Big data control system based on artificial intelligence and block chain

Abstract

The invention relates to the technical field of task scheduling control, and discloses a big data control system based on artificial intelligence and a block chain, and the system comprises a task data collection module which is used for collecting feature data of a to-be-executed task, and the feature data comprises a historical execution error record and an executor experience value; the task risk assessment module is used for predicting the failure risk probability of each to-be-executed task; the high-risk task identification module is used for marking high-risk tasks according to the failure risk probability; by introducing multi-dimensional indexes such as historical execution error records, executor experience value weights and task difficulty scores, a comprehensive assessment model of risk scores is established, and the potential failure risk of each to-be-executed task is accurately quantified. And through weight adjustment, management policy requirements of different scenes and different stages can be flexibly adapted. The accuracy of risk identification is improved, and the capability of early warning potential failure risks in advance is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of task scheduling control, and particularly to a big data control system based on artificial intelligence and blockchain. Background Art

[0002] In various task execution scenarios, traditional task scheduling methods mainly adopt methods based on fixed rules, triggered by simple conditions, or adjusted according to the overall task volume. However, these methods have many deficiencies: First, existing systems usually adjust based on the number of tasks or the execution progress, lacking the identification and differential processing of the risk attributes of individual tasks (such as historical execution error records, experience of execution personnel, etc.), and unable to specifically control potential high-risk tasks; Second, existing technologies fail to dynamically optimize the scheduling arrangement by combining the specific status of tasks and the expected execution duration, resulting in an increased risk of task failure when high-risk tasks are concentrated; Third, current task scheduling mostly targets the overall task flow, lacking fine-grained execution control of high-risk tasks in batches, which easily leads to the concentrated execution of high-risk tasks and increases the potential for task failure; Finally, existing systems also have deficiencies in data storage and traceability, lacking tamper-proof evidence storage and transparent management of task scheduling process data, affecting subsequent risk analysis and responsibility tracing. In summary, there is obvious room for improvement in the security, refined management, and data credibility of existing task scheduling methods, and new technical solutions are urgently needed for optimization.

[0003] The present invention proposes a big data control system based on artificial intelligence and blockchain. Summary of the Invention

[0004] The present invention provides a big data control system based on artificial intelligence and blockchain to help solve the problems mentioned in the above background art.

[0005] The present invention provides the following technical solution: A big data control system based on artificial intelligence and blockchain, comprising:

[0006] A task data acquisition module: used to acquire the characteristic data of tasks to be executed, and the characteristic data includes historical execution error records and the experience value of execution personnel;

[0007] A task risk assessment module, predicting the failure risk probability of each task to be executed;

[0008] A high-risk task identification module, used to mark high-risk tasks according to the failure risk probability;

[0009] An execution time calculation module, used to calculate the required execution duration of the task to be executed according to the execution speed of historical similar tasks and combining the current status of the task to be executed;

[0010] Scheduling strategy dynamic adjustment module: used to dynamically adjust the task scheduling strategy within a fixed scheduling cycle and arrange high-risk tasks for execution in batches;

[0011] Scheduling instruction issuing and execution module: used to generate instructions for dynamically adjusting task scheduling, issue instructions and control the execution of instructions;

[0012] Blockchain storage module: used to record data in the system and store the data in the blockchain network in real time.

[0013] Preferably, the task data collection module is used to collect characteristic data of the task to be executed, including:

[0014] The tasks to be executed are divided into multiple task categories according to different types, and each task category contains multiple specific tasks.

[0015] For each specific task, its historical execution error records are collected, including the error type and the corresponding number of errors; at the same time, the experience value of the person responsible for executing the task is obtained. The experience value can be comprehensively evaluated based on factors such as the number of similar tasks completed by the executor and the quality of completion.

[0016] Preferably, the task risk assessment module is used to predict the failure risk probability of each task to be executed based on the collected feature data, including:

[0017] Set a weight for each error type, calculate the weight of each error type and multiply it by the corresponding number of errors, and record the result as the error score;

[0018] Set the weight of the executor's experience value, calculate the executor's experience value multiplied by the weight of the experience value, and record the result as the experience score;

[0019] Set the task difficulty score. Different task categories correspond to different task difficulty scores.

