Remote case management method and system for multidisciplinary medical platform

Abstract

An embodiment of the present application provides a remote case management method and system for a multidisciplinary medical platform, the method comprising: a server receiving case query information sent by a first remote terminal, the case query information including: a patient ID and a case department, performing encryption operations on the patient ID using a plurality of encryption algorithms to obtain a plurality of encrypted information, broadcasting the broadcast information of the query information to all remote terminals of the multidisciplinary medical platform, if any one of the plurality of encrypted information is consistent with a first case identifier, extracting a first remote case corresponding to the first case identifier, and obtaining a first department corresponding to the first remote case; the server sending a case response message to the first remote terminal, the first remote terminal receiving the case response message, obtaining an address of the random code according to the mapping relationship, replacing the stored content of the address of the random code with the patient ID and saving it.

Description

Technical Field

[0001] The present application belongs to the field of communication and medical technology, and specifically relates to a remote case management method and system for a multidisciplinary medical platform. Background Art

[0002] Telemedicine is the use of computer technology, remote sensing, telemetry, and telecontrol to leverage the medical technology and equipment of large hospitals or specialized medical centers to provide remote diagnosis, treatment, and consultation for patients in remote areas, on islands, or on ships with poor medical conditions. A physical examination typically refers to a physical exam, which checks the condition of various organs and determines whether certain diseases are present.

[0003] For medical care, telemedicine has become the norm, and telemedicine also has case management. However, the existing multi-platform calls for remote case management are based on identity information, which leaks the patient's privacy and affects the user's safety. Summary of the Invention

[0004] The present application provides a remote case management method and system for a multidisciplinary medical platform, which can realize the management and call of cases on the multidisciplinary medical platform, protect the privacy of patients, and improve the safety of users.

[0005] In a first aspect, the present application provides a remote case management method for a multidisciplinary medical platform, the method comprising the following steps:

[0006] The server receives case query information sent by the first remote terminal, the case query information including: a patient ID and a case department, encrypts the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcasts broadcast information of the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including: the multiple encrypted information and the case department;

[0007] The second remote terminal receives the broadcast information, compares the multiple encrypted information with the case identification in the remote case database one by one, and discards the broadcast information if none of the multiple encrypted information is consistent with the case identification. If any one of the multiple encrypted information is consistent with the first case identification, extracts the first remote case corresponding to the first case identification, obtains the first department corresponding to the first remote case, and returns the first remote case to the server with the response message carried in the broadcast message if the first department is the same as the case department; if the first department is not the same as the case department, discards the broadcast information.

[0008] The server identifies the content of the first remote medical record and determines that it contains a storage address with a patient ID, replaces the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record, generates a mapping relationship between the random code and the storage address, and sends a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote medical record;

[0009] The first remote terminal receives the case response message, obtains the address of the random code according to the mapping relationship, replaces the storage content of the random code address with the patient ID, and saves it.

[0010] In a second aspect, a remote case management system for a multidisciplinary medical platform is provided, the system comprising: a server, a first remote terminal and a second remote terminal,

[0011] The server is configured to receive case query information sent by a first remote terminal, the case query information including a patient ID and a case department, encrypt the patient ID using a plurality of encryption algorithms to obtain a plurality of encrypted information, and broadcast broadcast information of the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including the plurality of encrypted information and the case department;

[0012] The second remote terminal is used to receive the broadcast information, compare the multiple encrypted information with the case identification in the remote case database one by one, discard the broadcast information if none of the multiple encrypted information is consistent with the case identification, extract the first remote case corresponding to the first case identification if any one of the multiple encrypted information is consistent with the first case identification, obtain the first department corresponding to the first remote case, and if the first department is the same as the case department, return the first remote case to the server in a response message carried in the broadcast message; if the first department is not the same as the case department, discard the broadcast information;

[0013] The server is further configured to identify the content of the first remote medical record and determine that it contains a storage address with a patient ID, replace the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record, generate a mapping relationship between the random code and the storage address, and send a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote medical record;

[0014] The first remote terminal is used to receive the case response message, obtain the address of the random code according to the mapping relationship, replace the storage content of the random code address with the patient ID, and then save it.

