Control system and method for regulating and controlling flow velocity and pressure in immune cell production system

Abstract

The invention provides a control system and method for regulating and controlling flow velocity and pressure in an immune cell production system. The method comprises the following steps: receiving a request signal which is sent by an immune cell production system and is used for regulating and controlling flow velocity and pressure, and analyzing the request signal to obtain an immune cell type, immune cell culture data and a bioreactor type; the immune cell type and immune cell cultivation data are imported into the simulation prediction model, and regulation and control target data are output; determining a corresponding conversion mode according to the bioreactor type, and converting the regulation and control target data into target regulation and control parameters of the mixing equipment according to the conversion mode; and feeding back the target regulation and control parameters to the immune cell production system, so that the immune cell production system controls mixing equipment of the bioreactor according to the target regulation and control parameters. According to the invention, the flow velocity and the pressure which are most adaptive to the immune cells cultured in the bioreactor can be automatically analyzed, so that the probability that the immune cells are damaged by improper flow velocity and pressure is reduced.

Description

Technical Field

[0001] The present invention relates to the fields of immune cell production and computer technology, and in particular to a control system and method for flow rate and pressure regulation in an immune cell production system. Background Art

[0002] Immune cells are an important part of the human immune system. They are responsible for recognizing and defending against pathogens such as bacteria, viruses, fungi and parasites, as well as cancer cells and transplanted tissues. The function of the immune system is crucial to maintaining the body's health by eliminating pathogens before they can cause disease.

[0003] Bioreactors are important equipment in immune cell production systems. These include stirred bioreactors and wave-type bioreactors, which can mix cell suspensions through stirring or rocking motions, ensuring that cells are evenly distributed within the reactor, thereby increasing the cells' access to nutrients. However, the stirring or rocking speeds of existing bioreactors are typically set based on empirical values. The actual flow rate and pressure of the cell suspension are not well-suited to immune cells, making them susceptible to damage due to excessive shear force and pressure. Setting the actual flow rate and pressure of the cell suspension too low will result in uneven distribution of cells within the reactor, affecting their access to nutrients.

[0004] Therefore, how to further improve the actual flow rate and pressure of the cell suspension to make it compatible with immune cells is a technical problem that needs to be solved at present. Summary of the Invention

[0005] To solve at least one of the above technical problems, the present invention specifically provides a control method, system, electronic device, computer storage medium and computer program product for flow rate and pressure regulation in an immune cell production system.

[0006] The present invention provides a control method for flow rate and pressure regulation in an immune cell production system, comprising the following steps: receiving a request signal for regulating flow rate and pressure from the immune cell production system, and parsing the request signal to obtain immune cell type, immune cell cultivation data, and bioreactor type; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determining a corresponding conversion method according to the type of the bioreactor, and converting the control target data into target control parameters of the mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

[0007] Furthermore, the receiving of a request signal for regulating flow rate and pressure sent by the immune cell production system includes: After receiving a request signal for regulating flow rate and pressure from the immune cell production system, determining whether the immune cell production system corresponding to the request signal is a registered system; If so, generating a trigger signal, wherein the trigger signal is used to trigger a response to the request signal of the immune cell production system; If not, a registration signal is fed back to the immune cell production system, and registration information sent by the immune cell production system in response to the registration signal is received; a rationality analysis is performed on the number ID of the immune cell production system and the detailed data of immune cell cultivation parsed from the registration information, and the rationality analysis is based on the pre-stored immune cell cultivation record information and plan information; if the rationality analysis passes, the trigger signal is generated.

[0008] Furthermore, the step of importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, includes: The simulation prediction model calls the stage prediction sub-model to analyze the immune cell cultivation data to obtain a predicted cell cultivation stage; wherein the immune cell cultivation data includes cell proliferation and quantity, cell purity and differentiation state, and cell functional activity; The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output the regulation target data.

[0009] Furthermore, the calling of the stage prediction sub-model to analyze the immune cell culture data to obtain a predicted cell culture stage includes: The convolutional network in the stage prediction sub-model performs feature extraction on the immune cell cultivation data to obtain cell cultivation feature data, and the cell cultivation feature data is input into the classification model in the stage prediction sub-model, and the classification model outputs the predicted cell cultivation stage.

