Hierarchical diagnosis and treatment method, device and equipment, storage medium and program product

Abstract

The invention discloses a hierarchical diagnosis and treatment method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: in response to a received task execution request sent by a user for a target task, forwarding the task execution request to a pre-constructed hierarchical diagnosis and treatment system; wherein the hierarchical diagnosis and treatment system adopts a distributed framework, the distributed framework comprises a plurality of nodes, and the nodes comprise a center node, region nodes and edge nodes; determining a task type of the target task and a current medical resource of each node of the hierarchical diagnosis and treatment system, and determining a target node from a plurality of nodes according to an execution strategy, the task type and the current medical resource pre-selected by a user; and performing hierarchical execution on the target task through the target node, and receiving a returned task execution result. According to the technical scheme of the embodiment of the invention, efficient utilization of global medical resources can be realized through dynamic task routing, and medical resource configuration is optimized through hierarchical execution.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a tiered diagnosis and treatment method, device, electronic device, storage medium, and program product. Background Technology

[0002] With the advancement of the tiered medical system, primary healthcare institutions are playing an increasingly important role in initial diagnosis and chronic disease management. However, due to limitations in personnel, technology, and resources, primary hospitals face problems such as low diagnostic accuracy and non-standardized treatment plans. Meanwhile, although urban medical institutions possess advanced AI-assisted systems and expert resources, they struggle to provide real-time support to primary healthcare institutions, resulting in low utilization and inefficient allocation of medical resources. Summary of the Invention

[0003] This invention provides a hierarchical diagnosis and treatment method, device, electronic device, storage medium, and program product, which can achieve efficient utilization of medical resources across the entire domain through dynamic task routing and optimize the allocation of medical resources through hierarchical execution.

[0004] According to one aspect of the present invention, a tiered medical service method is provided, the method comprising:

[0005] In response to receiving a task execution request from a user for a target task, the task execution request is forwarded to a pre-built hierarchical diagnosis and treatment system; wherein, the hierarchical diagnosis and treatment system adopts a distributed framework, the distributed framework includes multiple nodes, the nodes include a central node, regional nodes and edge nodes;

[0006] The task type of the target task and the current medical resources of each node in the hierarchical diagnosis and treatment system are determined. The target node is determined from multiple nodes based on the execution strategy pre-selected by the user, the task type, and the current medical resources.

[0007] The target task is executed hierarchically through the target node, and the returned task execution results are received.

[0008] According to another aspect of the present invention, a tiered medical treatment device is provided, the device comprising:

[0009] The execution request forwarding module is used to respond to receiving a task execution request sent by a user for a target task and forward the task execution request to a pre-built hierarchical diagnosis and treatment system; wherein, the hierarchical diagnosis and treatment system adopts a distributed framework, the distributed framework includes multiple nodes, the nodes include a central node, regional nodes and edge nodes;

[0010] The target node determination module is used to determine the task type of the target task and the current medical resources of each node in the hierarchical diagnosis and treatment system, and to determine the target node from multiple nodes based on the execution strategy pre-selected by the user, the task type, and the current medical resources.

[0011] The target task execution module is used to perform hierarchical execution of the target task through the target node and receive the returned task execution results.

[0012] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0013] At least one processor; and

[0014] A memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the hierarchical diagnosis and treatment method according to any embodiment of the present invention.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the hierarchical diagnosis and treatment method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the hierarchical diagnosis and treatment method as described in any of the embodiments of the present disclosure.

[0018] The technical solution of this invention, in response to receiving a task execution request sent by a user for a target task, forwards the task execution request to a pre-built hierarchical medical system. The hierarchical medical system employs a distributed framework, which includes multiple nodes, including central nodes, regional nodes, and edge nodes. The system determines the task type of the target task and the current medical resources of each node in the hierarchical medical system. Based on the user's pre-selected execution strategy, the task type, and the current medical resources, a target node is determined from the multiple nodes. The target task is then executed hierarchically through the target node, and the returned task execution results are received. This technical solution, in response to receiving a task execution request, forwards the task execution request to the hierarchical medical system based on a distributed framework. By combining the user's pre-selected execution strategy, task type, and the current medical resources of the node, a target node is determined from the multiple nodes of the distributed framework, and the target task is executed hierarchically. This allows for efficient utilization of medical resources across the entire system through dynamic task routing and optimizes medical resource allocation through hierarchical execution.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a hierarchical diagnosis and treatment method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a schematic diagram of a model parameter aggregation and update process provided in Embodiment 1 of the present invention;

