Cooperative transmission method and device of multiple communication nodes, electronic device, and storage medium

Abstract

This application provides a method, apparatus, electronic device, and storage medium for collaborative transmission among multiple communication nodes, belonging to the field of artificial intelligence technology. The collaborative transmission method includes: determining all transmission models based on all communication nodes; adding all transmission models to a pre-configured historical model library, wherein each transmission model is formed by connecting at least two communication nodes, and any two transmission models are different; generating a candidate sequence based on all transmission models, wherein the candidate sequence includes multiple candidate transmission models; performing optimization and iterative processing on the candidate sequence until the iteration termination condition is met; and selecting the candidate transmission model with the largest communication overhead index from the candidate sequence as the first target transmission model. In this application embodiment, by optimizing and iteratively processing the candidate sequence, the requirements for collaborative transmission can be met, which is beneficial to improving the accuracy of collaborative transmission calculations and ensuring that a compliant collaborative transmission model is obtained.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a collaborative transmission method and apparatus, electronic device, and storage medium for multiple communication nodes. Background Technology

[0002] With breakthroughs in deep learning algorithms, an increasing number of AI-powered mobile applications are being developed, offering intelligent services such as language translation, object recognition, health monitoring, and malware detection, enabling people to enjoy a more convenient and intelligent mobile life. However, significant heterogeneity exists between different mobile devices, making the accessibility of mobile services a challenging issue. For example, in the medical field, doctors and nurses need to make rounds between different wards to observe patients' specific medical conditions. However, when emergencies require timely notification to doctors and nurses, this is usually done through mobile devices. Due to the heterogeneity between mobile devices, such communication is not reliable, especially in emergency departments where this problem may be more pronounced.

[0003] Currently, one solution is to upload computing tasks to a remote server for collaborative cloud computing. However, data transmission based on cloud computing consumes a large amount of cloud bandwidth. As the number of medical staff and user devices increases, the traffic load will become increasingly large, which will adversely affect the quality of cloud services and result in low computing accuracy. Furthermore, there is a delay in the transmission between medical staff's local mobile devices and the remote cloud, making it impossible to achieve near real-time remote response, thus resulting in low computing efficiency. Summary of the Invention

[0004] The main objective of this application is to propose a collaborative transmission method, apparatus, electronic device, and storage medium for multiple communication nodes, aiming to improve the accuracy and efficiency of collaborative transmission calculations for multiple communication nodes.

[0005] To achieve the above objectives, a first aspect of this application proposes a cooperative transmission method for multiple communication nodes, the method comprising:

[0006] All transmission models are determined based on all the communication nodes, and all the transmission models are added to a pre-configured historical model library, wherein each transmission model is formed by connecting at least two of the communication nodes, and no two transmission models are the same;

[0007] A candidate sequence is generated based on all the aforementioned transmission models, wherein the candidate sequence includes multiple candidate transmission models;

[0008] The candidate sequences are optimized iteratively until the iteration termination condition is met;

[0009] From the candidate sequences, the candidate transmission model with the largest communication overhead index is selected as the first target transmission model;

[0010] The optimization iteration process includes:

[0011] The communication overhead index of each of the candidate transmission models is obtained according to the preset communication overhead function;

[0012] The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences.

[0013] Add the second transmission model to the historical model library;

[0014] The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted;

[0015] The iteration ends when the total number of all the transmission models in the historical model library reaches a preset threshold.

[0016] In some embodiments, the process of extending the first transmission model to obtain a second transmission model includes:

[0017] The second transmission model is obtained by sequentially disconnecting and connecting several communication nodes in the first transmission model.

[0018] In some embodiments, the step of sequentially disconnecting and connecting several communication nodes in the first transmission model to obtain a second transmission model includes:

[0019] Disconnect several communication nodes in the first transmission model that are connected by a first preset connection method to obtain several dispersed communication nodes;

[0020] A second transmission model is obtained by connecting several dispersed communication nodes using a second preset connection method, wherein the second preset connection method is different from the first preset connection method.

