R c = {U, O, I, S, h U , h O , h I , h S}.

[0188] Step 503: Query in the blockchain based on the first hash value to obtain the hash tree corresponding to the user identity information in the blockchain.

[0189] Further, the medical device management system queries in the blockchain through the first hash value h U to obtain the hash tree that matches the first hash value h U , that is, the hash tree corresponding to the user identity information in the blockchain. The hash tree in the embodiments of the present invention can be understood as a binary tree. Therefore, the hash tree includes a root node, multiple parent nodes, and multiple child nodes.

[0190] Step 504: Encrypt the user identity information based on the root hash value of the root node, and generate a first target record structure based on the encrypted user identity information and the initial record structure.

[0191] Further, the medical device management system obtains the root hash value h root of the root node, uses the root hash value h root as the private key, and uses the first hash value h U public key to digitally sign and encrypt the user identity information to obtain the encrypted user identity information. Therefore, the encrypted user identity information can be expressed as where Sign represents a digital signature algorithm, and the digital signature algorithm is such as ECDSA (Elliptic Curve Digital Signature Algorithm).

[0192] Further, the medical device management system fuses the encrypted user identity information and the initial record structure to generate a first target record structure. Therefore, the first target record structure can be expressed as

[0193] Step 505: Store the first target record structure in the hash tree based on the structure hash value.

[0194] Further, the medical device management system stores the first target record structure in the hash tree according to the second hash value, the third hash value, and the fourth hash value in the structure hash value, as specifically described in steps 5051 to 5053.

[0195] In the embodiment of the present invention, the device usage record information is stored in the hash tree of the blockchain. Since any tampering with the device usage record information will cause the hash value of its corresponding branch to change, data tampering can be prevented, ensuring the authenticity and security of the data. At the same time, the hierarchical structure of the hash tree fits well with the storage structure of the blockchain, which can organize the device usage record information and facilitate storage management and retrieval in the blockchain network, helping to quickly locate and query.

[0196] In one embodiment, the descriptions of steps 5051 to 5053 are as follows:

[0197] Step 5051: Traverse the hash tree with the fourth hash value as the first traversal index to obtain the parent node of the first target record structure in the hash tree.

[0198] Step 5052: Traverse the child nodes of the parent node with the second hash value and the third hash value as the second traversal index to obtain the target child node in the parent node.

[0199] Step 5053: Concatenate the first target record structure with the second target record structure in the target child node and store it in the target child node.

[0200] Specifically, the medical device management system first traverses the hash tree with the fourth hash value corresponding to the status information as the first traversal index, obtains the parent node in the hash tree with the same hash value as the fourth hash value, and determines this parent node as the parent node of the first target record structure in the hash tree. If no parent node with the same hash value as the fourth hash value is traversed in the hash tree, a new parent node is created under the root node, and the first target record structure is stored as a child node of this new parent node in the hash tree.

[0201] Further, for the case where there is a parent node with the same hash value as the fourth hash value, the medical device management system traverses the child nodes of this parent node with the second hash value corresponding to the outbound information and the third hash value corresponding to the inbound information as the second traversal index, obtains the child node in this parent node with the same hash values as both the second hash value and the third hash value, and determines this child node as the target child node of the first target record structure in the parent node. If no child node with the same hash values as both the second hash value and the third hash value is traversed in this parent node, a new child node is created under this parent node, and the first target record structure is stored as this new child node in the hash tree.

[0202] Further, for the case where there are child nodes with the same second hash value and third hash value, the medical device management system splices the first target record structure R1 with the second target record structure R2 in the target child node and stores it in the target child node. Therefore, the record structure R in the target child node total can represent || represents splicing.

[0203] In the embodiment of the present invention, the device usage record information is stored in the hash tree of the blockchain. Since any tampering with the device usage record information will cause the hash value of its corresponding branch to change, data tampering can be prevented, ensuring the authenticity and security of the data. At the same time, the hierarchical structure of the hash tree fits well with the storage structure of the blockchain, which can organize the device usage record information, facilitating storage management and retrieval in the blockchain network and helping to quickly locate and query.

[0204] Please refer to Figure 3 , Figure 3 which is the embodiment diagram of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored on the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0205] Respond to the outbound request of the target medical device, collect user identity information, and identify the Internet of Things tag of the target medical device to obtain the outbound information of the target medical device;

[0206] Respond to the inbound request of the target medical device, identify the Internet of Things tag of the target medical device to obtain the inbound information of the target medical device;

[0207] Collect the original device image when the target medical device is put into storage, and obtain the status information of the target medical device based on the original device image;

[0208] Associate and bind the user identity information, outbound information, inbound information, and status information to obtain the device usage record information of the target medical device;

[0209] Based on the user identity information, upload the device usage record information to the blockchain for storage.

