Cognitive space value comprehensive evaluation method based on health and medical treatment big data of medical and health institutions

By building an evaluation framework and model in medical and health institutions, the problem of single data sources and no automatic updates is solved, the reliability and practicality of the evaluation is improved, and safe and efficient medical big data evaluation is achieved.

CN118983039APending Publication Date: 2024-11-19SOUTHERN MEDICAL UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410998782.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The comprehensive evaluation method of cognitive spatial value of existing medical and health institutions has problems such as unreliability and security of the evaluation results, and cannot be automatically updated, which affects the practicality of the evaluation.

Method used

A comprehensive evaluation method for health and medical big data based on medical institutions was designed, including framework construction, terminal data storage, data docking and transmission, establishment of evaluation models and evaluation architecture updates, through institutional docking modules, central processing modules, repository modules, The combination of cloud connection module and evaluation processing module realizes the tag storage, classification and model training of data, and automatically updates the evaluation model.

Benefits of technology

It improves the efficiency of data calling and the security of evaluation management, expands the amount of evaluation data, ensures the reliability of evaluation results, and improves the practicality of evaluation methods through the automatic update process, avoiding the iterative update requirement of manual participation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983039A_ABST
    Figure CN118983039A_ABST
Patent Text Reader

Abstract

The invention discloses a cognitive space value comprehensive evaluation method based on health and medical treatment big data of a medical and health institution. The method comprises the following steps: step 1, constructing a framework; step 2, terminal data storage; step 3, data butt joint transmission; 4, establishing an evaluation model; 5, evaluating and updating the architecture; according to the invention, the information is segmented and coded and the storage path is defined in the process of terminal data storage, so that patient information leakage caused by data loss is avoided, and meanwhile, the whole storage library does not need to be scanned during data calling, so that the data calling processing efficiency is improved; the medical cloud module is connected with a medical cloud, so that the assessment process of cognitive space value based on health and medical treatment big data of a medical and health institution is realized, and the reliability of an assessment result is guaranteed; when it is verified that the transmitted data is abnormal, the change process of the evaluation model is automatically completed through the change processing module, manual participation is not needed, and the practicability of the cognitive space value comprehensive evaluation method is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical value assessment, and in particular to a comprehensive assessment method of cognitive space value based on health and medical big data of medical and health institutions. Background Art

[0002] The comprehensive evaluation of cognitive space value is a value evaluation process for a specific institution. By clearly evaluating the specific goals of cognitive space value of health and medical big data in medical and health institutions, such as improving the quality of medical services, optimizing resource allocation, and supporting disease prevention and management, the medical quality of the institution can be improved according to specific medical goals. At the same time, the data types covered by the evaluation include clinical data, health records, physiological monitoring data, medical records, clinical trial data, etc. The existing comprehensive evaluation methods for cognitive space value used in medical and health institutions can basically meet the daily evaluation needs, but there are still some shortcomings. First, the data source of the existing evaluation methods is single, and the basic data used for evaluation is limited, which limits the amount of evaluation data for cognitive space value and affects the reliability of the evaluation results. Second, the data repository structure of the existing evaluation methods is simple, and when data is lost, it is easy to cause patient information leakage, thereby affecting the security of evaluation management. Third, the existing evaluation methods cannot automatically perform iterative updates in the case of abnormal data. In order to ensure the accuracy of the evaluation, it is necessary to arrange manual participation in the iterative update process regularly. The system has a long update cycle, which affects the practicality of the evaluation method. Therefore, it is necessary to design a comprehensive evaluation method for cognitive space value based on health and medical big data of medical and health institutions. Summary of the invention

[0003] The purpose of the present invention is to provide a comprehensive evaluation method of cognitive space value based on health and medical big data of medical and health institutions to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a comprehensive evaluation method of cognitive space value based on health and medical big data of medical and health institutions, comprising the following steps: step one, framework construction; step two, terminal data storage; step three, data docking and transmission; step four, establishment of evaluation model; step five, evaluation and framework update;

[0005] In the above step 1, a corresponding evaluation framework is established in the terminal of the medical institution, wherein the evaluation framework includes an institution docking module, a central processing module, a storage repository module, a cloud connection module, a data call module and an evaluation processing module. The institution docking module is connected to the central processing module through the data upload module, and the central processing module controls the connection to the storage repository module, the cloud connection module and the data call module respectively. Finally, the data call module is controlled to be connected to the evaluation processing module to complete the construction process of the evaluation framework.