[0021] In some embodiments, generating candidate sequences based on all said transmission models includes:

[0022] From all the transmission models, a plurality of the transmission models are randomly selected as a plurality of the candidate transmission models;

[0023] Candidate sequences are generated based on multiple alternative transmission models.

[0024] In some embodiments, randomly selecting a plurality of the transmission models from all the transmission models as a plurality of candidate transmission models includes:

[0025] From all the transmission models, a plurality of the transmission models are randomly selected with equal probability as a plurality of the candidate transmission models.

[0026] In some embodiments, generating candidate sequences based on a plurality of candidate transmission models includes:

[0027] The candidate transmission models are arranged in a random order to generate a candidate sequence.

[0028] In some embodiments, after performing iterative optimization on the candidate sequences until the iteration termination condition is met, the process further includes:

[0029] From the candidate sequence, select all candidate transmission models whose communication overhead index is greater than a preset overhead index as the second transmission model.

[0030] To achieve the above objectives, a second aspect of this application provides a cooperative transmission device for multiple communication nodes, the device comprising:

[0031] The model generation module is used to determine all transmission models based on all the communication nodes and add all the transmission models to a pre-configured historical model library, wherein each transmission model is formed by connecting at least two of the communication nodes, and no two transmission models are the same;

[0032] A sequence generation module is used to generate candidate sequences based on all the transmission models, wherein the candidate sequences include multiple candidate transmission models;

[0033] An optimization processing module is used to perform optimization iterative processing on the candidate sequences until the iteration termination condition is met, wherein the optimization iterative processing includes:

[0034] The communication overhead index of each of the candidate transmission models is obtained according to the preset communication overhead function;

[0035] The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences.

[0036] Add the second transmission model to the historical model library;

[0037] The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted;

[0038] The iteration ends when the total number of all the transmission models in the historical model library reaches a preset threshold.

[0039] The selection module is used to select the candidate transmission model with the largest communication overhead index from the candidate sequence as the first target transmission model.

[0040] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0041] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0042] The collaborative transmission method, apparatus, electronic device, and storage medium proposed in this application construct a transmission model for local collaboration among all communication nodes. Based on this model, a candidate sequence including multiple alternative transmission models is generated. This candidate sequence is then optimized and iteratively processed. This not only reduces the global processing time in a single given domain, lowering computational latency and improving the efficiency of collaborative transmission computation, but also allows the candidate sequence to continuously evolve towards a higher communication overhead index. This meets the collaborative transmission requirements among multiple communication nodes, facilitating the selection of the candidate transmission model with the highest communication overhead index as the primary target transmission model. This improves the accuracy of collaborative transmission computation, ensuring a compliant collaborative transmission model and enhancing the efficiency of medical communication. Attached Figure Description

[0043] Figure 1 This is a flowchart of a collaborative transmission method for multiple communication nodes provided in one embodiment of this application;

[0044] Figure 2 This is a schematic diagram of multiple communication nodes performing coordinated transmission according to an embodiment of this application;

[0045] Figure 3 yes Figure 1 The flowchart of step S102 in the document;

[0046] Figure 4 yes Figure 3 The flowchart of step S201 in the text;

[0047] Figure 5 yes Figure 3The flowchart of step S202 in the text;

[0048] Figure 6 This is a flowchart of step S501 provided in one embodiment of this application;

[0049] Figure 7 This is a schematic diagram of a transmission model provided in one embodiment of this application;

[0050] Figure 8 This is a schematic diagram of the structure of a cooperative transmission device with multiple communication nodes provided in one embodiment of this application;

[0051] Figure 9 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0055] With breakthroughs in deep learning algorithms, an increasing number of AI-powered mobile applications are being developed, offering intelligent services such as language translation, object recognition, health monitoring, and malware detection, enabling people to enjoy a more convenient and intelligent mobile life. However, significant heterogeneity may exist between different mobile devices, making the maintenance of mobile service accessibility a challenging problem.

