Task scheduling method, task scheduling device, electronic equipment and readable storage medium

Abstract

The application discloses a task scheduling method, a task scheduling device, an electronic device and a readable storage medium. The method comprises the following steps: in response to a trigger operation, a first super SIM card is used to broadcast a task processing request to a set of edge devices, wherein the trigger operation is used to indicate that a target task is unloaded to an edge device for execution, and the set of edge devices comprises at least one edge device; the first super SIM card is used to receive state characteristics fed back by each edge device based on a second super SIM card; a first scheduling decision is generated based on task characteristics of the target task and the state characteristics fed back by each edge device; and the first super SIM card is used to send corresponding task execution instructions to a target edge device corresponding to the first scheduling decision.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computers, and particularly relates to a task scheduling method, a task scheduling device, an electronic device, and a readable storage medium. BACKGROUND

[0002] In the field of task offloading, a centralized scheduling strategy is usually relied on, which relies on real-time communication between a center node and edge nodes. However, when the network condition is poor or the node scale is too large, the timely delivery of scheduling instructions is difficult to guarantee, which affects the task execution efficiency. SUMMARY

[0003] Embodiments of the present application provide a task scheduling method, a task scheduling device, an electronic device, and a readable storage medium, which can solve the problem of low task execution efficiency of the traditional task scheduling strategy.

[0004] In a first aspect, embodiments of the present application provide a task scheduling method, which comprises: in response to a trigger operation, broadcasting, by a first super SIM card, a task processing request to a set of edge devices, wherein the trigger operation is used to indicate that a target task is to be offloaded to an edge device for execution, and the set of edge devices comprises at least one edge device; receiving, by the first super SIM card, a state feature fed back by each edge device based on a second super SIM card; generating a first scheduling decision based on a task feature of the target task and the state feature fed back by each edge device; and sending, by the first super SIM card, a corresponding task execution instruction to a target edge device corresponding to the first scheduling decision.

[0005] In a second aspect, embodiments of the present application provide a task scheduling method, which comprises: acquiring, by a second super SIM card, a task execution instruction sent by a first terminal based on a first super SIM card; and executing a target task based on the task execution instruction.

[0006] In a third aspect, embodiments of the present application provide a task scheduling device, which comprises: a broadcasting module configured to broadcast, by a first super SIM card, a task processing request to a set of edge devices in response to a trigger operation, wherein the trigger operation is used to indicate that a target task is to be offloaded to an edge device for execution, and the set of edge devices comprises at least one edge device; a receiving module configured to receive, by the first super SIM card, a state feature fed back by each edge device based on a second super SIM card; a generating module configured to generate a first scheduling decision based on a task feature of the target task and the state feature fed back by each edge device; and a sending module configured to send, by the first super SIM card, a corresponding task execution instruction to a target edge device corresponding to the first scheduling decision.

[0007] In a fourth aspect, an embodiment of the present application provides a task scheduling apparatus, which comprises: a determination module configured to acquire, based on a second super SIM card, a task execution instruction sent by a first terminal based on a first super SIM card; and an execution module configured to execute a target task based on the task execution instruction.

[0008] In a fifth aspect, an embodiment of the present application provides an electronic device, which comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the steps of the method according to the first aspect or the steps of the method according to the second aspect are implemented.

[0009] In a sixth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the method according to the first aspect or the steps of the method according to the second aspect are implemented.

[0010] In a seventh aspect, an embodiment of the present application provides a chip, which comprises a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the method according to the first aspect or the steps of the method according to the second aspect.

[0011] In an eighth aspect, an embodiment of the present application provides a computer program product, which comprises at least one computer program, and when the computer program is loaded and executed by a processor, the method according to the first aspect or the steps of the method according to the second aspect are implemented.

[0012] In the embodiment of the present application, in response to a trigger operation, a task processing request is broadcasted to a set of edge devices by using a first super SIM card, wherein the trigger operation is used to indicate that a target task is to be offloaded to an edge device for execution, the set of edge devices comprises at least one edge device, then a state feature fed back by each edge device based on a second super SIM card is received by using the first super SIM card, a first scheduling decision is generated based on a task feature of the target task and the state feature fed back by each edge device, finally, a corresponding task execution instruction is sent to a target edge device corresponding to the first scheduling decision by using the first super SIM card, which realizes reliable communication based on a super SIM card, when network conditions are poor or the scale of nodes is too large, scheduling instructions can be timely issued, thereby ensuring the task execution efficiency, and meanwhile, effectively solves the security challenges such as device heterogeneity, task diversity and network attack in the edge computing scenario, and can bring security protection for edge computing services. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1is a flowchart of a task scheduling method provided by an embodiment of the present application.

[0014] Figure 2 is a flowchart of a task scheduling method provided by an embodiment of the present application.

[0015] Figure 3 is a flowchart of a task scheduling method provided by an embodiment of the present application.

[0016] Figure 4 is a structural diagram of a task scheduling device provided by an embodiment of the present application.

[0017] Figure 5 is a structural diagram of a task scheduling device provided by an embodiment of the present application.

[0018] Figure 6 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without any creative work fall within the scope of protection of the present application.

[0020] The task scheduling method, task scheduling device, electronic device and readable storage medium provided by the embodiments of the present application will be described in detail below with reference to the drawings and specific embodiments and application scenarios.

[0021] Figure 1 A task scheduling method provided by an embodiment of the present application is shown, which can be executed by a first terminal, and the method comprises the following steps:

[0022] S110: In response to a trigger operation, a task processing request is broadcasted to a set of edge devices by using a first super SIM card.

[0023] The trigger operation is used to indicate that a target task is to be offloaded to an edge device for execution, and the set of edge devices comprises at least one edge device.