[0023] Figure 3 This is a flowchart of a hierarchical diagnosis and treatment method provided according to Embodiment 2 of the present invention;

[0024] Figure 4 This is a schematic diagram of a hierarchical execution process for a target task according to Embodiment 2 of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of a tiered diagnosis and treatment device according to Embodiment 3 of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the hierarchical diagnosis and treatment method of this invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a tiered diagnosis and treatment method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where tiered diagnosis and treatment are performed based on a user-proposed target task. This method can be executed by a tiered diagnosis and treatment device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110. In response to receiving a task execution request sent by a user for a target task, forward the task execution request to a pre-built hierarchical diagnosis and treatment system; wherein, the hierarchical diagnosis and treatment system adopts a distributed framework, the distributed framework includes multiple nodes, including central nodes, regional nodes and edge nodes.

[0032] In this context, the target task refers to a specific diagnostic and treatment task established by the user (doctor / patient) based on their own needs. A tiered healthcare system is a medical service model aimed at rationally allocating and utilizing medical resources and improving the efficiency and quality of medical services. It is typically tiered according to the severity and urgency of diseases and the difficulty of treatment, with different levels of medical institutions undertaking the treatment of different diseases. In this embodiment of the invention, the pre-built tiered healthcare system adopts a distributed framework, dividing the system into multiple independent nodes, including central nodes, regional nodes, and edge nodes, which communicate and collaborate with each other through a network to jointly complete the functions of the tiered healthcare system.

[0033] In this embodiment of the invention, task execution requests sent by users can be continuously monitored. Upon receiving a task execution request sent by a user for a target task, the system responds by performing preliminary parsing and verification of the task execution request and forwarding it to a pre-built hierarchical diagnosis and treatment system. This ensures that the user's needs are accurately transmitted to the hierarchical diagnosis and treatment system, providing a foundation for subsequent task processing.

[0034] Optionally, the pre-construction process of the hierarchical medical system includes: determining the deployment locations of the central node, the regional node, and the edge node based on the medical resources of each medical institution; training the triage model of the edge node based on the first local medical data of the first medical institution corresponding to the deployment location of the edge node; wherein the triage model is constructed based on a convolutional neural network; training the specialty model of the regional node based on the second local medical data of the second medical institution corresponding to the deployment location of the regional node; wherein the specialty model is constructed based on a shift window Transformer; and updating the model parameters of the triage model and the specialty model through the central node using a federated averaging algorithm according to a first preset period.

[0035] The triage model is a lightweight deep learning model built on a convolutional neural network, used to handle lightweight AI tasks such as initial screening and triage, and supports offline low-power operation. The specialist model is a deep learning model built on a shift-window Transformer, using a shift-window mechanism to achieve local attention computation, and is used to perform AI inference for complex cases. The federated averaging algorithm is the most basic and widely used distributed optimization algorithm in federated learning. Its core idea is to coordinate multiple clients (such as mobile devices and edge nodes) to train the model locally, and then have a central server periodically aggregate local updates to build a globally shared model.

[0036] In this embodiment of the invention, the specific process for pre-constructing the hierarchical medical system is as follows: First, based on the medical resources of each medical institution, the deployment locations of the central node, regional nodes, and edge nodes are determined. Specifically, the central node is typically deployed in a medical data center, the regional nodes are typically deployed in regional central hospitals, and the edge nodes are typically deployed in primary healthcare institutions. Second, based on the first local medical data of the first medical institution corresponding to the deployment location of the edge node, the triage model of the edge node is trained. Based on the second local medical data of the second medical institution corresponding to the deployment location of the regional node, the specialty model of the regional node is trained. It should be noted that before training the triage model and the specialty model, the first and second local medical data need to be anonymized, and standardized feature vectors need to be extracted to avoid disclosing patient privacy. Finally, according to a first preset period, the data features of multiple medical institutions are aggregated through the central node using a federated averaging algorithm to update the model parameters of the triage model and the specialty model, thereby improving the generalization ability of the triage model and the specialty model. The first preset period can be determined and set by technicians according to the actual situation, such as one week, and this embodiment of the invention does not limit it. Federated learning can break down data barriers between medical institutions, enabling primary healthcare institutions to learn advanced diagnostic methods from large hospitals, and achieving cross-level medical institution model collaboration and the downward flow of high-quality medical resources.