[0020] Calculate the error score + experience score + task difficulty score, and record the result as the risk score z;

[0021] Calculate the failure risk probability of the task to be executed .

[0022] Preferably, the high-risk task identification module is used to mark high-risk tasks according to the failure risk probability, including:

[0023] Setting risk probability thresholds ;

[0024] The failure risk probability of the task to be executed and Make comparisons;

[0025] like , then the to-be-executed task is recorded as a high-risk task.

[0026] Preferably, the execution time estimation module is configured to estimate the execution duration required for the to-be-executed task according to the execution speed of historical similar tasks and in combination with the current state of the to-be-executed task, including:

[0027] Obtain the execution speed of historical similar tasks, calculate the average value, and use the result as the average execution speed;

[0028] For any to-be-executed task, evaluate the workload required from the current state to the completion of the task, and record it as the execution workload;

[0029] Calculate the execution workload ÷ the average execution speed, and record the result as the execution duration.

[0030] Preferably, the scheduling policy dynamic adjustment module is configured to dynamically adjust the task scheduling policy within a fixed scheduling period and arrange the execution of high-risk tasks in batches, including:

[0031] Divide the scheduling period into multiple execution stages according to the task category, and each execution stage corresponds to a different task category;

[0032] Obtain the number of high-risk tasks in each execution stage , where i represents different execution stages;

[0033] Sort in ascending order, and record the execution stages corresponding to the number of high-risk tasks in ascending order as ;

[0034] Obtain the benchmark execution time set for the scheduling period , , is the total available execution time in the scheduling period, and m is the number of execution stages;

[0035] Set the time adjustment range of the execution stage ;

[0036] Adjust the execution time of the execution stage :

[0037] ;

[0038] ;

[0039] ;

[0040] Among them, is the adjustment coefficient.

[0041] Preferably, the scheduling policy dynamic adjustment module is used to dynamically adjust the task scheduling policy within a fixed scheduling period and arrange the execution of high-risk tasks in batches, including:

[0042] According to the execution time of the execution stage Calculate the batches into which the tasks to be executed are divided:

[0043] Obtain the execution stage For all tasks to be executed on it, calculate the average execution duration, and record the result as the average execution duration ;

[0044] Calculate the maximum number of tasks to be executed in this execution stage within the current scheduling period , where is the floor symbol;

[0045] Obtain the execution stage The number of all tasks to be executed on it ;

[0046] If , then The batches into which the tasks to be executed on it are divided are ;

[0047] Set the high-risk quantity threshold;

[0048] Detect the number of high-risk tasks in any batch. If the number is greater than or equal to the high-risk quantity threshold, then halve the number of tasks executed in the batch.

[0049] Preferably, the blockchain storage module includes:

[0050] Data preprocessing unit: used to standardize and structurally encapsulate the recorded data to generate corresponding data hash values.

[0051] Transaction packaging unit: used to package the data during a single adjustment of the task scheduling period into a blockchain data, and add a timestamp, signature authentication, and system node identifier.

[0052] On-chain synchronization unit: used to broadcast the packaged data to the blockchain network to complete the distributed consensus and on-chain storage of the data.

[0053] Data query and traceability unit: used to support the quick retrieval and traceability of historical on-chain data according to time, task category, task identifier, and scheduling period.

[0054] Privacy and security protection unit: used to desensitize the task identifier and executor characteristic information, and store the encrypted anonymous identifier.

[0055] The present invention has the following beneficial effects:

[0056] 1. This big data control system based on artificial intelligence and blockchain establishes a comprehensive evaluation model of risk scores by introducing multi-dimensional indicators such as historical execution error records, the weight of executor experience values, and task difficulty scores, accurately quantifying the potential failure risks of each task to be executed. Through weight adjustment, it can flexibly adapt to the management policy requirements of different scenarios and different stages. It improves the accuracy of risk identification, enhances the early warning ability for potential failure risks, and provides solid data support for the screening and differential management of subsequent high-risk tasks.