[0024] S120: The first super SIM card is used to receive a state feature fed back by each edge device based on a second super SIM card.

[0025] It can be understood that, in S110 and S120, if the user needs to offload the target task to the edge device for execution, the user can first broadcast a task processing request to the network by using the super SIM card of the first terminal. After receiving the request, the edge devices in the edge device set feed back their current hardware states and load conditions to the user by using the super SIM card.

[0026] In the embodiments of the present application, the first terminal communicates with each edge device by using the super SIM card. Since the super SIM card has the characteristics of high security and high network performance, when the network condition is poor or the network load is high, the communication quality can be effectively improved, the occurrence of disconnection, delay, and packet loss can be reduced, and stable and efficient connection between the two parties can be ensured.

[0027] In an exemplary embodiment, the edge device set can include edge devices within a first distance from the first terminal.

[0028] S130: generating a first scheduling decision based on the task characteristics of the target task and the state characteristics fed back by each edge device.

[0029] It can be understood that, after collecting the feedback state characteristics of all edge devices, the first terminal generates a first scheduling decision in combination with the characteristics of the task, such as the calculation amount, the delay requirement, the security level, and the like. The first scheduling decision indicates the target edge device for executing the target task.

[0030] In this step, based on the task characteristics of the target task and the state characteristics fed back by each edge device, the scheduling decision can be dynamically adjusted to ensure that the sensitive task is allocated to the device with high credibility while meeting the task calculation requirement.

[0031] S140: sending a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision by using the first super SIM card.

[0032] It can be understood that, after generating the first scheduling decision, the first super SIM card is used to send a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision.

[0033] In the embodiment of the present application, in response to a trigger operation, a task processing request is broadcast to a set of edge devices using a first super SIM card, wherein the trigger operation is used to indicate that a target task is to be offloaded to an edge device for execution, the set of edge devices includes at least one edge device, then the first super SIM card is used to receive state characteristics fed back by each edge device based on a second super SIM card, then a first scheduling decision is generated based on the task characteristics of the target task and the state characteristics fed back by each edge device, finally the first super SIM card is used to send a corresponding task execution instruction to a target edge device corresponding to the first scheduling decision, which realizes reliable communication based on a super SIM card. When the network condition is not good or the node scale is too large, the scheduling instruction can be timely issued, thereby ensuring the task execution efficiency, and at the same time, effectively solving the security challenges such as device heterogeneity, task diversity and network attack in the edge computing scene, which can bring security protection for edge computing services.

[0034] In an example embodiment, S130 described above can include the following steps:

[0035] S132: determining an attention weight of each edge device based on the task characteristics of the target task and the state characteristics fed back by each edge device, wherein the attention weight is used to represent an importance coefficient of the edge device.

[0036] It can be understood that by determining the attention weight of each edge device, the importance coefficient of the edge device, i.e., the matching degree of the edge device and the target task, can be obtained.

[0037] In an example embodiment, S132 can include the following steps:

[0038] Step 1: for each edge device, determining a correlation score of the edge device and the target task based on the task characteristics of the target task and the state characteristics fed back by the edge device.

[0039] Step 2: for each edge device, determining the attention weight of the edge device as a ratio of the correlation score and a target total score, wherein the target total score is a sum of the correlation scores of all the edge devices and the target task.

[0040] Exemplarily, the calculation formula of the attention weight can be:

[0041]

[0042] wherein, is the attention weight, represents the correlation score of the edge device and the target task T. is a dummy variable of the summation symbol, and in To traverse all devices within the range. The attention weight may range from , and the sum of the attention weight of all edge devices equals 1. The greater the attention weight , the stronger the correlation between the edge device and the target task, and the greater the probability of being selected in subsequent device selection.

[0043] In another example embodiment, the state features include computing power, network bandwidth, average load value, and security trust level, and the task features include task computing amount, task data amount, task delay threshold, and task security level. The determination of the correlation score between the edge device and the target task based on the task features of the target task and the state features fed back by the edge device includes: determining a first score as a product of a first weight coefficient and a first ratio, wherein the first ratio is a ratio of the computing power to the task computing amount; determining a second score as a product of a second weight coefficient and a second ratio, wherein the second ratio is a ratio of the network bandwidth to the task data amount; determining a third score as a product of a third weight coefficient and a third ratio, wherein the third ratio is a ratio of the average load value to the task delay threshold; determining a fourth score as a product of a fourth weight coefficient and a fourth ratio, wherein the fourth ratio is a ratio of the security trust level to the task security level; and obtaining the correlation score by adding the first score, the second score, the third score, and the fourth score.

[0044] In an example, the correlation score can be calculated by the following formula:

[0045]

[0046] wherein, represents the computing power of the edge device , represents the network bandwidth of the edge device , represents the average load level of the edge device , represents the security trust level of the edge device , represents the task computing amount of the target task, represents the task data amount of the target task, represents the task delay threshold of the target task, represents the task security level of the target task. represents the first ratio, This represents the second ratio. Indicates the third ratio. This represents the fourth ratio. This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the third weighting coefficient. Denotes the fourth weighting coefficient, where, To balance the importance of different factors, satisfying:

[0047] The larger the first ratio, the more suitable the edge device is for performing the target task; the larger the second ratio, the faster the data transmission; the larger the third ratio, the more idle the edge device; and the larger the fourth ratio, the more trustworthy the edge device.

[0048] In this embodiment, multiple dimensions such as device performance, network conditions, load status and security level are considered, and a relevance score is obtained by weighted summation. The higher the score, the better the match between the device and the task, that is, the greater the attention weight.

