Automatic entry and exit method and device, electronic equipment and storage medium

Abstract

The invention discloses an automatic input and output method and device, electronic equipment and a storage medium, and belongs to the technical field of data processing, and the automatic input and output method comprises the steps: obtaining a basic medical record image of a patient; identifying text information in the basic medical record image; identifying key information and related information of the key information in the text information by using a trained first deep learning model; and using a trained second deep learning model to determine whether the patient accords with an enrollment condition according to the key information and the related information. According to the method, manual intervention is reduced, the matching speed and accuracy are improved, and a patient can find a clinical test suitable for himself / herself more quickly. The method is of great significance in accelerating the progress of medical research, especially in the field of precise oncology.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and specifically relates to an automated entry and exit method, device, electronic device and storage medium. Background Art

[0002] Currently, the design and management of clinical trials are becoming increasingly complex. Especially in the field of oncology, with the in-depth study of the molecular characteristics of cancer, the number of personalized treatment options has increased rapidly. This requires the ability to accurately and quickly match patients with appropriate clinical trials, especially considering the patient's genetic characteristics, disease type and treatment history. However, existing manual matching methods are not only time-consuming but also prone to errors, limiting patients' opportunities to participate in appropriate clinical trials. Summary of the invention

[0003] The purpose of the present application is to provide an automated entry and sorting method, device, electronic device and storage medium to achieve automatic matching entry and sorting, and improve the speed and accuracy of analysis and matching.

[0004] According to a first aspect of an embodiment of the present application, an automated entry and exit method is provided, which may include:

[0005] Obtain images of the patient's basic medical records;

[0006] Recognize text information in basic medical record images;

[0007] Using the trained first deep learning model to identify key information and related information of the key information in the text information;

[0008] The trained second deep learning model is used to determine whether the patient meets the admission criteria based on key information and related information.

[0009] In some optional embodiments of the present application, identifying text information in a basic medical record image includes:

[0010] Perform OCR processing on the basic medical record images to extract text information from the basic medical record images.

[0011] In some optional embodiments of the present application, the trained first deep learning model is obtained by the following training:

[0012] Collect medical text data;

[0013] Labeling key data and data related to the key data in the medical text data to obtain a first training set;

[0014] The first deep learning model is trained using the first training set so that the first deep learning model can identify key data and understand the relationship between the key data and related data, thereby obtaining a trained first deep learning model.

[0015] In some optional embodiments of the present application, the trained second deep learning model is obtained by the following training:

[0016] Collect medical history data and inclusion criteria. Medical history data includes information on patients who were successfully included or not included in the clinical trial.

[0017] The medical history data is labeled according to the admission and exclusion criteria. For patients who are successfully admitted, the specific medical evidence for meeting the criteria is labeled. For patients who fail to be admitted, the specific reasons for not meeting the criteria are labeled to form the second training set.

[0018] The second deep learning model is trained using the second training set to obtain a trained second deep learning model.

[0019] In some optional embodiments of the present application, using the second training set to train the second deep learning model to obtain the trained second deep learning model includes:

[0020] The second deep learning model is trained on multiple tasks using the second training set, so that the second deep learning model can understand and explain why the patient meets or does not meet the inclusion criteria, thereby obtaining a trained second deep learning model.

[0021] In some optional embodiments of the present application, the second deep learning model is a ChatGLM2-6B model.

[0022] In some optional embodiments of the present application, after training the second deep learning model using the second training set to obtain the trained second deep learning model, the method further includes:

[0023] Use the validation set to verify the accuracy of the trained second deep learning model;

[0024] The test machine is used to evaluate the performance of the trained second deep learning model.

[0025] According to a second aspect of an embodiment of the present application, an automatic inlet and outlet device is provided, which may include:

[0026] An acquisition module, used to acquire the patient's basic medical record images;

[0027] A text recognition module, used to recognize text information in basic medical record images;

[0028] A target information recognition module, used to recognize key information and related information of the key information in the text information by using the trained first deep learning model;

[0029] The determination module is used to use the trained second deep learning model to determine whether the patient meets the admission and exclusion conditions based on key information and related information.