[0006] In the above step 2, the data in the medical institution terminal is transmitted to the evaluation framework built in step 1 through the institution docking module, and then transmitted to the central processing module through the data upload module, and synchronously sent to the repository module for marked storage;

[0007] In the above step 3, the cloud connection module calls the cloud big data and sends it to the evaluation processing module through the central processing module and the data calling module. At the same time, the central processing module calls the storage data of the medical institution terminal and sends them to the evaluation processing module to establish a comprehensive evaluation model of cognitive space value.

[0008] In the above step 4, the evaluation processing module receives the cloud big data and storage data sent in the above step 3, and then classifies the data and trains the model;

[0009] In the above step five, the cognitive space value of the health institution terminal is comprehensively evaluated through the model established in the above step four. When abnormalities occur in the cloud big data and the storage data of the medical institution terminal or data adjustments and updates are required, corresponding changes and adjustments are made in the evaluation processing module.

[0010] As a further technical solution of the present invention, in the step one, the institution docking module is respectively connected to the medical record management module, the physician management module and the monitoring management module, and the medical record management module, the physician management module and the monitoring management module are all connected to the local area network of the medical institution terminal, and the local area network of the medical institution terminal is used as the perception layer to be connected to the evaluation framework.

[0011] As a further technical solution of the present invention, in the step one, the library module is composed of a data receiving module, a data processing module, a flash memory docking module, a library output module and a code extraction module. The data receiving module controls the connection to the data processing module, and the data processing module controls the connection to the flash memory docking module and the code extraction module respectively, and the flash memory docking module and the code extraction module both control the connection to the library output module, and the library output module controls the connection to the data processing module.

[0012] As a further technical solution of the present invention, in the step one, the cloud connection module is composed of a medical cloud module, a data classification module, a data monitoring module, a deletion output module, a linear analysis module and a format adjustment module. The medical cloud module controls the connection to the data classification module, the data classification module controls the connection to the data monitoring module, the data monitoring module controls the connection to the deletion output module and the linear analysis module respectively, and the deletion output module controls the connection to the format adjustment module.

[0013] As a further technical solution of the present invention, in the step one, the evaluation processing module is composed of an evaluation receiving module, a data grouping module, a basic training module, a basic model module, an intensive training module, an enhanced model module, a deepening learning module, an evaluation model module, a feature value calling module, a feature value output module and an iterative processing module.

[0014] As a further technical solution of the present invention, the evaluation receiving module controls the connection to the data grouping module, the data grouping module controls the connection to the basic training module, the basic training module controls the connection to the basic model module, the basic model module controls the connection to the enhanced training module, the enhanced training module controls the connection to the data grouping module and the enhanced model module respectively, the enhanced model module controls the connection to the deepening learning module, the deepening learning module controls the connection to the data grouping module and the evaluation model module respectively, the evaluation model module controls the connection to the iterative processing module and the eigenvalue calling module respectively, and the eigenvalue calling module controls the connection to the eigenvalue output module.

[0015] As a further technical solution of the present invention, in the step 2, the specific process of marking and storing in the storage repository module is: first, the medical record information, doctor's orders and daily test reports of patients sent by the medical record management module, the physician management module and the monitoring management module are received by the data receiving module, and then the information is segmented and encoded by the data processing module so that each individual data unit has an independent corresponding sequence code, and the storage path is defined before the flash docking module stores it, and then the corresponding data code is extracted by the code extraction module and sent to the library output module, and synchronously fed back to the central processing module. During the data call process, targeted data calls are made according to the defined storage address, without scanning the entire storage repository, thereby reducing the data call processing efficiency. After the call is completed, the data processing module is used to restore the data to avoid data loss leading to patient information leakage, thereby improving the security of evaluation management.

[0016] As a further technical solution of the present invention, in the step three, the process of the cloud connection module calling the cloud big data is: first, the medical cloud module is used to connect to the medical cloud and call the big data information on the cloud, then the cloud big data is classified through the data classification module, and the cloud big data information is divided into medical records, doctor's orders and patients' daily test reports, and then the data monitoring module is used to analyze the data, and the linear analysis module is used to analyze the data changes, and then the deletion output module is used to delete the abnormal data in combination with the data changes, and the data verification instructions are fed back to avoid abnormal data registration; then the format of the data is unified through the format adjustment module, and finally transmitted to the evaluation framework through the deletion output module.