[0037] Optionally, updating the model parameters of the triage model and the specialty model using a federated averaging algorithm through the central node according to a first preset period includes: uploading the first model parameters of the triage model to the regional node via the edge node with encryption according to a second preset period; wherein the second preset period is shorter than the first preset period; uploading the first model parameters and the encrypted second model parameters of the specialty model to the central node through the regional node according to the first preset period; and aggregating the first model parameters and the second model parameters through the central node using a federated averaging algorithm based on a secure multi-party computation method, and sending the aggregated updated first model parameters to the edge node and the aggregated updated second model parameters to the regional node.

[0038] Secure Multi-Party Computation (MPC) is a cryptographic protocol that allows multiple participants to jointly complete computation tasks without disclosing their own private data. Its core objective is to solve the problem of collaborative computation involving the private data of multiple parties, ensuring data privacy and computational correctness, while also meeting requirements such as fairness, input independence, and output delivery.

[0039] In this embodiment of the invention, the specific process of updating the model parameters of the triage model and the specialty model using a federated averaging algorithm through the central node according to a first preset period is as follows: First, according to a second preset period, the first model parameters of the triage model can be encrypted and uploaded to the regional node through the edge node. The second preset period is shorter than the first preset period and can be set by technical personnel according to actual conditions, such as one day; this embodiment of the invention does not limit this. Second, according to the first preset period, the encrypted first model parameters uploaded by the edge node and the encrypted second model parameters of the specialty model can be uploaded to the central node through the regional node. Finally, based on a secure multi-party computation method, the central node aggregates the first and second model parameters using a federated averaging algorithm, and distributes the aggregated and updated first model parameters to the edge nodes and the aggregated and updated second model parameters to the regional nodes. When distributing the model parameters, the aggregated and updated first and second model parameters are first distributed to the regional nodes, and then the regional nodes distribute the aggregated and updated first model parameters to the edge nodes. Optionally, before uploading the model parameters, some random noise can be added to the model parameters to prevent attackers from deducing individual patient characteristics through the model parameters. For example, Figure 2 A schematic diagram of a model parameter aggregation and update process is shown.

[0040] S120. Determine the task type of the target task and the current medical resources of each node in the hierarchical diagnosis and treatment system. Based on the execution strategy, task type and current medical resources selected by the user, determine the target node from multiple nodes.

[0041] The target tasks include diagnostic reasoning, image updates, model updates, and scientific research analysis. The current medical resources of each node represent the available resources, including computing resources, bandwidth, latency, and queue status. The execution strategy outlines the methods and rules for task execution, including proximity priority, latency priority, load balancing, and capacity priority.

[0042] In this embodiment of the invention, the target task can be analyzed in detail. Based on the characteristics and purpose of the target task, the task type is determined. Communication with each node of the hierarchical medical system is used to collect real-time information on the current medical resources of each node. Finally, combining the user-preselected execution strategy, the target task type, and the current medical resources of each node, the most suitable target node for handling the target task is determined from multiple nodes. By determining the target node from multiple nodes based on the user-preselected execution strategy, task type, and current medical resources, it is ensured that the target task is processed at the most appropriate node, improving task processing efficiency and quality.

[0043] S130. Perform hierarchical execution of the target task through the target node and receive the returned task execution results.

[0044] In this embodiment of the invention, after determining the target node from multiple nodes based on the user's pre-selected execution strategy, task type, and current medical resources, the target task can be executed hierarchically through the target node, and the returned task execution results can be received. By executing the target task hierarchically through the target node, the resources of each node in the hierarchical diagnosis and treatment system can be fully utilized, and the optimal allocation of resources can be achieved.