[0015] In a third aspect, the present application provides a computer storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of the present application.

[0016] The embodiments of the present application have the following beneficial effects:

[0017] The technical solution provided by the present application is that a server receives case query information sent by a first remote terminal, and the case query information includes: patient ID and case department, and performs encryption operation on the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcasts the query information to all remote terminals of the multidisciplinary medical platform, and the broadcast information includes: multiple encrypted information and case department; the second remote terminal receives the broadcast information, and compares the multiple encrypted information with the case identification in the remote case database one by one. If the multiple encrypted information is not consistent with the case identification, the broadcast information is discarded. If any of the multiple encrypted information is consistent with the first case identification, the first remote case corresponding to the first case identification is extracted, and the first department corresponding to the first remote case is obtained. If the first department If the first department is the same as the case department, the first remote case is carried in the response message of the broadcast message and returned to the server; if the first department is different from the case department, the broadcast message is discarded; the server identifies the content of the first remote case to determine the storage address containing the content information with patient information, replaces the storage information corresponding to the storage address with a random code to obtain the scrambled first remote case, and generates a mapping relationship between the random code and the storage address, and sends a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote case; the first remote case receives the case response message, obtains the address of the random code according to the mapping relationship, replaces the storage content of the random code address with the patient ID and saves it. In this way, the remote terminal can hide the patient ID when executing the case query, avoiding the leakage of patient information caused by interception during the transmission process, and improving the security of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a schematic diagram of the structure of a telemedicine system architecture provided by an embodiment of the present application;

[0020] Figure 2This is a flow chart of a remote case management method for a multidisciplinary medical platform provided in an embodiment of the present application;

[0021] Figure 3 This is a structural diagram of a remote case management system for a multidisciplinary medical platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 this application.

[0023] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, system, product, or apparatus.

[0024] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0025] The following is an introduction to the relevant terms involved in this application.

[0026] Remote terminal: It can also be called an intelligent physical examination machine. It is generally controlled by a microcomputer, so that relevant physical examination data can be recorded directly without manual operation, and the physical examination data can be uploaded.

[0027] Remote medical records are generally electronic medical records, that is, electronic medical records built by the medical platform for users.

[0028] The following describes the system architecture of telemedicine related to the embodiments of the present application.

[0029] The present application also provides a server 10 and a remote terminal 20, such as Figure 1As shown, the server 10 is connected to the remote terminal 20 via a wireless network. The remote terminal includes at least one processor 11 and a memory 12. It may also include a communication interface 14, one or more cameras 15, a display screen 16, and a bus 13. The processor 11, the memory 12, the camera 15, the display screen 16, and the communication interface 14 can communicate with each other through the bus 13. The communication interface 14 can transmit information. The communication interface 14 can have a wireless communication function. The wireless communication function can be a short-range wireless communication or a long-range communication function (such as LTE or NR mode). The processor 11 can call the logic instructions in the memory 12 to execute or support the method in the embodiment of the present application. The remote terminal 20 may also include: a microphone, a lighting device, etc.

[0030] The memory 12 is a computer-readable storage medium that can be configured to store software programs or computer-executable programs, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 11 executes the software programs, instructions, or modules stored in the memory 12 to perform functional applications and data processing, thereby implementing or supporting the methods in the embodiments of the present disclosure.

[0031] The following describes the main technical application scenarios of the embodiments of this application:

[0032] In medical care, medical records are files that must be constructed for users. However, for users, for example, user A uses platform A this time and platform B next time. If two medical records are constructed for both, first of all, for user A, the case is incomplete, and doctors on different platforms cannot construct system information. If a case is constructed, platform A and platform B may not be able to construct it directly, and both platform A and platform B have certain impacts on patient privacy.

