A remote medical data processing method and related device

Abstract

The application provides a remote medical data processing method and related equipment, homomorphic encryption is performed on original remote medical data of a target patient according to key information, and encrypted medical data is obtained; the encrypted medical data is processed, and encrypted medical results are obtained, the medical results are disease risk assessment indexes obtained by processing the original remote medical data; medical measure information is obtained according to the encrypted medical results, and the medical measure information includes sending the medical results to a client; compared with the prior art, the original remote medical data is homomorphic encrypted, and data transmission and processing are completed in an encrypted state, and medical measure information is obtained, so that the security of the remote medical data is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart medical treatment, and particularly relates to a remote medical data processing method and related equipment. BACKGROUND

[0002] With the improvement of informatization degree and the development of network communication technology, remote medical treatment has been rapidly developed, and medical diagnosis in remote areas can be carried out with the help of modern communication technology, and medical information and medical services can be provided. However, the medical data of users belongs to personal privacy data, and some people do not even want to reveal their true identity while receiving medical services. In addition, some enterprises are driven and tempted by interests, and privately obtain and analyze the medical user data which belongs to personal privacy, and use it to seek benefits. SUMMARY

[0003] The present application provides a remote medical data processing method and related equipment, which aims to ensure the security of remote medical data.

[0004] In order to achieve the above purpose, the present application provides a remote medical data processing method, comprising:

[0005] Homomorphic encryption is performed on the original remote medical data of the target patient according to the key information, and encrypted medical data is obtained;

[0006] The encrypted medical data is processed to obtain encrypted medical results, and the medical results are disease risk assessment indexes obtained by processing the original remote medical data;

[0007] Medical measure information is obtained according to the encrypted medical results, and the medical measure information includes sending the medical results to the client.

[0008] Further, the key information is a key pair generated by the monitoring service equipment through a homomorphic encryption algorithm.

[0009] Further, the key pair comprises:

[0010] The public key is set in the client and is used for homomorphic encryption of the original remote medical data of the target patient;

[0011] The evaluation key is set in the edge server and is used for processing the encrypted medical data;

[0012] The secret key is set in the edge server and is used for decrypting the encrypted medical results.

[0013] Further, the encrypted medical data is processed to obtain the encrypted medical results, comprising:

[0014] An edge graphics computing device acceleration engine is optimized to obtain an optimized edge graphics computing device acceleration engine;

[0015] The encrypted medical data is input into the optimized edge graphics computing device acceleration engine, the encrypted medical data is processed by using the evaluation key, and the processing process is accelerated by using the optimized edge graphics computing device acceleration engine to obtain encrypted medical results.

[0016] Further, the processing process is accelerated by using the optimized edge graphics computing device acceleration engine, which includes:

[0017] The encrypted medical data is processed by using a parallel processing mode;

[0018] The encrypted medical data is processed by using a targeted implementation strategy for multiple homomorphic encryption operation types;

[0019] The system data of the encrypted medical data in the processing process is stored in the register of the optimized edge graphics computing device acceleration engine, and the shared memory of the optimized edge graphics computing device acceleration engine is used for data exchange and transmission.

[0020] Further, the encrypted medical data is processed by using a targeted implementation strategy for multiple homomorphic encryption operation types, which includes spatial operation, non-spatial operation and number theory transformation operation;

[0021] For the spatial operation, a two-dimensional convolution kernel is used to slide on the spatial domain of the encrypted medical data to extract a local feature map, and a pooling layer is used to down-sample the local feature map on the spatial domain of the encrypted medical data to obtain an edge feature map;

[0022] For the non-spatial operation, an activation function is used to perform a nonlinear transformation on the encrypted medical data to obtain a one-dimensional feature vector;

[0023] For the number theory transformation operation, a hierarchical reconstruction operation is used to perform a number theory transformation to obtain a data transformation result.

[0024] Further, for the number theory transformation operation, a hierarchical reconstruction operation is used to perform a number theory transformation to obtain a data transformation result, which includes:

[0025] The number theory transformation operation is divided into two kernels, and each kernel includes multiple threads;

[0026] In each kernel, each thread manages multiple coefficients, stores all the coefficients in a register, performs transformation in the register, and exchanges data by using the shared memory of the optimized edge graphics computing device acceleration engine after the transformation to obtain a data exchange result.

