CN117224778A

CN117224778A - Infusion alarm method, device, equipment and system

Info

Publication number: CN117224778A
Application number: CN202211440630.1A
Authority: CN
Inventors: 方建才; 刘陈林
Original assignee: Hangzhou Haikang Huiying Technology Co ltd
Current assignee: Hangzhou Haikang Huiying Technology Co ltd
Priority date: 2022-11-17
Filing date: 2022-11-17
Publication date: 2023-12-15

Abstract

The application provides an infusion alarm method, device, equipment and system, wherein the method comprises the following steps: acquiring a target image corresponding to an infusion object of a target scene; determining position information corresponding to an infusion device based on a target image, wherein the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube; intercepting a first sub-image of the infusion tube from a target image based on a first target position; detecting whether bubbles exist in the infusion tube or not based on the first sub-image; if bubbles exist in the infusion tube, alarm information is sent out, and the alarm information comprises a first alarm code aiming at the bubbles. By the technical scheme, the alarm information can be timely pushed to the nursing object, and additional deployment cost and operation cost are not required to be increased.

Description

Infusion alarm method, device, equipment and system

Technical Field

The application relates to the field of image recognition, in particular to an infusion alarm method, device, equipment and system.

Background

When an infusion object (such as a patient) infuses in a hospital, a nursing object (such as a nurse or a family member) is usually needed to nurse, and when the liquid infusion is finished, the nursing object needs to be treated in time, and if the nursing object is not nursed, great trouble and even danger are brought to the infusion object. Therefore, the infusion alarm device is provided, the infusion alarm device can detect whether liquid exists in the infusion bottle, and can give an alarm to prompt a nursing object to pull out the infusion tube once the liquid does not exist in the infusion bottle, so that the burden of the nursing object is reduced.

For example, the infusion alarm device can be arranged on (e.g. clamped on) an infusion bottle, and the photoelectric non-contact type is used for detecting whether the infusion bottle is filled with liquid or not, and when the infusion bottle is not filled with liquid, an electric signal is generated, so that the infusion alarm device is triggered to give an alarm. However, in the above-described method, an additional transfusion alarm device is required to be installed on the transfusion bottle, which is relatively costly and complicated to deploy. Because the infusion alarm device is required to be installed on the infusion bottle, when the infusion bottle is replaced, the infusion alarm device is required to be taken down from one infusion bottle to another infusion bottle, the operation cost of a nursing object is increased, and the operation is troublesome.

Disclosure of Invention

The application provides an infusion alarm method, which comprises the following steps:

acquiring a target image corresponding to an infusion object of a target scene;

determining position information corresponding to the infusion device based on the target image; the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube;

intercepting a first sub-image of the infusion tube from the target image based on the first target position;

detecting whether bubbles exist in the infusion tube or not based on the first sub-image; if bubbles exist in the infusion tube, alarm information is sent out, and the alarm information comprises a first alarm code aiming at the bubbles.

The application provides an infusion alarm device, which comprises:

the acquisition module is used for acquiring a target image corresponding to an infusion object of a target scene;

the determining module is used for determining the position information corresponding to the infusion device based on the target image; the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube; intercepting a first sub-image of the infusion tube from the target image based on the first target position; detecting whether bubbles exist in the infusion tube or not based on the first sub-image;

and the alarm module is used for sending alarm information if bubbles exist in the infusion tube, and the alarm information comprises a first alarm code aiming at the bubbles.

The present application provides a video analysis apparatus comprising: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute machine-executable instructions to implement the infusion alert method of the above example.

The application provides an infusion alarm system, comprising:

the video acquisition unit is used for acquiring a target image corresponding to an infusion object of a target scene;

The video analysis unit is used for acquiring the target image from the video acquisition unit and determining the position information corresponding to the infusion device based on the target image; the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube; intercepting a first sub-image of the infusion tube from the target image based on the first target position; detecting whether bubbles exist in the infusion tube or not based on the first sub-image; if bubbles exist in the infusion tube, sending information of the bubbles existing in the infusion tube to an alarm control unit;

the alarm control unit is used for sending out alarm information aiming at the transfusion object when bubbles exist in the transfusion tube, and the alarm information comprises a first alarm code aiming at the bubbles;

the video analysis unit and the alarm control unit are deployed in video analysis equipment, the video analysis equipment and the video acquisition equipment are deployed in the same equipment, or the video analysis equipment and the video acquisition equipment are deployed in different equipment.

According to the technical scheme, whether the air bubble exists in the infusion tube or not can be determined based on the target image corresponding to the infusion object, if the air bubble exists in the infusion tube, the alarm information aiming at the infusion object is sent out, so that the alarm information is timely pushed to the nursing object, the infusion object can be monitored in all directions, an infusion alarm device is not required to be additionally installed, additional deployment cost and operation cost are not required to be increased, better user experience is provided, nursing efficiency is improved, and labor cost is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly describe the drawings required to be used in the embodiments of the present application or the description in the prior art, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings of the embodiments of the present application for a person having ordinary skill in the art.

FIG. 1 is a flow chart of an infusion alarm method in one embodiment of the application;

FIG. 2 is a flow chart of an infusion alarm method in one embodiment of the application;

FIG. 3 is a schematic diagram of an intelligent infusion detection system in one embodiment of the application;

FIG. 4 is a schematic diagram of an infusion alarm device in accordance with an embodiment of the present application;

fig. 5 is a hardware configuration diagram of a video analysis apparatus in one embodiment of the present application.

Detailed Description

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to any or all possible combinations including one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in embodiments of the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. Depending on the context, furthermore, the word "if" used may be interpreted as "at … …" or "at … …" or "in response to a determination".

The embodiment of the application provides an infusion alarm method which can be applied to video analysis equipment, wherein the video analysis equipment can be any equipment with video calculation force, such as a camera of an infusion site, a bedside screen equipment of a ward, a bedside screen equipment and the like, and the type of the video analysis equipment is not limited. Referring to fig. 1, a flow chart of an infusion alarm method is shown, and the method may include:

step 101, obtaining a target image corresponding to an infusion object of a target scene.

102, determining position information corresponding to an infusion device based on a target image; the infusion device may include an infusion tube, and the position information may include a first target position corresponding to the infusion tube.

Step 103, a first sub-image of the infusion tube is intercepted from the target image based on the first target position.

Step 104, detecting whether bubbles exist in the infusion tube based on the first sub-image.