[0010] Furthermore, the simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output the control target data, including: The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output first regulation target data; Obtaining the number of self-regulations of the immune cell production system corresponding to the cell cultivation stage before the request signal is issued, and determining a first regulation index and a second regulation index based on the number of self-regulations; wherein the first regulation index is negatively correlated with the number of self-regulations, and the second regulation index is positively correlated with the number of self-regulations; Using the first adjustment index, the first control target data is adjusted to second control target data, and the second control target data is determined as the control target data; wherein the first adjustment index is a value less than 1; Furthermore, a re-adjustment frequency is determined based on the second adjustment index, and the control target data is predicted multiple times according to the re-adjustment frequency; wherein the re-adjustment frequency is positively correlated with the second adjustment index.

[0011] Furthermore, determining a corresponding conversion method according to the bioreactor type, and converting the control target data into target control parameters of the mixing device according to the conversion method, includes: If the bioreactor type is a stirring type, the first conversion method is used to convert the control target data into the first target control parameter of the mixing device; if the bioreactor type is a swing type, the second conversion method is used to convert the control target data into the second target control parameter of the mixing device.

[0012] The present invention also provides a control system for flow rate and pressure regulation in an immune cell production system, the system comprising a processing module and a storage module; the processing module is electrically connected to the storage module; the processing module calls the executable computer program code stored in the storage module to perform the following steps: receiving a request signal for regulating flow rate and pressure from the immune cell production system, and parsing the request signal to obtain immune cell type, immune cell cultivation data, and bioreactor type; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determining a corresponding conversion method according to the type of the bioreactor, and converting the control target data into target control parameters of the mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

[0013] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute any of the methods described above.

[0014] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0015] The present invention also provides a computer program product, which is used to be called and executed by a processor of an electronic device to implement any of the methods described above.

[0016] The beneficial effect of the present invention is that the scheme of the present invention uses the constructed simulation prediction model to conduct in-depth analysis and processing of immune cell types and immune cell cultivation data, and obtains the target flow rate and target pressure that are most suitable for the immune cells cultivated in the bioreactor, so as to reduce the probability of immune cells being damaged by inappropriate flow rate and pressure, and can significantly improve the cultivation efficiency of immune cells. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of a control method for flow rate and pressure regulation in an immune cell production system disclosed in an embodiment of the present invention.

[0019] Figure 2 This is a structural schematic diagram of a control system for flow rate and pressure regulation in an immune cell production system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize 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.

[0021] The stirring or rocking speeds of existing bioreactors are typically set based on empirical values. The actual flow rate and pressure of the cell suspension are not well-suited to immune cells, making them susceptible to damage due to excessive shear and pressure. Setting the actual flow rate and pressure too low can lead to uneven cell distribution within the reactor, hindering their ability to access nutrients. Therefore, further improving the compatibility of the actual flow rate and pressure of the cell suspension with immune cells is a technical challenge that needs to be addressed.

[0022] See Figure 1 As shown in the flow diagram, an embodiment of the present invention provides a control method for flow rate and pressure regulation in an immune cell production system, comprising the following steps: receiving a request signal for regulating flow rate and pressure from the immune cell production system, and parsing the request signal to obtain immune cell type, immune cell cultivation data, and bioreactor type; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determining a corresponding conversion method according to the type of the bioreactor, and converting the control target data into target control parameters of the mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

[0023] In response to the above technical problems, the present invention, after receiving the request signal for regulating the flow rate and pressure sent by the immune cell production system, parses and obtains the immune cell type, immune cell cultivation data, and bioreactor type. Then, the immune cell type and immune cell cultivation data obtained by the analysis are imported into the simulation prediction model, and the simulation prediction model conducts an in-depth analysis of the aforementioned data to obtain the control target data, which includes the target flow rate and target pressure. Then, according to the type of bioreactor, a suitable conversion method is selected, and the aforementioned control target data is converted into target control parameters that can be specifically executed by the mixing device of the bioreactor according to the corresponding conversion method. Finally, the converted target control parameters are fed back to the corresponding immune cell production system. After the immune cell production system receives the target control parameters, it can control the mixing device of the bioreactor to execute, thereby achieving the flow rate and pressure of the cell suspension in the bioreactor being regulated to the target flow rate and target pressure, respectively.

[0024] Therefore, the solution of the present invention uses the constructed simulation prediction model to conduct in-depth analysis and processing of immune cell types and immune cell cultivation data, and obtains the target flow rate and target pressure that are most suitable for the immune cells cultivated in the bioreactor, so as to reduce the probability of immune cells being damaged by inappropriate flow rate and pressure, and can significantly improve the cultivation efficiency of immune cells.