[0056] Currently, one solution is to upload computing tasks to a remote server for collaborative cloud computing. For example, when a local mobile device needs to identify a person in an image, it only needs to upload the image to the cloud and wait for the remote response of the final recognition result. This relies on the premise that current mobile devices can provide powerful GPU or even NPU computing capabilities. In other words, these mobile devices can partially act as cloud computing and can quickly connect via Wi-Fi, Bluetooth, or Near Field Communication (NFC). However, data transmission based on cloud computing consumes a large amount of cloud bandwidth. As the number of user devices accumulates, the traffic load will increase, adversely affecting the quality of cloud services and resulting in low computing accuracy. Furthermore, there is a latency in transmission between the local mobile device and the remote cloud, making it impossible to achieve near real-time remote response, thus resulting in low actual computing efficiency.

[0057] Based on this, embodiments of this application provide a method, apparatus, electronic device, and storage medium for collaborative transmission of multiple communication nodes, aiming to improve the accuracy and efficiency of collaborative transmission calculation of multiple communication nodes.

[0058] The collaborative transmission method, apparatus, electronic device, and storage medium for multiple communication nodes provided in this application are specifically described through the following embodiments. First, the collaborative transmission method for multiple communication nodes in this application is described.

[0059] The collaborative transmission method for multiple communication nodes provided in this application relates to the field of medical technology. This method can be applied to communication nodes, servers, or software running on either the communication node or the server. In some embodiments, the communication node can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the collaborative transmission method for multiple communication nodes, but is not limited to the above forms.

[0060] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via communication networks. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0061] Figure 1 This is an optional flowchart of the collaborative transmission method for multiple communication nodes provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S104.

[0062] Step S101: Determine all transmission models based on all communication nodes, and add all transmission models to the pre-configured historical model library. Each transmission model is formed by connecting at least two communication nodes, and no two transmission models are the same.

[0063] Step S102: Generate candidate sequences based on all transmission models, wherein the candidate sequences include multiple candidate transmission models;

[0064] Step S103: Perform optimization iteration on the candidate sequence until the iteration termination condition is met;

[0065] Step S104: Select the candidate transmission model with the largest communication overhead index from the candidate sequence as the first target transmission model;

[0066] The optimization iterative process includes:

[0067] The communication overhead index of each candidate transmission model is obtained according to the preset communication overhead function;

[0068] The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences.

[0069] Add the second transmission model to the historical model library;

[0070] The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted;

[0071] The iteration ends when the total number of all transmission models in the historical model library reaches a preset threshold.

[0072] Steps S101 to S104 of this embodiment construct a transmission model for local collaboration between all communication nodes. Based on this model, a candidate sequence including multiple alternative transmission models is generated. The candidate sequence is then optimized iteratively. This not only reduces the global processing time in a single given domain, lowering computational latency and improving collaborative transmission computation efficiency, but also allows the candidate sequence to continuously evolve towards a higher communication overhead index. This meets the collaborative transmission requirements between multiple communication nodes, facilitating the selection of the candidate transmission model with the highest communication overhead index as the first target transmission model. This improves the accuracy of collaborative transmission computation, ensuring a satisfactory collaborative transmission model and enhancing medical communication efficiency.

[0073] For example, all mobile devices in all departments of the hospital can be included in a unified management system, with each mobile device acting as a communication node. Then, all transmission models can be determined based on all communication nodes, and all transmission models can be added to a pre-configured historical model library. Next, candidate sequences can be generated based on all transmission models, and the candidate sequences can be optimized and iterated until the iteration termination condition is met. Finally, the candidate transmission model with the highest communication overhead index can be selected as the first target transmission model from the candidate sequences. This helps to improve the accuracy of collaborative transmission calculations, ensures that a collaborative transmission model that meets the requirements can be obtained, and improves the efficiency of medical communication.