[0027] The application further provides a remote medical identity verification device based on threshold cryptography, comprising:

[0028] An encryption module is configured to homomorphically encrypt original remote medical data of a target patient according to key information to obtain encrypted medical data.

[0029] A processing module is configured to process the encrypted medical data to obtain encrypted medical results, wherein the medical results are disease risk assessment indexes obtained by processing the original remote medical data.

[0030] An acquisition module is configured to acquire medical measure information according to the encrypted medical results, wherein the medical measure information comprises sending the medical results to a client.

[0031] The application further provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the remote medical data processing method.

[0032] The application further provides a terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the remote medical data processing method when executing the computer program.

[0033] The above scheme of the application has the following advantages:

[0034] The application homomorphically encrypts original remote medical data of a target patient according to key information to obtain encrypted medical data, processes the encrypted medical data to obtain encrypted medical results, wherein the medical results are disease risk assessment indexes obtained by processing the original remote medical data, and acquires medical measure information according to the encrypted medical results, wherein the medical measure information comprises sending the medical results to a client.

[0035] Other advantages of the application will be described in detail in the following specific embodiment part. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 The figure is a flowchart of an embodiment of the application.

[0037] Figure 2 The figure is a schematic diagram of an application scenario of an embodiment of the application.

[0038] Figure 3 The figure is a structural schematic diagram of a remote medical identity verification device in an embodiment of the application.

[0039] Figure 4 Fig. 1 is a schematic diagram of a terminal device in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the technical problems solved by the present application, technical solutions and advantages clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0041] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0042] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be a locking connection, or a detachable connection, or an integral connection; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the internal communication of two elements. For a person of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0043] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0044] The present application aims at the existing problems, and provides a remote medical data processing method and related equipment.

[0045] As shown in Figure 1 and Figure 2 An embodiment of the present application provides a remote medical data processing method, which comprises:

[0046] Homomorphically encrypt the original remote medical data of the target patient according to the key information to obtain encrypted medical data;

[0047] Processing the encrypted medical data to obtain encrypted medical results, the medical results being a disease risk assessment index obtained by processing the original remote medical data;

[0048] The medical measure information is acquired according to the encrypted medical result, and the medical measure information includes sending the medical result to the client.

[0049] Most preferably, the key information is a key pair generated by the monitoring service device through a homomorphic encryption algorithm.

[0050] In the embodiment of the application, the homomorphic encryption algorithm is a specific operation such as multiplication and addition on the original remote medical data under the possession of the key, to obtain scrambled ciphertext; and the encryption of data through multiplication and addition is a conventional data encryption algorithm, and the specific operation process thereof will not be described herein.

[0051] In the embodiment of the application, the original remote medical data of the target patient can be an electrocardiogram or an electroencephalogram.

[0052] Most preferably, the key pair includes:

[0053] The public key is arranged on the client and used for homomorphic encryption of the original remote medical data of the target patient;

[0054] The evaluation key is arranged on the edge server and used for processing of the encrypted medical data;

[0055] The secret key is arranged on the edge server and used for decryption of the encrypted medical result.

[0056] In the embodiment of the application, the client can be an APP or application program loaded on a desktop computer, a notebook computer, a palm computer, a mobile phone or the like of a doctor and / or a target patient; and the edge server can be a general server, a server cluster, a cloud server or the like.

[0057] Most preferably, the encrypted medical data is processed to obtain an encrypted medical result, including:

[0058] The edge graphics computing device acceleration engine is optimized to obtain an optimized edge graphics computing device acceleration engine;

[0059] The encrypted medical data is input into the optimized edge graphics computing device acceleration engine, the encrypted medical data is processed by using the evaluation key, and the processing process is accelerated by the optimized edge graphics computing device acceleration engine to obtain the encrypted medical result.

[0060] Most preferably, the processing process is accelerated by the optimized edge processor acceleration engine, including:

[0061] The encrypted medical data is processed in a parallel processing manner;

[0062] The encrypted medical data is processed by using a targeted implementation strategy for multiple homomorphic encryption operation types;

[0063] The system data of the encrypted medical data in the processing process is stored in the registers of the optimized edge processor acceleration engine, and the shared memory of the optimized edge processor acceleration engine is used for data exchange and transmission.