[0049] S134: Based on a preset number of selections, the attention weight and performance index of each edge device, and the difference between any two edge devices, a second scheduling decision is generated, wherein the second scheduling decision corresponds to a first selection set, the first selection set includes at least one edge device in the edge device set, wherein the performance index is determined based on the task characteristics of the target task and the state characteristics fed back by the edge devices, and the difference is determined based on the state characteristics fed back by the edge devices.

[0050] For example, the process of generating the second scheduling decision can be represented by the following formula:

[0051]

[0052] Where m represents the preset selection quantity. Indicates edge device Performance metrics; Indicates edge device and The degree of difference; This is a balancing factor used to balance the impact of overall equipment performance and differences between equipment on the selection result. The goal of the function is to select a size of First choice set This maximizes the sum of weighted performance metrics for edge devices in the first selection set, while minimizing the differences in load and security levels between devices.

[0053] Among these, when the state characteristics include computing power, network bandwidth, average load value, and security trust level, and the task characteristics include task computation volume, task data volume, task latency threshold, and task security level, the edge device... performance indicators This can be expressed by the following formula:

[0054]

[0055] This formula takes into account computational capabilities. and network bandwidth With task characteristics The matching degree is calculated, and a logarithmic transformation is performed to smooth the values.

[0056] The difference between any two edge devices can be expressed by the following formula:

[0057]

[0058] Indicates edge device and At load level and security level The degree of difference in the data, and the delay requirements of the task. and security level Normalize.

[0059] S136: Based on the state characteristics and task characteristics of each edge device, the second scheduling decision is optimized by a multi-objective optimization model to obtain the first scheduling decision, wherein the first scheduling decision corresponds to a second selection set, and the second selection set includes at least one edge device in the first selection set.

[0060] Given that the state characteristics include computing power, network bandwidth, average load, and security trust level, and the task characteristics include task computation volume, task data volume, task latency threshold, and task security level, this multi-objective optimization model can be expressed by the following formula:

[0061] in, For task execution time, and respectively equipment Computing power and energy consumption per unit; Total energy consumption; For the overall security of the scheduling scheme, For equipment Security trust level. Indicates task The computational workload, i.e. the total amount of computing resources required to complete the task. It is equipment Attention weights reflect the relationship between the device and the task. The degree of correlation.

[0062] In this step, a multi-objective optimization model is used, and the second scheduling decision is continuously optimized by considering factors such as task execution time, energy consumption, and security, so as to obtain the first scheduling decision.

[0063] Compared with traditional static scheduling algorithms, the task scheduling method provided in this application has significant advantages in adaptability and security. It can dynamically adjust the scheduling strategy based on the real-time status and security trust level of edge devices, ensuring that sensitive tasks are assigned to highly trusted devices while meeting the computational needs of the tasks. Furthermore, the task scheduling method provided in this application employs an attention mechanism and multi-objective optimization technology, balancing task performance and system security in scheduling decisions, avoiding single points of bottleneck and security vulnerabilities in the scheduling process, thereby effectively improving the flexibility, reliability, and confidentiality of edge computing.

[0064] In one exemplary embodiment, the method further includes: obtaining at least one fourth scheduling decision determined by a second terminal; and iteratively optimizing at least one of the fourth scheduling decisions and the first scheduling decision.

[0065] Understandably, to ensure that the generated first scheduling decision is globally optimal, negotiation with a second terminal is necessary. This second terminal corresponds to the task execution time of the first terminal. During the negotiation process, distributed negotiation can be conducted via the Super SIM card to exchange scheduling decisions and provide feedback based on the actual task execution status of each terminal in the overall network. In this embodiment, the negotiation process can employ a blockchain smart contract mechanism, and the transmitted messages are encrypted by the Super SIM card to ensure the security, fairness, trustworthiness, and privacy protection of the negotiation process.

[0066] In an exemplary embodiment, the iterative optimization of at least one fourth scheduling decision and the first scheduling decision includes: in each iteration, determining the difference between any two fifth scheduling decisions, optimizing the fifth scheduling decision based on the difference, until the difference between any two fifth scheduling decisions is less than a preset threshold, wherein the fifth scheduling decision includes each of the fourth scheduling decisions and the first scheduling decision.

[0067] For example, suppose there is Each fifth terminal participates in the negotiation, and each fifth terminal holds an initial scheduling scheme. ,in, The goal of the negotiation is to achieve this. A consensus is reached among the various solutions to obtain the globally optimal solution. .

[0068] Define distance function Representing two scheduling decisions and Difference between them:

[0069]

[0070] in, Representing scheduling decisions and medium equipment The choice of [option / condition]. The negotiation process adopts an iterative optimization approach, reaching the [option / condition] in the [process / stage]. In each round of iteration, each terminal makes its own scheduling decision. The distance (or difference) between the scheduling decisions of other terminals is used to update a new scheme. :

[0071]

[0072] in, This is a balancing factor used to balance the importance of the individual's preferences and the group's opinions. When... When the value is large, the terminal tends to stick to its own scheduling decisions; when When the size is smaller, the terminal is more inclined to accept the scheduling decisions of other terminals. Several mathematical operators are used to represent the values ​​of the independent variables in solving the minimization problem. The iterative process is repeated until the solutions of all terminals converge to a consensus, i.e., for a certain threshold. ,have:

[0073]

[0074] At this point, a consensus is reached through negotiation, allowing for scheduling decisions from any fifth terminal. All can serve as the final globally optimal decision. The scheduling decision corresponding to a certain fifth terminal. It can be represented as:

[0075]

[0076] in, Indicates equipment Selected to participate in task execution This indicates that it was not selected.