Step 105, if there is a bubble in the infusion tube, sending out alarm information, where the alarm information may include a first alarm code for the bubble. If no bubble exists in the infusion tube, no alarm information for the bubble is sent out.

In one possible embodiment, it is also possible to detect whether there is a flashback in the infusion tube based on the first sub-image. If blood return exists in the infusion tube, alarm information aiming at the infusion object is sent out, and the alarm information can comprise a second alarm code aiming at the blood return. If no blood return exists in the infusion tube, no alarm information for the infusion object is sent out, namely no alarm information for the blood return of the infusion object is sent out.

In one possible embodiment, the infusion device may further include an infusion container, the location information may further include a second target location for the infusion container, based on which a second sub-image of the infusion container may be taken from the target image based on the second target location, and the first liquid location in the infusion container may be determined based on the second sub-image. If the first liquid position is smaller than the first alarm threshold, alarm information aiming at the transfusion object is sent out, and the alarm information can comprise a third alarm code corresponding to the transfusion container. If the first liquid position is not smaller than the first alarm threshold value, alarm information carrying a third alarm code for the infusion object is not sent.

For example, the priority of the first alert code may be greater than the priority of the third alert code.

The priority of the second alert code may be greater than the priority of the third alert code.

In one possible embodiment, the second liquid location in the infusion tube may be determined based on the first sub-image. If the first liquid position indicates that no liquid exists in the infusion container and the second liquid position is smaller than the second alarm threshold, alarm information aiming at the infusion object is sent out, wherein the alarm information can comprise a fourth alarm code corresponding to the infusion tube, and the priority of the fourth alarm code is larger than that of the third alarm code. If the second liquid position is not smaller than the second alarm threshold value, alarm information carrying a fourth alarm code for the infusion object is not sent.

In one possible implementation manner, after the target image corresponding to the infusion object of the target scene is acquired, the infusion position identifier corresponding to the infusion object can be determined based on the target image, and the infusion position identifier can be the identifier of the bed where the infusion object is located or the identifier of the seat where the infusion object is located. When the alarm information for the infusion object is sent out, the alarm information can also comprise an infusion position identifier corresponding to the infusion object.

In one possible embodiment, the infusion device may include a drip cup, the position information may include a third target position corresponding to the drip cup, based on which a third sub-image of the drip cup may be further captured from the target image based on the third target position, a time difference between two consecutive drops of liquid may be determined based on the third sub-image in the multi-frame target image, and an infusion speed corresponding to the infusion object may be determined based on the time difference. The first alarm threshold and/or the second alarm threshold may be determined based on an infusion rate corresponding to the infusion subject.

According to the technical scheme, in the embodiment of the application, the first liquid position in the infusion container can be determined based on the target image corresponding to the infusion object, when the first liquid position is smaller than the first alarm threshold, the alarm information aiming at the infusion object is sent out, whether the air bubble exists in the infusion tube or not can be determined based on the target image corresponding to the infusion object, if the air bubble exists in the infusion tube, the alarm information aiming at the infusion object is sent out, so that the alarm information is timely pushed to the nursing object, the infusion object can be monitored in an omnibearing manner, the additional installation of an infusion alarm device is not needed, the additional deployment cost and the operation cost are not needed, the better user experience is provided, the nursing efficiency is improved, and the labor cost is reduced.

The above technical solution of the embodiments of the present application is described below with reference to specific application scenarios.

The embodiment of the application provides an infusion alarm method, which is characterized in that a first liquid position in an infusion container is identified by analyzing a target image corresponding to an infusion object, and whether alarm information for the infusion object is sent or not is determined based on the first liquid position in the infusion container. And analyzing the target image corresponding to the infusion object, identifying the second liquid position in the infusion tube, and determining whether to send out alarm information for the infusion object based on the second liquid position in the infusion tube. By analyzing the target image corresponding to the infusion object, whether bubbles exist in the infusion tube is detected, and whether alarm information for the infusion object is sent out is determined based on the bubble detection result. By analyzing the target image corresponding to the infusion object, whether the blood return exists in the infusion tube is detected, and whether alarm information for the infusion object is sent out is determined based on the blood return detection result.

In the embodiment of the application, the infusion alarm method can be realized through the infusion intelligent detection system, and the infusion intelligent detection system can comprise video acquisition equipment, video analysis equipment and a management host. The video acquisition device can be a camera of an infusion site, a video source of the ward monitoring device (the video source is used for providing video images for the ward monitoring device so that the ward monitoring device can process based on the video images, such as a head screen device, a bedside screen device and the like), and the like, the type of the video acquisition device is not limited, and the video acquisition device is used for acquiring target images of the infusion site and providing the target images to the video analysis device.

The video analysis device may be any device with video computing power (i.e. image processing function), such as a camera of an infusion site, a video source of ward monitoring device (such as a bedside screen device, etc. of a ward), a management host, etc., and the type of the video analysis device is not limited, and the video analysis device is used for analyzing a target image corresponding to an infusion object to determine whether to send out alarm information for the infusion object, and sending out alarm information for the infusion object to the management host when the alarm information needs to be sent out.

The management host is used for receiving the alarm information sent by the video analysis equipment, and sending an alarm to the nursing object in time when receiving the alarm information so as to prompt the nursing object to nurse the infusion object in time.

The video analysis device may be an existing device, i.e. the function of the video analysis device is implemented on the existing device, and the existing device analyzes the target image corresponding to the infusion object to determine whether to send out alarm information for the infusion object. For example, the video analysis device and the video acquisition device are disposed in the same device, that is, the video acquisition device realizes the function of the video analysis device, in which case the video analysis device may be a camera of an infusion site, a bedside screen device of a ward, a bedside screen device, and the like. As another example, the video analytics device is disposed on the same device as the management host, i.e., the functions of the video analytics device are implemented by the management host, in which case the video analytics device may be the management host. Of course, the above is just two examples, and is not limited in this regard, as long as the video analysis device is deployed on an existing device. Of course, the video analysis device may also be a stand-alone device, i.e. a device is deployed separately as a video analysis device.

In the embodiment of the application, in the infusion process of an infusion object in a target scene, the video analysis equipment can determine whether to send out alarm information aiming at the infusion object. The target scene can be a ward scene or an infusion room scene. The ward scene can comprise a plurality of beds, the infusion object infuses in a certain bed, the infusion room scene can comprise a plurality of seats, and the infusion object infuses in a certain seat.