[0030] According to a third aspect of an embodiment of the present application, an electronic device is provided, which may include:

[0031] processor;

[0032] a memory for storing processor-executable instructions;

[0033] The processor is configured to execute instructions to implement the automated queuing method as shown in any one of the embodiments of the first aspect.

[0034] According to the fourth aspect of the embodiments of the present application, a storage medium is provided. When the instructions in the storage medium are executed by a processor of an information processing device or a server, the information processing device or the server implements the automated queuing method as shown in any one of the embodiments of the first aspect.

[0035] The above technical solution of the present application has the following beneficial technical effects:

[0036] The method of the embodiment of the present application uses a trained first deep learning model to identify key information and related information of the key information in the text information, and uses a trained second deep learning model to determine whether the patient meets the inclusion criteria based on the key information and related information. This method reduces manual intervention, improves the speed and accuracy of matching, and enables patients to find clinical trials that suit them more quickly. This is of great significance for accelerating the progress of medical research, especially in the field of precision oncology. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flow chart of an automated entry and exit method in an exemplary embodiment of the present application;

[0038] Figure 2 It is a schematic structural diagram of an automated inlet and outlet device in an exemplary embodiment of the present application;

[0039] Figure 3 is a schematic structural diagram of an electronic device in an exemplary embodiment of the present application;

[0040] Figure 4 It is a schematic diagram of the hardware structure of an electronic device in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with specific implementations and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present application. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concepts of the present application.

[0042] The accompanying drawings show schematic diagrams of layer structures according to embodiments of the present application. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clarity. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0043] Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0044] In the description of the present application, it should be noted that the terms "first", "second" and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0045] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0046] In conjunction with the accompanying drawings, the following describes in detail the automated entry and exit method, device, electronic device, and storage medium provided by the embodiments of the present application through specific embodiments and their application scenarios.

[0047] like Figure 1 As shown, in a first aspect of an embodiment of the present application, an automatic entry and exit method is provided, which may include:

[0048] S110: Acquire the patient's basic medical record image;

[0049] S120: Identify text information in the basic medical record image;

[0050] S130: Using the trained first deep learning model to identify key information in the text information and related information of the key information;

[0051] S140: Determine whether the patient meets the admission criteria based on the key information and the related information using the trained second deep learning model.

[0052] The method of this embodiment uses the trained first deep learning model to identify key information and related information of the key information in the text information, and uses the trained second deep learning model to determine whether the patient meets the inclusion and exclusion conditions based on the key information and related information. This method reduces manual intervention, improves the speed and accuracy of matching, and enables patients to find clinical trials that suit them more quickly. This is of great significance for accelerating the progress of medical research, especially in the field of precision oncology.

[0053] In some embodiments, the identifying text information in the basic medical record image includes:

[0054] Perform OCR processing on the basic medical record image to extract text information in the basic medical record image.

[0055] In this embodiment, OCR processing is used to extract text content from medical images uploaded to the EDC system (such as scanned copies of pathology reports or laboratory results). The key to this step is to convert important medical information in the image into a text format that can be analyzed.

[0056] In some embodiments, the trained first deep learning model is obtained by the following training:

[0057] Collect medical text data;

[0058] Annotating key data in the medical text data and data related to the key data to obtain a first training set;

[0059] The first deep learning model is trained using the first training set so that the first deep learning model can recognize the key data and understand the relationship between the key data and the related data, thereby obtaining a trained first deep learning model.

[0060] The first deep learning model in this embodiment can be an entity relationship extraction model that identifies medical entities such as diseases, drugs, biomarkers, etc. from the text extracted by OCR and the electronic records of the EDC system. For each identified entity, the model pays special attention to the surrounding qualifiers or phrases, which are critical to understanding the medical significance of the entity. For example, if the text mentions "white blood cell count is higher than normal", the model will identify "white blood cell count" as an entity and extract the qualifier "higher than normal" associated with it, so as to understand the potential impact of this indicator on the inclusion and exclusion criteria of clinical trials.