[0045] Optionally, while returning the task execution result, the execution result, performance data, etc. can also be uploaded to the blockchain to incentivize the nodes participating in the task execution through the blockchain incentive control module of the central node, thereby promoting the prosperity of the ecosystem.

[0046] The technical solution of this invention, in response to receiving a task execution request sent by a user for a target task, forwards the task execution request to a pre-built hierarchical medical system. The hierarchical medical system employs a distributed framework, which includes multiple nodes, including central nodes, regional nodes, and edge nodes. It determines the task type of the target task and the current medical resources of each node in the hierarchical medical system. Based on the user's pre-selected execution strategy, task type, and current medical resources, it determines a target node from among the multiple nodes. The target task is then executed hierarchically through the target node, and the returned task execution results are received. This technical solution, in response to receiving a task execution request, forwards the request to the hierarchical medical system based on a distributed framework. Combining the user's pre-selected execution strategy, task type, and the current medical resources of the node, it determines a target node from among the multiple nodes in the distributed framework, performs hierarchical execution of the target task, and achieves efficient utilization of all medical resources through dynamic task routing and optimizes medical resource allocation through hierarchical execution.

[0047] Example 2

[0048] Figure 2 This is a flowchart of a hierarchical diagnosis and treatment method provided in Embodiment 2 of the present invention. The embodiments of the present invention are optimized based on the above embodiments. Solutions not described in detail in the embodiments of the present invention are found in the above embodiments. Figure 2 As shown, the method includes:

[0049] S210. In response to receiving a task execution request sent by a user for a target task, forward the task execution request to the pre-built hierarchical diagnosis and treatment system.

[0050] S220. Determine the task type of the target task and the current medical resources of each node in the hierarchical diagnosis and treatment system. Based on the execution strategy, task type and current medical resources selected by the user, determine the target node from multiple nodes.

[0051] S230. Based on the complexity of the task, the task level corresponding to the task is divided into Level 1, Level 2 and Level 3, and the target task level corresponding to the target task is determined; among them, the task complexity corresponding to Level 1, Level 2 and Level 3 increases in that order.

[0052] In this embodiment of the invention, when executing target tasks in a hierarchical manner through target nodes, the task levels corresponding to the tasks can be divided into Level 1, Level 2, and Level 3 according to the task complexity, with the task complexity increasing sequentially for each level. Based on the task complexity of the target task and according to the classification criteria, the target task level corresponding to the target task is determined.

[0053] S240. Through the target node, the target task is executed in a hierarchical manner according to the target task level.

[0054] Optionally, the target node includes an edge node; the step of performing hierarchical execution of the target task according to the target task level through the target node includes: if the target task level is level one, executing the target task through the triage model of the edge node; otherwise, forwarding the target task to the regional node.

[0055] In this embodiment of the invention, the target node includes an edge node. When the target task is executed in a hierarchical manner according to the target task level through the edge node, the triage model of the edge node can only execute the target task level of level one, that is, the target task with low task complexity. For target tasks with other task complexity, it is necessary to forward them to the regional node and execute them through the specialist model of the regional node.

[0056] Optionally, the target node includes a regional node; the step of performing hierarchical execution of the target task according to the target task level through the target node includes: if the target task level is less than or equal to level two, the target task is executed through the specialized model of the regional node; otherwise, the target task is forwarded to the central node.

[0057] In this embodiment of the invention, the target node includes a regional node. When the target task is executed in a hierarchical manner according to the target task level through the regional node, the specialized model of the regional node can execute the target task level of less than or equal to level two (mainly level two), that is, the target task with moderate complexity. For target tasks with higher complexity, it needs to be forwarded to the central node. The central node schedules the specialized models of multiple regional nodes across regions to jointly execute the target task.

[0058] Optionally, the target node includes a central node; the step of executing the target task in a hierarchical manner according to the target task level through the target node includes: if the target task level is greater than level two, the target task is jointly executed by a specialized model that schedules multiple regional nodes across regions through the central node.