[0074] Communication equipment can be referred to as an access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, wireless communication equipment, user agent, or user device. For example, communication equipment can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA), handheld device with wireless communication capabilities, computing device or other processing device connected to a wireless modem, vehicle-mounted device, wearable device, terminal device in a 5G network or a future 5G or higher network, etc. This embodiment does not specifically limit it in this way.

[0075] In step S101 of some embodiments, since the connection relationship between the various communication devices can be mutually evolved and adjusted, for example, the connection relationship between the three communication devices can be interconnected in pairs, or it can be just a chain connection, and so on, so there can be a variety of actual transmission models, which is not limited here; the historical model library is used to store transmission models and to perform statistics and analysis on the transmission models therein, and those skilled in the art can set up the corresponding historical model library according to the specific application scenario.

[0076] It should be noted that in medical scenarios, there may be situations where different communication nodes have the same connection relationship and form the same transmission model. In this case, these same transmission models can be regarded as a type of transmission model, which is also applicable to the multi-communication node collaborative transmission method in this embodiment. To avoid ambiguity, this will not be elaborated further.

[0077] In step S103 of some embodiments, the preset communication overhead function is a function used to calculate the communication overhead index of the alternative transmission model. It can be selected and set according to the specific application scenario. The specific type and construction of the preset communication overhead function are not limited here. This will be described in subsequent embodiments.

[0078] In step S103 of some embodiments, setting the second transmission model at the end of the candidate sequence and deleting the candidate transmission model at the beginning of the candidate sequence helps to better explore the solution space of the candidate transmission model and avoid prematurely focusing on its local solution. In other words, similar to the idea of ​​the genetic algorithm, this is conducive to further optimization of the preferred candidate transmission model.

[0079] In step S103 of some embodiments, considering that the storage limit of the historical model library is fixed, in order to avoid the situation of excessive storage of the historical model library, the iteration end condition is set here to be that the number of all transmitted models in the historical model library reaches a preset number threshold. That is to say, when the number of all transmitted models in the historical model library reaches the preset number threshold, it means that the optimization iteration process has been maintained for a relatively long time and can meet the optimization iteration requirements as a whole.

[0080] In step S104 of some embodiments, the candidate transmission model with the largest communication overhead index is selected as the first target transmission model. That is, the candidate transmission model with the largest communication overhead index has higher fitness and can be used as the first target transmission model.

[0081] To better illustrate the working principle of the above embodiments, a specific example is given below.

[0082] Example 1:

[0083] like Figure 2 As shown, suppose there are N mobile devices capable of running deep neural networks (DNNs) (i.e., Figure 2 (S1, S2, S3, etc. in the DNN model), and the DNN model has been pre-trained and installed on mobile devices. Each device i∈N has n j The amount of data needs to be processed. Mobile devices connect directly using methods such as Bluetooth and WiFi, and different devices can use different data processing methods. The communication latency between two devices i and j is denoted by d. ij This indicates that, based on existing technology, batch processing of mobile device workloads on GPUs can effectively reduce processing time. Multiple mobile devices can aggregate their workloads on a single device. For this purpose, a binary variable x is defined. i This indicates whether node i∈N is an aggregate node, i.e.

[0084]

[0085] It's important to note that some nodes only process their own data and do not receive workloads from other nodes; these are considered as x. i =1 aggregate node, each non-aggregate node (e.g. Figure 2 The “S1” shown can connect multiple aggregation nodes (e.g., Figure 2 (S2, S3, and S4 shown in the diagram) Define a variable y. ij This represents the portion of the workload unloaded from node i to node j. Since the aggregation node does not unload workload to other nodes, therefore... For each non-aggregate node, then... It can be summarized as

[0086]

[0087]

[0088] The total cost of node i is defined as T i Specifically, it is the sum of the computation and communication overhead of this node, expressed as