In the infusion process of the infusion object, the infusion device can perform infusion operation on the infusion object, the infusion device can comprise, but is not limited to, an infusion container, an infusion tube and a drip cup, the infusion container can be an infusion bottle or an infusion bag, the infusion container is connected with the drip cup, and liquid in the infusion container enters the drip cup. The infusion tube is used for connecting the drip cup with an infusion object, namely one end of the infusion tube is connected with the drip cup, and the other end of the infusion tube is connected with the infusion object, so that liquid in the drip cup (infusion container) is subjected to infusion object.

Referring to fig. 2, a flow chart of an infusion alarm method is shown, and the method may include:

step 201, a video acquisition device acquires a target image (i.e. an image of an infusion site) corresponding to an infusion object of a target scene, and sends the target image corresponding to the infusion object to a video analysis device.

Step 202, the video analysis equipment acquires a target image corresponding to an infusion object of a target scene.

Step 203, the video analysis device determines an infusion position identifier corresponding to the infusion object based on the target image, where the infusion position identifier may be an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located.

For example, when the target scene is a ward scene, the ward scene may include a plurality of beds, the infusion object infuses in a certain bed, and the infusion position identifier may be an identifier (such as a bed number) of the bed where the infusion object is located. When the target scene is an infusion room scene, the infusion room scene can comprise a plurality of seats, the infusion object infuses in a certain seat, and the infusion position mark can be the mark (such as a seat number) of the seat where the infusion object is located.

For example, when an infusion object infuses in a certain bed, the target image generally includes an identifier of the bed where the infusion object is located, so that OCR (Optical Character Recognition ) character extraction can be performed on the target image, thereby obtaining the identifier of the bed where the infusion object is located (i.e. an infusion position identifier), and the OCR character extraction process is not limited as long as the identifier of the bed can be obtained.

For example, when an infusion object infuses at a certain seat, the target image generally includes an identification of the seat where the infusion object is located, so that OCR character extraction can be performed on the target image, thereby obtaining an identification of the seat where the infusion object is located (i.e. an infusion position identification), and the OCR character extraction process is not limited.

Step 204, the video analysis device determines a second target position corresponding to the infusion container based on the target image, and intercepts a second sub-image of the infusion container from the target image based on the second target position.

For example, the minimum bounding rectangle of the infusion container may be determined from the target image, and the 4 vertex coordinates (such as the upper left corner vertex coordinate, the upper right corner vertex coordinate, the lower right corner vertex coordinate, and the lower left corner vertex coordinate) of the minimum bounding rectangle may be taken as the second target position corresponding to the infusion container, where, of course, the foregoing is merely an example of the second target position, and the second target position is not limited as long as the second target position can reflect the position of the infusion container in the target image. For example, the second target position may also be a vertex coordinate of the minimum bounding rectangle, and a length and width of the minimum bounding rectangle. For another example, a circle including the infusion container may be determined from the target image, with the center and radius of the circle as the second target location, and so on.

After obtaining the second target position corresponding to the infusion container, a second sub-image of the infusion container may be taken from the target image based on the second target position, that is, the second sub-image of the infusion container may be taken from the target image based on the 4 vertex coordinates of the minimum bounding rectangle, that is, the 4 vertex coordinates of the second sub-image are the 4 vertex coordinates of the minimum bounding rectangle, that is, the second sub-image is the minimum bounding rectangle of the infusion container.

In one possible implementation, the video analysis device may analyze the target image using an image recognition algorithm to obtain a second target location corresponding to the infusion container, or input the target image to a trained network model, and output the second target location corresponding to the infusion container from the network model. Of course, the above is merely two examples, and the second target position corresponding to the infusion container may be obtained without limitation.

Step 205, the video analysis device determines a first target position corresponding to the infusion tube based on the target image, and intercepts a first sub-image of the infusion tube from the target image based on the first target position.

For example, the minimum bounding rectangle of the infusion tube may be determined from the target image, and the 4 vertex coordinates (such as the upper left corner vertex coordinate, the upper right corner vertex coordinate, the lower right corner vertex coordinate, and the lower left corner vertex coordinate) of the minimum bounding rectangle may be taken as the first target position corresponding to the infusion tube, where, of course, the foregoing is merely an example of the first target position, and the first target position is not limited as long as the first target position can reflect the position of the infusion tube in the target image. For example, the first target position may also be a vertex coordinate of the minimum bounding rectangle, and a length and width of the minimum bounding rectangle. For another example, other shapes including the infusion tube may be determined from the target image, the first target location may be determined based on information about the shape, and so on.

After the first target position corresponding to the infusion tube is obtained, a first sub-image of the infusion tube can be intercepted from the target image based on the first target position, that is, the first sub-image of the infusion tube is intercepted from the target image based on 4 vertex coordinates of the minimum bounding rectangle, that is, the 4 vertex coordinates of the first sub-image are the 4 vertex coordinates of the minimum bounding rectangle, that is, the first sub-image is the minimum bounding rectangle of the infusion tube.

In one possible implementation manner, the video analysis device may analyze the target image by using an image recognition algorithm to obtain a first target position corresponding to the infusion tube, or input the target image into a trained network model, and output the first target position corresponding to the infusion tube by using the network model. Of course, the above is merely two examples, and the first target position corresponding to the infusion tube may be obtained without limitation.

Step 206, the video analysis device determines a third target position corresponding to the drip cup based on the target image, and intercepts a third sub-image of the drip cup from the target image based on the third target position.

For example, the minimum bounding rectangle of the drip chamber may be determined from the target image, and the 4 vertex coordinates (such as the upper left corner vertex coordinate, the upper right corner vertex coordinate, the lower right corner vertex coordinate, and the lower left corner vertex coordinate) of the minimum bounding rectangle may be taken as the third target position corresponding to the drip chamber, where, of course, the foregoing is only an example of the third target position, and the third target position is not limited, as long as the third target position can reflect the position of the drip chamber in the target image. For example, the third target position may also be a vertex coordinate of the minimum bounding rectangle, and a length and width of the minimum bounding rectangle. For another example, a circle including a drip cup may be determined from the target image, with the center and radius of the circle as the third target location, and so on.

After obtaining the third target position corresponding to the drip cup, a third sub-image of the drip cup may be cut from the target image based on the third target position, that is, the third sub-image of the drip cup may be cut from the target image based on the 4 vertex coordinates of the smallest bounding rectangle, that is, the 4 vertex coordinates of the third sub-image may be the 4 vertex coordinates of the smallest bounding rectangle, that is, the third sub-image is the smallest bounding rectangle of the drip cup.

