Patient information management method and system based on multistage communication

Abstract

The invention relates to a patient information management method and system based on multilevel communication, and belongs to the technical field of information management. The method comprises the following steps: acquiring personal information data of a patient, establishing a database table, acquiring pathological data of the patient, and storing the pathological data into the database table; the database table is retrieved according to the search semantics to obtain patient pathology data, and the patient pathology data is transmitted to the doctor subsystem; structuring the medical record data of the patient, dividing the structured data, retrieving a preset influence relation library according to disease names to obtain influence factors, and retrieving the pathological data of the patient according to the influence factors to obtain related index data; comparing the related index data with a preset threshold value to obtain illness degree data, and marking the disease name according to the illness degree data; and retrieving the database table to obtain treatment data, and transmitting the treatment data to a service center subsystem to obtain post-treatment data of the patient. The multi-level communication of patient information is realized, and the problem of information islands is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of information management, and in particular relates to a patient information management method and system based on multi-level communication. Background Art

[0002] With the development of medical informatization, hospital information management systems have gradually become an important part of medical institutions. Traditional patient information management mainly relies on manual records and paper medical records, which is not only inefficient but also prone to information errors and loss. In recent years, although electronic medical record systems have been widely used, they still have many shortcomings in data sharing, real-time updates and cross-departmental collaboration.

[0003] (1) Information islands: Information between different hospitals cannot be seamlessly connected, resulting in the inability to share information when patients visit different hospitals, affecting the continuity and effectiveness of medical services.

[0004] (2) Data security risks: Due to the lack of effective data encryption and access control mechanisms, patients’ personal information can be easily leaked or tampered with.

[0005] (3) Data redundancy: During the treatment process, different departments require different information. Obtaining all the patient information through simple information retrieval and then manually screening the information to obtain useful information results in low work efficiency. Manual participation in information screening will increase the error rate. Summary of the invention

[0006] In order to solve the above problems existing in the prior art, the present invention provides a patient information management method based on multi-level communication.

[0007] S1: Obtaining patient personal information data through the patient subsystem, establishing a database table according to the patient personal information data, obtaining patient pathology data, and encrypting the patient pathology data through a block encryption algorithm according to the patient personal information data and storing it in the database table;

[0008] S2: Acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and obtain the patient's medical record data through the doctor subsystem;

[0009] S3: Calculating structured data through a standardized model based on the patient medical record data, dividing the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, searching a preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and searching the patient pathology data according to the influence factors to obtain relevant indicator data;

[0010] S4: Compare the relevant indicator data with a preset threshold to obtain disease severity data, label the disease name according to the disease severity data to obtain labeled data, and encrypt the labeled data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table;

[0011] S5: Retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, encrypt the patient's post-treatment data through a block encryption algorithm according to the search semantics and store it in the database table.

[0012] As a preferred technical solution of the present invention, the patient's pathological data includes lifestyle survey data, vital signs data, patient's basic medical history, and imaging data; the lifestyle survey data includes smoking history, drinking history, sleep status, eating habits, and exercise frequency; the vital signs data are measured by external equipment, including blood routine, height, weight, and measurements; the patient's basic medical history includes genetic disease history and family medical history.

[0013] Specifically, the standardization model is used to unify the format of the unstructured patient medical record data from different sources to form the structured data, thereby ensuring the consistency and compatibility of the data. The standardization model obtains an identification result by identifying the suffix name of the patient medical record data, selects a conversion model based on the identification result, and calculates the patient medical record data through the conversion model to obtain the structured data; the conversion model includes a text conversion model and an image conversion model.

[0014] Specifically, the specific calculation steps of the text conversion model are as follows:

[0015] S401: predefine an entity word-logical label relationship sequence, perform numerical encoding on the text-based medical record data to obtain encoded text data, and calculate a word vector sequence based on the encoded text data using a skip-gram model;

[0016] S402: Calculating the word vector sequence through the Bi-LSTM-CRF model to obtain a logical label sequence for identifying entity words;

[0017] S403: searching the entity word-logical label relationship sequence according to the logical label sequence to obtain the entity word sequence;

[0018] S404: extracting the relationship data from the entity word sequence according to the features of the logical tag sequence, and combining the entity word sequence and the relationship data into triples to obtain the structured data.