[0025] It should be noted that the solution of the present invention can be executed on the server side, and the server can be connected to multiple groups of immune cell production systems at the same time, and respectively receive the request signals sent by each immune cell production system to control the flow rate and pressure, and then generate corresponding target control parameters for it to achieve efficient centralized control of the immune cell production system. Among them, each group of immune cell production systems can be an immune cell production system located in the same production workshop, or it can be an immune cell production system located in different production workshops and belonging to different regions or personnel. Correspondingly, the server can be a local server or an online server, and the present invention does not specifically limit this.

[0026] Furthermore, the receiving of a request signal for regulating flow rate and pressure sent by the immune cell production system includes: After receiving a request signal for regulating flow rate and pressure from the immune cell production system, determining whether the immune cell production system corresponding to the request signal is a registered system; If so, generating a trigger signal, wherein the trigger signal is used to trigger a response to the request signal of the immune cell production system; If not, a registration signal is fed back to the immune cell production system, and registration information sent by the immune cell production system in response to the registration signal is received; a rationality analysis is performed on the number ID of the immune cell production system and the detailed data of immune cell cultivation parsed from the registration information, and the rationality analysis is based on the pre-stored immune cell cultivation record information and plan information; if the rationality analysis passes, the trigger signal is generated.

[0027] In this example, the server in the present invention can provide services for regulating the flow rate and pressure of bioreactors for multiple groups of immune cell production systems, but these immune cell production systems are required to register in the server in advance to avoid abuse of the service. In this regard, after receiving the request signal for regulating the flow rate and pressure sent by the immune cell production system, the server first determines whether the immune cell production system that sends the request signal is registered in the server. If it has been registered, a trigger signal can be directly generated, and the subsequent response to the request signal of the immune cell production system can be started based on the trigger signal, that is, the corresponding target control parameters are analyzed for it. If it has not been registered, a registration signal is fed back to the immune cell production system to prompt the immune cell production system to submit a registration request and related registration data, and the number ID of the immune cell production system and the detailed data of immune cell cultivation submitted by the immune cell production system are subjected to rationality analysis. If the rationality analysis passes, a trigger signal can be generated, that is, it is started to analyze the corresponding target control parameters for it.

[0028] The rationality analysis is based on pre-stored immune cell cultivation record information and plan information. Specifically, the server stores immune cell cultivation record information and plan information automatically uploaded by the manufacturer's management system or manually uploaded by the manufacturer's management personnel for the corresponding immune cell production system. The immune cell cultivation record information is the manufacturer's current immune cell cultivation information, which includes which immune cell production system is performing which type of immune cell cultivation. The plan information is the manufacturer's planned immune cell cultivation information for the near future (e.g., one month, one quarter). The received immune cell production system ID and detailed immune cell cultivation data are matched with the immune cell cultivation record information and plan information stored in the server for analysis. For example, if the detailed immune cell cultivation data currently being performed by the immune cell production system with the ID matches the immune cell cultivation record information, and / or the detailed immune cell cultivation data matches the immune cell cultivation plan information (the ID of the immune cell production system used for the specific cultivation may not yet be determined), the rationality analysis is determined to have passed; otherwise, it is determined to have failed.

[0029] Furthermore, the step of importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, includes: The simulation prediction model calls the stage prediction sub-model to analyze the immune cell cultivation data to obtain a predicted cell cultivation stage; wherein the immune cell cultivation data includes cell proliferation and quantity, cell purity and differentiation state, and cell functional activity; The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output the regulation target data.

[0030] In this example, the upper limits of the adaptability of different immune cells to shear force and pressure are different, and the differences are large. For example, CHO cells and intestinal stem cells have limited adaptability to shear force and pressure in bioreactors, while macrophages and neutrophils have higher adaptability to shear force and pressure. At the same time, in different culture stages, the physiological state of immune cells is different, and the required flow rate and pressure are also different. For example, in the cell expansion stage, a higher oxygen supply and nutrient exchange are required, and correspondingly, the cell suspension is required to have a higher flow rate and pressure; and in the cell harvesting stage, the integrity and activity protection of the cells need to be considered, and correspondingly, the flow rate and pressure of the cell suspension need to be appropriately lowered. Therefore, the simulation prediction model of the present invention can simultaneously conduct in-depth analysis of the immune cell type and the cell culture stage to obtain adaptive regulation target data.