[0077] In one exemplary embodiment, the above-described S140 may include the following steps:

[0078] S142: Encrypt each task execution instruction using the first super SIM card to obtain the encrypted scheduling token of the target edge device corresponding to each task execution instruction.

[0079] Understandably, by leveraging the encryption capabilities of the Super SIM card and transmitting anti-interference scheduling instructions, an organic combination of encrypted transmission and distributed execution of scheduling instructions can be achieved, which can effectively meet the security requirements of edge computing.

[0080] In one exemplary embodiment, S142 may include the following steps:

[0081] Step 1: For each task execution instruction, encrypt the task execution instruction based on the random number generated using the first super SIM card and the public key of the target edge device corresponding to the task execution instruction to obtain an encrypted task execution instruction.

[0082] For example, each task executes instructions Use the first super SIM card to generate a random number Used to calculate ciphertext instructions:

[0083]

[0084] in, Indicates task execution instructions The corresponding encryption task execution instructions, To understand encryption algorithms, Indicates splicing, The public key of the target edge device is used for encryption.

[0085] Step 2: Based on the random number generated using the first super SIM card and T polynomial coefficient vectors, determine the T ciphertext components corresponding to each encryption task execution instruction, where T is an integer greater than 0.

[0086] For example, a polynomial coefficient vector is generated using a Super SIM card. ,in, , This represents the number of transmission paths.

[0087] Each ciphertext vector t can be represented by the following formula:

[0088]

[0089] in, Cyclic group generator, Let be the order of the group.

[0090] Step 3: Based on the T ciphertext components corresponding to each task execution instruction, the identifier of the target edge device, and the private key of the first super SIM card, generate a first authentication code corresponding to each task execution instruction.

[0091] For example, the first authentication code can be represented by the following formula:

[0092]

[0093] in, For collision-resistant hash functions, For target edge devices The generated identifier, MK is the private key for the first SuperSIM card, used for signing.

[0094] Prior to this step, the method further includes: generating a key pair using the first super SIM card. ,in For private key, For public keys; obtain the cognitive key pair generated by each edge device. and the public key Register to the first super SIM card; use the first super SIM card to generate a unique identifier for each target edge device i. .

[0095] Step 4: Based on the encrypted task execution instruction corresponding to each task execution instruction, T ciphertext components and the first authentication code, construct the ciphertext scheduling token corresponding to each task execution instruction.

[0096] For example, the encrypted scheduling token can be represented by the following formula:

[0097]

[0098] In other words, the target ciphertext corresponding to each task execution instruction includes the ciphertext component corresponding to the task execution instruction and the authentication code. Wherein, This represents the encrypted task execution instruction corresponding to the i-th task execution instruction. This represents the T ciphertext components corresponding to the execution instruction of the i-th task. This represents the first authentication code corresponding to the execution instruction of the i-th task.

[0099] S144: Use the first super SIM card to send the encrypted scheduling token to the target edge device corresponding to each task execution instruction.

[0100] In one exemplary embodiment, S144 may include: for each of the encrypted scheduling tokens, using the first super SIM card to send T+2 token components of the encrypted scheduling token to the target edge device via T+2 physical links, wherein the T+2 token components include one encrypted task execution instruction, T of the encrypted components, and one first authentication code.

[0101] Understandably, in order to achieve interference-resistant scheduling command transmission, a super SIM card can be used. Different physical links will transmit encrypted scheduling tokens. In Each component is sent to the target edge device. .

[0102] In this embodiment, traditional command transmission algorithms typically employ a single encryption method, which is insufficient to withstand complex network attack environments. The task scheduling method provided in this application, however, introduces a cognitive key system and threshold key recovery technology. By distributing ciphertext components through multiple paths, it constructs a secure, efficient, and robust command transmission channel. This method leverages the computing and control capabilities of the Super SIM card to achieve confidentiality, integrity, and authentication verification of scheduling commands, effectively resisting various malicious behaviors such as man-in-the-middle attacks and replay attacks. This significantly enhances the anti-interference and fault tolerance capabilities of the scheduling system, providing reliable security for edge computing. Furthermore, traditional security measures often require additional hardware investment and professional maintenance, resulting in high costs. The task scheduling method provided in this application, however, utilizes the secure encryption capabilities of the Super SIM card, embedding security mechanisms into the scheduling decision-making and command transmission processes. This reduces reliance on dedicated security equipment and significantly lowers the deployment, maintenance, and upgrade costs of the system.

[0103] Figure 2 The illustration shows another flowchart of a task scheduling method provided in one embodiment of this application. The method can be executed by a target edge device and includes the following steps:

[0104] S210: Obtain the task execution instruction sent by the first terminal based on the first super SIM card based on the second super SIM card;

[0105] S220: Execute the target task based on the task execution instruction.

[0106] Understandably, in Figure 1 In the illustrated embodiment, the first terminal uses the first super SIM card to send a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision. Therefore, after receiving the task execution instruction, the target edge device executes the target task based on the task execution instruction.

[0107] In this embodiment, the task execution instruction sent by the first terminal based on the first super SIM card is obtained based on the second super SIM card, and then the target task is executed based on the task execution instruction. This realizes reliable communication based on the super SIM card. When the network condition is poor or the number of nodes is too large, the task execution instruction can be received on time, thereby ensuring the efficiency of task execution.

[0108] In an exemplary embodiment, before obtaining the task execution instruction sent by the first terminal based on the first super SIM card based on the second super SIM card, the method further includes: when receiving a broadcast task processing request sent by the first terminal using the second super SIM card, feeding back the status characteristics of the target edge device to the first terminal using the second super SIM card.