[0019] Specifically, the image conversion model is implemented based on the text conversion model, and the specific calculation steps are:

[0020] S501: obtaining corrected image data through perspective transformation according to the image-based medical record data, and obtaining preprocessed data through preprocessing according to the corrected image data; the preprocessing includes noise reduction, binarization, and parameter adjustment;

[0021] S502: performing edge positioning on the pre-processed data by using a canny operator to obtain text area positioning image data;

[0022] S503: performing character correction based on the text area positioning image data by a character projection image correction technique to obtain corrected character image data, and calculating character segmentation image data by a vertical projection segmentation method based on the corrected character image data;

[0023] S504: Normalized text image data is calculated based on the character segmentation image data by using the split-merge normalization method, feature data is extracted from the normalized text image data by using the stroke direction density feature extraction technology, text recognition results are calculated based on the feature data by using the OCR character recognition technology, and the structured data is calculated based on the text recognition results by using the text class conversion model.

[0024] Specifically, the output of Bi-LSTM is used as the input of the CRF layer. The CRF layer calculates the probability value of each predicted label sequence by the softmax algorithm according to the score of each predicted label sequence. The maximum likelihood estimation method is used to calculate the maximum value of the correct label logarithmic probability. The label sequence corresponding to the maximum value of the correct label logarithmic probability is output to obtain the logical label sequence. The maximum value of the correct label logarithmic probability is calculated as follows:

[0025]

[0026] Among them, S(c, y) is the score of the predicted label sequence y, Yc is all possible label sequences of sentence c, p(y|c) is the probability value of the predicted label sequence y, n is the number of outputs of Bi-LSTM, and a is the variable parameter.

[0027] Specifically, the feature extraction algorithm is implemented based on the probability statistics of character strokes and directions, and the specific calculation formula is:

[0028]

[0029] Among them, pd i is the i-th directional feature, l represents the distance from the pixel point to the end of the character stroke in the 8 direction, and i is a variable parameter.

[0030] A patient information management method based on multi-level interconnection and a patient information management system based on multi-level interconnection, comprising: a table building module, a data acquisition module, a data processing module, a data labeling module, and a data storage module;

[0031] The table building module is used to obtain patient personal information data through the patient subsystem, establish a database table according to the patient personal information data, obtain patient pathology data, and encrypt the patient pathology data according to the patient personal information data by a block encryption algorithm and store it in the database table;

[0032] The data acquisition module is used to acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and acquire the patient's medical record data through the doctor subsystem;

[0033] The data processing module is used to calculate the structured data through the standardized model according to the patient medical record data, divide the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, search the preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and search the patient pathology data according to the influence factors to obtain relevant indicator data;

[0034] The data labeling module is used to compare the relevant indicator data with a preset threshold value to obtain disease severity data, label the disease name according to the disease severity data to obtain label data, and encrypt the label data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table;

[0035] The data storage module is used to retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, and encrypt the patient's post-treatment data through a group encryption algorithm according to the search semantics and store it in the database table.

[0036] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the patient information management method based on multi-level communication as described above is implemented.

[0037] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute the patient information management method based on multi-level communication as described above when executed by a computer processor.

[0038] The beneficial effects of the present invention are:

[0039] (1) Data is stored through a block encryption algorithm, which solves the data security risks and prevents the patient's personal information from being tampered with.

[0040] (2) By storing patient information according to the patient's name and ID number, different medical staff can obtain information by inputting search semantics into the system, thus solving the problem of information islands and achieving data sharing.

[0041] (3) By setting up a conversion model to extract information from electronic medical records and paper medical records, and using a standardized model to unify the format of medical record data to obtain structured data, the problem that paper medical records can only be stored in the form of pictures and the problem that unstructured data takes up a large amount of storage space are solved.

[0042] (4) Structured data is divided into diagnostic data and treatment data according to its entity word sequence and relational data. Different information is transmitted according to the different roles entering the system, which solves the error rate problem of service personnel extracting useful information from large amounts of data and improves the work efficiency of service personnel.