[0061] Specifically, the named entity recognition and relation extraction model training process may include:

[0062] Dataset preparation: Collect a large amount of clinical trial documents and patient data from medical record systems and clinical trial databases. These documents usually contain rich medical information, such as medical records, treatment plans, laboratory test results, etc.

[0063] Entity annotation: Medical experts or trained annotators accurately annotate key medical entities in large texts. For example, in the text "Patients receive dialysis treatment for chronic nephritis", "chronic nephritis" is annotated as the disease entity, and "dialysis treatment" is annotated as the treatment method entity.

[0064] Relation annotation: Also annotate the qualifiers or descriptive phrases around the entity, which are crucial to understanding the medical meaning of the entity. For example, in the sentence "white blood cell count is higher than 10,000 / mm 3 ", "white blood cell count" is marked as a medical indicator entity, and "higher than 10,000 / mm 3 ” is marked as a qualifier associated with it.

[0065] Model selection: The UIE (Unified Information Extraction) model is selected as the base model because it is suitable for processing complex text and entity relationships in the medical field.

[0066] Data input: Use previously annotated datasets as input, which contain specific entity and relationship annotation information.

[0067] Training details: During fine-tuning, the model learns how to accurately identify annotated entities from text, and how to understand relationships and qualifiers between entities.

[0068] Test data set: Use an independent test set that is not used in the model training process.

[0069] Evaluation metrics: Evaluate the accuracy, recall, and F1 score of the model in entity recognition and relation extraction to ensure the accuracy and generalization ability of the model.

[0070] Through this detailed training process, the UIE model can efficiently and accurately identify key entities from complex medical texts and extract the relationships between them. This is crucial for subsequent inclusion and exclusion criteria judgment, ensuring the accuracy and effectiveness of the entire system in the clinical trial patient screening process.

[0071] In some embodiments, the trained second deep learning model is obtained by the following training:

[0072] Collect medical history data and inclusion criteria, the medical history data including information on patients who were successfully included or not included in the clinical trial;

[0073] The medical history data is annotated according to the inclusion and exclusion criteria, and for patients who are successfully included and excluded, specific medical evidence for meeting the criteria is annotated, and for patients who are not included and excluded, specific reasons for not meeting the criteria are annotated, to form a second training set;

[0074] The second deep learning model is trained using the second training set to obtain a trained second deep learning model.

[0075] In this embodiment, medical history data and inclusion and exclusion criteria can be collected from clinical trial databases and electronic medical record systems. These data include information about patients who have been successfully included or failed to be included in clinical trials. This information covers a wide range of medical conditions, such as the patient's disease diagnosis, treatment history, laboratory test results, etc. Focus on collecting specific inclusion and exclusion criteria for clinical trials, including age restrictions, specific medical indicator requirements, disease stage, drug sensitivity and other information. Prepare the collected and labeled data as training data for the model. This includes the patient's medical information and the basis for judging the inclusion and exclusion conditions. Construct a specific input and output format for model training, the input includes the patient's medical information, and the output is the inclusion and exclusion conditions and reasons judged by the model.

[0076] The construction of the second training set can include input data and output data. For input data, the patient's structured medical information can be extracted and organized to ensure that key data points used for inclusion and exclusion decisions are included, such as age, gender, specific disease status, biomarker levels, etc. This information is converted into a format acceptable to the model to ensure data integrity and consistency. For output data, the specific reasons for inclusion and exclusion judgment can be organized and labeled. For patients who are successfully included or excluded, clearly indicate the conditions that are met and the relevant medical basis. For patients who fail to be included or excluded, indicate the conditions that are not met and their specific reasons, such as "age exceeds the upper limit set by the trial" or "laboratory indicators do not meet the trial requirements."