[0017] As a further technical solution of the present invention, in the step four, the process of classifying data and training the model is: first, the data is received through the evaluation receiving module, and then the data grouping module divides the data into a basic training set, an enhanced training set and a deepened training set, and sends the basic training set, the enhanced training set and the deepened training set to the basic training module, the enhanced training module and the deepened learning module respectively, and then the basic training module trains the initial model in combination with the basic training set, and then the enhanced training module combines the enhanced training set to perform enhanced training on the initial model to obtain an enhanced model, and then the deepened learning module combines the deepened training set to perform deepen training on the enhanced model to obtain an evaluation model and save it in the evaluation model module; after the training is completed, the weight parameters and the corresponding weight ratios in the model are called through the feature value calling module, and fed back to the central processing module.

[0018] As a further technical solution of the present invention, in step five, the iteration adjustment process is: sending the iteration instruction of the framework to the data calling module through the central processing module, and receiving the instruction through the iteration processing module in the evaluation processing module. After the instruction is received, the basic training set, the enhanced training set and the deepened training set are called through the iteration processing module, and the corresponding modified data in the training set are adjusted, and then synchronously updated to the evaluation model. After the update is completed, the weight parameters and the corresponding weight ratios are re-called through the feature value calling module, and synchronously fed back to the central processing module.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: the comprehensive evaluation method of cognitive space value based on health and medical big data of medical and health institutions, in the process of terminal data storage, the data processing module divides and encodes the information, so that each individual data unit has an independent corresponding sequence code, and defines the storage path before the flash memory docking module stores it, and then extracts the corresponding data code through the code extraction module and sends it to the library output module, and synchronously feeds back to the central processing module, and in the data call process, targeted data calls are made according to the defined storage address, without scanning the entire storage library, thereby improving the data call processing efficiency, and after the call is completed, the data processing module is used to restore it, thereby avoiding data loss and patient information leakage, thereby improving the security of evaluation management; the medical cloud module is connected to the medical cloud and the big data information on the cloud is called, and then the cloud big data is classified by the data classification module, and the cloud big data information is divided into medical records, doctor's orders and patients' daily test reports, and then the data is processed by the data classification module. According to the monitoring module, data analysis is carried out, and the linear analysis module is used to analyze the changes in the data. Then, the deletion output module is used to delete the abnormal data in combination with the changes in the data, and the data verification instructions are fed back to avoid abnormal data registration. At the same time, by connecting to the cloud of the institution, the evaluation of the cognitive space value based on the health and medical big data of the medical and health institutions is realized, the amount of evaluation data of the cognitive space value is expanded, and the reliability of the evaluation results is guaranteed; when it is verified that the transmitted data is abnormal, the instruction is received by the iteration processing module in the evaluation processing module, and after the instruction is received, the basic training set, the enhanced training set and the deepened training set are called through the iteration processing module, and the corresponding modified data in the training set are adjusted, and then synchronously updated to the evaluation model. After the update is completed, the weight parameters and the corresponding weight ratios are re-called through the characteristic value calling module, and synchronously fed back to the central processing module, the iteration process of the evaluation model is automatically completed without human participation, thereby improving the practicality of the comprehensive evaluation method of cognitive space value. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the evaluation method of the present invention;

[0021] Figure 2 This is a schematic diagram of the architecture of building an evaluation framework in step 1 of the present invention;

[0022] Figure 3 It is an operation flow chart of the repository module in the evaluation framework of the present invention;

[0023] Figure 4 It is an operation flow chart of the cloud connection module in the evaluation framework of the present invention;

[0024] Figure 5 It is an operation flow chart of the evaluation processing module in the evaluation framework of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Please see attached Figure 1 -Attached Figure 5 , an embodiment provided by the present invention: a comprehensive evaluation method of cognitive space value based on health and medical big data of medical and health institutions, comprising the following steps: step one, framework construction; step two, terminal data storage; step three, data docking and transmission; step four, establishment of evaluation model; step five, evaluation and framework update;

