Continuous infusion dressing change control method and system based on multi-connected liquid medicine tank

Abstract

The invention relates to a control method and system for continuous infusion dressing change based on a multi-connected liquid medicine tank, and the method comprises the steps: U1, hanging the multi-connected liquid medicine tank on a support for infusion, obtaining the image data information of the liquid medicine tank in real time based on a camera on the support, obtaining the image data information of liquid medicine drops in real time based on the camera on the support, and obtaining the image data information of the liquid medicine drops; the number data information of dripping liquid medicine drops is obtained in real time based on a laser counting sensor on the support; and U2, based on the image data information of the liquid medicine tank and the image data information of the liquid medicine drop, performing feature extraction on the images of the liquid medicine tank and the liquid medicine drop by adopting an improved Shii-Tomasi corner detection algorithm to obtain image feature data information of the liquid medicine tank and image feature data information of the liquid medicine drop. The infusion process of the liquid medicine tank can be accurately controlled, manual medicine changing is not needed in the whole process, the infusion efficiency and stability are improved, and therefore the use experience of a patient is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dressing change of multiple-joint liquid medicine tanks, and in particular to a control method and system for continuous transfusion dressing change based on multiple-joint liquid medicine tanks. Background Art

[0002] With the continuous development of automation technology, it is constantly affecting the rapid development of various industries. Among them, the medical industry is also constantly updating and developing. Innovating various technical points in the industry is the direction of our research and development.

[0003] In the prior art, the patent (application number: 202110549422.4) discloses an accurate, safe and convenient infusion dressing method, which includes the following steps: S01: information collection, before infusion, medical staff use information collection equipment to read drug information and mark the total volume of the drug V; S03: infusion time determination, the infusion control robot collects the current infusion speed v, and sets the control variable K at the same time. During the infusion process, the system calculates the drug infusion stop time T through the above parameters, and the infusion stop time T = total drug volume V* control variable K / infusion speed v. The accuracy of drug dressing change in this scheme is not high, and the drug bottle still needs to be replaced manually, which not only wastes time, but also reduces the efficiency of drug delivery. Summary of the invention

[0004] In view of the above shortcomings of the prior art, the present invention provides a control method and system for continuous infusion and dressing change based on a multi-connected medicine tank, which can not only accurately control the infusion process of the medicine tank, but also eliminate the need for manual dressing change during the entire process, thereby improving the efficiency and stability of infusion, thereby enhancing the patient's usage experience.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A control method for continuous drug delivery and drug change based on a multi-link drug liquid tank, the method comprising:

[0007] U1. Hang the multi-link drug tank on the bracket for infusion, obtain the image data information of the drug tank in real time based on the camera on the bracket, obtain the image data information of the drug drop in real time based on the camera on the bracket, and obtain the number data information of the dripping drug drop in real time based on the laser counting sensor on the bracket;

[0008] U2. Based on the image data information of the liquid medicine tank and the image data information of the liquid medicine droplets, the improved Shi-Tomasi corner detection algorithm is used to extract features of the images of the liquid medicine tank and the liquid medicine droplets to obtain image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplets;

[0009] U3. Based on the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets, a recurrent neural network prediction model based on the Spearman correlation coefficient is constructed to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted number data information of the medicine liquid droplets in the medicine liquid tank;

[0010] U4. Based on the predicted data information on the number of medicine droplets in the medicine liquid tank and the data information on the number of dripping medicine droplets, a continuous transfusion and medicine change control function G of the multi-unit medicine liquid tank is established to control and adjust the medicine liquid tank for continuous transfusion and medicine change, and obtain the control data information on continuous transfusion and medicine change of the multi-unit medicine liquid tank.

[0011] Furthermore, the continuous feeding and changing control function G of the multi-link liquid medicine tank is:

[0012]

[0013] Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, y is the data information of the number of medicine droplets dripping, α1 is the first control factor of the multi-unit medicine tank, α2 is the second control factor of the multi-unit medicine tank, and α3 is the third control factor of the multi-unit medicine tank.

[0014] Furthermore, the first control factor α1 of the multi-link liquid medicine tank is,

[0015]

[0016] The second control factor α2 of the multi-link liquid medicine tank is:

[0017]

[0018] The third control factor α3 of the multi-link liquid medicine tank is:

[0019]

[0020] Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, and y is the data information of the number of medicine droplets dripping.