[0109] Understandably, if a user needs to offload a target task to an edge device for execution, they can first use the first super SIM card of the first terminal to broadcast a task processing request to the network. After receiving the request, the edge devices in the edge device set can use the second super SIM card to provide feedback on their current status characteristics to the user.

[0110] In one exemplary embodiment, the above-described S210 may include the following steps:

[0111] S212: Utilize the second super SIM card to receive T+2 token components sent by the first terminal using the first super SIM card via T+2 physical links.

[0112] Understandably, in order to achieve interference-resistant scheduling command transmission, the first terminal uses the first super SIM card to send T+2 token components to the target edge device through T+2 different physical links. Therefore, the target edge device uses the second super SIM card to receive T+2 token components sent by the first terminal using the first super SIM card via T+2 physical links.

[0113] S214: Merge the T+2 token components in a preset order to obtain a ciphertext scheduling token.

[0114] The preset order is the order of the token components in the encrypted scheduling token constructed by the first terminal.

[0115] Optionally, each token component may carry its own sequence identifier.

[0116] S216: A security verification result is obtained by performing security verification on the encrypted scheduling token.

[0117] In other words, to prevent the encrypted scheduling token from being tampered with, it is necessary to perform security verification on the encrypted scheduling token.

[0118] In one exemplary embodiment, S216 may include the following steps:

[0119] S2162: Extract the T ciphertext components and the first authentication code carried by the ciphertext scheduling token.

[0120] Among them, the T ciphertext components are The first authentication code is: .

[0121] S2164: Generate a second authentication code based on the T ciphertext components, the identifier of the target edge device stored in the second super SIM card, and the public key of the first super SIM card.

[0122] For example, the second authentication code is: =

[0123] in, The identifier code representing the target edge device; This represents the public key of the first Super SIM card, used for verification; This is a collision-resistant hash function.

[0124] It is understandable that before receiving the task execution instructions sent by the first terminal using the second super SIM card, the first terminal uses the first super SIM card to generate a pair of keys. ,in For private key, As the public key, each edge device generates a cognitive key pair. and the public key Registered to the first SuperSIM card; the first SuperSIM card generates a unique identifier for each target edge device i. .

[0125] S2166: If the first authentication code and the second authentication code are consistent, the security verification result is determined based on the encrypted task execution instruction carried by the ciphertext scheduling token and the T ciphertext components.

[0126] It is understandable that a consistency check is performed on the first authentication code and the second authentication code. If they are consistent, the security verification result is determined based on the encrypted task execution instructions carried by the ciphertext scheduling token and the T ciphertext components.

[0127] In another exemplary embodiment, if there is a discrepancy, it indicates that the encrypted scheduling token has been tampered with.

[0128] Furthermore, S2166 may include the following steps:

[0129] Step 1: Extract the encrypted task execution instructions carried by the encrypted scheduling token.

[0130] The encrypted scheduling token is as follows:

[0131] The encryption task execution command is .

[0132] Step 2: Decrypt the encrypted task execution instruction using the private key of the target edge device to obtain the task execution instruction and a random number.

[0133] In other words, using the private key Decryption and encryption task execution instructions Obtain plaintext ,in, Instructions for task execution. The result is a random number because the target edge device's public key is used for encryption during the encryption phase, and the private key is used for decryption during the decryption phase.

[0134] Step 3: Determine the T polynomial coefficient vectors by interpolating the T ciphertext components.

[0135] In other words, according to Interpolation restores T polynomial coefficient vectors.

[0136] Step 4: If the first polynomial coefficient vector among the T polynomial coefficient vectors is equal to the random number, the security verification result is determined to be passed.

[0137] Obtain T polynomial coefficient vectors The first polynomial coefficient vector in Then judge Is it equal to a random number? If the result is equal to the given value, then the security verification result is determined to be passed.

[0138] In another exemplary embodiment, if they are not equal, it indicates that the encrypted scheduling token has been tampered with and can be discarded.

[0139] In this embodiment, authentication verification based on encrypted scheduling tokens can effectively resist various malicious behaviors such as man-in-the-middle attacks and replay attacks, greatly enhancing the anti-interference and fault tolerance capabilities of the scheduling system.

[0140] Figure 3This illustration shows an interaction diagram of a task scheduling system according to an embodiment of this application. The task scheduling system includes a user terminal and a target edge device, and its interaction process may include the following steps:

[0141] S310: The user terminal uses the Super SIM card to broadcast a task request to the network.

[0142] S320: Upon receiving a broadcast task request, the target edge device uses the Super SIM card to report the device status to the user terminal.

[0143] S330: Upon receiving feedback on the device status, the user terminal generates a scheduling scheme.

[0144] S330 includes:

[0145] S331: Generate locally optimal scheduling schemes based on lightweight online learning models.

[0146] S331: Based on a locally optimal scheduling scheme, a globally optimal scheduling scheme is generated through distributed negotiation using a super SIM card.

[0147] S340: Generates encrypted scheduling instructions based on the scheduling scheme.

[0148] S350: The Super SIM card uses SCITA to transmit encrypted scheduling commands to the target edge device in a way that is resistant to network interruptions and interference.

[0149] S360: Upon receiving an encrypted scheduling instruction, the target edge device decrypts the encrypted scheduling instruction and executes it.

[0150] S370: The target edge device uses the Super SIM card to report the execution progress to the user terminal.

[0151] S380: Upon completion of the task, the Super SIM card is used to report the execution result to the user terminal.

[0152] Figure 4 This specification shows a schematic diagram of the structure of a task scheduling device provided in an embodiment, as illustrated below. Figure 4 As shown, the task scheduling device 400 may include: a broadcast module 410, a receiving module 420, a generating module 430, and a sending module 440.