[0057] 2. This big data control system based on artificial intelligence and blockchain realizes the real-time identification of potential high-risk tasks by setting a risk probability threshold and marking high-risk tasks according to the failure risk probability of each task to be executed. It optimizes the task scheduling strategy in a targeted manner, reduces the task failure probability caused by non-standard execution processes, and makes the overall scheduling logic shift from traditional passive response to active prediction and prevention.

[0058] 3. This big data control system based on artificial intelligence and blockchain realizes a more fine-grained task scheduling optimization by dividing the execution order into execution stages of different task categories according to the scheduling cycle and sorting and adjusting the execution time based on the number of high-risk tasks in each stage. By increasing the execution time of the stage with fewer high-risk tasks and reducing the execution time of the stage with more high-risk tasks, it promotes the priority and efficient execution of low-risk tasks, and arranges the execution of high-risk tasks in batches at the same time, avoiding the aggregated execution of high-risk tasks and reducing the potential task failure risk.

[0059] 4. This big data control system based on artificial intelligence and blockchain calculates the execution batches in combination with the execution duration of the tasks according to the adjusted execution time, realizing the batch execution control of high-risk tasks. By reasonably dividing the batches, it can not only avoid the chaos and failure risks caused by the concentrated execution of high-risk tasks, but also ensure the stability and continuity of the overall task flow. After adopting the batch management strategy, the system can intelligently adapt the execution volume of each batch according to the real-time task status, making the task scheduling strategy more flexible and forward-looking, and further improving the order and success rate of task execution.

[0060] 5. The big data control system based on artificial intelligence and blockchain records and stores the key data in the task scheduling process in real time through the setting of the blockchain storage module, ensuring the immutability and full-process traceability of the data. Through a series of mechanisms such as data preprocessing, packaging, on-chain synchronization, data query, and privacy protection, it realizes the transparent and standardized management of the task scheduling decision-making process, effectively improving the security and compliance of the data. At the same time, the blockchain storage provides reliable data support for the subsequent management department to trace the responsibility for task failure, optimize scheduling analysis, and make management decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the system modules of the present invention.

[0062] Figure 2 It is a schematic diagram of the blockchain storage module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment 1. Refer to Figure 1 , a big data control system based on artificial intelligence and blockchain, including:

[0065] Task data acquisition module: used to collect the characteristic data of the tasks to be executed, and the characteristic data includes historical execution error records and the experience values of the executors; in this embodiment, the tasks are divided into three categories: A, B, and C. For each specific task, its historical execution error records and the experience values of the executors are collected in detail;

[0066] Task risk assessment module, predicting the failure risk probability of each task to be executed; calculating the error score, experience score, and task difficulty score according to the set weights, and then obtaining the risk score z, and finally calculating the failure risk probability;

[0067] High-risk task identification module, used to mark high-risk tasks according to the failure risk probability;

[0068] Execution time calculation module, used to calculate the required execution duration of the task to be executed according to the execution speed of historical similar tasks and the current state of the task to be executed; obtaining the average execution speed of historical similar tasks as the average execution speed, evaluating the execution workload of the task to be executed, and calculating the execution duration.

[0069] Scheduling Policy Dynamic Adjustment Module: It is used to dynamically adjust the task scheduling policy within a fixed scheduling period, and arrange the execution of high-risk tasks in batches; divide the scheduling period into execution phases corresponding to three types of tasks A, B, and C, count the number of high-risk tasks in each phase and sort them, and adjust the execution time of each phase according to the reference execution time , time adjustment range and adjustment coefficient to adjust the execution time of each phase ;

[0070] Scheduling Instruction Issuance and Execution Module: It is used to generate instructions for dynamically adjusting task scheduling, issue instructions and control the execution of instructions;

[0071] Blockchain Storage Module: It is used to record the data in the system and store the data on the blockchain network in real time. In this embodiment, the blockchain storage module includes a data preprocessing unit, a transaction packaging unit, a blockchain synchronization unit, a data query and traceability unit, and a privacy and security protection unit. Each unit works together to ensure the reliable storage and management of data.