[0043] (5) The disease names are labeled according to the severity data to obtain labeled data, so that patients can understand the severity of the disease more intuitively. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0045] Figure 1 The figure is a flow chart of a patient information management method based on multi-level communication of the present invention. DETAILED DESCRIPTION

[0046] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0047] See also Figure 1 , a patient information management method based on multi-level communication

[0048] S1: Obtaining patient personal information data through the patient subsystem, establishing a database table according to the patient personal information data, obtaining patient pathology data, and encrypting the patient pathology data through a block encryption algorithm according to the patient personal information data and storing it in the database table;

[0049] S2: Acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and obtain the patient's medical record data through the doctor subsystem;

[0050] S3: Calculating structured data through a standardized model based on the patient medical record data, dividing the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, searching a preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and searching the patient pathology data according to the influence factors to obtain relevant indicator data;

[0051] S4: Compare the relevant indicator data with a preset threshold to obtain disease severity data, label the disease name according to the disease severity data to obtain labeled data, and encrypt the labeled data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table;

[0052] S5: Retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, encrypt the patient's post-treatment data through a block encryption algorithm according to the search semantics and store it in the database table.

[0053] In this embodiment, the personal information data includes name, gender, age, and ID number; the search semantics include the patient's name and ID number. During the entire treatment cycle, the database table is retrieved according to the search semantics to obtain all the patient's data, which is convenient for diagnosing and treating the patient; the treatment data includes the relationship triple data between the disease name and the treatment method, the drug name, and the drug dosage, so that medical staff can better provide medical services to patients; the diagnostic data is the relationship triple data between the patient's symptoms and the disease name; the patient's medical record data includes text medical record data and image medical record data; the influence relationship library is used to store the relationship between the disease and the influencing factors.

[0054] Specifically, the patient's pathological data includes lifestyle survey data, vital signs data, basic medical history of the patient, and imaging data; the lifestyle survey data includes smoking history, drinking history, sleeping status, eating habits, and exercise frequency. During the doctor's diagnosis stage, the lifestyle survey data can be analyzed to find the cause of the disease; the vital signs data are measured by external equipment, including blood routine, height, weight, and measurements; the patient's basic medical history includes genetic disease history and family medical history; the imaging data needs to be compressed when it is encrypted and stored, so as to save storage space.

[0055] Specifically, the standardization model is used to unify the format of the unstructured patient medical record data from different sources to form the structured data, thereby ensuring the consistency and compatibility of the data. The standardization model obtains an identification result by identifying the suffix name of the patient medical record data, selects a conversion model based on the identification result, and calculates the patient medical record data through the conversion model to obtain the structured data; the conversion model includes a text conversion model and an image conversion model.

[0056] Specifically, the specific calculation steps of the text conversion model are as follows:

[0057] S401: predefine an entity word-logical label relationship sequence, perform numerical encoding on the text-based medical record data to obtain encoded text data, and calculate a word vector sequence based on the encoded text data using a skip-gram model;

[0058] S402: Calculating the word vector sequence through the Bi-LSTM-CRF model to obtain a logical label sequence for identifying entity words;

[0059] S403: searching the entity word-logical label relationship sequence according to the logical label sequence to obtain the entity word sequence;

[0060] S404: extracting the relationship data from the entity word sequence according to the features of the logical tag sequence, and combining the entity word sequence and the relationship data into triples to obtain the structured data.

[0061] Specifically, the image conversion model is implemented based on the text conversion model, and the specific calculation steps are:

[0062] S501: obtaining corrected image data through perspective transformation according to the image-based medical record data, and obtaining preprocessed data through preprocessing according to the corrected image data; the preprocessing includes noise reduction, binarization, and parameter adjustment;

[0063] S502: performing edge positioning on the pre-processed data by using a canny operator to obtain text area positioning image data;

[0064] S503: performing character correction based on the text area positioning image data by a character projection image correction technique to obtain corrected character image data, and calculating character segmentation image data by a vertical projection segmentation method based on the corrected character image data;

[0065] S504: Normalized text image data is calculated based on the character segmentation image data by using the split-merge normalization method, feature data is extracted from the normalized text image data by using the stroke direction density feature extraction technology, text recognition results are calculated based on the feature data by using the OCR character recognition technology, and the structured data is calculated based on the text recognition results by using the text class conversion model.