[0064] In the embodiments of the present application, the processing process is optimized and accelerated by the optimized edge processor acceleration engine from the aspects of architecture, algorithm and data structure;

[0065] Firstly, at the architecture level, the input encrypted medical data is packaged and batch-processed to optimize the calculation involving weight multiplication and addition, and to realize fine-grained and highly parallel processing.

[0066] Then, at the algorithm level, the optimized edge processor acceleration engine adopts a targeted implementation strategy for different homomorphic encryption operation types such as element addition (EleAdd), element multiplication (EleMult), convolution (Conv) and number theoretic transform (NTT, Number Theoretic Transform).

[0067] Finally, at the data structure optimization level, the optimized edge processor acceleration engine stores system data by using its own registers to improve memory access efficiency, and also fully utilizes its shared memory for intermediate result exchange and transmission, thereby reducing access to global memory.

[0068] Most preferably, the encrypted medical data is processed by using a targeted implementation strategy for multiple homomorphic encryption operation types including spatial operation, non-spatial operation and number theoretic transform operation.

[0069] For spatial operation, a two-dimensional convolution kernel is used to slide on the spatial domain of the encrypted medical data to extract a local feature map, and a pooling layer is used to down-sample the local feature map on the spatial domain of the encrypted medical data to obtain an edge feature map.

[0070] For non-spatial operation, an activation function is used to perform non-linear transformation on the encrypted medical data to obtain a one-dimensional feature vector.

[0071] For number theoretic transform operation, a hierarchical reconstruction operation is used to perform number theoretic transform to obtain a data transformation result.

[0072] In the embodiments of the present application, the spatial operation refers to an operation involving two-dimensional space processing of images or signals in the deep learning model, which includes convolution operation and pooling operation, and the convolution operation uses a two-dimensional convolution kernel to slide on the spatial domain of the input data to extract a local feature map, and the pooling operation performs down-sampling on the local feature map in the spatial domain to extract an edge feature map, which preserves the spatial structure of the input data, enabling the model to learn and understand the spatial hierarchical relationship in the input;

[0073] The non-spatial operation refers to an operation in the deep learning model that does not involve the two-dimensional spatial structure of the input data, including activation function (element addition and multiplication), in the fully connected layer, each neuron is connected to all neurons of the previous layer, without considering the positional relationship of the neurons in the space, and the activation function independently performs non-linear transformation on each input value without considering the spatial structure of the input data, which treats the input data as a one-dimensional vector, losing the spatial information of the original data;

[0074] For complex number theory transformation operation, the embodiments of the present application divide it into two kernels for processing by means of hierarchical reconstruction, which greatly reduces the computational complexity.

[0075] Most preferably, for the number theory transformation operation, hierarchical reconstruction operation is adopted to perform the number theory transformation to obtain the data transformation result, including:

[0076] The number theory transformation operation is divided into two kernels, and each kernel includes a plurality of threads;

[0077] In each kernel, each thread manages a plurality of coefficients, stores all the coefficients to a register, performs transformation in the register, and after transformation, utilizes the optimized edge processor acceleration engine shared memory for data exchange to obtain the data exchange result.

[0078] In the embodiments of the present application, 14 processing levels are realized for the case of N=2^14, and this process is divided into two kernels, the first kernel is responsible for the first 8 levels, and the second kernel is responsible for the last 6 levels, in each kernel, each thread manages 8 coefficients, which are stored in a register to perform transformation, and the GPU shared memory is used for data exchange; based on this parallel processing mode, homomorphic evaluation operations are developed, including HAdd / CAdd (composed of EleAdd) and more complex HMult / CMult / HRot (including EleMult, EleAdd, Conv and NTT); this hierarchical decomposition can simplify the calculation process of complex operations, making them easier to manage and execute; at the same time, the GPU acceleration engine ensures that these operations can be executed at a faster speed, improving the performance of the entire homomorphic CNN implementation, and the entire inference process is carried out in an encrypted state without involving the decryption of the original medical data.