[0077] The model can choose a model suitable for processing complex logic and text data, based on the ChatGLM2-6B model. Prepare the collected and labeled data as training data for the model. This includes the patient's medical information and the basis for judging the inclusion and exclusion conditions. Construct a specific input and output format for model training. The input includes the patient's medical information, and the output is the inclusion and exclusion conditions and reasons judged by the model. During the training process, the model learns how to predict whether the patient meets the inclusion and exclusion conditions based on the input medical information, and gives specific reasons. Focus on training the model's ability to understand and process medical data, and how to match this information with the inclusion and exclusion criteria of clinical trials.

[0078] Finally, the model is evaluated using an independent test set to ensure the accuracy and generalization ability of the fine-tuned model in real-world applications. The model's performance in judging eligibility criteria in different types of clinical situations is evaluated. Through this training process, the model is not only able to identify the eligibility criteria for clinical trials, but also understand and explain why a patient meets or does not meet these criteria. This approach improves the accuracy of eligibility criteria judgment.

[0079] In some embodiments, the step of training a second deep learning model using the second training set to obtain a trained second deep learning model includes:

[0080] The second deep learning model is trained on multiple tasks using the second training set, so that the second deep learning model can understand and explain why the patient meets or does not meet the inclusion criteria, thereby obtaining a trained second deep learning model.

[0081] Specifically, during the training process, the model learns how to predict whether a patient meets the inclusion criteria based on the input medical information and gives specific reasons. The focus is on training the model's ability to understand and process medical data, and how to match this information with the inclusion criteria of clinical trials. Finally, an independent test set is used to evaluate the model to ensure the accuracy and generalization ability of the fine-tuned model in practical applications. The performance of the model in judging inclusion criteria in different types of clinical situations is evaluated. Through this training process, the model is not only able to identify the inclusion criteria of clinical trials, but also understand and explain why a patient meets or does not meet these criteria. This approach improves the accuracy of inclusion criteria judgment.

[0082] The method of this embodiment combines advanced artificial intelligence technology, especially large language models (LLM), to automatically process clinical trial documents, improving the speed and accuracy of matching patients with clinical trials. By accurately identifying and parsing key information in medical texts, such as disease type, treatment plan, patient characteristics, etc., this solution can automatically evaluate whether a patient meets the inclusion criteria for a specific trial. This innovation not only significantly reduces the time and labor required for manual review, but also improves the accuracy of the matching process, thereby accelerating the progress of clinical trials, providing patients with more treatment opportunities, and promoting the development of medical research.

[0083] In some embodiments, the second deep learning model is a ChatGLM2-6B model. This model is suitable for processing complex logic and text data.

[0084] In some embodiments, after using the second training set to train the second deep learning model to obtain the trained second deep learning model, the method further includes:

[0085] Using a validation set to verify the accuracy of the trained second deep learning model;

[0086] A test machine is used to evaluate the performance of the trained second deep learning model.

[0087] This embodiment can use independent validation sets and test sets to evaluate the model to ensure the accuracy and generalization ability of the fine-tuned model in practical applications. The performance of the model in judging the inclusion and exclusion conditions in different types of clinical situations is evaluated to ensure that the model can accurately handle diverse medical data. Through careful fine-tuning of the model and meticulous construction of the data set, this process can accurately handle complex logical judgments in clinical trial patient screening. This method not only improves the accuracy of inclusion and exclusion judgments, but also enhances the transparency and interpretability of the evaluation, which is of great significance for optimizing the patient screening process for clinical trials.

[0088] The above-mentioned embodiment method can not only identify and classify biomedical entities in clinical trial documents, but also understand the complex relationship between these entity relationships and inclusion and exclusion conditions through a large model. This method represents an important innovation in the field of medical information technology and biomedical data processing. It combines the latest AI technology, especially large language models, to improve the screening efficiency and accuracy of clinical trials and provide patients with more treatment opportunities.