[0153] In this embodiment, the broadcast module 410 is configured to broadcast a task processing request to the edge device set using a first super SIM card in response to a trigger operation, wherein the trigger operation is configured to instruct the target task to be offloaded to the edge device for execution, and the edge device set includes at least one edge device; the receiving module 420 is configured to receive status features of each edge device based on feedback from a second super SIM card using the first super SIM card; the generating module 430 is configured to generate a first scheduling decision based on the task features of the target task and the status features feedback from each edge device; and the sending module 440 is configured to send a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision using the first super SIM card.

[0154] In an exemplary embodiment, the generation module 430 is specifically configured to: determine the attention weight of each edge device based on the task characteristics of the target task and the state characteristics fed back by each edge device, wherein the attention weight is used to represent the importance coefficient of the edge device; generate a second scheduling decision based on a preset selection number, the attention weight and performance index of each edge device, and the difference between any two edge devices, wherein the second scheduling decision corresponds to a first selection set, the first selection set includes at least one edge device in the edge device set, wherein the performance index is determined based on the task characteristics of the target task and the state characteristics fed back by the edge devices, and the difference is determined based on the state characteristics fed back by the edge devices; and optimize the second scheduling decision using a multi-objective optimization model based on the state characteristics of each edge device and the task characteristics to obtain a first scheduling decision, wherein the first scheduling decision corresponds to a second selection set, and the second selection set includes at least one edge device in the first selection set.

[0155] In an exemplary embodiment, the generation module 430 is specifically configured to: for each edge device, determine a relevance score between the edge device and the target task based on the task characteristics of the target task and the state characteristics fed back by the edge device; and for each edge device, determine the attention weight of the edge device as the ratio of the relevance score to the target total score, wherein the target total score is the sum of the relevance scores between all the edge devices and the target task.

[0156] In an exemplary embodiment, the state characteristics include computing power, network bandwidth, average load value, and security trust level; the task characteristics include task computation volume, task data volume, task latency threshold, and task security level; the generation module 430 is specifically configured to: determine a first score by multiplying a first weight coefficient by a first ratio, wherein the first ratio is the ratio of computing power to task computation volume; determine a second score by multiplying a second weight coefficient by a second ratio, wherein the second ratio is the ratio of network bandwidth to task data volume; determine a third score by multiplying a third weight coefficient by a third ratio, wherein the third ratio is the ratio of average load value to task latency threshold; determine a fourth score by multiplying a fourth weight coefficient by a fourth ratio, wherein the fourth ratio is the ratio of security trust level to task security level; and obtain the correlation score by adding the first score, the second score, the third score, and the fourth score.

[0157] In an exemplary embodiment, the task scheduling apparatus further includes: an acquisition module, configured to acquire at least one fourth scheduling decision determined by a second terminal; and an optimization module, configured to iteratively optimize at least one of the fourth scheduling decisions and the first scheduling decision.

[0158] In an exemplary embodiment, the optimization module is specifically configured to: determine the difference between any two fifth scheduling decisions during each iteration, and optimize the fifth scheduling decisions based on the difference until the difference between any two fifth scheduling decisions is less than a preset threshold, wherein the fifth scheduling decisions include each of the fourth scheduling decisions and the first scheduling decision.

[0159] In an exemplary embodiment, the sending module 440 is specifically configured to: encrypt each task execution instruction using the first super SIM card to obtain a ciphertext scheduling token for the target edge device corresponding to each task execution instruction; and send the ciphertext scheduling token to the target edge device corresponding to each task execution instruction using the first super SIM card.

[0160] In an exemplary embodiment, the sending module 440 is specifically configured to: for each task execution instruction, encrypt the task execution instruction based on a random number generated using the first super SIM card and the public key of the target edge device corresponding to the task execution instruction, to obtain an encrypted task execution instruction; determine T ciphertext components corresponding to each encrypted task execution instruction based on the random number generated using the first super SIM card and T polynomial coefficient vectors, where T is an integer greater than 0; generate a first authentication code corresponding to each task execution instruction based on the T ciphertext components corresponding to each task execution instruction, the identifier code of the target edge device, and the private key of the first super SIM card; and construct a ciphertext scheduling token corresponding to each task execution instruction based on the encrypted task execution instruction, the T ciphertext components, and the first authentication code.

[0161] In an exemplary embodiment, the sending module 440 is specifically configured to: for each of the encrypted scheduling tokens, use the first super SIM card to send T+2 token components of the encrypted scheduling token to the target edge device via T+2 physical links, wherein the T+2 token components include T of the encrypted components, 1 encrypted task execution instruction, and 1 first authentication code.

[0162] The task scheduling device provided in this application embodiment can achieve... Figure 1 The various processes implemented in the method embodiments shown will not be described again here to avoid repetition.

[0163] Figure 5 This application illustrates a task scheduling device 500 provided in an embodiment of the present application. The task scheduling device 500 may include a receiving module 510 and an execution module 520.

[0164] In this embodiment, the determining module 510 is used to obtain the task execution instruction sent by the first terminal based on the first super SIM card based on the second super SIM card; the execution module 520 is used to execute the target task based on the task execution instruction.

[0165] In an exemplary embodiment, the determining module 510 is specifically configured to: utilize the second super SIM card to receive T+2 token components sent by the first terminal using the first super SIM card via T+2 physical links; merge the T+2 token components in a preset order to obtain a ciphertext scheduling token; perform security verification on the ciphertext scheduling token to obtain a security verification result; and if the security verification result is successful, extract the task execution instruction from the ciphertext scheduling token.