[0021] Furthermore, in step U3, the constructing of a recurrent neural network prediction model based on the Spearman correlation coefficient to predict the number of drops of medicine in the medicine tank includes:

[0022] U31. Based on the image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplet, a Spearman correlation coefficient function H between the liquid medicine tank and the liquid medicine droplet is established.

[0023]

[0024] Among them, a iis the image feature data information of the liquid medicine tank, n is the sample size, b i is the image feature data information of the medicine droplet, f is the rank function of the image feature of the medicine tank, g is the rank function of the image feature of the medicine droplet, the correlation between the image features of the medicine tank and the medicine droplet is characterized, and the data information of the Spearman correlation coefficient between the medicine tank and the medicine droplet is obtained;

[0025] U32. Input the Spearman correlation coefficient data of the liquid medicine tank and the liquid medicine droplets into the recurrent neural network prediction model for training and learning, and determine the prediction function W of the number of drops in the liquid medicine tank.

[0026]

[0027] Among them, c is the data information of the Spearman correlation coefficient between the drug liquid tank and the drug droplet, α1, α2 and α3 are the learning factors of the prediction model, and the trained recurrent neural network model is obtained;

[0028] U33. Based on the trained recurrent neural network model, the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets are input to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted data information on the number of medicine liquid droplets in the medicine liquid tank.

[0029] Furthermore, the order function f of the image feature of the liquid medicine tank is,

[0030]

[0031] The order function g of the image feature of the drug droplet is:

[0032]

[0033] Among them, a i is the image feature data information of the liquid medicine tank, b i It is the image feature data information of the medicine droplet.

[0034] Furthermore, the constraints of the learning factors α1, α2 and α3 of the prediction model are:

[0035] Furthermore, in step U2, the use of the improved Shi-Tomasi corner detection algorithm to extract features from the images of the liquid medicine tank and the liquid medicine droplets includes:

[0036] U21. Based on the image data information of the medicine tank and the image data information of the medicine droplets, an image pixel matrix of the medicine tank and an image pixel matrix of the medicine droplets are constructed to obtain image pixel matrix data information of the medicine tank and the medicine droplets;

[0037] U22. Based on the image pixel matrix data information of the liquid medicine tank and the liquid medicine droplet, establish the corner point detection function R1 of the image pixel of the liquid medicine tank and the corner point detection function R2 of the image pixel of the liquid medicine droplet,

[0038]

[0039] Among them, p is the image pixel matrix data information of the medicine tank, q is the image pixel matrix data information of the medicine droplet, μ1, μ2 and μ3 are the image pixel detection factors of the medicine tank, ρ1, ρ2 and ρ3 are the image pixel detection factors of the medicine droplet;

[0040] U23. Based on the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine liquid droplets, feature extraction is performed on the images of the medicine liquid tank and the medicine liquid droplets to obtain image feature data information of the medicine liquid tank and image feature data information of the medicine liquid droplets.

[0041] Furthermore, in step U23, the feature extraction of the images of the medicine liquid tank and the medicine droplets is performed by obtaining the corner point detection value of the image pixels of the medicine liquid tank and the corner point detection value of the image pixels of the medicine droplets according to the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine droplets, and setting a preset threshold. If the corner point detection value of the image pixels of the medicine liquid tank is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine liquid tank is greater than the preset threshold, the corner point detection value is retained; if the corner point detection value of the image pixels of the medicine droplets is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine droplets is greater than the preset threshold, the corner point detection value is retained.

[0042] Furthermore, in step U4, the medicine tank for continuous infusion and dressing change is controlled and adjusted according to the continuous infusion and dressing change control function G of the multiple medicine tanks, the number of medicine drops in each medicine tank in the multiple medicine tanks is obtained, and a medicine drop threshold is set. If the number of medicine drops in the medicine tank is less than the medicine drop threshold, it is necessary to replace it with another medicine tank for infusion. If the number of medicine drops in the medicine tank is greater than the medicine drop threshold, the infusion is carried out normally.

[0043] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a control system for continuous transfusion and dressing change based on a multi-unit medicine liquid tank, including a computer device, which is programmed or configured to execute any one of the steps of the continuous transfusion and dressing change method based on a multi-unit medicine liquid tank.

[0044] The present invention has the following positive effects:

[0045] 1. The present invention uses an improved Shi-Tomasi corner detection algorithm to extract features from images of medicine liquid tanks and medicine drops, and combines it to build a recurrent neural network prediction model based on the Spearman correlation coefficient to predict the number of medicine drops in the medicine liquid tank. It can not only accurately predict the infusion process of the medicine liquid tank, ensure the smoothness of the medicine liquid tank replacement process, and improve the stability of the continuous infusion and changing process, but also can perform adaptive adjustments for different medicine liquid tanks and medicines without resetting parameters, thereby improving convenience and adaptability, and having strong robustness.

[0046] 2. The present invention controls and adjusts the continuous infusion and dressing change medicine tanks by establishing a continuous infusion and dressing change control function G of a multi-connected medicine liquid tank. Not only does the entire process require no manual dressing change, thereby improving the efficiency and stability of infusion, thereby enhancing the patient's user experience, but also further improving the smoothness of continuous infusion and dressing change. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0048] Figure 2 It is a schematic diagram of the flow of the improved Shi-Tomasi corner detection algorithm of the present invention;

[0049] Figure 3 A schematic diagram of a process for constructing a recurrent neural network prediction model based on the Spearman correlation coefficient of the present invention;

[0050] Figure 4 It is a schematic diagram of the structure of the present invention.

[0051] Explanation of the numbers in the figure: 1- bracket, 2- camera, 3- laser counting sensor, 4- medicine tank, 5- medicine drop. DETAILED DESCRIPTION

[0052] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0053] Example 1: Figure 1 or Figure 4 As shown, a control method for continuous drug delivery and changing based on a multi-link drug liquid tank, the method comprising:

[0054] U1. The multi-linked liquid medicine tank 4 is hung on the bracket 1 for infusion, and the image data information of the liquid medicine tank 4 is obtained in real time based on the camera 2 on the bracket 1, the image data information of the liquid medicine drop 5 is obtained in real time based on the camera 2 on the bracket 1, and the number data information of the dripping liquid medicine drop 5 is obtained in real time based on the laser counting sensor 3 on the bracket 1;

[0055] U2. Based on the image data information of the liquid medicine tank and the image data information of the liquid medicine droplets, the improved Shi-Tomasi corner detection algorithm is used to extract features of the images of the liquid medicine tank and the liquid medicine droplets to obtain image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplets;

[0056] U3. Based on the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets, a recurrent neural network prediction model based on the Spearman correlation coefficient is constructed to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted number data information of the medicine liquid droplets in the medicine liquid tank;

[0057] U4. Based on the predicted data information on the number of medicine droplets in the medicine liquid tank and the data information on the number of dripping medicine droplets, a continuous transfusion and medicine change control function G of the multi-unit medicine liquid tank is established to control and adjust the medicine liquid tank for continuous transfusion and medicine change, and obtain the control data information on continuous transfusion and medicine change of the multi-unit medicine liquid tank.

[0058] In this embodiment, the continuous feeding and changing control function G of the multi-link liquid medicine tank is:

[0059]

[0060] Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, y is the data information of the number of medicine droplets dripping, α1 is the first control factor of the multi-unit medicine tank, α2 is the second control factor of the multi-unit medicine tank, and α3 is the third control factor of the multi-unit medicine tank.

[0061] In this embodiment, the first control factor α1 of the multi-link liquid medicine tank is:

[0062]

[0063] The second control factor α2 of the multi-link liquid medicine tank is:

[0064]

[0065] The third control factor α3 of the multi-link liquid medicine tank is:

[0066]

[0067] Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, and y is the data information of the number of medicine droplets dripping.

[0068] In this embodiment, if Figure 3 As shown, in step U3, the construction of a recurrent neural network prediction model based on the Spearman correlation coefficient to predict the number of drops of medicine in the medicine tank includes:

[0069] U31. Based on the image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplet, a Spearman correlation coefficient function H between the liquid medicine tank and the liquid medicine droplet is established.

[0070]

[0071] Among them, a i is the image feature data information of the liquid medicine tank, n is the sample size, b i is the image feature data information of the medicine droplet, f is the rank function of the image feature of the medicine tank, g is the rank function of the image feature of the medicine droplet, the correlation between the image features of the medicine tank and the medicine droplet is characterized, and the data information of the Spearman correlation coefficient between the medicine tank and the medicine droplet is obtained;

[0072] U32. Input the Spearman correlation coefficient data of the liquid medicine tank and the liquid medicine droplets into the recurrent neural network prediction model for training and learning, and determine the prediction function W of the number of drops in the liquid medicine tank.

[0073]

[0074] Among them, c is the data information of the Spearman correlation coefficient between the drug liquid tank and the drug droplet, α1, α2 and α3 are the learning factors of the prediction model, and the trained recurrent neural network model is obtained;

[0075] U33. Based on the trained recurrent neural network model, the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets are input to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted data information on the number of medicine liquid droplets in the medicine liquid tank.

[0076] In this embodiment, the order function f of the image feature of the liquid medicine tank is:

[0077]

[0078] The order function g of the image feature of the drug droplet is:

[0079]

[0080] Among them, a i is the image feature data information of the liquid medicine tank, bi It is the image feature data information of the medicine droplet.

[0081] In this embodiment, the constraints of the learning factors α1, α2 and α3 of the prediction model are:

[0082]

[0083] Embodiment 2: Based on the control method of continuous transfusion and dressing change based on multiple medicine liquid tanks in Embodiment 1, the present invention is further illustrated and described below.

[0084] like Figure 1 or Figure 4 As shown, a control method for continuous drug delivery and changing based on a multi-link drug liquid tank, the method comprising:

[0085] U1. The multi-linked liquid medicine tank 4 is hung on the bracket 1 for infusion, and the image data information of the liquid medicine tank 4 is obtained in real time based on the camera 2 on the bracket 1, the image data information of the liquid medicine drop 5 is obtained in real time based on the camera 2 on the bracket 1, and the number data information of the dripping liquid medicine drop 5 is obtained in real time based on the laser counting sensor 3 on the bracket 1;

[0086] U2. Based on the image data information of the liquid medicine tank and the image data information of the liquid medicine droplets, the improved Shi-Tomasi corner detection algorithm is used to extract features of the images of the liquid medicine tank and the liquid medicine droplets to obtain image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplets;

[0087] U3. Based on the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets, a recurrent neural network prediction model based on the Spearman correlation coefficient is constructed to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted number data information of the medicine liquid droplets in the medicine liquid tank;

[0088] U4. Based on the predicted data information on the number of medicine droplets in the medicine liquid tank and the data information on the number of dripping medicine droplets, a continuous transfusion and medicine change control function G of the multi-unit medicine liquid tank is established to control and adjust the medicine liquid tank for continuous transfusion and medicine change, and obtain the control data information on continuous transfusion and medicine change of the multi-unit medicine liquid tank.

[0089] In this embodiment, if Figure 2 As shown, in step U2, the feature extraction of the images of the liquid medicine tank and the liquid medicine droplets using the improved Shi-Tomasi corner detection algorithm includes:

[0090] U21. Based on the image data information of the medicine tank and the image data information of the medicine droplets, an image pixel matrix of the medicine tank and an image pixel matrix of the medicine droplets are constructed to obtain image pixel matrix data information of the medicine tank and the medicine droplets;

[0091] U22. Based on the image pixel matrix data information of the liquid medicine tank and the liquid medicine droplet, establish the corner point detection function R1 of the image pixel of the liquid medicine tank and the corner point detection function R2 of the image pixel of the liquid medicine droplet,

[0092]

[0093] Among them, p is the image pixel matrix data information of the medicine tank, q is the image pixel matrix data information of the medicine droplet, μ1, μ2 and μ3 are the image pixel detection factors of the medicine tank, ρ1, ρ2 and ρ3 are the image pixel detection factors of the medicine droplet;

[0094] U23. Based on the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine liquid droplets, feature extraction is performed on the images of the medicine liquid tank and the medicine liquid droplets to obtain image feature data information of the medicine liquid tank and image feature data information of the medicine liquid droplets.

[0095] In this embodiment, in step U23, the feature extraction of the images of the medicine liquid tank and the medicine droplets is performed by obtaining the corner point detection value of the image pixels of the medicine liquid tank and the corner point detection value of the image pixels of the medicine droplets according to the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine droplets, and setting a preset threshold. If the corner point detection value of the image pixels of the medicine liquid tank is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine liquid tank is greater than the preset threshold, the corner point detection value is retained; if the corner point detection value of the image pixels of the medicine droplets is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine droplets is greater than the preset threshold, the corner point detection value is retained.

[0096] In this embodiment, in step U4, the medicine tank for continuous infusion and dressing change is controlled and adjusted according to the continuous infusion and dressing change control function G of the multiple medicine tanks, the number of medicine drops of each medicine tank in the multiple medicine tanks is obtained, and a medicine drop threshold is set. If the number of medicine drops of the medicine tank is less than the medicine drop threshold, it is necessary to replace it with another medicine tank for infusion. If the number of medicine drops of the medicine tank is greater than the medicine drop threshold, the infusion is carried out normally.

[0097] In this embodiment, the present invention provides a control system for continuous transfusion and dressing change based on a multiple-drug liquid tank, including a computer device programmed or configured to execute any one of the steps of the continuous transfusion and dressing change method based on a multiple-drug liquid tank.

[0098] In this embodiment, the present invention provides a computer-readable storage medium, on which is stored a computer program programmed or configured to execute any one of the improved Yolov5 pedestrian detection methods described above.

[0099] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0100] In summary, the present invention can not only accurately control the infusion process of the medicine tank, but also eliminate the need for manual dressing changes during the entire process, thereby improving the efficiency and stability of the infusion and thus enhancing the user experience of the patient.

[0101] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A control method for continuous drug delivery and drug change based on a multi-link drug liquid tank, characterized in that: The method comprises: U1. Hang the multi-link drug tank on the bracket for infusion, obtain the image data information of the drug tank in real time based on the camera on the bracket, obtain the image data information of the drug drop in real time based on the camera on the bracket, and obtain the number data information of the dripping drug drop in real time based on the laser counting sensor on the bracket; U2. Based on the image data information of the liquid medicine tank and the image data information of the liquid medicine droplets, the improved Shi-Tomasi corner detection algorithm is used to extract features of the images of the liquid medicine tank and the liquid medicine droplets to obtain image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplets; U3. Based on the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets, a recurrent neural network prediction model based on the Spearman correlation coefficient is constructed to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted number data information of the medicine liquid droplets in the medicine liquid tank; U4. Based on the predicted data information on the number of medicine droplets in the medicine liquid tank and the data information on the number of dripping medicine droplets, a continuous transfusion and medicine change control function G of the multi-unit medicine liquid tank is established to control and adjust the medicine liquid tank for continuous transfusion and medicine change, and obtain the control data information on continuous transfusion and medicine change of the multi-unit medicine liquid tank.

2. The control method for continuous infusion and dressing change based on multiple drug liquid tanks according to claim 1 is characterized in that: The continuous feeding and changing control function G of the multi-link liquid medicine tank is: Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, y is the data information of the number of medicine droplets dripping, α1 is the first control factor of the multi-unit medicine tank, α2 is the second control factor of the multi-unit medicine tank, and α3 is the third control factor of the multi-unit medicine tank.

3. The control method for continuous feeding and changing of medicines based on multiple medicine tanks according to claim 2 is characterized in that: The first control factor α1 of the multi-link liquid medicine tank is: The second control factor α2 of the multi-link liquid medicine tank is: The third control factor α3 of the multi-link liquid medicine tank is: Among them, x is the data information of the number of medicine droplets in the medicine tank after prediction, and y is the data information of the number of medicine droplets dripping.

4. The control method for continuous infusion and dressing change based on multiple drug liquid tanks according to claim 1 is characterized in that: In step U3, the construction of a recurrent neural network prediction model based on the Spearman correlation coefficient to predict the number of drops of medicine in the medicine tank includes: U31. Based on the image feature data information of the liquid medicine tank and the image feature data information of the liquid medicine droplet, a Spearman correlation coefficient function H between the liquid medicine tank and the liquid medicine droplet is established. Among them, a i is the image feature data information of the liquid medicine tank, n is the sample size, b i is the image feature data information of the medicine droplet, f is the rank function of the image feature of the medicine tank, g is the rank function of the image feature of the medicine droplet, the correlation between the image features of the medicine tank and the medicine droplet is characterized, and the data information of the Spearman correlation coefficient between the medicine tank and the medicine droplet is obtained; U32. Input the Spearman correlation coefficient data of the liquid medicine tank and the liquid medicine droplets into the recurrent neural network prediction model for training and learning, and determine the prediction function W of the number of drops in the liquid medicine tank. Among them, c is the data information of the Spearman correlation coefficient between the drug liquid tank and the drug droplet, α1, α2 and α3 are the learning factors of the prediction model, and the trained recurrent neural network model is obtained; U33. Based on the trained recurrent neural network model, the image feature data information of the medicine liquid tank and the image feature data information of the medicine liquid droplets are input to predict the number of medicine liquid droplets in the medicine liquid tank, and obtain the predicted data information on the number of medicine liquid droplets in the medicine liquid tank.

5. The control method for continuous transfusion and dressing change based on multiple drug liquid tanks according to claim 4 is characterized in that: The order function f of the image feature of the liquid medicine tank is: The order function g of the image feature of the drug droplet is: Among them, a i is the image feature data information of the liquid medicine tank, b i It is the image feature data information of the medicine droplet.

6. The control method for continuous infusion and dressing change based on multiple drug liquid tanks according to claim 4 is characterized in that: The constraints of the learning factors α1, α2 and α3 of the prediction model are:

7. The control method for continuous transfusion and dressing change based on multiple drug liquid tanks according to claim 1 is characterized in that: In step U2, the use of the improved Shi-Tomasi corner detection algorithm to extract features from the images of the liquid medicine tank and the liquid medicine droplets includes: U21. Based on the image data information of the medicine tank and the image data information of the medicine droplets, an image pixel matrix of the medicine tank and an image pixel matrix of the medicine droplets are constructed to obtain image pixel matrix data information of the medicine tank and the medicine droplets; U22. Based on the image pixel matrix data information of the liquid medicine tank and the liquid medicine droplet, establish the corner point detection function R1 of the image pixel of the liquid medicine tank and the corner point detection function R2 of the image pixel of the liquid medicine droplet, Among them, p is the image pixel matrix data information of the medicine tank, q is the image pixel matrix data information of the medicine droplet, μ1, μ2 and μ3 are the image pixel detection factors of the medicine tank, ρ1, ρ2 and ρ3 are the image pixel detection factors of the medicine droplet; U23. Based on the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine liquid droplets, feature extraction is performed on the images of the medicine liquid tank and the medicine liquid droplets to obtain image feature data information of the medicine liquid tank and image feature data information of the medicine liquid droplets.

8. The control method for continuous drug delivery and dressing change based on multiple drug liquid tanks according to claim 7 is characterized in that: In step U23, the feature extraction of the images of the medicine liquid tank and the medicine droplets is performed by obtaining the corner point detection value of the image pixels of the medicine liquid tank and the corner point detection value of the image pixels of the medicine droplets according to the corner point detection function R1 of the image pixels of the medicine liquid tank and the corner point detection function R2 of the image pixels of the medicine droplets, and setting a preset threshold. If the corner point detection value of the image pixels of the medicine liquid tank is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine liquid tank is greater than the preset threshold, the corner point detection value is retained; if the corner point detection value of the image pixels of the medicine droplets is less than the preset threshold, the corner point detection value is eliminated; if the corner point detection value of the image pixels of the medicine droplets is greater than the preset threshold, the corner point detection value is retained.

9. The control method for continuous transfusion and dressing change based on multiple drug liquid tanks according to claim 1, characterized in that: In step U4, the medicine tank for continuous infusion and dressing change is controlled and adjusted according to the continuous infusion and dressing change control function G of the multiple medicine tanks, the number of medicine drops in each medicine tank in the multiple medicine tanks is obtained, and a medicine drop threshold is set. If the number of medicine drops in the medicine tank is less than the medicine drop threshold, it is necessary to replace it with another medicine tank for infusion. If the number of medicine drops in the medicine tank is greater than the medicine drop threshold, the infusion is carried out normally.

10. A control system for continuous drug delivery and changing based on multiple drug liquid tanks, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the continuous transfusion and dressing change method based on multiple drug liquid tanks as described in any one of claims 1 to 9.

Images