[0089] T i =2*∑ j d ij *y ij +f(∑ j y ij *n j );

[0090] Where f(.) is a non-decreasing function describing the relationship between GPU processing time and workload, and the objective is to minimize the total cost of all mobile devices, the final result of the study can be expressed as the following equation, and is subject to the constraints of the above equations, namely:

[0091] min∑ i∈N T i ;

[0092] Please see Figure 2 Here, the communication nodes are mobile devices. Once a connection is established between mobile devices to form a transmission model, it is assumed that the transmission latency of each transmission model remains constant, but the transmission latency between different transmission models differs. Since the inference calculation process is near real-time, the mobile devices are reasonably considered to remain stationary until they receive the calculation results. To accurately select the optimal mobile device as... Figure 2 The compute nodes shown primarily focus on minimizing the overall time cost of data / result transfer between compute nodes and user nodes (unloaded compute tasks) and the computation of tasks within the compute nodes. Considering the mobility of mobile devices, local connection relationships are updated from time to time, making the optimal compute node selection in one instance not necessarily applicable to the next. Therefore, it is necessary to track the optimal selection in a dynamic environment.

[0093] Please see Figure 3 In some embodiments, step S102 may include, but is not limited to, steps S201 to S202:

[0094] Step S201: Randomly select multiple transmission models from all transmission models as multiple candidate transmission models;

[0095] Step S202: Generate alternative sequences based on multiple alternative transmission models.

[0096] In this step, multiple candidate transmission models can be obtained by randomly selecting multiple transmission models. Using random selection can encompass all transmission models as much as possible, and the selected candidate transmission models are more universal, thereby reducing the error in selecting candidate transmission models.

[0097] Please see Figure 4 In some embodiments, step S201 may include, but is not limited to, step S301:

[0098] Step S301: Randomly select multiple transmission models from all transmission models with equal probability as multiple candidate transmission models.

[0099] In this step, multiple transmission models are randomly selected as candidate transmission models with equal probability. This ensures that all transmission models have an equal probability of being selected. In other words, there will be no biased selection of one or more transmission models. This ensures that each transmission model can be selected with the same probability, thereby reducing the error in selecting candidate transmission models.

[0100] In step S301 of some embodiments, the probability of random selection can be set according to specific circumstances, and is not limited here.

[0101] Please see Figure 5 In some embodiments, step S202 may include, but is not limited to, step S401:

[0102] Step S401: Arrange the multiple candidate transmission models according to the order in which they are randomly selected to generate a candidate sequence.

[0103] In this step, after randomly selecting multiple candidate transmission models, the multiple candidate transmission models are arranged according to the order in which they were randomly selected. This arrangement of the selected candidate transmission models facilitates further processing of the first transmission model in subsequent optimization iterations.

[0104] In step S401 of some embodiments, multiple alternative transmission models can be arranged in a random manner to generate an alternative sequence, which is not limited here.

[0105] In some embodiments, the step S103 of "extending the first transmission model to obtain the second transmission model" may include, but is not limited to, step S501:

[0106] Step S501: The communication nodes in the first transmission model are disconnected and connected in sequence to obtain the second transmission model.

[0107] In this step, since the connection relationship between each communication node in the first transmission model is fixed, in order to change this connection relationship, several communication nodes in the first transmission model can be disconnected and connected in sequence, thereby enabling the reconstruction of the connection relationship to obtain the second transmission model.

[0108] In step S501 of some embodiments, the number of communication nodes that sequentially perform disconnection and connection processing is not limited. That is, all communication nodes in the first transmission model can be disconnected and connected, or only some communication nodes in the first transmission model can be disconnected and connected. There is no limitation here.

[0109] Please see Figure 6 In some embodiments, step S501 may include, but is not limited to, steps S601 to S602:

[0110] Step S601: Disconnect several communication nodes in the first transmission model that are connected by a first preset connection method to obtain several dispersed communication nodes.