[0166] In an exemplary embodiment, the determining module 510 is specifically configured to: extract the T ciphertext components and the first authentication code carried by the ciphertext scheduling token; generate a second authentication code based on the T ciphertext components, the identifier code of the target edge device stored in the second super SIM card, and the public key of the first super SIM card; and determine the security verification result based on the encrypted task execution instruction carried by the ciphertext scheduling token and the T ciphertext components if the first authentication code and the second authentication code are consistent.

[0167] In an exemplary embodiment, the determining module 510 is specifically configured to: extract the encrypted task execution instruction carried by the ciphertext scheduling token; decrypt the encrypted task execution instruction using the private key of the target edge device to obtain the task execution instruction and a random number; determine T polynomial coefficient vectors by interpolating the T ciphertext components; and determine the security verification result as passed if the first polynomial coefficient vector among the T polynomial coefficient vectors is equal to the random number.

[0168] The task scheduling device provided in this application embodiment can achieve... Figure 2 The various processes implemented in the method embodiments shown will not be described again here to avoid repetition.

[0169] The task scheduling device in the embodiments of this application can be a device, or it can be a component, integrated circuit, or chip in an electronic device. The embodiments of this application are not specifically limited.

[0170] One of the task scheduling devices in this application embodiment can be a device with an operating system. The operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system.

[0171] Optional, such as Figure 6 As shown, this application embodiment also provides an electronic device 600, including a processor 610, a memory 620, and a program or instructions stored in the memory 620 and executable on the processor 610. When the program or instructions are executed by the processor 610, they implement the various processes of the above-described task scheduling method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0172] This application also provides a computer-readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described task scheduling method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0173] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0174] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described task scheduling method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0175] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0176] This application also provides a computer program product, which includes at least one computer program. When the computer program is loaded and executed by a processor, it implements the various processes of the above-described task scheduling method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0177] It should be noted that, in this document, 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 limitations, 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 that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0178] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0179] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A task scheduling method, characterized in that, Applied to the first terminal, including: In response to a triggering operation, a task processing request is broadcast to an edge device set using a first super SIM card, wherein the triggering operation is used to instruct the target task to be offloaded to an edge device for execution, and the edge device set includes at least one of the edge devices; The first super SIM card is used to receive the status features of each edge device based on feedback from the second super SIM card; Based on the task characteristics of the target task and the state characteristics fed back by each edge device, a first scheduling decision is generated; The first super SIM card is used to send a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision. The step of generating a first scheduling decision based on the task characteristics of the target task and the state characteristics fed back by each edge device includes: Based on the task characteristics of the target task and the state characteristics fed back by each edge device, an attention weight for each edge device is determined, wherein the attention weight is used to represent the importance coefficient of the edge device; A second scheduling decision is generated based on a preset number of selections, the attention weight and performance index of each edge device, and the difference between any two edge devices. The second scheduling decision corresponds to a first selection set, which includes at least one edge device from the edge device set. The performance index is determined based on the task characteristics of the target task and the state characteristics fed back by the edge devices, and the difference is determined based on the state characteristics fed back by the edge devices. Based on the state characteristics and task characteristics of each edge device, the second scheduling decision is optimized by a multi-objective optimization model to obtain the first scheduling decision, wherein the first scheduling decision corresponds to a second selection set, and the second selection set includes at least one edge device in the first selection set; The status characteristics include computing power, network bandwidth, average load value, and security trust level, while the task characteristics include task computation volume, task data volume, task latency threshold, and task security level.

2. The method according to claim 1, characterized in that, The process of determining the attention weight of each edge device based on the task characteristics of the target task and the state characteristics fed back by each edge device includes: For each edge device, a relevance score between the edge device and the target task is determined based on the task characteristics of the target task and the state characteristics fed back by the edge device. For each edge device, the attention weight of the edge device is determined as the ratio of the relevance score to the target total score, wherein the target total score is the sum of the relevance scores of all edge devices to the target task.

3. The method according to claim 2, characterized in that, The process of determining the relevance score between the edge device and the target task based on the task characteristics of the target task and the state characteristics fed back by the edge device includes: The product of a first weighting coefficient and a first ratio is determined to be a first fraction, wherein the first ratio is the ratio of the computing power to the amount of computation of the task; The product of the second weighting coefficient and the second ratio is determined to be the second fraction, wherein the second ratio is the ratio of the network bandwidth to the amount of task data; The product of the third weighting coefficient and the third ratio is determined to be the third fraction, wherein the third ratio is the ratio of the average load value to the task delay threshold; The product of the fourth weighting coefficient and the fourth ratio is determined to be the fourth score, wherein the fourth ratio is the ratio of the security trust level to the task security level; The relevance score is obtained by adding the first score, the second score, the third score, and the fourth score together.

4. The method according to claim 1, characterized in that, The method further includes: Obtain at least one fourth scheduling decision determined by the second terminal; The first scheduling decision and at least one of the fourth scheduling decisions are iteratively optimized.

5. The method according to claim 4, characterized in that, The iterative optimization of at least one of the fourth scheduling decisions and the first scheduling decision includes: In each iteration, the difference between any two fifth scheduling decisions is determined, and the fifth scheduling decision corresponding to the difference is optimized until the difference between any two fifth scheduling decisions is less than a preset threshold. The fifth scheduling decision includes each of the fourth scheduling decisions and the first scheduling decision.

6. The method according to claim 1, characterized in that, The step of sending a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision using the first super SIM card includes: Each task execution instruction is encrypted using the first super SIM card to obtain a ciphertext scheduling token for the target edge device corresponding to each task execution instruction. The encrypted scheduling token is sent to the target edge device corresponding to each task execution instruction using the first super SIM card.