In one possible implementation, the video analysis device may analyze the target image using an image recognition algorithm to obtain a third target position corresponding to the drip cup, or input the target image to a trained network model, and output the third target position corresponding to the drip cup from the network model. Of course, the above is merely two examples, and the third target position corresponding to the drip cup may be obtained without limitation.

Step 207, the video analysis device determines a time difference between two drops of liquid continuously falling based on a third sub-image in the multi-frame target image, and determines an infusion speed corresponding to the infusion object based on the time difference.

For example, since the video capturing device periodically captures a plurality of target images and sends the plurality of target images to the video analyzing device, that is, the video analyzing device may obtain the plurality of target images, and each target image may obtain the third sub-image, the third sub-image in the plurality of target images may be obtained.

Based on the third sub-image in the multi-frame target image, the time difference for two drops of liquid to fall in succession can be determined. For example, a drop of liquid (hereinafter referred to as liquid A1) is determined based on the third sub-image in the A1-th frame target image, another drop of liquid (hereinafter referred to as liquid A2) is determined based on the third sub-image in the A2-th frame target image, and the liquid A1 and the liquid A2 are two drops of liquid that continuously drop, then the number of interval frames between the A1 frame and the A2 frame can be counted. On this basis, the time difference between the continuous dropping of two drops may be determined based on the frame rate (i.e., the number of frames per second) of the video capturing apparatus and the interval frame number, for example, the quotient between the interval frame number and the frame rate may be the time difference between the continuous dropping of two drops.

After the time difference of two drops of liquid continuously is obtained, the infusion speed corresponding to the infusion object can be determined based on the time difference, for example, assuming that the time difference is b seconds, the infusion speed corresponding to the infusion object can be 1/b, which means that 1/b drops of liquid are infused for the infusion object per second.

For example, after the infusion speed corresponding to the infusion object is obtained, the infusion speed corresponding to the infusion object may not be counted any more, and the infusion speed corresponding to the infusion object is kept unchanged. Or after obtaining the infusion speed corresponding to the infusion object, if it is determined that another drop of liquid A3 is dropped based on the third sub-image in the A3 frame target image, and the liquid a2 and the liquid A3 are two drops of liquid that continuously drop, then the infusion speed corresponding to the infusion object may be redetermined, and the infusion speed corresponding to the infusion object may be updated, and so on.

In one possible implementation, the video analysis device may analyze the multiple frames of the third sub-image using an image recognition algorithm to obtain a number of interval frames for two drops of liquid to be continuously dropped, or input the multiple frames of the third sub-image to a trained network model, and output the number of interval frames for two drops of liquid to be continuously dropped by the network model. Of course, the above is merely two examples, and there is no limitation to this, as long as the number of intervals between two drops of liquid that continuously fall can be obtained. After the number of the interval frames for continuously dropping two drops is obtained, the time difference for continuously dropping two drops can be determined based on the frame rate of the video acquisition device and the number of the interval frames, and then the infusion speed is obtained.

For example, after obtaining the infusion speed corresponding to the infusion object, the video analysis device may provide the infusion speed corresponding to the infusion object to the care object, so that the care object knows the infusion speed corresponding to the infusion object, and adjusts the infusion speed corresponding to the infusion object when the infusion speed is unreasonable.

For example, after obtaining the infusion speed corresponding to the infusion object, the first alarm threshold of the infusion container may be further determined based on the infusion speed corresponding to the infusion object. For example, if the time period for the nursing object to reach the position of the infusion object is K seconds (which may be configured by the nursing object), the total amount of the infusion corresponding to the time period may be determined based on the time period and the infusion speed, and the first alarm threshold of the infusion container may be determined based on the total amount of the infusion, for example, the amount of the liquid corresponding to the first alarm threshold of the infusion container may be greater than or equal to the total amount of the infusion. For example, assuming that the infusion speed corresponding to the infusion object is b drops per second, the total amount of infusion corresponding to K seconds is C drops, and C is k×b, that is, K seconds together corresponds to C drops of the infusion object, so the amount of liquid corresponding to the first alarm threshold of the infusion container may be greater than or equal to C drops. In one possible implementation, the first alarm threshold may be a height D1 (or greater than a height D1) corresponding to a total amount of infusion, C drops, and indicates that the infusion container co-exists with the C drops of liquid when the remaining height of the liquid in the infusion container is D1.

For example, after obtaining the infusion speed corresponding to the infusion object, the second alarm threshold of the infusion tube may be further determined based on the infusion speed corresponding to the infusion object. For example, if the time period for the nursing object to reach the position of the infusion object is K seconds (which may be configured by the nursing object), the total amount of the infusion corresponding to the time period may be determined based on the time period and the infusion speed, and the second alarm threshold of the infusion tube may be determined based on the total amount of the infusion, for example, the amount of the liquid corresponding to the second alarm threshold of the infusion tube may be greater than or equal to the total amount of the infusion. For example, assuming that the infusion speed corresponding to the infusion object is b drops per second, the total amount of infusion corresponding to K seconds is C drops, and C is k×b, that is, K seconds is the total amount of infusion corresponding to the infusion object, and therefore, the amount of liquid corresponding to the second alarm threshold of the infusion tube may be greater than C drops, so that when the nursing object arrives at the position where the infusion object is located, the liquid remains in the infusion tube, and the safety of the infusion object is prevented from being affected. In one possible implementation, the second alarm threshold may be a height D2 (or greater than a height D2) corresponding to M drops (M is greater than C), which indicates that M drops of liquid coexist in the infusion tube when the remaining height of the liquid in the infusion tube is D2.

Step 208, the video analysis device determines a first fluid location in the infusion container based on the second sub-image. If the first liquid position is smaller than the first alarm threshold, alarm information aiming at the transfusion object is sent to the management host, and the alarm information can comprise a third alarm code corresponding to the transfusion container. If the first liquid position is not smaller than the first alarm threshold value, alarm information aiming at the transfusion object is not sent to the management host.

In one possible implementation, the video analysis device may analyze the second sub-image (i.e., the sub-image corresponding to the infusion container) using an image recognition algorithm to obtain the first fluid location in the infusion container, or may input the second sub-image to a trained network model, and output the first fluid location in the infusion container from the network model. Of course, the above is merely two examples, and is not limited thereto, as long as the first liquid position in the infusion container, which indicates the liquid level in the infusion container, can be obtained.