[0031] The simulation prediction model in the present invention can be a composite model, further including a stage prediction sub-model embedded therein. This sub-model is used to analyze immune cell culture data to predict the cell culture stage. Therefore, after the immune cell type and immune cell culture data are imported into the simulation prediction model, if the simulation prediction model finds that the imported data does not contain cell culture stage information, the stage prediction sub-model can be invoked to independently predict the cell culture stage information. The previously determined immune cell type and cell culture stage are then subjected to prediction processing to obtain and output the control target data.

[0032] Among them, immune cell cultivation data include but are not limited to cell proliferation and quantity (expansion multiples, cell survival rate), cell purity and differentiation status (cell purity, cell differentiation markers), and cell functional activity (cytotoxicity, types and quantities of cytokine secretion).

[0033] It should be noted that the simulation prediction model can be constructed based on the Transformer model and fully trained using training data. The Transformer model includes several encoders and decoders. The encoder includes a Multi-Head Attention module, which is composed of multiple Self-Attentions, and the decoder includes two Multi-Head Attentions. There is also an Add+Norm layer above the Multi-Head Attention. Add represents the residual connection (Residual Connection) used to prevent network degradation, and Norm represents Layer Normalization, which is used to normalize the activation values ​​of each layer. The simulation prediction model can also be obtained by lightly training a general large model (such as BERT, GPT series models) with small sample data or medium sample data, which is not specifically limited in the present invention. For the stage prediction sub-model, it is preferred to use a conventional classification model, such as SVM, Bayesian, etc. Since the classification algorithms such as SVM and Bayesian are very mature, the present invention will not go into details about their model structure here.

[0034] Furthermore, the calling of the stage prediction sub-model to analyze the immune cell culture data to obtain a predicted cell culture stage includes: The convolutional network in the stage prediction sub-model performs feature extraction on the immune cell cultivation data to obtain cell cultivation feature data, and the cell cultivation feature data is input into the classification model in the stage prediction sub-model, and the classification model outputs the predicted cell cultivation stage.

[0035] In this example, the present invention improves conventional classification models such as SVM and Bayesian, and adds a convolutional network at the front end, that is, the stage prediction sub-model includes a convolutional network and a classification model. Among them, the convolutional network can be CNN, GCN, etc., and the classification model is the above-mentioned SVM, Bayesian and other classification models. The convolutional network first extracts features from the immune cell culture data, and then the classification model classifies and processes the obtained cell culture feature data to obtain the corresponding cell culture stage. Since the convolutional network has a stronger feature extraction capability and can extract more detailed and accurate features, coordinating it with the conventional classification model can make the predicted cell culture stage closer to the actual situation.

[0036] Furthermore, the simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output the control target data, including: The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output first regulation target data; Obtaining the number of self-regulations of the immune cell production system corresponding to the cell cultivation stage before the request signal is issued, and determining a first regulation index and a second regulation index based on the number of self-regulations; wherein the first regulation index is negatively correlated with the number of self-regulations, and the second regulation index is positively correlated with the number of self-regulations; Using the first adjustment index, the first control target data is adjusted to second control target data, and the second control target data is determined as the control target data; wherein the first adjustment index is a value less than 1; Furthermore, a re-adjustment frequency is determined based on the second adjustment index, and the control target data is predicted multiple times according to the re-adjustment frequency; wherein the re-adjustment frequency is positively correlated with the second adjustment index.

[0037] In this example, the trained simulation prediction model can perform an in-depth analysis of the input immune cell type and cell culture stage, and predict the first control target data suitable for the current cell culture situation of the immune cell production system. That is, according to the first control target data, appropriate shear force and pressure can be provided for the immune cells in the bioreactor, which is conducive to the cultivation of immune cells.