7. The method according to claim 6, characterized in that, The step of encrypting each task execution instruction using the first super SIM card to obtain a ciphertext scheduling token for the target edge device corresponding to each task execution instruction includes: For each task execution instruction, the task execution instruction is encrypted based on a random number generated using the first super SIM card and the public key of the target edge device corresponding to the task execution instruction, to obtain an encrypted task execution instruction; Based on the random number generated using the first super SIM card and T polynomial coefficient vectors, T ciphertext components corresponding to each encryption task execution instruction are determined, where T is an integer greater than 0; Based on the T ciphertext components corresponding to each task execution instruction, the identifier of the target edge device, and the private key of the first super SIM card, a first authentication code corresponding to each task execution instruction is generated; Based on the encrypted task execution instruction corresponding to each task execution instruction, T ciphertext components, and the first authentication code, a ciphertext scheduling token corresponding to each task execution instruction is constructed.

8. The method according to claim 7, characterized in that, The step of sending the encrypted scheduling token to the target edge device corresponding to each task execution instruction using the first super SIM card includes: For each of the encrypted scheduling tokens, the first super SIM card is used to send the T+2 token components of the encrypted scheduling token to the target edge device through T+2 physical links. The T+2 token components include T encrypted components, 1 encrypted task execution instruction, and 1 first authentication code.

9. A task scheduling method, characterized in that, Applied to target edge devices, including: Obtain the task execution instructions sent by the first terminal based on the first super SIM card based on the second super SIM card; Execute the target task based on the task execution instructions; The step of obtaining the task execution instruction sent by the first terminal based on the first super SIM card based on the second super SIM card includes: The second super SIM card is used to enable it to receive T+2 token components sent by the first terminal using the first super SIM card through T+2 physical links; The T+2 token components are merged in a preset order to obtain a ciphertext scheduling token; The security verification result is obtained by performing security verification on the encrypted scheduling token; If the security verification result is successful, the task execution instruction is extracted from the encrypted scheduling token; The T+2 token components include T ciphertext components, one encryption task execution instruction, and one first authentication code.

10. The method according to claim 9, characterized in that, The step of performing security verification on the task execution instructions to obtain a security verification result includes: Extract the T ciphertext components and the first authentication code carried by the ciphertext scheduling token; A second authentication code is generated based on the T ciphertext components, the identifier of the target edge device stored in the second super SIM card, and the public key of the first super SIM card; If the first authentication code and the second authentication code are consistent, the security verification result is determined based on the encrypted task execution instructions carried by the ciphertext scheduling token and the T ciphertext components.

11. The method according to claim 10, characterized in that, The process of determining the security verification result based on the encrypted task execution instructions carried by the ciphertext scheduling token and the T ciphertext components includes: Extract the encrypted task execution instructions carried by the encrypted scheduling token; The encrypted task execution instruction is decrypted using the private key of the target edge device to obtain the task execution instruction and a random number; By interpolating the T ciphertext components, T polynomial coefficient vectors are determined; If the first of the T polynomial coefficient vectors is equal to the random number, the security verification result is determined to be passed.

12. A task scheduling device, characterized in that, Applied to the first terminal, including: A broadcast module is configured to broadcast a task processing request to an edge device set using a first super SIM card in response to a trigger operation, wherein the trigger operation is configured to instruct the target task to be offloaded to an edge device for execution, and the edge device set includes at least one of the edge devices. The receiving module is used to receive the status features of each edge device based on the feedback from the second super SIM card using the first super SIM card; The generation module is used to generate a first scheduling decision based on the task characteristics of the target task and the state characteristics fed back by each edge device; The sending module is used to send a corresponding task execution instruction to the target edge device corresponding to the first scheduling decision using the first super SIM card; Specifically, the generation module is used for: Based on the task characteristics of the target task and the state characteristics fed back by each edge device, an attention weight for each edge device is determined, wherein the attention weight is used to represent the importance coefficient of the edge device; A second scheduling decision is generated based on a preset number of selections, the attention weight and performance index of each edge device, and the difference between any two edge devices. The second scheduling decision corresponds to a first selection set, which includes at least one edge device from the edge device set. The performance index is determined based on the task characteristics of the target task and the state characteristics fed back by the edge devices, and the difference is determined based on the state characteristics fed back by the edge devices. Based on the state characteristics and task characteristics of each edge device, the second scheduling decision is optimized by a multi-objective optimization model to obtain the first scheduling decision, wherein the first scheduling decision corresponds to a second selection set, and the second selection set includes at least one edge device in the first selection set; The status characteristics include computing power, network bandwidth, average load value, and security trust level, while the task characteristics include task computation volume, task data volume, task latency threshold, and task security level.

13. A task scheduling device, characterized in that, Applied to target edge devices, including: The receiving module is used to obtain the task execution instructions sent by the first terminal based on the first super SIM card based on the second super SIM card; The execution module is used to execute the target task based on the task execution instructions; Specifically, the receiving module is used for: The second super SIM card is used to enable it to receive T+2 token components sent by the first terminal using the first super SIM card through T+2 physical links; The T+2 token components are merged in a preset order to obtain a ciphertext scheduling token; The security verification result is obtained by performing security verification on the encrypted scheduling token; If the security verification result is successful, the task execution instruction is extracted from the encrypted scheduling token; The T+2 token components include T ciphertext components, one encryption task execution instruction, and one first authentication code.

14. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the task scheduling method as described in any one of claims 1-11.

15. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the task scheduling method as described in any one of claims 1-11.

16. A computer program product, characterized in that, The computer program product includes program instructions that, when executed by a computer, cause the computer to perform the steps of the task scheduling method as described in any one of claims 1-11.

Images