[0027] In the above step one, a corresponding evaluation framework is established in the terminal of the medical institution, wherein the evaluation framework includes an institution docking module, a central processing module, a storage repository module, a cloud connection module, a data call module and an evaluation processing module. The institution docking module is connected to the central processing module through the data upload module, and the central processing module controls the connection to the storage repository module, the cloud connection module and the data call module respectively. Finally, the data call module is controlled to be connected to the evaluation processing module to complete the construction process of the evaluation framework; the institution docking module is respectively connected to the medical record management module, the physician management module and the monitoring management module, and the medical record management module, the physician management module and the monitoring management module are all connected to the local area network of the medical institution terminal, and the local area network of the medical institution terminal is used as the perception layer to connect to the evaluation framework; the storage repository module is composed of a data receiving module, a data processing module, a flash memory docking module, a library output module and a code extraction module. The data receiving module controls the connection to the data processing module, and the data processing module controls the connection to the flash memory docking module and the code extraction module respectively, and the flash memory docking module and the code extraction module both control the connection to the library output module, and the library output module controls the connection to the data processing module; the cloud connection module is composed of a medical The medical cloud module controls the connection to the data classification module, the data classification module controls the connection to the data monitoring module, the data monitoring module controls the connection to the deletion output module and the linear analysis module respectively, and the deletion output module controls the connection to the format adjustment module; the evaluation processing module is composed of an evaluation receiving module, a data grouping module, a basic training module, a basic model module, an enhanced training module, an enhanced model module, a deepening learning module, an evaluation model module, a characteristic value calling module, a characteristic value output module and an iteration processing module; the evaluation receiving module controls the connection to the data grouping module, the data grouping module controls the connection to the basic training module, the basic training module controls the connection to the basic model module, the basic model module controls the connection to the enhanced training module, the enhanced training module controls the connection to the data grouping module and the enhanced model module respectively, the enhanced model module controls the connection to the deepening learning module, the deepening learning module controls the connection to the data grouping module and the evaluation model module respectively, the evaluation model module controls the connection to the iteration processing module and the characteristic value calling module respectively, and the characteristic value calling module controls the connection to the characteristic value output module;

[0028] In the above step 2, the data in the medical institution terminal is transmitted to the evaluation framework built in step 1 through the institution docking module, and then transmitted to the central processing module through the data upload module, and synchronously sent to the storage repository module for marked storage; the specific process of marked storage in the storage repository module is: first, the medical record information, doctor's orders and daily test reports of patients sent by the medical record management module, the physician management module and the monitoring management module are received through the data receiving module, and then the data processing module divides and encodes the information so that each individual data unit has an independent corresponding sequence code, and defines the storage path before the flash docking module stores it, and then extracts the corresponding data code through the code extraction module and sends it to the library output module, and synchronously feeds back to the central processing module. During the data call process, targeted data calls are made according to the defined storage address, without scanning the entire storage repository, which reduces the data call processing efficiency, and after the call is completed, it is restored through the data processing module to avoid data loss and patient information leakage, thereby improving the security of evaluation management;

[0029] Among them, in the above step three, the cloud connection module calls the cloud big data and sends it to the evaluation processing module through the central processing module and the data calling module. At the same time, the central processing module calls the storage data of the medical institution terminal and sends them to the evaluation processing module to establish a comprehensive evaluation model of cognitive space value; the process of the cloud connection module calling the cloud big data is: first, the medical cloud module is connected to the medical cloud and the cloud big data information is called, and then the cloud big data is classified through the data classification module, and the cloud big data information is divided into medical records, doctor's orders and patients' daily test reports, and then the data monitoring module is used to analyze the data, and the linear analysis module is used to analyze the data changes, and then the deletion output module is used to delete the abnormal data in combination with the data changes, and the data verification instruction is fed back to avoid abnormal data registration; then the format of the data is unified through the format adjustment module, and finally transmitted to the evaluation framework through the deletion output module;

[0030] In the above step 4, the evaluation processing module receives the cloud big data and storage data sent in the above step 3, and then classifies the data and trains the model; the process of classifying the data and training the model is: first, the evaluation receiving module receives the data, and then the data grouping module divides the data into a basic training set, an enhanced training set and a deepening training set, and sends the basic training set, the enhanced training set and the deepening training set to the basic training module, the enhanced training module and the deepening learning module respectively, and then the basic training module combines the basic training set to train the initial model, and then the enhanced training module combines the enhanced training set to strengthen the initial model to obtain a strengthened model, and then the deepening learning module combines the deepening training set to deepen the strengthened model to obtain an evaluation model and save it in the evaluation model module; after the training is completed, the weight parameters and the corresponding weight ratios in the model are called by the feature value calling module, and fed back to the central processing module;