[0210] Please refer to Figure 4 , Figure 4 which is the embodiment diagram of the computer-readable storage medium provided by the embodiment of the present invention. As Figure 4As shown in the figure, this embodiment provides a computer-readable storage medium 400, on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0211] In response to the outbound request of the target medical device, collect the user identity information and identify the Internet of Things tag of the target medical device to obtain the outbound information of the target medical device;

[0212] In response to the inbound request of the target medical device, identify the Internet of Things tag of the target medical device to obtain the inbound information of the target medical device;

[0213] Collect the original device image of the target medical device at the time of inbound, and obtain the status information of the target medical device based on the original device image;

[0214] Associate and bind the user identity information, outbound information, inbound information, and status information to obtain the device usage record information of the target medical device;

[0215] Based on the user identity information, upload the device usage record information to the blockchain for storage.

[0216] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the intelligent management method of medical devices based on Internet of Things monitoring provided by the above methods. The method includes:

[0217] In response to the outbound request of the target medical device, collect the user identity information and identify the Internet of Things tag of the target medical device to obtain the outbound information of the target medical device;

[0218] In response to the inbound request of the target medical device, identify the Internet of Things tag of the target medical device to obtain the inbound information of the target medical device;

[0219] Collect the original device image of the target medical device at the time of inbound, and obtain the status information of the target medical device based on the original device image;

[0220] Associate and bind the user identity information, outbound information, inbound information, and status information to obtain the device usage record information of the target medical device;

[0221] Based on the user identity information, upload the device usage record information to the blockchain for storage.

[0222] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0223] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0224] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A medical device intelligent management method based on Internet of Things monitoring, characterized in that: include: Responding to the outbound delivery request of the target medical device, collecting user identity information, and identifying the IoT tag of the target medical device to obtain the outbound delivery information of the target medical device; Responding to the storage request of the target medical device, identifying the Internet of Things tag of the target medical device, and obtaining the storage information of the target medical device; Collecting an original device image of the target medical device when it is put into storage, and acquiring status information of the target medical device based on the original device image; Associating and binding the user identity information, the outbound information, the inbound information, and the status information to obtain the device usage record information of the target medical device; Uploading the device usage record information to the blockchain for storage based on the user identity information; Wherein, in the step of obtaining the status information of the target medical device, the original device image is first segmented based on the target grayscale pixel threshold and the background image is removed, including: For a target medical device of a diagnostic type, a multi-peak grayscale histogram of the target medical device when it is put into storage is collected as an original device image; For the first instrument sub-image with the maximum peak value, a first size range is set as a first sliding window with a pixel point corresponding to the peak in the first instrument sub-image as the center, and a first pixel point in the first sliding window is obtained; a first grayscale pixel threshold is determined based on the grayscale pixel value of the first pixel point; For the second instrument sub-image with the minimum peak value, a second size range is set as a second sliding window with the pixel point corresponding to the peak in the second instrument sub-image as the center, and a second pixel point in the second sliding window is obtained; and a second grayscale pixel threshold is determined based on the grayscale pixel value of the second pixel point; Determine a peak difference according to the maximum peak value and the minimum peak value; for a third instrument sub-image other than the first instrument sub-image and the second instrument sub-image, set a third size range as a third sliding window with a pixel point corresponding to the peak in the third instrument sub-image as the center, and obtain a third pixel point in the third sliding window; determine a third grayscale pixel threshold based on the grayscale pixel value of the third pixel point; The first size range is larger than the third size range, and the third size range is larger than the second size range; the third size range includes a first target size range and a second target size range, and the first target size range is larger than the second target size range; when the peak value of the third instrument sub-image is greater than or equal to the peak difference, the third size range is set to the first target size range, otherwise it is set to the second target size range; The target grayscale pixel threshold is determined based on the first grayscale pixel threshold, the second grayscale pixel threshold, and the third grayscale pixel threshold.

2. The intelligent management method of medical equipment based on Internet of Things monitoring according to claim 1 is characterized in that: The collecting of the original device image of the target medical device when it is put into storage includes: If the device type is a treatment type, a skewed grayscale histogram of the target medical device when it is put into storage is collected as an original device image; If the device type is a monitoring type, a unimodal grayscale histogram of the target medical device when it is put into storage is collected as the original device image; The acquiring the status information of the target medical device based on the original device image includes: Obtaining a target grayscale pixel threshold of the original device image; Segmenting the original instrument image based on the target grayscale pixel threshold to obtain a foreground image and a background image of the original instrument image; Eliminating the background image in the original device image to obtain a target device image; Inputting the target device image into a defect detection model to obtain a defect detection result output by the defect detection model; the defect detection model is trained based on sample images and their corresponding defect labels; The status information of the target medical device is determined based on the defect detection result.