[0111] Step S602: Connect several dispersed communication nodes using a second preset connection method to obtain a second transmission model, wherein the second preset connection method is different from the first preset connection method.

[0112] In this step, by disconnecting the original first preset connection method of the communication nodes, we obtain scattered communication nodes. Then, we connect these scattered communication nodes using a second preset connection method that is different from the first preset connection method, thus obtaining a new second transmission model. In other words, through such disconnection and connection processing, we can ensure that a reliable second transmission model is obtained.

[0113] In some embodiments, step S103 may be followed by, but is not limited to, step S701:

[0114] Step S701: Select all candidate transmission models whose communication overhead index is greater than the preset overhead index from the candidate sequence as the second transmission model.

[0115] In this step, the preset overhead index is used as a critical index to measure whether the overhead of the communication node meets the corresponding requirements. In other words, by selecting all candidate transmission models whose communication overhead index is greater than the preset overhead index as the second transmission model, all candidate transmission models that meet the preset index requirements can be selected, which is beneficial to selecting multiple second transmission models that meet the index requirements.

[0116] In step S701 of some embodiments, the specific value of the preset cost index can be set according to the specific application scenario, and there is no limitation here.

[0117] To better illustrate the working principle and content of the above embodiments, a specific example is given below.

[0118] Example 2:

[0119] The following process is used to implement a collaborative transmission method for multiple communication nodes, including but not limited to:

[0120] First, we treat the different connections between mobile devices as a transmission model, such as... Figure 7 As shown, Figure 7 The system includes two transmission models: one connected by 1, 2, and 4, and another connected by 3 and 5, and so on. The structure of each transmission model is known. At this point, N transmission models are randomly selected from all possible structures with equal probability as the initial population. The selected transmission models will be recorded in the historical model library.

[0121] Then, the fitness value of the transport model in the population is calculated according to the optimized objective function formula (refer to the function formula provided in Example 1, which will not be repeated here);

[0122] Then, the transmission models in the population set are randomly sampled into a candidate set, and the transmission model with the highest fitness on the validation set of the objective function in this set is selected as the parent transmission model.

[0123] Then, the parent transmission model architecture is transformed into a new transmission model, i.e., the child architecture, through mutation operations. Here, mutation operations refer to disconnecting and creating new connections, for example... Figure 7 In the example, node 4 is disconnected from node 2 and connected to node 3, and node 5 is disconnected from node 3 and connected to node 2. Each disconnection and reconnection operation is recorded as a mutation. Figure 7 The transmission model in the text has undergone two mutations.

[0124] Then, the generated offspring architectures are added to the population and the historical model library. To keep the population size constant, the oldest transmission model that was first added to the population is removed, which helps to explore the solution space more thoroughly rather than focusing on local solutions too early.

[0125] Finally, repeat the above steps until the number of models in the historical model library is greater than the preset threshold. Finally, select the best-fitting transfer model from the historical model library as the target transfer model.

[0126] As can be seen from the examples above, by optimizing and iteratively processing the candidate sequences, not only can the global processing time in a single given domain be reduced, thus lowering the latency of computation and improving the efficiency of collaborative transmission computation, but the candidate sequences can also be continuously updated and evolved towards a direction with a larger communication overhead index. This allows them to meet the collaborative transmission requirements between multiple communication nodes, enabling the selection of the candidate transmission model with the largest communication overhead index as the first target transmission model. This is beneficial for improving the accuracy of collaborative transmission computation, ensuring that a compliant collaborative transmission model is obtained, and improving the efficiency of medical communication.

[0127] Please see Figure 8 This application also provides a cooperative transmission device for multiple communication nodes, which can realize the above-mentioned cooperative transmission method for multiple communication nodes. The device includes:

[0128] The model generation module is used to determine all transmission models based on all communication nodes and add all transmission models to a pre-configured historical model library. Each transmission model is formed by connecting at least two communication nodes, and no two transmission models are the same.