[0031] Among them, in the above step five, the cognitive space value of the health institution terminal is comprehensively evaluated through the model established in the above step four. When abnormalities occur in the cloud big data and the storage data of the medical institution terminal or data adjustment and update are performed, corresponding iteration adjustments are made in the evaluation processing module; the process of iteration adjustment is: the framework iteration instruction is sent to the data calling module through the central processing module, and the instruction is received by the iteration processing module in the evaluation processing module. After the instruction is received, the basic training set, the enhanced training set and the deepened training set are called through the iteration processing module, and the corresponding modified data in the training set are adjusted, and then synchronously updated to the evaluation model. After the update is completed, the weight parameters and the corresponding weight ratios are re-called through the feature value calling module, and synchronously fed back to the central processing module.

[0032] Based on the above, the advantage of the present invention is that when the present invention is used, the data processing module divides and encodes the information during the terminal data storage process, so that each individual data unit has an independent corresponding sequence code, and defines the storage path before the flash memory docking module stores it, and then extracts the corresponding data code through the code extraction module and sends it to the library output module, and synchronously feeds back to the central processing module. During the data call process, targeted data calls are made according to the defined storage address, without scanning the entire storage library, thereby improving the data call processing efficiency. After the call is completed, it is restored through the data processing module to avoid data loss and patient information leakage, thereby improving the security of evaluation management; the medical cloud module is connected to the medical cloud and the big data information on the cloud is called, and then the cloud big data is classified through the data classification module, and the cloud big data information is divided into medical records, doctor's orders and patients' daily test reports, and then the data monitoring module is used for data analysis, and combined with The linear analysis module analyzes the changes in the data, and then deletes the abnormal data through the deletion output module in combination with the changes in the data, and at the same time feeds back the data verification instructions to avoid abnormal data registration. At the same time, by connecting to the institutional cloud, the cognitive space value is evaluated based on the health and medical big data of medical and health institutions, which expands the amount of evaluation data for the cognitive space value and ensures the reliability of the evaluation results. When it is verified that the transmitted data is abnormal, the instruction is received by the iteration processing module in the evaluation processing module. After the instruction is received, the basic training set, the enhanced training set and the deepened training set are called through the iteration processing module, and the corresponding modified data in the training set are adjusted, and then synchronously updated to the evaluation model. After the update is completed, the weight parameters and the corresponding weight ratios are re-called through the characteristic value calling module, and synchronously fed back to the central processing module, the iteration process of the evaluation model is automatically completed without human participation, thereby improving the practicality of the comprehensive evaluation method of cognitive space value.

[0033] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A comprehensive evaluation method of cognitive space value based on health and medical big data of medical and health institutions includes the following steps: Step 1: framework building; Step 2: terminal data storage; Step 3: data connection and transmission; Step 4: establishment of evaluation model; Step 5: evaluation and architecture update; It is characterized by: In the above step 1, a corresponding evaluation framework is established in the terminal of the medical institution, wherein the evaluation framework includes an institution docking module, a central processing module, a storage repository module, a cloud connection module, a data call module and an evaluation processing module. The institution docking module is connected to the central processing module through the data upload module, and the central processing module controls the connection to the storage repository module, the cloud connection module and the data call module respectively. Finally, the data call module is controlled to be connected to the evaluation processing module to complete the construction process of the evaluation framework. In the above step 2, the data in the medical institution terminal is transmitted to the evaluation framework built in step 1 through the institution docking module, and then transmitted to the central processing module through the data upload module, and synchronously sent to the repository module for marked storage; In the above step 3, the cloud connection module calls the cloud big data and sends it to the evaluation processing module through the central processing module and the data calling module. At the same time, the central processing module calls the storage data of the medical institution terminal and sends them to the evaluation processing module to establish a comprehensive evaluation model of cognitive space value. In the above step 4, the evaluation processing module receives the cloud big data and storage data sent in the above step 3, and then classifies the data and trains the model; In the above step five, the cognitive space value of the health institution terminal is comprehensively evaluated through the model established in the above step four. When abnormalities occur in the cloud big data and the storage data of the medical institution terminal or data adjustments and updates are required, corresponding changes and adjustments are made in the evaluation processing module.

2. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In step one, the institution docking module is respectively connected to the medical record management module, the physician management module and the monitoring management module, and the medical record management module, the physician management module and the monitoring management module are all connected to the local area network of the medical institution terminal, and the local area network of the medical institution terminal is used as the perception layer to connect to the evaluation framework.

3. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step one, the library module is composed of a data receiving module, a data processing module, a flash memory docking module, a library output module and a code extraction module. The data receiving module controls the connection to the data processing module, and the data processing module controls the connection to the flash memory docking module and the code extraction module respectively, and the flash memory docking module and the code extraction module both control the connection to the library output module, and the library output module controls the connection to the data processing module.

4. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step one, the cloud connection module is composed of a medical cloud module, a data classification module, a data monitoring module, a deletion output module, a linear analysis module and a format adjustment module. The medical cloud module controls the connection to the data classification module, the data classification module controls the connection to the data monitoring module, the data monitoring module controls the connection to the deletion output module and the linear analysis module respectively, and the deletion output module controls the connection to the format adjustment module.

5. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step one, the evaluation processing module is composed of an evaluation receiving module, a data grouping module, a basic training module, a basic model module, an intensive training module, an enhanced model module, a deepening learning module, an evaluation model module, a feature value calling module, a feature value output module and an iteration processing module.

6. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 5 is characterized by: The evaluation receiving module controls the connection to the data grouping module, the data grouping module controls the connection to the basic training module, the basic training module controls the connection to the basic model module, the basic model module controls the connection to the enhanced training module, the enhanced training module controls the connection to the data grouping module and the enhanced model module respectively, the enhanced model module controls the connection to the deepening learning module, the deepening learning module controls the connection to the data grouping module and the evaluation model module respectively, the evaluation model module controls the connection to the iterative processing module and the eigenvalue calling module respectively, and the eigenvalue calling module controls the connection to the eigenvalue output module.

7. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step 2, the specific process of marking and storing in the storage repository module is as follows: first, the medical record information, doctor's orders and daily test reports of patients sent by the medical record management module, the physician management module and the monitoring management module are received by the data receiving module, and then the information is segmented and encoded by the data processing module, so that each individual data unit has an independent corresponding sequence code, and the storage path is defined before the flash docking module stores it, and then the corresponding data code is extracted by the code extraction module and sent to the library output module, and synchronously fed back to the central processing module. During the data call process, targeted data calls are made according to the defined storage address, without scanning the entire storage repository, thereby improving the data call processing efficiency, and after the call is completed, the data is restored by the data processing module to avoid data loss leading to patient information leakage, thereby improving the security of evaluation management.

8. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step three, the process of the cloud connection module calling the cloud big data is: first, the medical cloud module is used to connect to the medical cloud and call the big data information on the cloud; then, the cloud big data is classified through the data classification module, and the cloud big data information is divided into medical records, doctor's orders and patients' daily test reports; then, the data monitoring module is used to analyze the data, and the linear analysis module is used to analyze the data changes; then, the deletion output module is used to delete the abnormal data based on the data changes, and the data verification instructions are fed back to avoid abnormal data registration; then, the format of the data is unified through the format adjustment module, and finally, it is transmitted to the evaluation framework through the deletion output module.

9. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In the step 4, the process of classifying the data and training the model is as follows: first, the evaluation receiving module receives the data, and then the data grouping module divides the data into a basic training set, an enhanced training set, and a deepening training set, and sends the basic training set, the enhanced training set, and the deepening training set to the basic training module, the enhanced training module, and the deepening learning module, respectively. Then, the basic training module trains the initial model in combination with the basic training set, and then the enhanced training module performs enhanced training on the initial model in combination with the enhanced training set to obtain an enhanced model, and then the deepening learning module performs deepening training on the enhanced model in combination with the deepening training set to obtain an evaluation model and save it in the evaluation model module; After the training is completed, the weight parameters and corresponding weight ratios in the model are called through the feature value calling module and fed back to the central processing module.

10. The method for comprehensive evaluation of cognitive space value based on health and medical big data of medical and health institutions according to claim 1 is characterized by: In step five, the process of iteration and adjustment is as follows: the framework iteration instruction is sent to the data calling module through the central processing module, and the instruction is received by the iteration processing module in the evaluation processing module. After the instruction is received, the basic training set, the enhanced training set and the deepened training set are called through the iteration processing module, and the corresponding modified data in the training set are adjusted, and then synchronously updated to the evaluation model. After the update is completed, the weight parameters and the corresponding weight ratios are re-called through the feature value calling module, and synchronously fed back to the central processing module.