[0033] The specific methods are introduced in detail below.

[0034] See also Figure 2 , this application also provides a remote case management method for a multidisciplinary medical platform, Figure 2 This is a flow chart of a remote case management method for a multidisciplinary medical platform provided in this application. The above method can be used in Figure 1 The telemedicine system architecture shown is implemented as follows, specifically, Figure 2 The method shown can be executed by the server and remote terminal under the telemedicine system architecture, wherein the first remote terminal corresponds to the first medical platform and the second remote terminal corresponds to the second medical platform; the above method is as follows Figure 2 As shown, the following steps are included:

[0035] Step S201: The server receives case query information sent by a first remote terminal, the case query information including a patient ID and a case department, encrypts the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcasts the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including the multiple encrypted information and the case department.

[0036] The above-mentioned multiple encryption algorithms can adopt general encryption algorithms, such as AES, DES, and 3DES. Of course, other encryption algorithms can also be used in application scenarios. This application does not limit the specific expression form and specific encryption implementation method of the above-mentioned encryption algorithms.

[0037] The above-mentioned patient ID includes but is not limited to: patient medical insurance number, patient ID number, patient name, etc., which can uniquely identify patient information. This application does not limit the specific form of the above-mentioned patient ID.

[0038] Step S202: The second remote terminal receives the broadcast information and compares the multiple encrypted information with the case identification in the remote case database one by one. If none of the multiple encrypted information matches the case identification, the broadcast information is discarded. If any one of the multiple encrypted information matches the first case identification, the first remote case corresponding to the first case identification is extracted, and the first department corresponding to the first remote case is obtained. If the first department is the same as the case department, the response message carrying the first remote case in the broadcast message is returned to the server; if the first department is different from the case department, the broadcast information is discarded.

[0039] The above case identification is the encrypted information obtained by encrypting the patient ID using any one of multiple encryption algorithms; the above departments can correspond to multiple disciplines. For example, the gastroenterology department corresponds to the internal medicine-gastroenterology department. This is the classification of medicine, and no examples are given here one by one.

[0040] Step S203: The server identifies the content of the first remote medical record and determines that it contains a storage address with a patient ID. The server replaces the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record. The server generates a mapping relationship between the random code and the storage address, and sends a case response message to the first remote terminal. The case response message includes the mapping relationship and the scrambled first remote medical record.

[0041] Step S204: The first remote terminal receives the case response message, obtains the address of the random code according to the mapping relationship, replaces the storage content of the random code address with the patient ID, and saves it.

[0042] The technical solution provided by the present application is that a server receives case query information sent by a first remote terminal, and the case query information includes: patient ID and case department, and performs encryption operation on the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcasts the query information to all remote terminals of the multidisciplinary medical platform, and the broadcast information includes: multiple encrypted information and case department; the second remote terminal receives the broadcast information, and compares the multiple encrypted information with the case identification in the remote case database one by one. If the multiple encrypted information is not consistent with the case identification, the broadcast information is discarded. If any of the multiple encrypted information is consistent with the first case identification, the first remote case corresponding to the first case identification is extracted, and the first department corresponding to the first remote case is obtained. If the first department If the first department is the same as the case department, the first remote case is carried in the response message of the broadcast message and returned to the server; if the first department is different from the case department, the broadcast message is discarded; the server identifies the content of the first remote case to determine the storage address containing the content information with patient information, replaces the storage information corresponding to the storage address with a random code to obtain the scrambled first remote case, and generates a mapping relationship between the random code and the storage address, and sends a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote case; the first remote case receives the case response message, obtains the address of the random code according to the mapping relationship, replaces the storage content of the random code address with the patient ID and saves it. In this way, the remote terminal can hide the patient ID when executing the case query, avoiding the leakage of patient information caused by interception during the transmission process, and improving the security of the data.