After the first liquid position in the infusion container is obtained, whether the first liquid position is smaller than a first alarm threshold value can be judged, wherein the first alarm threshold value can be a height value configured according to experience, or can be a height D1 determined based on the infusion speed corresponding to the infusion object, and the first alarm threshold value is not limited.

If the first liquid position is smaller than the first alarm threshold, alarm information can be sent to the management host, and the alarm information can comprise a third alarm code and an infusion position identifier corresponding to the infusion object (such as an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located). The third alarm code may be a first character (i.e. alarm is implemented by a character), and the third alarm code may also be a first sound (i.e. alarm is implemented by a sound), which is, of course, only a few examples, and the third alarm code is not limited thereto.

Step 209, the video analysis device determines a second fluid location in the infusion tube based on the first sub-image. If the first liquid position indicates that no liquid exists in the infusion container and the second liquid position is smaller than the second alarm threshold, alarm information aiming at the infusion object is sent to the management host, wherein the alarm information can comprise a fourth alarm code corresponding to the infusion tube, and the priority of the fourth alarm code is larger than that of the third alarm code. If the second liquid position is not smaller than the second alarm threshold value, alarm information aiming at the transfusion object is not sent to the management host.

In one possible implementation, the video analysis device may analyze the first sub-image (i.e., the sub-image corresponding to the infusion tube) using an image recognition algorithm to obtain the second liquid location in the infusion tube, or input the first sub-image to a trained network model, and output the second liquid location in the infusion tube from the network model. Of course, the above is merely two examples, and is not limited thereto, as long as the second liquid position in the infusion tube can be obtained, the second liquid position indicating the liquid level in the infusion tube.

For example, after the first liquid position in the infusion container is obtained, whether the liquid exists in the infusion container can be determined based on the first liquid position, if the first liquid position indicates that the liquid still exists in the infusion container (i.e., the first liquid position is not 0), the infusion tube is full of the liquid, whether the second liquid position is smaller than the second alarm threshold value is not needed to be judged, and alarm information is not sent based on the second liquid position.

If the first liquid position indicates that no liquid exists in the infusion container (i.e., the first liquid position is 0), after the second liquid position in the infusion tube is obtained, whether the second liquid position is smaller than a second alarm threshold value can be judged, and the second alarm threshold value can be a height value configured according to experience or a height D2 determined based on an infusion speed corresponding to an infusion object, and is not limited.

If the second liquid position is smaller than the second alarm threshold, alarm information can be sent to the management host, and the alarm information can comprise a fourth alarm code and an infusion position identifier corresponding to the infusion object (such as an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located). The fourth alarm code may be a second character (i.e. alarm is implemented by a character), or may be a second sound (i.e. alarm is implemented by sound), which is, of course, only a few examples and is not limited thereto.

For example, since the fourth alarm code and the third alarm code are different, i.e. different characters or different sounds, the care object can distinguish the alarm types based on the fourth alarm code and the third alarm code, that is, if the alarm information carries the fourth alarm code, it indicates that no liquid exists in the infusion container, and the position of the second liquid in the infusion tube is smaller than the second alarm threshold, so that the care object needs to reach the position of the infusion object in time. If the alarm information carries the third alarm code, the state that the liquid still exists in the infusion container is indicated, but the first liquid position in the infusion container is smaller than the first alarm threshold value, so that the nursing object can start to prepare, and the second liquid position in the infusion tube is waiting for being smaller than the second alarm threshold value, so that the position of the infusion object can be reached in time.

For example, the priority of the fourth alarm code may be greater than the priority of the third alarm code, for example, when the fourth alarm code and the third alarm code are both characters, the font of the characters of the fourth alarm code is greater than the font of the characters of the third alarm code, or the characters of the fourth alarm code may be thickened, the characters of the third alarm code are not thickened, or the characters of the fourth alarm code may be red, blue, etc., and the characters of the third alarm code are black. For another example, when the fourth alarm code and the third alarm code are both sound, the sound volume of the sound of the fourth alarm code is larger than the sound volume of the sound of the third alarm code, or the content of the sound of the fourth alarm code is more important than the content of the sound of the third alarm code. Of course, the foregoing is merely a few examples and is not limiting in this regard.

The priority of the fourth alarm code is greater than that of the third alarm code, which means that: the event corresponding to the fourth alarm code is more important than the event corresponding to the third alarm code, for example, if the alarm information of the fourth alarm code is sent out for the infusion object 1 and the alarm information of the third alarm code is sent out for the infusion object 2, then the alarm event of the infusion object 1 needs to be preferably processed, and then the alarm event of the infusion object 2 needs to be processed.

Step 210, the video analysis device detects whether bubbles exist in the infusion tube based on the first sub-image. If the air bubble exists in the infusion tube, sending alarm information aiming at the infusion object to the management host, wherein the alarm information can comprise a first alarm code aiming at the air bubble, and the priority of the first alarm code is higher than that of the third alarm code. If no bubble exists in the infusion tube, no alarm information for the infusion object is sent to the management host.

In one possible implementation, the video analysis device may employ an image recognition algorithm to detect the first sub-image (i.e., the sub-image corresponding to the infusion tube) to determine whether there is an air bubble in the infusion tube, for example, detect the area of the infusion tube below the drip cup in the first sub-image to determine whether there is an air bubble in the infusion tube. Or inputting the first sub-image into a trained network model, detecting the infusion tube area below the drip cup in the first sub-image by the network model to determine whether bubbles exist in the infusion tube, and outputting a detection result of whether the bubbles exist in the infusion tube. Of course, the above is merely two examples, and is not limited thereto, as long as a detection result of whether or not there is a bubble in the infusion tube can be obtained.

For example, after the detection result of whether the air bubble exists in the infusion tube is obtained, if it is determined that the air bubble exists in the infusion tube based on the detection result, alarm information may be sent to the management host, where the alarm information may include the first alarm code and an infusion position identifier corresponding to the infusion object (such as an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located). The first alarm code may be a third character (i.e. alarm is implemented by a character), or the first alarm code may be a third sound (i.e. alarm is implemented by a sound), which is, of course, only a few examples, and the first alarm code is not limited.

For example, since the first alarm code and the third alarm code are different, and the first alarm code and the fourth alarm code are different, that is, different characters or different sounds, the care object can distinguish the alarm types based on the first alarm code, the fourth alarm code and the third alarm code, that is, if the alarm information carries the first alarm code, it indicates that there is a bubble in the infusion tube, and the care object needs to arrive at the location of the infusion object in time.