[0059] In this embodiment of the invention, the target node includes a central node. When the central node performs hierarchical execution of the target task according to the target task level, the central node can schedule the specialized models of multiple regional nodes across regions to execute the target task at level three, that is, a target task with a high degree of complexity. For example, Figure 4 A flowchart illustrating the hierarchical execution of target tasks is shown.

[0060] S250: Receive the returned task execution result.

[0061] The technical solution of this invention, in response to receiving a task execution request sent by a user for a target task, forwards the task execution request to a pre-built hierarchical diagnosis and treatment system; determines the task type of the target task and the current medical resources of each node in the hierarchical diagnosis and treatment system; determines the target node from multiple nodes according to the user's pre-selected execution strategy, task type, and current medical resources; classifies the task level corresponding to the task into Level 1, Level 2, and Level 3 according to the task complexity, and determines the target task level corresponding to the target task; wherein the task complexity corresponding to Level 1, Level 2, and Level 3 increases sequentially; performs hierarchical execution of the target task through the target node according to the target task level; and receives the returned task execution result. The technical solution of this invention, in response to receiving a task execution request, forwards the task execution request to a hierarchical diagnosis and treatment system based on a distributed framework, and, in conjunction with the user's pre-selected execution strategy, task type, and the current medical resources of the node, determines the target node from multiple nodes in the distributed framework, performs hierarchical execution of the target task, and achieves efficient utilization of medical resources across the entire domain through dynamic task routing, and optimizes medical resource allocation through hierarchical execution.

[0062] Example 3

[0063] Figure 5 This is a schematic diagram of a tiered diagnosis and treatment device provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes:

[0064] The execution request forwarding module 310 is used to forward the task execution request to a pre-built hierarchical diagnosis and treatment system in response to receiving a task execution request sent by a user for a target task; wherein the hierarchical diagnosis and treatment system adopts a distributed framework, the distributed framework includes multiple nodes, the nodes include a central node, regional nodes and edge nodes.

[0065] The target node determination module 320 is used to determine the task type of the target task and the current medical resources of each node of the hierarchical diagnosis and treatment system, and to determine the target node from multiple nodes according to the execution strategy pre-selected by the user, the task type and the current medical resources.

[0066] The target task execution module 330 is used to perform hierarchical execution of the target task through the target node and receive the returned task execution results.

[0067] Optionally, the request forwarding module 310 includes:

[0068] The deployment location determination unit is used to determine the deployment locations of the central node, the regional node, and the edge node based on the medical resources of each medical institution.

[0069] The triage model training unit is used to train the triage model of the edge node based on the first local medical data of the first medical institution corresponding to the deployment location of the edge node; wherein the triage model is constructed based on a convolutional neural network.

[0070] The specialty model training unit is used to train the specialty model of the regional node based on the second local medical data of the second medical institution corresponding to the deployment location of the regional node; wherein the specialty model is constructed based on the Transformer shift window.

[0071] The model parameter update unit is used to update the model parameters of the triage model and the specialty model through the central node using a federated averaging algorithm according to a first preset period.

[0072] Optionally, the model parameter update unit is specifically used for:

[0073] According to a second preset period, the first model parameters of the triage model are encrypted and uploaded to the regional node through the edge node; wherein the second preset period is shorter than the first preset period;

[0074] According to the first preset cycle, the first model parameters and the encrypted second model parameters of the specialty model are uploaded to the central node through the regional node;

[0075] Based on a secure multi-party computation method, the central node uses a federated averaging algorithm to aggregate the first model parameters and the second model parameters, and then sends the aggregated and updated first model parameters to the edge nodes and the aggregated and updated second model parameters to the regional nodes.

[0076] Optionally, the target task execution module 330 includes:

[0077] The task level determination unit is used to classify the task level corresponding to the task into level one, level two, and level three according to the task complexity, and to determine the target task level corresponding to the target task; wherein the task complexity corresponding to level one, level two, and level three increases sequentially.

[0078] The target task execution unit is used to execute the target task in a hierarchical manner according to the target task level through the target node.