[0129] The sequence generation module is used to generate candidate sequences based on all transmission models, wherein the candidate sequences include multiple candidate transmission models;

[0130] The optimization processing module is used to perform iterative optimization processing on the candidate sequences until the iteration termination condition is met. The optimization iterative processing includes:

[0131] The communication overhead index of each candidate transmission model is obtained according to the preset communication overhead function;

[0132] The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences.

[0133] Add the second transmission model to the historical model library;

[0134] The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted;

[0135] The iteration ends when the total number of all transmitted models in the historical model library reaches a preset threshold.

[0136] The selection module is used to select the candidate transmission model with the largest communication overhead index from the candidate sequence as the first target transmission model.

[0137] The specific implementation of the multi-communication node cooperative transmission device is basically the same as the specific implementation of the multi-communication node cooperative transmission method described above, and belongs to the same inventive concept, so it will not be described again here.

[0138] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned collaborative transmission method for multiple communication nodes. This electronic device can be any intelligent communication node, including a tablet computer, an in-vehicle computer, or similar device.

[0139] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0140] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0141] The memory 902 can be implemented in the form of read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 to execute the multi-communication node cooperative transmission method of the embodiments of this application.

[0142] The input / output interface 903 is used to implement information input and output;

[0143] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0144] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0145] The processor 901, memory 902, input / output interface 903, and communication interface 904 communicate with each other within the device via bus 905.

[0146] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described cooperative transmission method for multiple communication nodes.

[0147] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state memory device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0148] The collaborative transmission method, apparatus, electronic device, and storage medium for multiple communication nodes provided in this application instantiate a first business component using application containers and business scenario information to obtain a second business component, and generate a list of business components representing the routing configuration of the second business component. This enables the initialization of components with different configurations according to different scenarios, achieving component logic reuse and effectively realizing component instantiation and configuration injection, which is beneficial to improving the flexibility of business processing. Furthermore, the mechanism of abstracting multi-level routing units based on business scenario routing to achieve the orchestration of the business component list provides a more effective and reliable way to execute the routing of the business component list, greatly improving the scalability of business orchestration execution and improving the efficiency of business development and maintenance.

[0149] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0150] The foregoing has described specific embodiments of this application; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and computer-readable storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0152] The apparatus, device, computer-readable storage medium and method provided in the embodiments of this application are corresponding. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and computer storage medium will not be described again here.

[0153] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules.

[0154] For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system onto a PLD themselves, eliminating the need for chip manufacturers to design and fabricate dedicated integrated circuit chips. Furthermore, instead of manually fabricating integrated circuit chips, this programming is now mostly implemented using "logic compiler" software, similar to the software compiler used in program development. The source code before compilation must be written in a specific programming language called a Hardware Description Language (HDL). There is not just one type of HDL, but many, such as:

[0155] ABEL (Advanced Boolean Expression Language); AHDL (Altera Hardware Description Language); Confluence; CUPL (Cornell University Programming Language); HDCal; and JHDL (Java Hardware Description Language); Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, among the technologies in this field, VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog are more commonly used. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using the aforementioned hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0156] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) that can be executed by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers:

[0157] The memory controller, including the ARC 625D, Atmel AT91SAM, Microchip IP address PIC18F26K20, and Silicon Labs C8051F320, can also be implemented as part of the memory's control logic. Those skilled in the art will also recognize that, in addition to implementing the controller as purely computer-readable program code, the same functionality can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included within it for implementing various functions can also be considered structures within that hardware component. Alternatively, the devices for implementing various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0158] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0159] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing the embodiments of this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0160] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, embodiments of this application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of this application can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0162] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0163] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0164] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0165] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0166] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0167] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0168] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0169] The embodiments of this application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can reside in local and remote computer storage media, including storage devices.