For example, the priority of the first alarm code may be greater than the priority of the third alarm code, for example, when the first alarm code and the third alarm code are both characters, the font of the characters of the first alarm code is greater than the font of the characters of the third alarm code, or the characters of the first alarm code may be thickened, the characters of the third alarm code are not thickened, or the characters of the first alarm code may be red, blue, etc., and the characters of the third alarm code are black. For another example, when the first alarm code and the third alarm code are both sound, the sound volume of the sound of the first alarm code is larger than the sound volume of the sound of the third alarm code, or the content of the sound of the first alarm code is more important than the content of the sound of the third alarm code. Of course, the foregoing is merely a few examples and is not limiting in this regard.

For example, the priority of the first alarm code may be greater than the priority of the fourth alarm code, the priority of the first alarm code may be equal to the priority of the fourth alarm code, the priority of the first alarm code may be less than the priority of the fourth alarm code, and the priority relationship between the first alarm code and the fourth alarm code is not limited.

Step 211, the video analysis device detects whether blood return exists in the infusion tube based on the first sub-image. If blood return exists in the infusion tube, alarm information aiming at the infusion object is sent to the management host, wherein the alarm information can comprise a second alarm code aiming at the blood return, and the priority of the second alarm code is higher than that of the third alarm code. If no blood return exists in the infusion tube, no alarm information for the infusion object is sent to the management host.

In one possible implementation, the video analysis device may detect the first sub-image (i.e., the sub-image corresponding to the infusion tube) by using an image recognition algorithm to determine whether there is any blood return in the infusion tube, for example, detect an infusion tube region on the infusion object side in the first sub-image to determine whether there is any blood return in the infusion tube. Or inputting the first sub-image into a trained network model, detecting the infusion tube area at the infusion object side in the first sub-image by the network model to determine whether the infusion tube has blood return or not, and outputting a detection result of whether the infusion tube has blood return or not. Of course, the above is merely two examples, and is not limited thereto, as long as a detection result of whether or not there is blood return in the infusion tube can be obtained.

For example, after the detection result of whether there is blood return in the infusion tube is obtained, if it is determined that there is blood return in the infusion tube based on the detection result, alarm information may be sent to the management host, where the alarm information may include the second alarm code and an infusion position identifier corresponding to the infusion object (such as an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located). The second alarm code may be a fourth character (i.e. alarm is implemented by a character), or the second alarm code may be a fourth sound (i.e. alarm is implemented by sound), which is, of course, only a few examples, and the second alarm code is not limited thereto.

For example, since the second alarm code and the third alarm code are different, and the second alarm code and the fourth alarm code are different, and the second alarm code and the first alarm code are different, that is, different alarm codes are implemented through different characters or different sounds, the nursing object can distinguish the alarm types based on the second alarm code, the first alarm code, the fourth alarm code and the third alarm code, that is, if the alarm information carries the second alarm code, it indicates that there is blood return in the infusion tube, and the nursing object needs to arrive at the position of the infusion object in time.

For example, the priority of the second alarm code may be greater than the priority of the third alarm code, for example, when the second alarm code and the third alarm code are both characters, the font of the characters of the second alarm code is greater than the font of the characters of the third alarm code, or the characters of the second alarm code may be thickened, the characters of the third alarm code are not thickened, or the characters of the second alarm code may be red, blue, etc., and the characters of the third alarm code are black. For another example, when the second alarm code and the third alarm code are both sound, the sound volume of the sound of the second alarm code is larger than the sound volume of the sound of the third alarm code, or the content of the sound of the second alarm code is more important than the content of the sound of the third alarm code. Of course, the foregoing is merely a few examples and is not limiting in this regard.

For example, the priority of the second alarm code may be greater than the priority of the fourth alarm code, the priority of the second alarm code may be equal to the priority of the fourth alarm code, the priority of the second alarm code may be less than the priority of the fourth alarm code, and the priority relationship between the second alarm code and the fourth alarm code is not limited.

For example, the priority of the second alarm code may be greater than the priority of the first alarm code, the priority of the second alarm code may be equal to the priority of the first alarm code, the priority of the second alarm code may be less than the priority of the first alarm code, and the priority relationship between the second alarm code and the first alarm code is not limited.

According to the technical scheme, in the embodiment of the application, the alarm information can be timely pushed to the nursing object, the infusion object can be monitored in all directions, the infusion alarm device is not required to be additionally installed, the additional deployment cost and the operation cost are not required to be increased, better user experience is provided, the nursing efficiency is improved, and the labor cost is reduced. By combining on-site video equipment (the video acquisition equipment is a video camera of an infusion site, a video source of ward monitoring equipment and the like), the intelligent video analysis method is adopted to monitor the infusion in all directions, and the additional deployment cost and the medical care operation cost are not required to be increased. Based on the mode of video detection, the bubble, the blood return and the infusion speed in the infusion process and the infusion progress are identified, an original infusion system is not required to be changed, additional operation steps are not required to be added, and better user experience is provided. The video analysis equipment can be deployed on equipment with video computing power, can be a camera, a bedside screen equipment and a bedside screen equipment on the transfusion site, and does not need to increase extra hardware cost.

In one possible implementation, referring to fig. 3, a schematic structural diagram of an intelligent infusion detection system may include a video acquisition unit, a video analysis unit, an alarm control unit, and a management unit. The video acquisition unit can be deployed in the video acquisition equipment, the video analysis unit and the alarm control unit can be deployed in the video analysis equipment, and the management unit can be deployed in the management host.

Video acquisition unit: and the system is used for acquiring a target image (namely an image of an infusion site) corresponding to an infusion object of the target scene and sending the target image corresponding to the infusion object to the video analysis unit.

Video analysis unit: the video analysis unit is used for acquiring a target image corresponding to an infusion object of a target scene and analyzing the target image, for example, the video analysis unit can analyze the target image by adopting the following functional modules.

Bed/seat number identification module: the method is used for determining the infusion position identification corresponding to the infusion object based on the target image, and the infusion position identification can be the identification of the bed where the infusion object is located or the identification of the seat where the infusion object is located.

Infusion container identification module: the liquid level detection module is used for determining a second target position corresponding to the infusion container based on the target image and providing the second target position corresponding to the infusion container for the liquid level detection module.

Infusion tube identification module: the liquid level detection module is used for determining a first target position corresponding to the infusion tube based on the target image and providing the first target position corresponding to the infusion tube for the liquid level detection module.