[0066] Specifically, the output of Bi-LSTM is used as the input of the CRF layer. The CRF layer calculates the probability value of each predicted label sequence by the softmax algorithm according to the score of each predicted label sequence. The maximum likelihood estimation method is used to calculate the maximum value of the correct label logarithmic probability. The label sequence corresponding to the maximum value of the correct label logarithmic probability is output to obtain the logical label sequence. The maximum value of the correct label logarithmic probability is calculated as follows:

[0067]

[0068] Among them, S(c, y) is the score of the predicted label sequence y, Yc is all possible label sequences of sentence c, p(y|c) is the probability value of the predicted label sequence y, n is the number of outputs of Bi-LSTM, and a is the variable parameter.

[0069] Specifically, the feature extraction algorithm is implemented based on the probability statistics of character strokes and directions, and the specific calculation formula is:

[0070]

[0071] Among them, pd i is the i-th directional feature, l represents the distance from the pixel point to the end of the character stroke in the 8 direction, and i is a variable parameter.

[0072] In this embodiment, a conversion model is set up to extract information from electronic medical records and paper medical records, and the medical record data is formatted in a unified manner through a standardized model to obtain structured data, thereby solving the problem that paper medical records can only be stored in the form of pictures and the problem that unstructured data occupies a large amount of storage space. The structured data is divided according to the entity word sequence and relationship data of the structured data to obtain diagnostic data and treatment data, and different information is transmitted according to different roles entering the system, which solves the error rate problem of service personnel extracting useful information from large amounts of data and improves the work efficiency of service personnel.

[0073] A patient information management method based on multi-level interconnection and a patient information management system based on multi-level interconnection, comprising: a table building module, a data acquisition module, a data processing module, a data labeling module, and a data storage module;

[0074] The table building module is used to obtain patient personal information data through the patient subsystem, establish a database table according to the patient personal information data, obtain patient pathology data, and encrypt the patient pathology data according to the patient personal information data by a block encryption algorithm and store it in the database table;

[0075] The data acquisition module is used to acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and acquire the patient's medical record data through the doctor subsystem;

[0076] The data processing module is used to calculate the structured data through the standardized model according to the patient medical record data, divide the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, search the preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and search the patient pathology data according to the influence factors to obtain relevant indicator data;

[0077] The data labeling module is used to compare the relevant indicator data with a preset threshold value to obtain disease severity data, label the disease name according to the disease severity data to obtain label data, and encrypt the label data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table;

[0078] The data storage module is used to retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, and encrypt the patient's post-treatment data through a group encryption algorithm according to the search semantics and store it in the database table.

[0079] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the patient information management method based on multi-level communication as described above is implemented.

[0080] A storage medium containing computer executable instructions, characterized in that the computer executable instructions are used to execute the patient information management method based on multi-level communication as described above when executed by a computer processor.

[0081] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0082] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0083] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0084] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A patient information management method based on multi-level communication, characterized in that: include: S1: Obtaining patient personal information data through the patient subsystem, establishing a database table according to the patient personal information data, obtaining patient pathology data, and encrypting the patient pathology data through a block encryption algorithm according to the patient personal information data and storing it in the database table; S2: Acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and obtain the patient's medical record data through the doctor subsystem; S3: Calculating structured data through a standardized model based on the patient's medical record data, dividing the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, searching a preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and searching the patient's pathology data according to the influence factors to obtain relevant indicator data; S4: Compare the relevant indicator data with a preset threshold to obtain disease severity data, label the disease name according to the disease severity data to obtain labeled data, and encrypt the labeled data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table; S5: Retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, encrypt the patient's post-treatment data through a block encryption algorithm according to the search semantics and store it in the database table.

2. The patient information management method based on multi-level communication according to claim 1, characterized in that: The patient's pathological data includes lifestyle survey data, vital signs data, basic medical history of the patient, and imaging data; the lifestyle survey data includes smoking history, drinking history, sleeping status, eating habits, and exercise frequency; the vital signs data are measured by external equipment and include blood routine, height, weight, and measurements; the patient's basic medical history includes genetic disease history and family medical history.

3. The patient information management method based on multi-level communication according to claim 1, characterized in that: The standardized model obtains a recognition result by identifying the suffix name of the patient medical record data, selects a conversion model according to the recognition result, and calculates the patient medical record data through the conversion model to obtain the structured data; the conversion model includes a text conversion model and an image conversion model.

4. The patient information management method based on multi-level communication according to claim 1, characterized in that: The specific calculation steps of the text conversion model are as follows: S401: predefine an entity word-logical label relationship sequence, perform numerical encoding on the text-based medical record data to obtain encoded text data, and calculate a word vector sequence based on the encoded text data using a skip-gram model; S402: Calculating the word vector sequence through the Bi-LSTM-CRF model to obtain a logical label sequence for identifying entity words; S403: searching the entity word-logical label relationship sequence according to the logical label sequence to obtain the entity word sequence; S404: extracting the relationship data from the entity word sequence according to the features of the logical tag sequence, and combining the entity word sequence and the relationship data into triples to obtain the structured data.

5. The patient information management method based on multi-level communication according to claim 1, characterized in that: The image conversion model is implemented based on the text conversion model, and the specific calculation steps are: S501: Obtaining corrected image data by perspective transformation according to the image-based medical record data, and obtaining preprocessed data by preprocessing according to the corrected image data; S502: performing edge positioning on the pre-processed data by using a canny operator to obtain text area positioning image data; S503: performing character correction based on the text area positioning image data by a character projection image correction technique to obtain corrected character image data, and calculating character segmentation image data by a vertical projection segmentation method based on the corrected character image data; S504: Normalized text image data is calculated based on the character segmentation image data by using the split-merge normalization method, feature data is extracted from the normalized text image data by using the stroke direction density feature extraction technology, text recognition results are calculated based on the feature data by using the OCR character recognition technology, and the structured data is calculated based on the text recognition results by using the text class conversion model.

6. The patient information management method based on multi-level communication according to claim 4 is characterized in that: The output of Bi-LSTM is used as the input of the CRF layer. The CRF layer calculates the probability value of each predicted label sequence by the softmax algorithm according to the score of each predicted label sequence. The maximum probability value of the correct label logarithm is calculated by the maximum likelihood estimation method according to the probability value of each predicted label sequence. The label sequence corresponding to the maximum probability value of the correct label logarithm is output to obtain the logical label sequence. The maximum probability value of the correct label logarithm is calculated as follows: Among them, S(c, y) is the score of the predicted label sequence y, Yc is all possible label sequences of sentence c, p(y|c) is the probability value of the predicted label sequence y, n is the number of outputs of Bi-LSTM, and a is the variable parameter.

7. The patient information management method based on multi-level communication according to claim 5, characterized in that: The feature extraction algorithm is implemented based on the probability statistics of character strokes and directions. The specific calculation formula is: Among them, pd i is the i-th directional feature, l represents the distance from the pixel point to the end of the character stroke in the 8 direction, and i is a variable parameter.

8. A patient information management system based on multi-level communication using the patient information management method based on multi-level communication according to claim 1, characterized in that: include: Table building module, data acquisition module, data processing module, data label module, data storage module; The table building module is used to obtain patient personal information data through the patient subsystem, establish a database table according to the patient personal information data, obtain patient pathology data, and encrypt the patient pathology data according to the patient personal information data by a block encryption algorithm and store it in the database table; The data acquisition module is used to acquire search semantics, retrieve the database table according to the search semantics to obtain the patient's pathological data, transmit the patient's pathological data to the doctor subsystem, and acquire the patient's medical record data through the doctor subsystem; The data processing module is used to calculate the structured data through the standardized model according to the patient medical record data, divide the structured data according to the entity word sequence and relationship data of the structured data to obtain diagnosis data and treatment data, search the preset influence relationship library according to the disease name in the diagnosis data to obtain influence factors, and search the patient pathology data according to the influence factors to obtain relevant indicator data; The data labeling module is used to compare the relevant indicator data with a preset threshold value to obtain disease severity data, label the disease name according to the disease severity data to obtain label data, and encrypt the label data and the structured data through a block encryption algorithm according to the search semantics and store them in the database table; The data storage module is used to retrieve the database table according to the search semantics to obtain the treatment data, transmit the treatment data to the service center subsystem, obtain the patient's post-treatment data through the service center subsystem, and encrypt the patient's post-treatment data through a group encryption algorithm according to the search semantics and store it in the database table.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the patient information management method based on multi-level communication as described in any one of claims 1-7 is implemented.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the patient information management method based on multi-level communication as described in any one of claims 1-7 when executed by a computer processor.

Images