[0038] At the same time, the immune cell production system itself will also be equipped with a self-regulating system, based on which the mixing device can be controlled to adjust the flow rate and pressure in the bioreactor. However, since the server's control system is continuously updated and trained with more data, its control capability is stronger than that of the self-regulating system. When the self-regulating system analyzes that it cannot complete the target control, it will send the above-mentioned request signal to the server to request the server to assist in determining the control target data. Therefore, the present invention also obtains the number of self-regulations of the immune cell production system corresponding to the current cell culture stage before the request signal is issued, and determines the first regulation index and the second regulation index based on the number of self-regulations. Among them, the first regulation index is a value less than 1, and the first regulation index is negatively correlated with the number of self-regulation times, that is, the first regulation index decreases as the number of self-regulation times of the self-regulation system of the immune cell production system increases, and increases as the number of self-regulation times of the self-regulation system of the immune cell production system decreases; and the second regulation index is positively correlated with the number of self-regulation times, that is, the second regulation index increases as the number of self-regulation times of the self-regulation system of the immune cell production system increases, and decreases as the number of self-regulation times of the self-regulation system of the immune cell production system decreases.

[0039] Next, the first control target data predicted by the simulation prediction model is multiplied by the first control index to obtain the second control target data, which is used as the control target data. That is, after the immune cell production system's self-regulatory system has made multiple adjustments, the server uses a weaker adjustment method (using a first control index less than 1 to appropriately lower the target flow rate and target pressure in the first control target data) to make tentative adjustments to avoid damage to the immune cells caused by improper flow rate and pressure.

[0040] Furthermore, the readjustment frequency is determined based on the second adjustment index, and the control target data is predicted multiple times according to the readjustment frequency, that is, the mixing device is adjusted multiple times. Since the first adjustment index is weakened as described above, it is necessary to perform multiple prediction analyses on the control target data in the future to ensure that the immune cells obtain the best cultivation environment as a whole during the cultivation stage. Specifically, the more times the self-regulation system of the immune cell production system is self-regulated, the larger the second adjustment index is set accordingly, and the larger the readjustment frequency is, that is, the more times the control target data is predicted during the cultivation stage (that is, the prediction interval is lowered); conversely, the fewer times the self-regulation system of the immune cell production system is self-regulated, the smaller the second adjustment index is set accordingly, and the smaller the readjustment frequency is, that is, the fewer times the control target data is predicted during the cultivation stage (that is, the prediction interval is increased).

[0041] It should be noted that, for the negative correlation between the first adjustment index and the number of self-regulations, the positive correlation between the second adjustment index and the number of self-regulations, and the positive correlation between the readjustment frequency and the second adjustment index, the present invention does not limit the specific form of expression of the above-mentioned correlations, which can be in the form of a conversion function or a comparison table.

[0042] Furthermore, determining a corresponding conversion method according to the bioreactor type, and converting the control target data into target control parameters of the mixing device according to the conversion method, includes: If the bioreactor type is a stirring type, the first conversion method is used to convert the control target data into the first target control parameter of the mixing device; if the bioreactor type is a swing type, the second conversion method is used to convert the control target data into the second target control parameter of the mixing device.

[0043] In this example, the bioreactor types are stirred and rocking (i.e., wave-type), corresponding to different mixing equipment types. Therefore, after determining the target flow rate and target pressure for the suspension—the target control data—it is necessary to select the appropriate conversion method based on the type of mixing equipment to determine the corresponding target control parameters. This ensures that different mixing equipment can control the suspension to the target flow rate and target pressure.

[0044] It should be noted that the mixing device of the present invention includes both a mixing device for regulating the flow rate of the suspension and a pressurizing device for regulating the pressure of the suspension. However, since different flow rates of the suspension will also result in different pressures, the effect of the mixing device on the pressure needs to be considered when determining the target control parameter, and the pressure applied by the pressurizing device should be adjusted accordingly, for example, by appropriately reducing the pressure applied by the pressurizing device.

[0045] like Figure 2 As shown in the structural schematic diagram, an embodiment of the present invention further discloses a control system for flow rate and pressure regulation in an immune cell production system, the system comprising a processing module and a storage module; the processing module is electrically connected to the storage module; the processing module calls the executable computer program code stored in the storage module to perform the following steps: receiving a request signal for regulating flow rate and pressure from the immune cell production system, and parsing the request signal to obtain immune cell type, immune cell cultivation data, and bioreactor type; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determining a corresponding conversion method according to the type of the bioreactor, and converting the control target data into target control parameters of the mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

[0046] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in the above embodiment.

[0047] An embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0048] An embodiment of the present invention further discloses a computer program product, which is used to be called and executed by a processor of an electronic device to implement any of the above methods.