3. The intelligent management method of medical equipment based on Internet of Things monitoring according to claim 2 is characterized in that: The step of obtaining a target grayscale pixel threshold of the original device image includes: For a target medical device of a treatment type, segmenting the original device image according to a preset area size to obtain a plurality of first image areas; Determining the first image area as the second image area when the density of pixels in the first image area is greater than a density threshold; Determine a grayscale pixel threshold of each second image region based on a grayscale pixel value corresponding to a pixel point in each second image region; The target grayscale pixel threshold is determined based on the grayscale pixel threshold of each of the second image regions.

4. The intelligent management method of medical equipment based on Internet of Things monitoring according to claim 2 is characterized in that: The step of obtaining a target grayscale pixel threshold of the original device image includes: For a target medical device of the monitoring type, taking each pixel corresponding to a quarter peak value in the original device image as the center and the first preset radius as the diffusion radius, a fourth pixel point is obtained; and a fourth grayscale pixel threshold is determined based on the grayscale pixel value of the fourth pixel point; Taking each pixel corresponding to one-half peak value in the original device image as the center and the second preset radius as the diffusion radius, a fifth pixel point is obtained; and a fifth grayscale pixel threshold is determined based on the grayscale pixel value of the fifth pixel point; Taking each pixel point corresponding to three-quarters of the peak value in the original device image as the center and the third preset radius as the diffusion radius, a sixth pixel point is obtained; Determine a sixth grayscale pixel threshold based on the grayscale pixel value of the sixth pixel point; The first preset radius is smaller than the second preset radius, and the second preset radius is smaller than the third preset radius; The target grayscale pixel threshold is determined based on the fourth grayscale pixel threshold, the fifth grayscale pixel threshold and the sixth grayscale pixel threshold.

5. The intelligent management method of medical equipment based on Internet of Things monitoring according to any one of claims 1 to 4, characterized in that: The step of uploading the device usage record information to a blockchain for storage based on the user identity information includes: Performing a hash operation on the device usage record information to obtain a structure hash value; the structure hash value includes a first hash value corresponding to the user identity information, a second hash value corresponding to the outbound information, a third hash value corresponding to the inbound information, and a fourth hash value corresponding to the status information; Generate an initial record structure based on the device usage record information and the structure hash value; Based on the first hash value, query the blockchain to obtain a hash tree corresponding to the user identity information in the blockchain; the hash tree includes a root node, a parent node, and a child node; Encrypting the user identity information based on the root hash value of the root node, and generating a first target record structure based on the encrypted user identity information and the initial record structure; The first target record structure is stored in the hash tree based on the structure hash value.

6. The intelligent management method of medical equipment based on Internet of Things monitoring according to claim 5 is characterized in that: The storing the first target record structure into the hash tree based on the structure hash value includes: Using the fourth hash value as a first traversal index to traverse the hash tree, and obtaining a parent node of the first target record structure in the hash tree; Using the second hash value and the third hash value as a second traversal index, traverse the child nodes of the parent node to obtain a target child node in the parent node; The first target record structure is concatenated with the second target record structure in the target subnode and stored in the target subnode.

7. An intelligent management system for medical devices based on Internet of Things monitoring, applied to the intelligent management method for medical devices based on Internet of Things monitoring as claimed in any one of claims 1 to 6, characterized in that: It includes IoT monitoring platform, identity collection module, IoT tag recognition module, device status recognition module, association binding module and data uploading module; The IoT monitoring center is respectively connected to the identity acquisition module, the IoT tag identification module, the device status identification module, the association binding module and the data uplink module to manage each module; The IoT monitoring middle platform is used to respond to the outbound request of the target medical device and the inbound request of the target medical device; The identity collection module is used to collect user identity information; The Internet of Things tag recognition module is used to identify the Internet of Things tag of the target medical device and obtain the storage and outbound information of the target medical device; The device status recognition module is used to collect the original device image of the target medical device when it is put into storage, and obtain the status information of the target medical device based on the original device image; The association and binding module is used to associate and bind the user identity information, the storage information and the status information to obtain the device usage record information of the target medical device; The data uploading module is used to upload the device usage record information to the blockchain for storage based on the user identity information.

8. An electronic device, comprising: A memory and a processor, characterized in that a computer software program is stored in the memory, and when the processor reads and executes the computer software program, the intelligent management method of medical equipment based on Internet of Things monitoring as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the intelligent management method of medical equipment based on Internet of Things monitoring as described in any one of claims 1 to 6 is implemented.

Images