[0072] The task data acquisition module is used to acquire the characteristic data of the tasks to be executed, including:

[0073] Divide the tasks to be executed into multiple task categories according to different types, and each task category contains multiple specific tasks.

[0074] For each specific task, collect its historical execution failure records, including the failure type and the corresponding number of failures; at the same time, obtain the experience value of the personnel responsible for the execution of the task, and the experience value can be comprehensively evaluated according to factors such as the number and quality of similar tasks completed by the executor.

[0075] The task risk assessment module is used to predict the failure risk probability of each task to be executed based on the acquired characteristic data, including:

[0076] Set weights for each failure type, calculate the product of the weight of each failure type and the corresponding number of failures, and record the result as the failure score;

[0077] Set the weight of the executor's experience value, calculate the product of the executor's experience value and the weight of the experience value, and record the result as the experience score;

[0078] Set the task difficulty score, and different task categories correspond to different task difficulty scores;

[0079] Calculate the failure score + experience score + task difficulty score, and record the result as the risk score z;

[0080] Calculate the failure risk probability of the task to be executed .

[0081] The high-risk task identification module is used to mark high-risk tasks according to the failure risk probability, including:

[0082] Set a risk probability threshold ;

[0083] Compare the failure risk probability of the task to be executed and ;

[0084] If , then the task to be executed is marked as a high-risk task.

[0085] The execution time calculation module is used to calculate the required execution duration of the task to be executed based on the execution speed of historical similar tasks and the current state of the task to be executed, including:

[0086] Obtain the execution speed of historical similar tasks, calculate the average value, and use the result as the average execution speed;

[0087] For any task to be executed, evaluate the workload required from the current state to the completion of the task, and record it as the execution workload;

[0088] Calculate the execution workload ÷ average execution speed, and record the result as the execution duration.

[0089] The scheduling strategy dynamic adjustment module is used to dynamically adjust the task scheduling strategy within a fixed scheduling period and arrange the execution of high-risk tasks in batches, including:

[0090] Divide the scheduling period into multiple execution stages according to the task category, and each execution stage corresponds to a different task category;

[0091] Obtain the number of high-risk tasks in each execution stage , where i represents different execution stages;

[0092] Sort in ascending order, and record the execution stages corresponding to the number of high-risk tasks in ascending order as ;

[0093] Obtain the benchmark execution time set for the scheduling period , , , where is the total available execution time in the scheduling period and m is the number of execution stages;

[0094] Set the time adjustment range of the execution stage ;

[0095] Adjust the execution time of the execution stage :

[0096] ;

[0097] ;

[0098] ;

[0099] Among them, is an adjustment coefficient.

[0100] The scheduling policy dynamic adjustment module is used to dynamically adjust the task scheduling policy within a fixed scheduling period, and arrange the execution of high-risk tasks in batches, including:

[0101] Calculate the batches into which the tasks to be executed are divided according to the execution time of the execution phase :

[0102] Obtain the execution phase The execution durations of all tasks to be executed on are obtained, and the average value is calculated, and the result is recorded as the average execution duration ;

[0103] Calculate the maximum number of tasks to be executed in this execution phase within the current scheduling period , where is the floor symbol;

[0104] Obtain the number of all tasks to be executed on the execution phase ; ;

[0105] If , then The batches into which the tasks to be executed on are divided are ;

[0106] Set the high-risk quantity threshold;

[0107] Detect the quantity of high-risk tasks in any batch. If the quantity is greater than or equal to the high-risk quantity threshold, then halve the quantity of tasks executed in the batch.

[0108] In this embodiment, referring to Figure 2 , the blockchain storage module includes:

[0109] Data preprocessing unit: used to standardize and structurally encapsulate the recorded data to generate corresponding data hash values.

[0110] Transaction packaging unit: used to package the data during the process of a single adjustment task scheduling cycle to form a piece of blockchain data, and add a timestamp, signature authentication, and system node identifier.

[0111] On-chain synchronization unit: used to broadcast the packaged data to the blockchain network to complete the distributed consensus and on-chain storage of the data.

[0112] Data query and traceback unit: used to support rapid retrieval and traceability of historical data uploaded to the chain according to time, task category, task identifier, and scheduling period.