[0049] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0050] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable load balancing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0051] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0052] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0053] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A control method for flow rate and pressure regulation in an immune cell production system, characterized in that: The steps include: Receiving a request signal for regulating flow rate and pressure sent by the immune cell production system, and parsing the request signal to obtain immune cell types, immune cell cultivation data, and bioreactor types; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determine a corresponding conversion method according to the type of the bioreactor, and convert the control target data into a target control parameter of a mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

2. A control method for flow rate and pressure regulation in an immune cell production system according to claim 1, characterized in that: Receive request signals from the immune cell production system to regulate flow rate and pressure, including: After receiving a request signal for regulating flow rate and pressure sent by the immune cell production system, determining whether the immune cell production system corresponding to the request signal is a registered system; If so, a trigger signal is generated, wherein the trigger signal is used to trigger a response to the request signal of the immune cell production system; If not, a registration signal is fed back to the immune cell production system, and registration information sent by the immune cell production system in response to the registration signal is received; a rationality analysis is performed on the number ID of the immune cell production system and the detailed data of immune cell cultivation parsed from the registration information, and the rationality analysis is based on the pre-stored immune cell cultivation record information and plan information; if the rationality analysis passes, the trigger signal is generated.

3. A control method for flow rate and pressure regulation in an immune cell production system according to claim 2, characterized in that: Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs regulation target data, including: The simulation prediction model calls the stage prediction sub-model to analyze the immune cell cultivation data to obtain a predicted cell cultivation stage; wherein the immune cell cultivation data includes cell proliferation and quantity, cell purity and differentiation state, and cell functional activity; The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output the regulation target data.

4. A control method for flow rate and pressure regulation in an immune cell production system according to claim 3, characterized in that: The stage prediction sub-model is called to analyze the immune cell cultivation data to obtain a predicted cell cultivation stage, including: The convolutional network in the stage prediction sub-model performs feature extraction on the immune cell cultivation data to obtain cell cultivation feature data, and the cell cultivation feature data is input into the classification model in the stage prediction sub-model, and the classification model outputs the predicted cell cultivation stage.

5. A control method for flow rate and pressure regulation in an immune cell production system according to claim 4, characterized in that: The simulation prediction model predicts the immune cell type and the cell culture stage to obtain and output the regulation target data, including: The simulation prediction model performs prediction processing on the immune cell type and the cell culture stage to obtain and output first regulation target data; Obtaining the number of self-regulations of the immune cell production system corresponding to the cell cultivation stage before the request signal is issued, and determining a first regulation index and a second regulation index according to the number of self-regulations; wherein the first regulation index is negatively correlated with the number of self-regulations, and the second regulation index is positively correlated with the number of self-regulations; Using the first adjustment index, the first adjustment target data is adjusted to second adjustment target data, and the second adjustment target data is determined as the adjustment target data; wherein the first adjustment index is a value less than 1; And, a re-adjustment frequency is determined according to the second adjustment index, and the control target data is predicted multiple times according to the re-adjustment frequency; wherein the re-adjustment frequency is positively correlated with the second adjustment index.

6. A control method for flow rate and pressure regulation in an immune cell production system according to claim 1, characterized in that: Determining a corresponding conversion method according to the bioreactor type, and converting the control target data into a target control parameter of a mixing device according to the conversion method, including: If the bioreactor type is a stirring type, a first conversion method is used to convert the control target data into a first target control parameter of a mixing device; if the bioreactor type is a swing type, a second conversion method is used to convert the control target data into a second target control parameter of a mixing device.

7. A control system for flow rate and pressure regulation in an immune cell production system, the system comprising a processing module and a storage module; the processing module is electrically connected to the storage module; characterized in that: The processing module calls the executable computer program code stored in the storage module to perform the following steps: Receiving a request signal for regulating flow rate and pressure sent by the immune cell production system, and parsing the request signal to obtain immune cell types, immune cell cultivation data, and bioreactor types; Importing the immune cell type and the immune cell cultivation data into a simulation prediction model, wherein the simulation prediction model outputs control target data, wherein the control target data includes a target flow rate and a target pressure; Determine a corresponding conversion method according to the type of the bioreactor, and convert the control target data into a target control parameter of a mixing device according to the conversion method; The target control parameters are fed back to the immune cell production system so that the immune cell production system controls the mixing device of the bioreactor according to the target control parameters.

8. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, characterized in that: The computer program product is used to be called and executed by a processor of an electronic device to implement the method according to any one of claims 1 to 6.

Images