Drip cup identification module: and the infusion speed calculation module is used for determining a third target position corresponding to the drip cup based on the target image and providing the third target position corresponding to the drip cup for the infusion speed calculation module.

An infusion speed calculation module: and the device is used for intercepting a third sub-image of the drip cup from the target image based on a third target position corresponding to the drip cup, determining a time difference for continuously dropping two drops of liquid based on the third sub-image in the multi-frame target image, and determining the infusion speed corresponding to the infusion object based on the time difference.

The liquid level detection module: the system is used for intercepting a second sub-image of the infusion container from the target image based on a second target position corresponding to the infusion container, determining a first liquid position in the infusion container based on the second sub-image and providing the first liquid position to the alarm control unit. And the alarm control unit is used for intercepting a first sub-image of the infusion tube from the target image based on the first target position corresponding to the infusion tube, determining a second liquid position in the infusion tube based on the first sub-image and providing the second liquid position to the alarm control unit.

And the bubble detection module is used for: the liquid level detection module is used for detecting whether bubbles exist in the infusion tube or not based on the first sub-image, and providing a detection result of whether the bubbles exist in the infusion tube or not to the alarm control unit.

Blood return detection module: the liquid level detection module is used for detecting whether the blood return exists in the infusion tube or not based on the first sub-image, and providing a detection result of whether the blood return exists in the infusion tube or not to the alarm control unit.

Alarm control unit: based on the first liquid position provided by the liquid level detection module, if the first liquid position is smaller than a first alarm threshold, alarm information aiming at the infusion object is sent to the management unit, and the alarm information can comprise a third alarm code and an infusion position identifier. Based on the second liquid position provided by the liquid level detection module, if the first liquid position indicates that no liquid exists in the infusion container and the second liquid position is smaller than a second alarm threshold, alarm information aiming at the infusion object is sent to the management unit, and the alarm information can comprise a fourth alarm code and an infusion position identifier. Based on the bubble detection result provided by the bubble detection module, if the bubble detection result indicates that bubbles exist in the infusion tube, alarm information aiming at an infusion object is sent to the management unit, and the alarm information can comprise a first alarm code and an infusion position identifier. Based on the blood return detection result provided by the blood return detection module, if the blood return detection result indicates that blood return exists in the infusion tube, alarm information aiming at an infusion object is sent to the management unit, and the alarm information can comprise a second alarm code and an infusion position identifier.

Management unit: and the device is used for pushing the alarm information to the nursing object after receiving the alarm information.

Based on the same application concept as the above method, an infusion alarm device is provided in the embodiment of the present application, and referring to fig. 4, which is a schematic structural diagram of the infusion alarm device, the device may include:

an acquisition module 41, configured to acquire a target image corresponding to an infusion object in a target scene;

a determining module 42, configured to determine position information corresponding to the infusion device based on the target image; the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube; intercepting a first sub-image of the infusion tube from the target image based on the first target position; detecting whether bubbles exist in the infusion tube or not based on the first sub-image;

and the alarm module 43 is configured to send alarm information if there is a bubble in the infusion tube, where the alarm information includes a first alarm code for the bubble.

Illustratively, the determining module 42 is further configured to detect whether there is flashback in the infusion tube based on the first sub-image; the alarm module 43 is further configured to send alarm information if there is blood return in the infusion tube, where the alarm information includes a second alarm code for blood return.

Illustratively, the infusion device further includes an infusion container, and the location information further includes a second target location corresponding to the infusion container; the determining module 42 is further configured to intercept a second sub-image of the infusion container from the target image based on the second target location; determining a first liquid location in the infusion container based on the second sub-image; the alarm module 43 is further configured to send out alarm information for the infusion object if the first liquid position is smaller than a first alarm threshold, where the alarm information includes a third alarm code corresponding to the infusion container; the priority of the first alarm code is greater than that of the third alarm code; the priority of the second alarm code is greater than the priority of the third alarm code.

Illustratively, the determining module 42 is further configured to determine a second fluid location in the infusion tube based on the first sub-image; the alarm module 43 is further configured to send alarm information if the first liquid position indicates that there is no liquid in the infusion container and the second liquid position is less than a second alarm threshold, where the alarm information includes a fourth alarm code corresponding to the infusion tube, and a priority of the fourth alarm code is greater than a priority of the third alarm code.

Illustratively, the determining module 42 is further configured to determine, based on the target image, an infusion position identifier corresponding to the infusion object, where the infusion position identifier is an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located; when the alarm module 43 sends the alarm information for the infusion object, the alarm information further includes an infusion position identifier corresponding to the infusion object.

Illustratively, the infusion device includes a drip cup, and the location information includes a third target location corresponding to the drip cup; the determining module 42 is further configured to intercept a third sub-image of the drip cup from the target image based on the third target position; determining a time difference of two drops of liquid continuously based on a third sub-image in the multi-frame target image; determining the infusion speed corresponding to the infusion object based on the time difference; the first alarm threshold and/or the second alarm threshold are/is determined based on the infusion speed.

Based on the same application concept as the above method, a video analysis device is provided in an embodiment of the present application, and referring to fig. 5, the video analysis device includes: a processor 51 and a machine-readable storage medium 52, the machine-readable storage medium 52 storing machine-executable instructions executable by the processor 51; the processor 51 is configured to execute machine-executable instructions to implement the infusion alarm method disclosed in the above-described examples of the present application.

Based on the same application concept as the above method, the embodiment of the present application further provides a machine-readable storage medium, where a plurality of computer instructions are stored on the machine-readable storage medium, and when the computer instructions are executed by a processor, the infusion alarm method disclosed in the above example of the present application can be implemented.

Wherein the machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, or the like. For example, a machine-readable storage medium may be: RAM (Radom Access Memory, random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., hard drive), a solid state drive, any type of storage disk (e.g., optical disk, dvd, etc.), or a similar storage medium, or a combination thereof.

Based on the same application concept as the method, an infusion alarm system is provided in the embodiment of the application, and the system comprises: the video acquisition unit is used for acquiring a target image corresponding to an infusion object of a target scene; the video analysis unit is used for acquiring the target image from the video acquisition unit and determining the position information corresponding to the infusion device based on the target image; the infusion device comprises an infusion tube, and the position information comprises a first target position corresponding to the infusion tube; intercepting a first sub-image of the infusion tube from the target image based on the first target position; detecting whether bubbles exist in the infusion tube or not based on the first sub-image; if bubbles exist in the infusion tube, sending information of the bubbles existing in the infusion tube to an alarm control unit; the alarm control unit is used for sending out alarm information aiming at the transfusion object when bubbles exist in the transfusion tube, and the alarm information comprises a first alarm code aiming at the bubbles; the video analysis unit and the alarm control unit are deployed in video analysis equipment, the video analysis equipment and the video acquisition equipment are deployed in the same equipment, or the video analysis equipment and the video acquisition equipment are deployed in different equipment.