[0089] It should be noted that the automated entry and exit method provided in the embodiment of the present application can be executed by an automated entry and exit device, or a control module in the automated entry and exit device for executing the automated entry and exit method. In the embodiment of the present application, the automated entry and exit device executing the automated entry and exit method is taken as an example to illustrate the automated entry and exit device provided in the embodiment of the present application.

[0090] like Figure 2 As shown, in a second aspect of an embodiment of the present application, an automatic inlet and outlet device is provided, which may include:

[0091] An acquisition module 210 is used to acquire a basic medical record image of a patient;

[0092] A text recognition module 220, used to recognize text information in the basic medical record image;

[0093] A target information identification module 230, configured to identify key information in the text information and related information of the key information by using the trained first deep learning model;

[0094] The determination module 240 is used to use the trained second deep learning model to determine whether the patient meets the admission and exclusion conditions according to the key information and the related information.

[0095] The automatic entry and exit device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0096] The automatic entry and exit device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0097] The automatic inlet and outlet device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0098] Alternatively, if Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the above-mentioned automatic queuing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0099] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0100] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0101] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .

[0102] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0103] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 409 may be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and applications, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 410.

[0104] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned automatic sorting method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0105] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0106] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned automatic entry and exit method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0107] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0108] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0110] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An automated entry and exit method, characterized in that: include: Obtain images of the patient's basic medical records; Recognizing text information in the basic medical record image; Using the trained first deep learning model to identify key information in the text information and related information of the key information; The trained second deep learning model is used to determine whether the patient meets the admission criteria based on the key information and the related information.

2. The automated discharge method according to claim 1, characterized in that: The identifying text information in the basic medical record image includes: Perform OCR processing on the basic medical record image to extract text information in the basic medical record image.

3. The automated discharge method according to claim 1, characterized in that: The trained first deep learning model is obtained by the following training: Collect medical text data; Annotating key data in the medical text data and data related to the key data to obtain a first training set; The first deep learning model is trained using the first training set so that the first deep learning model can recognize the key data and understand the relationship between the key data and the related data, thereby obtaining a trained first deep learning model.

4. The automated entry and exit method according to claim 1, characterized in that: The trained second deep learning model is obtained by the following training: Collect medical history data and inclusion criteria, the medical history data including information on patients who were successfully included or not included in the clinical trial; The medical history data is annotated according to the inclusion and exclusion criteria, and for patients who are successfully included and excluded, specific medical evidence for meeting the criteria is annotated, and for patients who are not included and excluded, specific reasons for not meeting the criteria are annotated, to form a second training set; The second deep learning model is trained using the second training set to obtain a trained second deep learning model.

5. The automated discharge method according to claim 4, characterized in that: The step of training a second deep learning model using the second training set to obtain a trained second deep learning model includes: The second deep learning model is trained on multiple tasks using the second training set, so that the second deep learning model can understand and explain why the patient meets or does not meet the inclusion criteria, thereby obtaining a trained second deep learning model.

6. The automated discharge method according to claim 4, characterized in that: The second deep learning model is the ChatGLM2-6B model.

7. The automated discharge method according to claim 4, characterized in that: After the second deep learning model is trained using the second training set to obtain a trained second deep learning model, the method further includes: Using a validation set to verify the accuracy of the trained second deep learning model; A test machine is used to evaluate the performance of the trained second deep learning model.

8. An automatic feeding and discharging device, characterized in that: include: An acquisition module, used to acquire the patient's basic medical record images; A text recognition module, used to recognize text information in the basic medical record image; A target information identification module, used to identify key information in the text information and related information of the key information using the trained first deep learning model; A determination module is used to use the trained second deep learning model to determine whether the patient meets the admission and exclusion conditions based on the key information and the related information.

9. An electronic device, characterized in that: include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the automated entry and exit method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the automated queuing method as described in any one of claims 1-7 are implemented.

Images