[0079] Optionally, the target node includes an edge node; the target task execution unit is specifically used for:

[0080] If the target task is classified as Level 1, the target task is executed through the triage model of the edge node; otherwise, the target task is forwarded to the regional node.

[0081] Optionally, the target node includes a region node; the target task execution unit is specifically used for:

[0082] If the target task level is less than or equal to level two, the target task is executed through the specialized model of the regional node; otherwise, the target task is forwarded to the central node.

[0083] Optionally, the target node includes a central node; the target task execution unit is specifically used for:

[0084] If the target task level is greater than level two, the target task is jointly executed by a specialized model that uses the central node to schedule multiple regional nodes across regions.

[0085] The hierarchical diagnosis and treatment device provided in the embodiments of the present invention can execute the hierarchical diagnosis and treatment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0086] Example 4

[0087] Figure 6A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0088] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0089] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0090] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as tiered diagnosis and treatment methods.

[0091] In some embodiments, the triage method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the triage method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the triage method by any other suitable means (e.g., by means of firmware).

[0092] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0094] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0096] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0097] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0098] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0099] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of stepped care, characterized in that, The method comprises: In response to receiving a task execution request sent by a user for a target task, forwarding the task execution request to a pre-constructed hierarchical medical treatment system; wherein the hierarchical medical treatment system adopts a distributed framework, the distributed framework comprises a plurality of nodes, the nodes comprise a center node, a regional node and an edge node; Determine the task type of the target task and the current medical resources of each node of the hierarchical medical treatment system, and determine the target node from the plurality of nodes according to the user's pre-selected execution strategy, the task type and the current medical resources; The target task is executed by the target node, and the returned task execution result is received.

2. The method of claim 1, wherein, The pre-construction process of the hierarchical medical treatment system comprises: According to the medical resources of each medical institution, the deployment positions of the center node, the regional node and the edge node are determined; According to the first local medical data of the first medical institution corresponding to the deployment position of the edge node, the triage model of the edge node is trained; wherein the triage model is constructed based on convolutional neural network; According to the second local medical data of the second medical institution corresponding to the deployment position of the regional node, the specialist model of the regional node is trained; wherein the specialist model is constructed based on shift window Transformer; According to a first preset period, the model parameters of the triage model and the specialist model are updated by the center node using a federated average algorithm.

3. The method of claim 2, wherein, According to a first preset period, the model parameters of the triage model and the specialist model are updated by the center node using a federated average algorithm. According to a second preset period, the first model parameter of the triage model is uploaded to the regional node by the edge node; wherein the second preset period is less than the first preset period; According to the first preset period, the first model parameter and the second model parameter of the encrypted specialist model are uploaded to the center node by the regional node; Based on secure multi-party computation, the first model parameter and the second model parameter are aggregated by the center node using a federated average algorithm, and the aggregated updated first model parameter is distributed to the edge node and the aggregated updated second model parameter is distributed to the regional node.

4. The method of claim 1, wherein, The target task is executed by the target node, and the returned task execution result is received. According to the task complexity, the task level corresponding to the task is divided into one level, two levels and three levels, and the target task level corresponding to the target task is determined; wherein the task complexity corresponding to one level, two levels and three levels increases in turn; The target task is executed by the target node according to the target task level.

5. The method of claim 4, wherein, The target node comprises an edge node; The target task is executed by the target node according to the target task level. If the target task level is level one, the target task is executed by a triage model of the edge node, otherwise, the target task is forwarded to a regional node.

6. The method of claim 4, wherein, The target node includes a regional node; The target task is executed by the target node according to the target task level, including: If the target task level is less than or equal to level two, the target task is executed by a specialist model of the regional node, otherwise, the target task is forwarded to a central node.

7. The method of claim 4, wherein, The target node includes a central node; The target task is executed by the target node according to the target task level, including: If the target task level is greater than level two, the target task is jointly executed by the central node scheduling specialist models of multiple regional nodes.

8. An electronic device, comprising: The electronic device includes: At least one processor; and The memory is in communication with the at least one processor; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the hierarchical diagnosis and treatment method of any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing the processor to execute the hierarchical diagnosis and treatment method of any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the hierarchical diagnosis and treatment method of any one of claims 1-7.

Images