[0079] In the embodiment of the present application, the medical measure information is acquired according to the encrypted medical result, mainly by decrypting the medical measure information in the encrypted state through a secret key. The decryption mode is the inverse operation of the encryption mode, that is, if the encryption is through multiplication operation, the decryption needs to be through division operation, and if the encryption is through addition operation, the decryption needs to be through subtraction operation. The medical measure information can be the diagnosis result of the patient's condition by the doctor according to the encrypted medical result, which is whether drug treatment intervention, hospitalization treatment intervention or self-care.

[0080] In the embodiment of the present application, the original remote medical data of the target patient is homomorphic encrypted according to the key information, to obtain encrypted medical data; the encrypted medical data is processed to obtain encrypted medical result, which is a disease risk assessment index obtained by processing the original remote medical data; and the medical measure information is acquired according to the encrypted medical result, which includes sending the medical result to the client. Compared with the prior art, the original remote medical data is homomorphic encrypted, and the data transmission and processing are completed in the encrypted state to obtain the medical measure information, thereby ensuring the security of the remote medical data.

[0081] Corresponding to the remote medical data processing method described in the above embodiment, as shown in Figure 3 The embodiment of the present application also provides a remote medical identity authentication device 100 based on threshold cryptography, which comprises:

[0082] An encryption module 101 is configured to homomorphic encrypt the original remote medical data of a target patient according to key information, to obtain encrypted medical data.

[0083] A processing module 102 is configured to process the encrypted medical data to obtain encrypted medical result, which is a disease risk assessment index obtained by processing the original remote medical data.

[0084] An acquisition module 103 is configured to acquire medical measure information according to the encrypted medical result, which includes sending the medical result to the client.

[0085] It should be noted that the information interaction, execution process and the like between the above-mentioned devices / units are based on the same concept as the method embodiments of the present application, and the specific functions and the technical effects brought by the method embodiments can be referred to the method embodiments part, which will not be described here.

[0086] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of the embodiments of the present invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0087] This invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements a remote medical data processing method.

[0088] If an integrated module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above method embodiments of the present invention can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a building device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0089] like Figure 4 As shown, this embodiment of the invention also provides a terminal device D10 including: at least one processor D100 ( Figure 4The terminal device D10 can be a desktop computer, a notebook computer, a palm computer, a server, a server cluster, a cloud server, and the like. The terminal device can include, but is not limited to, the processor D100 and the memory D101.

[0090] The terminal device D10 can be a desktop computer, a notebook computer, a palm computer, a server, a server cluster, a cloud server, and the like. The terminal device can include, but is not limited to, the processor D100 and the memory D101.

[0091] In the embodiments of the present application, the processor D100 implements the following steps when executing the computer program D102:

[0092] The original remote medical data of the target patient is homomorphically encrypted according to the key information to obtain encrypted medical data; the encrypted medical data is processed to obtain encrypted medical results, and the medical results are disease risk assessment indexes obtained by processing the original remote medical data; medical measure information is obtained according to the encrypted medical results, and the medical measure information includes sending the medical results to the client.

[0093] The processor D100 can be a central processing unit (CPU). The processor can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0094] The memory D101 can be an internal storage unit of the terminal device D10, such as a hard disk or a memory of the terminal device, in some embodiments. The memory D101 can also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device D10, in other embodiments. Further, the memory D101 can include both the internal storage unit and the external storage device of the terminal device. The memory D101 is used to store an operating system, an application program, a boot loader, data, and other programs, such as the program code of the computer program D102. The memory D101 can also be used to temporarily store data that has been output or will be output.

[0095] It should be noted that the information interaction and execution process between the above devices / units are based on the same concept as the method embodiments of the embodiments of the application, and the specific functions and technical effects brought about can be referred to the method embodiments part, which will not be described here.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the embodiments of the application. The specific working process of the units and modules in the system can be referred to the corresponding process in the foregoing method embodiments, which will not be described here.

[0097] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of the application.

[0098] In the embodiments of the present application provided in the embodiments, it should be understood that the disclosed apparatus / network device and method can be implemented in other manners. For example, the embodiments of the apparatus / network device described above are merely schematic; for example, the division of the modules or units is only a logical function division; there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between the units can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0099] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0100] The above describes the preferred embodiments of the present application. It should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. A method for processing remote medical data, characterized in that, include: The original remote medical data of the target patient is homomorphically encrypted based on the key information to obtain the encrypted medical data. The encrypted medical data is processed to obtain encrypted medical results, which are disease risk assessment indicators obtained by processing the original remote medical data. Medical intervention information is obtained based on the encrypted medical results, and the medical intervention information includes sending the medical results to the client; The encrypted medical data is processed to obtain encrypted medical results, including: The edge graphics computing device acceleration engine is optimized to obtain the optimized edge graphics computing device acceleration engine. The encrypted medical data is input into the optimized edge graphics computing device acceleration engine, the encrypted medical data is processed using the evaluation key, and the processing is accelerated by the optimized edge graphics computing device acceleration engine to obtain encrypted medical results. The processing is accelerated through the optimized edge graphics computing device acceleration engine, including: The encrypted medical data is processed in parallel. A targeted implementation strategy is adopted to process various homomorphic encryption operation types of the encrypted medical data; The encrypted medical data is stored in the system data of the optimized edge graphics computing device acceleration engine during the processing, and the data is exchanged and transmitted using the shared memory of the optimized edge graphics computing device acceleration engine.

2. The remote medical data processing method according to claim 1, characterized in that, The key information is a key pair generated by the monitoring service device using a homomorphic encryption algorithm.

3. The remote medical data processing method according to claim 2, characterized in that, The key pair includes: A public key, set on the client, is used to homomorphically encrypt the target patient's raw telemedicine data; An evaluation key, set on an edge server, is used to process the encrypted medical data; A secret key, set on an edge server, is used to decrypt encrypted medical results.

4. The remote medical data processing method according to claim 1, characterized in that, A targeted implementation strategy is adopted to process various homomorphic encryption operation types of the encrypted medical data, including spatial operations, non-spatial operations, and number theory transformation operations; For the spatial operation, a two-dimensional convolution kernel is slid across the spatial domain of the encrypted medical data to extract local feature maps. A pooling layer is then used to downsample the local feature maps across the spatial domain of the encrypted medical data to obtain edge feature maps. For the non-spatial operation, a one-dimensional feature vector is obtained by performing a non-linear transformation on the encrypted medical data through an activation function. For number theory transformation operations, a hierarchical reconstruction operation is used to perform number theory transformations to obtain data transformation results.

5. The remote medical data processing method according to claim 4, characterized in that, For number-theoretic transformation operations, a hierarchical reconstruction operation is used to perform number-theoretic transformations, resulting in data transformation results, including: The number theory transformation operation is divided into two kernels, each kernel including multiple threads; In each kernel, each thread manages multiple coefficients, stores all coefficients in a register, performs transformations in the register, and after transformations, uses the shared memory of the optimized edge graphics computing device acceleration engine to exchange data and obtain the data exchange result.

6. A remote medical authentication device based on threshold cryptography, characterized in that, include: The encryption module is used to homomorphically encrypt the original remote medical data of the target patient based on the key information to obtain the encrypted medical data. The processing module is used to process the encrypted medical data to obtain encrypted medical results, wherein the medical results are disease risk assessment indicators obtained by processing the original remote medical data. The acquisition module is used to acquire medical intervention information based on the encrypted medical results, wherein the medical intervention information includes sending the medical results to the client; Specifically, the processing module is used to implement: The encrypted medical data is processed to obtain encrypted medical results, including: The edge graphics computing device acceleration engine is optimized to obtain the optimized edge graphics computing device acceleration engine. The encrypted medical data is input into the optimized edge graphics computing device acceleration engine, the encrypted medical data is processed using the evaluation key, and the processing is accelerated by the optimized edge graphics computing device acceleration engine to obtain encrypted medical results. The processing is accelerated through the optimized edge graphics computing device acceleration engine, including: The encrypted medical data is processed in parallel. A targeted implementation strategy is adopted to process various homomorphic encryption operation types of the encrypted medical data; The encrypted medical data is stored in the system data of the optimized edge graphics computing device acceleration engine during the processing, and the data is exchanged and transmitted using the shared memory of the optimized edge graphics computing device acceleration engine.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the remote medical data processing method as described in any one of claims 1 to 5.

8. A terminal 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 computer program, it implements the remote medical data processing method as described in any one of claims 1 to 5.

Images