[0043] For example, the server identifying the content of the first remote medical record and determining that the storage address includes the patient ID may specifically include:

[0044] The server generates input data based on the content of the first remote case, inputs the input data into the multi-layer neural network model to obtain a calculation result, and determines a storage address with a patient ID based on the calculation result.

[0045] The above-mentioned generation of input data, execution of operations to obtain operation results, and determination of the storage address with the patient ID can all be carried out in existing ways, and this application is not limited thereto. The main improvement of the solution of this application to the above-mentioned neural network recognition is the training method of the multi-layer neural network type. Specifically, the training method of the above-mentioned multi-layer neural network model can specifically include:

[0046] The server extracts the multi-layer original neural network model, determines the multi-layer value x, obtains the historical maximum training layer value y of the multi-layer original neural network model, determines the number of training layers of the multi-layer original neural network model to be 1, 2...y, determines the last layer of the multi-layer original neural network model as the training layer, and randomly constructs y models to be trained according to the number of training layers, wherein the number of training layers of each model in the y models to be trained is 1, 2...y in sequence, and the last layer of the y models to be trained is fixed as the training layer, and the marked training data is used to train the y models to be trained to obtain y trained models, and w models are randomly constructed. The labeled training data is input as input data to y trained models to obtain y confidence values, and the number of training layers α of the model to be trained corresponding to the maximum confidence value is selected from the y confidence values. β quadratic models to be trained are randomly constructed, and the number of training layers of each model in the β quadratic models to be trained is α and the last layer is fixed as the training layer. After training the β quadratic models to be trained, β quadratic trained models are obtained, and β confidence values of the β quadratic trained models are obtained. The quadratic trained model corresponding to the maximum confidence value is selected from the β confidence values as the multi-layer neural network model.

[0047] The above-mentioned step of inputting the w labeled training data as input data into y trained models to obtain y confidence values specifically includes: inputting the w labeled training data as input data into one of the y trained models, performing w operations to obtain w operation results, obtaining v values whose w operation results are the same as the labeling results of the w labeled training data, the confidence value of one model = v / w, and traversing the y trained models to obtain y confidence values.

[0048] The above-mentioned labeling results are the results of labeling the w labeled training data before the operation, and the above-mentioned labeling can use a variety of labeling methods; the above-mentioned w operation results are the results after performing the neural network operation.

[0049] The idea behind the above training is: corresponding to the multi-layer neural network model, it has multiple layers of operations. In the actual recognition process, the more training layers, the better. Therefore, the larger the training layer, the more likely it is to overfit. Therefore, it is necessary to control the number of training layers. Therefore, the number of layers to be trained is determined by the value of the historical maximum training layer. After determining the maximum number of training layers, it is also necessary to see how many specific layers are appropriate. Therefore, first of all, it is necessary to screen the training models with different numbers of training layers to obtain the appropriate number of layers α. After determining the number of layers α, it is necessary to determine the specific distribution of α training layers. Then, a second screening is required, that is, screening is performed by constructing β secondary training models, and then the number of multi-layer neural network models that best suit the above data is determined through the training data.

[0050] Let's take a practical example to illustrate. Here, we assume that the above multi-layer value x=16, and here we assume that y=4. Then, first, we build four training models, and the four training models have training layers 1, 2, 3, and 4 respectively. After training the four training models, it is assumed that α=2 is found. Then, it is necessary to build β secondary training models, that is, it is necessary to build 15 secondary training models, corresponding to training layers (1, 16), (2, 16)...(15, 16), and then after training the 15 secondary training models, perform identification to determine the most suitable model. Suppose that it is determined to be (13, 16), then the secondary trained model corresponding to the training layer (13, 16) is determined as the above multi-layer neural network model to perform input data operations.

[0051] The above (1, 16) indicates that the training layers of a training model are the 1st and 16th layers. Because the last layer needs to output the result, it is necessary to determine the last layer as the training layer during training.

[0052] The technical solution of the present application obtains the most suitable multi-layer neural network model corresponding to the above-mentioned recognition information through secondary training screening, which can make the trained neural network model more compatible with the corresponding recognition data, thereby improving the recognition accuracy.

[0053] For example, the above method may further include:

[0054] If the server receives multiple first remote cases, it performs conflict identification on the multiple first remote cases to determine whether the multiple first remote cases have conflicts. If there are no conflicts, the multiple first remote cases are scrambled and sent to the first remote terminal. If there are conflicts, the multiple first remote cases are discarded.

[0055] The above-mentioned conflict determination can be made through a neural network model. Of course, other methods can also be used to determine whether there is a conflict. This application does not limit the specific method of the above-mentioned conflict determination.

[0056] See Figure 3 , Figure 3 A remote case management system for a multidisciplinary medical platform is provided, the system comprising: a server 300, a first remote terminal 301 and a second remote terminal 302,

[0057] Server 300 is configured to receive case query information sent by a first remote terminal, the case query information including a patient ID and a case department, encrypt the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcast the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including the multiple encrypted information and the case department;

[0058] The second remote terminal 302 is used to receive the broadcast information, compare the multiple encrypted information with the case identification in the remote case database one by one, and discard the broadcast information if none of the multiple encrypted information is consistent with the case identification. If any one of the multiple encrypted information is consistent with the first case identification, extract the first remote case corresponding to the first case identification, obtain the first department corresponding to the first remote case, and if the first department is the same as the case department, return the first remote case to the server in a response message carried in the broadcast message; if the first department is not the same as the case department, discard the broadcast information;

[0059] The server 300 is further configured to identify the content of the first remote medical record and determine that it contains a storage address having a patient ID, replace the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record, generate a mapping relationship between the random code and the storage address, and send a case response message to the first remote terminal, the case response message including the mapping relationship and the scrambled first remote medical record;

[0060] The first remote terminal 301 is used to receive the case response message, obtain the address of the random code according to the mapping relationship, replace the storage content of the random code address with the patient ID, and save it.

[0061] Optional,

[0062] The server 300 is specifically configured to generate input data based on the content of the first remote case, input the input data into a multi-layer neural network model to obtain a calculation result, and determine a storage address with a patient ID based on the calculation result.

[0063] Optional,

[0064] Server 300 is specifically used to extract a multi-layer original neural network model, determine a multi-layer value x, obtain a historical maximum training layer value y of the multi-layer original neural network model, determine the number of training layers of the multi-layer original neural network model to be 1, 2...y, determine the last layer of the multi-layer original neural network model as a training layer, randomly construct y models to be trained according to the number of training layers, wherein the number of training layers of each model in the y models to be trained is 1, 2...y in sequence, and the last layer of the y models to be trained is fixed as the training layer, and train the y models to be trained using the marked training data to obtain y trained models , w labeled training data are input as input data to y trained models respectively to obtain y confidence values, the number of training layers α of the model to be trained corresponding to the maximum confidence value is selected from the y confidence values, β secondary models to be trained are randomly constructed, the number of training layers of each model in the β secondary models to be trained is α and the last layer is fixed as the training layer, β secondary models to be trained are trained to obtain β secondary trained models, β confidence values of the β secondary trained models are obtained, and the secondary trained model corresponding to the maximum confidence value is selected from the β confidence values as the multi-layer neural network model.

[0065] Optional,

[0066] Server 300 is specifically used to input w labeled training data as input data into one of y trained models to perform w operations to obtain w operation results, obtain v values whose w operation results are the same as the labeling results of the w labeled training data, the confidence value of one model = v / w, and traverse the y trained models to obtain y confidence values.

[0067] Optional,

[0068] The server 300 is also used to perform conflict identification on the multiple first remote cases to determine whether the multiple first remote cases have conflicts if multiple first remote cases are received. If there are no conflicts, the multiple first remote cases are scrambled and sent to the first remote terminal. If there are conflicts, the multiple first remote cases are discarded.

[0069] The embodiment of the present application can divide the functional units of the electronic device according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0070] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of this application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0071] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0072] The present application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may comprise an electronic device.

[0073] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed methods, devices, and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the units is merely a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection of devices or units, which may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may be physically included separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0077] The above-mentioned integrated unit implemented as a software functional unit can be stored in a computer-readable storage medium. The software functional unit is stored in a storage medium and includes instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform some of the steps of the method described in various embodiments of the present invention. The aforementioned storage medium includes a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a volatile memory, or a non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM (DR RAM). Various media can store program code.

[0078] Although the present invention is disclosed above, it is not limited thereto. Any person skilled in the art may readily conceive of variations or substitutions, and may make various modifications and alterations without departing from the spirit and scope of the present invention. Combinations of the above-described functions and implementation steps, including software and hardware implementations, are all within the scope of protection of the present invention.

Claims

1. A remote case management method for a multidisciplinary medical platform, characterized in that: The method comprises the following steps: The server receives case query information sent by the first remote terminal, the case query information including: a patient ID and a case department, encrypts the patient ID using multiple encryption algorithms to obtain multiple encrypted information, and broadcasts broadcast information of the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including: the multiple encrypted information and the case department; The second remote terminal receives the broadcast information, compares the multiple encrypted information with the case identification in the remote case database one by one, and discards the broadcast information if none of the multiple encrypted information is consistent with the case identification. If any one of the multiple encrypted information is consistent with the first case identification, extracts the first remote case corresponding to the first case identification, obtains the first department corresponding to the first remote case, and returns the first remote case to the server with the response message carried in the broadcast message if the first department is the same as the case department; if the first department is not the same as the case department, discards the broadcast information. The server identifies the content of the first remote medical record and determines that it contains a storage address with a patient ID, replaces the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record, generates a mapping relationship between the random code and the storage address, and sends a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote medical record; The first remote terminal receives the case response message, obtains the address of the random code according to the mapping relationship, replaces the stored content of the random code address with the patient ID, and saves the content; The server identifies the content of the first remote medical record and determines that the storage address containing the patient ID specifically includes: The server generates input data based on the content of the first remote medical record, inputs the input data into a multi-layer neural network model to obtain a calculation result, and determines a storage address with the patient ID based on the calculation result; The training method of the multi-layer neural network model specifically includes: The server extracts the multi-layer original neural network model, determines the multi-layer value x, obtains the historical maximum training layer value y of the multi-layer original neural network model, determines the number of training layers of the multi-layer original neural network model to be 1, 2...y, determines the last layer of the multi-layer original neural network model as the training layer, and randomly constructs y models to be trained according to the number of training layers, wherein the number of training layers of each model in the y models to be trained is 1, 2...y in sequence, and the last layer of the y models to be trained is fixed as the training layer, and the labeled training data is used to train the y models to be trained to obtain y trained models, and the w labeled The training data of β are respectively input into y trained models as input data to obtain y confidence values, the number of training layers α of the model to be trained corresponding to the maximum confidence value is selected from the y confidence values, β quadratic models to be trained are randomly constructed, the number of training layers of each model in the β quadratic models to be trained is α and the last layer is fixed as the training layer, β quadratic trained models are obtained after training the training layers of the β quadratic models to be trained, β confidence values of the β quadratic trained models are obtained, and the quadratic trained model corresponding to the maximum confidence value is selected from the β confidence values as the multi-layer neural network model.

2. The remote case management method of the multidisciplinary medical platform according to claim 1, characterized in that: The w labeled training data are input as input data to y trained models to obtain y confidence values, specifically including: Input w labeled training data as input data to one of y trained models, perform w operations to obtain w operation results, obtain v values whose w operation results are the same as the labeled results of the w labeled training data, the confidence value of one model = v / w, traverse the y trained models to obtain y confidence values.

3. The remote case management method of the multidisciplinary medical platform according to claim 1, characterized in that: The method further comprises: If the server receives multiple first remote cases, it performs conflict identification on the multiple first remote cases to determine whether the multiple first remote cases have conflicts. If there are no conflicts, the multiple first remote cases are scrambled and sent to the first remote terminal. If there are conflicts, the multiple first remote cases are discarded.

4. A remote case management system for a multidisciplinary medical platform, the system comprising: The server, the first remote terminal and the second remote terminal are characterized in that The server is configured to receive case query information sent by a first remote terminal, the case query information including a patient ID and a case department, encrypt the patient ID using a plurality of encryption algorithms to obtain a plurality of encrypted information, and broadcast broadcast information of the query information to all remote terminals of the multidisciplinary medical platform, the broadcast information including the plurality of encrypted information and the case department; The second remote terminal is used to receive the broadcast information, compare the multiple encrypted information with the case identification in the remote case database one by one, discard the broadcast information if none of the multiple encrypted information is consistent with the case identification, extract the first remote case corresponding to the first case identification if any one of the multiple encrypted information is consistent with the first case identification, obtain the first department corresponding to the first remote case, and if the first department is the same as the case department, return the first remote case to the server in a response message carried in the broadcast message; if the first department is not the same as the case department, discard the broadcast information; The server is further configured to identify the content of the first remote medical record and determine that it contains a storage address with a patient ID, replace the storage information corresponding to the storage address with a random code to obtain a scrambled first remote medical record, generate a mapping relationship between the random code and the storage address, and send a case response message to the first remote terminal, the case response message including: the mapping relationship and the scrambled first remote medical record; A first remote terminal is configured to receive the case response message, obtain the address of the random code according to the mapping relationship, replace the stored content of the random code address with the patient ID, and then save the content; The server is specifically configured to generate input data based on the content of the first remote case, input the input data into a multi-layer neural network model to obtain a calculation result, and determine a storage address with a patient ID based on the calculation result. The server is specifically used to extract a multi-layer original neural network model, determine a multi-layer value x, obtain a historical maximum training layer value y of the multi-layer original neural network model, determine the number of training layers of the multi-layer original neural network model to be 1, 2...y, determine the last layer of the multi-layer original neural network model as a training layer, randomly construct y models to be trained according to the number of training layers, wherein the number of training layers of each model in the y models to be trained is 1, 2...y in sequence, and the last layer of the y models to be trained is fixed as the training layer, perform training on the y models to be trained using the marked training data to obtain y trained models, and w The labeled training data are input as input data to y trained models respectively to obtain y confidence values, the number of training layers α of the model to be trained corresponding to the maximum confidence value is selected from the y confidence values, β quadratic models to be trained are randomly constructed, the number of training layers of each model in the β quadratic models to be trained is α and the last layer is fixed as the training layer, β quadratic trained models are obtained after training the training layers of the β quadratic models to be trained, β confidence values of the β quadratic trained models are obtained, and the quadratic trained model corresponding to the maximum confidence value is selected from the β confidence values as the multi-layer neural network model.

5. The remote case management system of the multidisciplinary medical platform according to claim 4, characterized in that: The server is specifically used to input w labeled training data as input data into one of y trained models to perform w operations to obtain w operation results, obtain v values whose w operation results are the same as the labeling results of the w labeled training data, the confidence value of one model = v / w, and traverse the y trained models to obtain y confidence values.

6. The remote case management system of the multidisciplinary medical platform according to claim 4, characterized in that: The server is also used to perform conflict identification on the multiple first remote cases to determine whether the multiple first remote cases have conflicts if multiple first remote cases are received; if there are no conflicts, scramble the multiple first remote cases and send them to the first remote terminal; if there are conflicts, discard the multiple first remote cases.

Images