The video analysis unit is further configured to detect whether blood return exists in the infusion tube based on the first sub-image; if the blood return exists in the infusion tube, sending the information of the blood return exists in the infusion tube to an alarm control unit; the alarm control unit is used for sending out alarm information if blood returns in the infusion tube, and the alarm information comprises a second alarm code aiming at the blood return.

Illustratively, the infusion device further includes an infusion container, the location information further includes a second target location corresponding to the infusion container, and the video analysis unit is further configured to intercept a second sub-image of the infusion container from the target image based on the second target location; determining a first liquid location in the infusion container based on the second sub-image; if the first liquid position is smaller than a first alarm threshold value, sending information that the first liquid position is smaller than the first alarm threshold value to an alarm control unit; the alarm control unit is used for sending out alarm information aiming at the transfusion object if the first liquid position is smaller than a first alarm threshold value, and the alarm information comprises a third alarm code corresponding to the transfusion container;

The priority of the first alarm code is greater than that of the third alarm code;

the priority of the second alarm code is greater than the priority of the third alarm code.

The video analysis unit is further configured to determine a second liquid position in the infusion tube based on the first sub-image; if the first liquid position indicates that the infusion container has no liquid and the second liquid position is smaller than a second alarm threshold value, sending information that the infusion container has no liquid and the second liquid position is smaller than the second alarm threshold value to an alarm control unit; the alarm control unit is configured to send out alarm information if the first liquid position indicates that there is no liquid in the infusion container and the second liquid position is smaller than a second alarm threshold, where the alarm information includes a fourth alarm code corresponding to the infusion tube, and a priority of the fourth alarm code is greater than a priority of the third alarm code.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer or an entity, or by an article of manufacture having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Moreover, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. An infusion warning method, the method comprising:

acquiring a target image corresponding to an infusion object of a target scene;

2. The method of claim 1, wherein after the capturing the first sub-image of the infusion tube from the target image based on the first target location, the method further comprises:

detecting whether blood return exists in the infusion tube or not based on the first sub-image; and if the blood return exists in the infusion tube, sending out alarm information, wherein the alarm information comprises a second alarm code aiming at the blood return.

3. The method of claim 2, wherein the infusion device further comprises an infusion container, the location information further comprising a second target location corresponding to the infusion container, the method further comprising:

Intercepting a second sub-image of the infusion container from the target image based on the second target location;

determining a first liquid location in the infusion container based on the second sub-image;

if the first liquid position is smaller than a first alarm threshold, sending alarm information aiming at the infusion object, wherein the alarm information comprises a third alarm code corresponding to the infusion container;

4. The method of claim 3, wherein after said capturing a first sub-image of the infusion tube from the target image based on the first target location, the method further comprises:

determining a second fluid location in the infusion tube based on the first sub-image;

and if the first liquid position indicates that no liquid exists in the infusion container and the second liquid position is smaller than a second alarm threshold, sending alarm information, wherein the alarm information comprises a fourth alarm code corresponding to the infusion tube, and the priority of the fourth alarm code is larger than that of the third alarm code.

5. The method according to any one of claim 1 to 4, wherein,

after the target image corresponding to the infusion object of the target scene is acquired, the method further comprises:

determining an infusion position identifier corresponding to the infusion object based on the target image, wherein the infusion position identifier is an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located;

the alarm information also comprises an infusion position identifier corresponding to the infusion object.

6. The method of claim 3 or 4, wherein the infusion device comprises a drip cup, the location information comprising a third target location for the drip cup, the method further comprising:

intercepting a third sub-image of the drip cup from the target image based on the third target position;

determining a time difference of two drops of liquid continuously based on a third sub-image in the multi-frame target image;

determining the infusion speed corresponding to the infusion object based on the time difference;

the first alarm threshold and/or the second alarm threshold are/is determined based on the infusion speed.

7. An infusion warning device, the device comprising:

8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,

the determining module is further used for detecting whether blood return exists in the infusion tube or not based on the first sub-image; the alarm module is further used for sending alarm information if blood returns in the infusion tube, and the alarm information comprises a second alarm code for the blood returns;

the infusion device further comprises an infusion container, and the position information further comprises a second target position corresponding to the infusion container; the determining module is further configured to intercept a second sub-image of the infusion container from the target image based on the second target position; determining a first liquid location in the infusion container based on the second sub-image; the alarm module is further configured to send alarm information for the infusion object if the first liquid position is smaller than a first alarm threshold, where the alarm information includes a third alarm code corresponding to the infusion container; the priority of the first alarm code is greater than that of the third alarm code; the priority of the second alarm code is greater than that of the third alarm code;

Wherein the determining module is further configured to determine a second liquid location in the infusion tube based on the first sub-image; the alarm module is further configured to send alarm information if the first liquid position indicates that there is no liquid in the infusion container and the second liquid position is less than a second alarm threshold, where the alarm information includes a fourth alarm code corresponding to the infusion tube, and a priority of the fourth alarm code is greater than a priority of the third alarm code;

the determining module is further configured to determine an infusion position identifier corresponding to the infusion object based on the target image, where the infusion position identifier is an identifier of a bed where the infusion object is located or an identifier of a seat where the infusion object is located; when the alarm module sends out the alarm information aiming at the infusion object, the alarm information also comprises an infusion position identifier corresponding to the infusion object;

the infusion device comprises a drip cup, and the position information comprises a third target position corresponding to the drip cup; the determining module is further used for intercepting a third sub-image of the drip cup from the target image based on the third target position; determining a time difference of two drops of liquid continuously based on a third sub-image in the multi-frame target image; determining the infusion speed corresponding to the infusion object based on the time difference; the first alarm threshold and/or the second alarm threshold are/is determined based on the infusion speed.

9. A video analysis apparatus, comprising: a processor and a machine-readable storage medium storing machine-executable instructions executable by the processor; the processor is configured to execute machine executable instructions to implement the method of any of claims 1-6.

10. An infusion alarm system, the system comprising: