Dynamic uniform mixing method, device and equipment for cell subpackaging and medium

By dynamically adjusting the stroke and speed of the extrusion plate during cell partitioning and optimizing the mixing strategy using neural network model, the problem of uneven cell distribution in traditional methods is solved, and the timeliness and consistency of partitioning is improved.

CN118909726APending Publication Date: 2024-11-08SINO BIOCAN (SHANGHAI) BIOTECH LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410983680.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional cell aliquoting methods can easily lead to uneven cell distribution, affecting the concentration uniformity of the product after aliquoting, and the fixed stroke extrusion mixing method is inefficient, resulting in increased control complexity and increased motor noise.

Method used

By determining the current volume during the inlet or outlet of the cell mixing bag, adjusting the stroke distance of the extrusion plate, and dynamically adjusting the stroke and speed of the extrusion plate according to the neural network model to achieve cell suspension Mix the liquid evenly.

Benefits of technology

The timeliness, accuracy and consistency of cell aliquots are improved, and the low efficiency and control complexity are prevented from being mixed until the liquid is injected and the stroke is fixed in traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118909726A_ABST
    Figure CN118909726A_ABST
Patent Text Reader

Abstract

The invention discloses a dynamic uniform mixing method, a dynamic uniform mixing device, dynamic uniform mixing equipment and a dynamic uniform mixing medium for cell subpackaging, relates to the technical field of biomedicine, and is used for solving the problem of non-uniform cell distribution in a subpackaging process caused by an existing cell suspension subpackaging method. The method comprises the following steps: determining the current volume of liquid in a cell blending bag in a liquid inlet or outlet process of the cell blending bag; according to the current volume, the current stroke distance of an extrusion plate is determined; according to the current travel distance, adjusting a preset blending strategy to obtain a target blending strategy; and carrying out extrusion dynamic uniform mixing on the cell uniform mixing bag by adopting the target uniform mixing strategy. Therefore, compared with the prior art, the method has the advantages that the cell suspension can be kept in a uniform state in the subpackaging process by dynamically adjusting the uniform mixing strategy, so that the timeliness, the accuracy and the consistency of cell subpackaging are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of biomedical technology and provides a dynamic mixing method, device, equipment and medium for cell packaging. Background Art

[0002] As we all know, cell packaging is a key step in biomedical experiments, which requires maintaining the uniformity of cell suspension during the packaging process to ensure the reliability and consistency of experimental results. In traditional cell packaging methods, physical stirring, static mixing, or fixed-stroke extrusion mixing are often relied on. However, these methods are very likely to cause uneven cell distribution, thus affecting the concentration uniformity of the product after packaging. In addition, the fixed-stroke extrusion mixing method mainly uses the same stroke to mix liquids of different volumes in the bag, and its effective mixing efficiency is low. For example, the effective mixing time starting from the surface of the bag is 1s. If the stroke is fixed, there is a gap between the surface of the bag and the extrusion plate. This gap stroke is invalid mixing. Furthermore, if the effective mixing time is to be 1s, the extrusion plate stroke time needs to be greater than 1s. Therefore, the mixing efficiency is greatly reduced. Of course, in order to ensure the efficiency of effective mixing, the speed of the extrusion plate can be increased, but this will cause the complexity of the extrusion plate control, and as the liquid is packaged, the amount of liquid in the bag will decrease. In order to ensure the efficiency of effective mixing, the speed of the extrusion plate will increase accordingly, which will affect the life of the control motor and increase the motor noise.

[0003] Therefore, how to maintain uniform distribution during the cell suspension packaging process has become an urgent problem to be solved. Summary of the invention

[0004] The present application provides a dynamic mixing method, device, equipment and medium for cell packaging, which are used to solve the problem of uneven cell distribution during the packaging process caused by existing cell suspension packaging methods.

[0005] In one aspect, a dynamic mixing method for cell packaging is provided, the method comprising:

[0006] During the process of liquid inflow or liquid outflow into the cell mixing bag, determining the current volume of the liquid in the cell mixing bag;

[0007] Determining a current travel distance of the extrusion plate according to the current volume;

[0008] According to the current travel distance, the preset mixing strategy is adjusted to obtain a target mixing strategy;

[0009] The target mixing strategy is adopted to perform extrusion dynamic mixing on the cell mixing bag.

[0010] Optionally, the step of determining the current volume of the liquid in the cell mixing bag during the process of liquid inflow or liquid outflow from the cell mixing bag includes:

[0011] During the process of liquid filling in the cell mixing bag, the current volume in the cell mixing bag during the liquid filling stage is determined according to the reduction in the cell suspension on the weight scale; or,

[0012] During the process of discharging liquid from the cell mixing bag, the current volume of liquid in the cell mixing bag during the discharging stage is determined according to the historical volume in the cell mixing bag, the number of revolutions of the peristaltic pump and the flow rate per revolution of the peristaltic pump.

[0013] Optionally, the step of determining the current travel distance of the extrusion plate according to the current volume includes:

[0014] The current volume is input into the trained first neural network model, and the current travel distance of the extrusion plate is output; wherein the trained first neural network model is obtained based on the YOLO model.

[0015] Optionally, before inputting the current volume into the trained first neural network model and outputting the current travel distance of the extrusion plate, the method further includes:

[0016] Acquire multiple groups of cell mixing bag data; wherein each group of cell mixing bag data corresponds to a volume and travel distance obtained by measuring the cell mixing bag once;

[0017] Constructing a first training data set, a first validation data set, and a first test data set according to the multiple groups of cell mixing bag data and a first preset ratio;

[0018] The initial YOLO model is trained according to the first training data set, the first validation data set, and the first test data set to obtain the trained first neural network model.

[0019] Optionally, the step of determining the current travel distance of the extrusion plate according to the current volume includes:

[0020] The current travel distance of the extrusion plate is determined according to the current volume and a preset linear fitting function; wherein the preset linear fitting function is obtained by linear fitting based on multiple groups of cell mixing bag data, and each group of cell mixing bag data corresponds to the volume and travel distance obtained by measuring the cell mixing bag once.

[0021] Optionally, the step of adjusting the preset mixing strategy according to the current travel distance to obtain a target mixing strategy includes:

[0022] The current travel distance is input into the trained second neural network model, and the target mixing strategy is output; wherein the trained second neural network model is obtained based on a long short-term memory network LSTM model.

[0023] Optionally, before inputting the current travel distance into the trained second neural network model and outputting the target mixing strategy, the method further includes:

[0024] Acquire multiple groups of mixing and extrusion data; wherein each group of mixing and extrusion data corresponds to an extrusion stroke and speed of a group of extrusion plates;

[0025] Constructing a second training data set, a second verification data set, and a second test data set according to the multiple sets of mixed extrusion data and the second preset ratio;

[0026] The initial LSTM model is trained according to the second training data set, the second verification data set and the second test data set to obtain the trained second neural network model.

[0027] In one aspect, a dynamic mixing device for cell packaging is provided, the device comprising:

[0028] A current volume determination unit, used to determine the current volume of the liquid in the cell mixing bag during the process of liquid inflow or liquid outflow from the cell mixing bag;

[0029] a current travel distance determination unit, used to determine the current travel distance of the extrusion plate according to the current volume;

[0030] A mixing strategy obtaining unit, used to adjust the preset mixing strategy according to the current travel distance to obtain a target mixing strategy;

[0031] The extrusion dynamic mixing unit is used to perform extrusion dynamic mixing on the cell mixing bag by adopting the target mixing strategy.

[0032] On the one hand, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein any one of the above methods is implemented when the processor executes the computer program.

[0033] In one aspect, a computer storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, any of the above methods is implemented.

[0034] Compared with the prior art, the beneficial effects of this application are:

[0035] In the embodiment of the present application, during the process of liquid inflow or outflow from the cell mixing bag, first, the current volume of the liquid in the cell mixing bag can be determined; then, the current travel distance of the extrusion plate can be determined based on the current volume; next, the preset mixing strategy can be adjusted based on the current travel distance to obtain the target mixing strategy; finally, the target mixing strategy can be used to perform dynamic extrusion mixing on the cell mixing bag. Therefore, in the embodiment of the present application, since the adjusted mixing strategy is used to perform dynamic extrusion mixing on the liquid in the cell mixing bag during the process of liquid inflow or outflow from the cell mixing bag, compared to the prior art of "starting extrusion mixing only after the liquid is inflow, and the extrusion travel is fixed", the present application can ensure that the cell suspension remains in a uniform state during the packaging process by dynamically adjusting the mixing strategy, thereby improving the timeliness, accuracy and consistency of cell packaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0037] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a process flow of a dynamic mixing method for cell packaging provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of a cell mixing bag provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of linear fitting provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of a dynamic mixing device for cell packaging provided in an embodiment of the present application.

[0042] Markings in the figure: 10 - dynamic mixing equipment for cell packaging, 101 - processor, 102 - memory, 103 - I / O interface, 104 - database, 50 - dynamic mixing device for cell packaging, 501 - current volume determination unit, 502 - current travel distance determination unit, 503 - mixing strategy acquisition unit, 504 - extrusion dynamic mixing unit, 505 - model training unit. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the described embodiment is only a part of the embodiment of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in an order different from that here.

[0044] As we all know, cell packaging is a key step in biomedical experiments, which requires maintaining the uniformity of cell suspension during the packaging process to ensure the reliability and consistency of experimental results. In traditional cell packaging methods, physical stirring, static mixing, or fixed-stroke extrusion mixing are often relied on. However, these methods are very likely to cause uneven cell distribution, thus affecting the concentration uniformity of the product after packaging. In addition, the fixed-stroke extrusion mixing method mainly uses the same stroke to mix liquids of different volumes in the bag, and its effective mixing efficiency is low. For example, the effective mixing time starting from the surface of the bag is 1s. If the stroke is fixed, there is a gap between the surface of the bag and the extrusion plate. This gap stroke is invalid mixing. Furthermore, if the effective mixing time is to be 1s, the extrusion plate stroke time needs to be greater than 1s. Therefore, the mixing efficiency is greatly reduced. Of course, in order to ensure the efficiency of effective mixing, the speed of the extrusion plate can be increased, but this will cause the complexity of the extrusion plate control, and as the liquid is packaged, the amount of liquid in the bag will decrease. In order to ensure the efficiency of effective mixing, the speed of the extrusion plate will increase accordingly, which will affect the life of the control motor and increase the motor noise.

[0045] Based on this, the embodiment of the present application provides a dynamic mixing method for cell packaging, in which, during the process of liquid inflow or outflow of the cell mixing bag, first, the current volume of the liquid in the cell mixing bag can be determined; then, the current travel distance of the extrusion plate can be determined according to the current volume; next, the preset mixing strategy can be adjusted according to the current travel distance to obtain the target mixing strategy; finally, the target mixing strategy can be used to perform extrusion dynamic mixing on the cell mixing bag. Therefore, in the embodiment of the present application, since the adjusted mixing strategy is used to perform extrusion dynamic mixing on the liquid in the cell mixing bag during the process of liquid inflow or outflow of the cell mixing bag, compared with the prior art "extrusion mixing starts only after the liquid is fully inflow, and the extrusion stroke is fixed", the present application can ensure that the cell suspension remains in a uniform state during the packaging process by dynamically adjusting the mixing strategy, thereby improving the timeliness, accuracy and consistency of cell packaging.

[0046] After introducing the design ideas of the embodiments of the present application, the following briefly introduces the application scenarios to which the technical solutions of the embodiments of the present application can be applied. It should be noted that the application scenarios introduced below are only used to illustrate the embodiments of the present application and are not limited. In the specific implementation process, the technical solutions provided by the embodiments of the present application can be flexibly applied according to actual needs.

[0047] like Figure 1 FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application. The application scenario may include a dynamic mixing device 10 for cell packaging.

[0048] Among them, the dynamic mixing device 10 for cell packaging can squeeze and dynamically mix the liquid in the cell mixing bag, for example, it can be a personal computer (PC), a server and a laptop. The dynamic mixing device 10 for cell packaging may include one or more processors 101, a memory 102, an I / O interface 103 and a database 104. Specifically, the processor 101 can be a central processing unit (CPU), or a digital processing unit, etc. The memory 102 can be a volatile memory (volatile memory), such as a random-access memory (RAM); the memory 102 can also be a non-volatile memory (non-volatile memory), such as a read-only memory, a flash memory (flash memory), a hard disk drive (HDD) or a solid-state drive (SSD); or the memory 102 can be any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 102 can be a combination of the above memories. The memory 102 may store some program instructions of the dynamic mixing method for cell packaging provided in the embodiment of the present application, and these program instructions can be used to implement the steps of the dynamic mixing method for cell packaging provided in the embodiment of the present application when executed by the processor 101, so as to solve the problem of uneven cell distribution in the packaging process caused by the existing cell suspension packaging method. The database 104 can be used to store the current volume, current travel distance, target mixing strategy, historical volume, number of peristaltic pump rotations, flow rate per peristaltic pump, first neural network model after training, multiple groups of cell mixing bag data, first preset ratio, second neural network model after training, multiple groups of mixing extrusion data, and second preset ratio and other data involved in the scheme provided in the embodiment of the present application.

[0049] In the embodiment of the present application, the dynamic mixing device 10 for cell packaging can obtain the current volume through the I / O interface 103, and then the processor 101 of the dynamic mixing device 10 for cell packaging will always maintain uniform distribution during the cell suspension packaging process according to the program instructions of the dynamic mixing method for cell packaging provided in the embodiment of the present application in the memory 102. In addition, the current volume, the current travel distance, the target mixing strategy, the historical volume, the number of rotations of the peristaltic pump, the flow rate per rotation of the peristaltic pump, the trained first neural network model, multiple groups of cell mixing bag data, the first preset ratio, the trained second neural network model, multiple groups of mixing extrusion data, and the second preset ratio can also be stored in the database 104.

[0050] Of course, the method provided in the embodiment of the present application is not limited to Figure 1 The application scenarios shown can also be used in other possible application scenarios, and the embodiments of the present application are not limited thereto. Figure 1 The functions that can be realized by each device in the application scenario shown will be described in the subsequent method embodiments, and will not be described in detail here. Below, the method of the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0051] like Figure 2 As shown, it is a schematic diagram of a process flow of a dynamic mixing method for cell packaging provided in an embodiment of the present application. The method can be Figure 1 The method is performed by the dynamic mixing device 10 for cell packaging. Specifically, the process of the method is described as follows.

[0052] Step 201: During the process of liquid inflow or liquid outflow into the cell mixing bag, determine the current volume of the liquid in the cell mixing bag.

[0053] Specifically, the cell mixing bag can be hung on the back plate of the mixing structure, the back plate has a certain slope, and the squeezing plate above is controlled to squeeze back and forth to dynamically mix the cell suspension in the cell mixing bag.

[0054] Furthermore, when performing dynamic mixing of the cell suspension, since it can be specifically divided into a liquid inlet stage and a liquid outlet stage, for the dynamic mixing of the cell suspension in the liquid inlet stage, first, the dynamic mixing mode can be turned on the mixing structure, and then liquid can be added to the cell mixing bag suspended on the mixing structure (from the beginning of inputting the sample liquid into the mixing bag, the squeezing plate can be started to mix the liquid in the cell mixing bag), such as Figure 3 As shown, it is a schematic diagram of a cell mixing bag provided in an embodiment of the present application, wherein the cell mixing bag can be 1L, 3L, 5L, 7L, 10L, 20L and other mixing bags, and it is stipulated that the liquid that can be contained in the bag is half of the designed capacity, and bags of different specifications are enlarged in equal proportion. Based on this, the current volume in the cell mixing bag during the liquid filling stage can be determined according to the reduction of the cell suspension hung on the weight scale. Specifically, the following formula (1) can be used to determine the current volume in the cell mixing bag during the liquid filling process of the cell mixing bag:

[0055] Current volume in the cell mixing bag = reduction in cell suspension on the weight scale (1)

[0056] For the dynamic mixing of the cell suspension in the liquid discharge stage, since the cell mixing bag will continuously discharge liquid, the current volume of the liquid in the cell mixing bag during the liquid discharge process can be determined based on the historical volume in the cell mixing bag (the historical volume is the initial volume of the cell mixing bag when the liquid discharge starts), the number of revolutions of the peristaltic pump and the flow rate per revolution of the peristaltic pump. Specifically, the following formula (2) can be used:

[0057] Current volume in the cell mixing bag = Historical volume in the cell mixing bag - Number of revolutions of the peristaltic pump * Flow rate per revolution of the peristaltic pump (2)

[0058] That is, the current volume in the cell mixing bag is equal to the volume of the influent minus the volume of the effluent.

[0059] Step 202: Determine the current travel distance of the extrusion plate according to the current volume.

[0060] Specifically, the current volume can be input into the trained first neural network model, thereby outputting the current travel distance of the extrusion plate; wherein the trained first neural network model is obtained based on the YOLO model, and the YOLO model can be a YOLO5 model, a YOLO7 model, etc.

[0061] In an embodiment of the present application, before the current volume is input into the trained neural network model and the current travel distance of the extrusion plate is output, the initial YOLO model can also be trained to obtain a trained first neural network model. Specifically, first, multiple sets of cell mixing bag data can be obtained from a local database or a cloud database; wherein each set of cell mixing bag data corresponds to a volume and travel distance obtained by measuring the cell mixing bag once; then, a first training data set, a first validation data set, and a first test data set can be constructed based on the multiple sets of cell mixing bag data and a first preset ratio (for example, 6:3:1); finally, the initial YOLO model can be directly trained based on the first training data set, the first validation data set, and the first test data set to obtain a trained first neural network model.

[0062] Of course, in order to reduce the preliminary preparation time, in the embodiment of the present application, the current travel distance of the extrusion plate can also be determined by a preset linear fitting function obtained by "linear fitting".

[0063] That is, the current travel distance of the extrusion plate can be determined based on the current volume and a preset linear fitting function; wherein the preset linear fitting function is obtained by linear fitting based on multiple sets of cell mixing bag data, and each set of cell mixing bag data corresponds to the volume and travel distance obtained by measuring the cell mixing bag once.

[0064] Specifically, the height from different cell mixing bags to the extrusion plate after entering the same liquid can be measured to obtain multiple groups of cell mixing bag data. Then, for the same amount of liquid in the cell mixing bags, the bag thickness (i.e., travel distance) of the cell mixing bags of different capacities can be averaged to obtain the average values ​​corresponding to different liquid amounts. Next, the average values ​​corresponding to different liquid amounts can be linearly fitted to obtain a preset linear fitting function.

[0065] Table 1

[0066]

[0067] For example, as shown in Table 1, a relationship table between the amount of liquid and the thickness of the bag provided in the embodiment of the present application is shown. According to the data of multiple groups of cell mixing bags shown in Table 1, through linear fitting, as shown in FIG. Figure 4 As shown, it is a schematic diagram of the linear fitting provided in the embodiment of the present application, and the mathematical expression of the current volume in the cell mixing bag and the current travel distance shown in the following formula (3) can be obtained:

[0068] y=11.832x+38.789 (3)

[0069] Wherein, y represents the current travel distance (i.e., bag thickness, distance from the back plate to the extrusion plate); x represents the current volume in the cell mixing bag.

[0070] Furthermore, when determining the current volume in the cell mixing bag, the current volume can be directly substituted into formula (3) to determine the current travel distance of the extrusion plate.

[0071] Step 203: According to the current volume travel distance, the preset mixing strategy is adjusted to obtain the target mixing strategy.

[0072] In the embodiment of the present application, the target mixing strategy is used to adjust the extrusion stroke and speed of the extrusion plate. Of course, only the extrusion stroke of the extrusion plate can be adjusted (under the premise that the speed of the extrusion plate is fixed).

[0073] Specifically, the current travel distance can be input into the trained second neural network model, thereby outputting the target mixing strategy; wherein the trained second neural network model is obtained based on the long short-term memory network LSTM model.

[0074] In an embodiment of the present application, before inputting the current travel distance into the trained second neural network model and outputting the target mixing strategy, the initial long short-term memory network (Long Short-Term Memory, LSTM) model can also be trained to obtain the trained second neural network model. Specifically, first, multiple groups of mixing extrusion data can be obtained from a local database or a cloud database; wherein each group of mixing extrusion data corresponds to a group of extrusion strokes and speeds of an extrusion plate; then, a second training data set, a second verification data set, and a second test data set can be constructed based on the multiple groups of mixing extrusion data and a second preset ratio (for example, 5:3:2); finally, the initial LSTM model can be directly trained based on the second training data set, the second verification data set, and the second test data set to obtain the trained second neural network model.

[0075] Step 204: Adopting a target mixing strategy, the cell mixing bag is subjected to extrusion dynamic mixing.

[0076] In an embodiment of the present application, based on the target mixing strategy, the cell mixing bag can be dynamically mixed by squeezing the cell mixing bag by controlling the motor command and issuing the extrusion stroke and speed of the extrusion plate, thereby ensuring that the cell suspension remains evenly distributed during the packaging process when the cell mixing bag is filled with liquid or discharged with liquid.

[0077] To summarize, since the adjusted mixing strategy is used to dynamically mix the liquid in the cell mixing bag by squeezing during the process of liquid entering or exiting the cell mixing bag, compared to the prior art of "starting extrusion mixing only after the liquid has entered, and the extrusion stroke is fixed", the present application can ensure that the cell suspension remains in a uniform state during the packaging process by dynamically adjusting the mixing strategy, thereby improving the timeliness, accuracy and consistency of cell packaging.

[0078] Based on the same inventive concept, the present embodiment provides a dynamic mixing device 50 for cell packaging, such as Figure 5 As shown, the dynamic mixing device 50 for cell packaging includes:

[0079] The current volume determination unit 501 is used to determine the current volume of the liquid in the cell mixing bag during the process of liquid inflow or liquid outflow from the cell mixing bag;

[0080] A current travel distance determination unit 502, used to determine the current travel distance of the extrusion plate according to the current volume;

[0081] A mixing strategy obtaining unit 503 is used to adjust the preset mixing strategy according to the current travel distance to obtain a target mixing strategy;

[0082] The extrusion dynamic mixing unit 504 is used to perform extrusion dynamic mixing on the cell mixing bag by adopting a target mixing strategy.

[0083] Optionally, the current volume determining unit 501 is further configured to:

[0084] During the process of liquid filling into the cell mixing bag, the current volume in the cell mixing bag during the liquid filling phase is determined according to the reduction in the cell suspension on the weight scale; or,

[0085] During the process of discharging liquid from the cell mixing bag, the current volume of liquid in the cell mixing bag during the discharging stage is determined according to the historical volume in the cell mixing bag, the number of revolutions of the peristaltic pump and the flow rate per revolution of the peristaltic pump.

[0086] Optionally, the current travel distance determining unit 502 is further configured to:

[0087] The current volume is input into the trained first neural network model, and the current travel distance of the extrusion plate is output; wherein the trained first neural network model is obtained based on the YOLO model.

[0088] Optionally, the dynamic mixing device 50 for cell packaging includes a model training unit 505, which is used to:

[0089] Acquire multiple groups of cell mixing bag data; wherein each group of cell mixing bag data corresponds to a volume and travel distance obtained by measuring the cell mixing bag once;

[0090] Constructing a first training data set, a first validation data set, and a first test data set according to the multiple groups of cell mixing bag data and a first preset ratio;

[0091] The initial YOLO model is trained according to the first training data set, the first verification data set, and the first test data set to obtain a trained first neural network model.

[0092] Optionally, the current travel distance determining unit 502 is further configured to:

[0093] The current travel distance of the extrusion plate is determined based on the current volume and a preset linear fitting function; wherein the preset linear fitting function is obtained by linear fitting based on multiple groups of cell mixing bag data, and each group of cell mixing bag data corresponds to the volume and travel distance obtained by measuring the cell mixing bag once.

[0094] Optionally, the mixing strategy obtaining unit 503 is further used to:

[0095] The current travel distance is input into the trained second neural network model, and the target mixing strategy is output; wherein the trained second neural network model is obtained based on the long short-term memory network LSTM model.

[0096] Optionally, the model training unit 505 is further used for:

[0097] Acquire multiple groups of mixing and extrusion data; wherein each group of mixing and extrusion data corresponds to an extrusion stroke and speed of a group of extrusion plates;

[0098] Constructing a second training data set, a second validation data set, and a second test data set according to the multiple sets of mixed extrusion data and the second preset ratio;

[0099] The initial LSTM model is trained according to the second training data set, the second verification data set, and the second test data set to obtain a trained second neural network model.

[0100] The dynamic mixing device 50 for cell packaging can be used to perform Figure 2-Figure 4 The method is performed in the embodiment shown in the figure. Therefore, the functions that can be realized by each functional module of the dynamic mixing device 50 for cell packaging can be referred to. Figure 2-Figure 4 The description of the illustrated embodiment is not repeated in detail.

[0101] In some possible implementations, various aspects of the method provided in the present application may also be implemented in the form of a program part, which includes a program code. When the program part is run on a computer device, the program code is used to enable the computer device to execute the steps of the method according to various exemplary embodiments of the present application described above in this specification. For example, the computer device may execute the following steps: Figure 2-Figure 4 The method performed in the illustrated embodiment.

[0102] It can be understood by those skilled in the art that all or part of the steps of the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above method embodiment are executed; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk. Alternatively, if the above integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent part, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present invention can be essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software part, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. And the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disk or optical disk.

[0103] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A dynamic mixing method for cell packaging, characterized in that: The method comprises: During the process of liquid inflow or liquid outflow into the cell mixing bag, determining the current volume of the liquid in the cell mixing bag; Determining a current travel distance of the extrusion plate according to the current volume; According to the current travel distance, the preset mixing strategy is adjusted to obtain a target mixing strategy; The target mixing strategy is adopted to perform extrusion dynamic mixing on the cell mixing bag.

2. The method according to claim 1, characterized in that The step of determining the current volume of the liquid in the cell mixing bag during the process of liquid inflow or liquid outflow from the cell mixing bag comprises: During the process of liquid filling in the cell mixing bag, the current volume in the cell mixing bag during the liquid filling stage is determined according to the reduction in the cell suspension on the weight scale; or, During the process of discharging liquid from the cell mixing bag, the current volume of liquid in the cell mixing bag during the discharging stage is determined according to the historical volume in the cell mixing bag, the number of revolutions of the peristaltic pump and the flow rate per revolution of the peristaltic pump.

3. The method according to claim 1, characterized in that The step of determining the current travel distance of the extrusion plate according to the current volume comprises: The current volume is input into the trained first neural network model, and the current travel distance of the extrusion plate is output; wherein the trained first neural network model is obtained based on the YOLO model.

4. The method according to claim 3, characterized in that Before inputting the current volume into the trained first neural network model and outputting the current travel distance of the extrusion plate, the method further includes: Acquire multiple groups of cell mixing bag data; wherein each group of cell mixing bag data corresponds to a volume and a travel distance obtained by measuring the cell mixing bag once; Constructing a first training data set, a first validation data set, and a first test data set according to the multiple groups of cell mixing bag data and a first preset ratio; The initial YOLO model is trained according to the first training data set, the first validation data set, and the first test data set to obtain the trained first neural network model.

5. The method according to claim 1, characterized in that The step of determining the current travel distance of the extrusion plate according to the current volume comprises: The current travel distance of the extrusion plate is determined according to the current volume and a preset linear fitting function; wherein the preset linear fitting function is obtained by linear fitting based on multiple groups of cell mixing bag data, and each group of cell mixing bag data corresponds to the volume and travel distance obtained by measuring the cell mixing bag once.

6. The method according to claim 1, characterized in that The step of adjusting the preset mixing strategy according to the current travel distance to obtain the target mixing strategy includes: The current travel distance is input into the trained second neural network model, and the target mixing strategy is output; wherein the trained second neural network model is obtained based on a long short-term memory network LSTM model.

7. The method according to claim 6, characterized in that Before inputting the current travel distance into the trained second neural network model and outputting the target mixing strategy, the method further includes: Acquire multiple groups of mixing and extrusion data, wherein each group of mixing and extrusion data corresponds to an extrusion stroke and speed of a group of extrusion plates; Constructing a second training data set, a second verification data set, and a second test data set according to the multiple sets of mixed extrusion data and the second preset ratio; The initial LSTM model is trained according to the second training data set, the second verification data set and the second test data set to obtain the trained second neural network model.

8. A dynamic mixing device for cell packaging, characterized in that: The device comprises: A current volume determination unit, used to determine the current volume of the liquid in the cell mixing bag during the process of liquid inflow or liquid outflow from the cell mixing bag; a current travel distance determination unit, used to determine the current travel distance of the extrusion plate according to the current volume; A mixing strategy obtaining unit, used to adjust the preset mixing strategy according to the current travel distance to obtain a target mixing strategy; The extrusion dynamic mixing unit is used to perform extrusion dynamic mixing on the cell mixing bag by adopting the target mixing strategy.

9. An electronic device, characterized in that: The device comprises: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute any method according to claims 1-7 according to the obtained program instructions.

10. A storage medium, characterized in that: The storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute any one of the methods of claims 1-7.