[0170] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0171] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A cooperative transmission method for multiple communication nodes, characterized in that, include: All transmission models are determined based on all the communication nodes, and all the transmission models are added to a pre-configured historical model library, wherein each transmission model is formed by connecting at least two of the communication nodes, and no two transmission models are the same; A candidate sequence is generated based on all the aforementioned transmission models, wherein the candidate sequence includes multiple candidate transmission models; The candidate sequences are optimized iteratively until the iteration termination condition is met; From the candidate sequences, the candidate transmission model with the largest communication overhead index is selected as the first target transmission model; The optimization iteration process includes: The communication overhead index of each of the candidate transmission models is obtained according to the preset communication overhead function; The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences. Add the second transmission model to the historical model library; The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted; The iteration ends when the total number of all the transmission models in the historical model library reaches a preset threshold.

2. The cooperative transmission method for multiple communication nodes according to claim 1, characterized in that, The process of extending the first transmission model to obtain the second transmission model includes: The second transmission model is obtained by sequentially disconnecting and connecting several communication nodes in the first transmission model.

3. The collaborative transmission method for multiple communication nodes according to claim 2, characterized in that, The process of sequentially disconnecting and connecting several communication nodes in the first transmission model to obtain the second transmission model includes: Disconnect several communication nodes in the first transmission model that are connected by a first preset connection method to obtain several dispersed communication nodes; A second transmission model is obtained by connecting several dispersed communication nodes using a second preset connection method, wherein the second preset connection method is different from the first preset connection method.

4. The cooperative transmission method for multiple communication nodes according to claim 1, characterized in that, The step of generating candidate sequences based on all the transmission models includes: From all the transmission models, a plurality of the transmission models are randomly selected as a plurality of the candidate transmission models; Candidate sequences are generated based on multiple alternative transmission models.

5. The cooperative transmission method for multiple communication nodes according to claim 4, characterized in that, The step of randomly selecting multiple transmission models from all the transmission models as multiple candidate transmission models includes: From all the transmission models, a plurality of the transmission models are randomly selected with equal probability as a plurality of the candidate transmission models.

6. The cooperative transmission method for multiple communication nodes according to claim 4, characterized in that, The step of generating candidate sequences based on multiple candidate transmission models includes: The candidate transmission models are arranged in a random order to generate a candidate sequence.

7. The cooperative transmission method for multiple communication nodes according to any one of claims 1 to 6, characterized in that, The step of optimizing and iterating the candidate sequences until the iteration termination condition is met further includes: From the candidate sequence, select all candidate transmission models whose communication overhead index is greater than a preset overhead index as the second transmission model.

8. A cooperative transmission device for multiple communication nodes, characterized in that, The device includes: The model generation module is used to determine all transmission models based on all the communication nodes and add all the transmission models to a pre-configured historical model library, wherein each transmission model is formed by connecting at least two of the communication nodes, and no two transmission models are the same; A sequence generation module is used to generate candidate sequences based on all the transmission models, wherein the candidate sequences include multiple candidate transmission models; An optimization processing module is used to perform optimization iterative processing on the candidate sequences until the iteration termination condition is met, wherein the optimization iterative processing includes: The communication overhead index of each of the candidate transmission models is obtained according to the preset communication overhead function; The first transmission model is extended to obtain the second transmission model, wherein the first transmission model is the candidate transmission model with the largest communication overhead index among the candidate sequences. Add the second transmission model to the historical model library; The second transmission model is set at the very end of the candidate sequence, and the candidate transmission model at the very beginning of the candidate sequence is deleted; The iteration ends when the total number of all the transmission models in the historical model library reaches a preset threshold. The selection module is used to select the candidate transmission model with the largest communication overhead index from the candidate sequence as the first target transmission model.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the cooperative transmission method of multiple communication nodes as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the cooperative transmission method for multiple communication nodes as described in any one of claims 1 to 7.

Images