[0113] Privacy and security protection unit: used to desensitize task identifiers and executor characteristic information, and store encrypted anonymous identifiers.

[0114] In this embodiment, the scheduling period is 120 minutes, the total available execution time is set to 80 minutes, and the initial benchmark execution time for each stage is 20 minutes;

[0115] It is recognized that there are 8 high-risk tasks in the execution stage of Class A tasks, 3 high-risk tasks in the execution stage of Class B tasks, and 5 high-risk tasks in the execution stage of Class C tasks;

[0116] Then is the execution stage of Class B tasks, is the execution stage of Class C tasks, is the execution stage of Class A tasks;

[0117] Set the execution time adjustment range to 6 minutes and the adjustment coefficient to one-third;

[0118] ;

[0119] ;

[0120] ;

[0121] 26 + 22 + 18 = 66 minutes;

[0122] For which is the execution stage of Class A tasks, calculate the batches;

[0123] Average passage duration Then ;

[0124] There are a total of 10 tasks to be executed in the execution stage of Class A tasks;

[0125] The batches into which the vehicles waiting to pass are divided are batches;

[0126] Batch 1: Task 1, Task 2 (high-risk), Task 3 (high-risk), Task 4 (high-risk), Task 5, Task 6; Batch 2: Task 7 (high-risk), Task 8 (high-risk), Task 9, Task 10. The high-risk quantity threshold is 2;

[0127] If the number of the first batch of high-risk tasks is equal to 3, then the tasks to be executed in the first batch are adjusted. Low-risk tasks and some high-risk tasks are preferentially arranged for execution. Control tasks 1, task 2 (high-risk), and task 5 to pass first, and then control tasks 3 (high-risk), task 4 (high-risk), and task 6 to execute.

[0128] For During the execution phase of type C tasks, calculate the batches;

[0129] Average execution duration , ;

[0130] The number of all tasks to be executed during the execution phase of type C tasks is 4;

[0131] 4 is less than 8, so there is no need for batching;

[0132] There are 3 high-risk tasks in a single batch, and two vehicles are controlled to pass through the traffic signal control intersection each time.

[0133] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0134] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A big data control system based on artificial intelligence and blockchain, characterized in that, Including: Task data acquisition module: used to acquire the characteristic data of the task to be executed, and the characteristic data includes historical execution error records and the experience value of the executor; Task risk assessment module, which predicts the failure risk probability of each task to be executed; High-risk task identification module, used to mark high-risk tasks according to the failure risk probability; Execution time calculation module, used to calculate the required execution duration of the task to be executed based on the execution speed of historical similar tasks and in combination with the current state of the task to be executed; Scheduling strategy dynamic adjustment module: used to dynamically adjust the task scheduling strategy within a fixed scheduling period and arrange the execution of high-risk tasks in batches; Scheduling instruction issuance and execution module: used to generate instructions for dynamically adjusting task scheduling, issue instructions and control the execution of instructions; Blockchain storage module: used to record the data in the system and store the data on the blockchain network in real time.

2. The big data control system based on artificial intelligence and blockchain according to claim 1, characterized in that, The task data acquisition module is used to acquire the characteristic data of the task to be executed, including: Dividing the tasks to be executed into multiple task categories according to different types, and each task category contains multiple specific tasks; For each specific task, collect its historical execution error records, including the error type and the corresponding number of errors; at the same time, obtain the experience value of the executor responsible for the task, and the experience value can be comprehensively evaluated according to factors such as the number and quality of similar tasks completed by the executor.

3. The big data control system based on artificial intelligence and blockchain according to claim 1, wherein The task risk assessment module is used to predict the failure risk probability of each task to be executed based on the acquired characteristic data, including: Set a weight for each error type, calculate the weight of each error type multiplied by the corresponding number of errors, and record the result as the error score; Set the weight of the executor's experience value, calculate the executor's experience value multiplied by the weight of the experience value, and record the result as the experience score; Set the task difficulty score, and different task categories correspond to different task difficulty scores; Calculate the error score + experience score + task difficulty score, and record the result as the risk score z; Calculate the failure risk probability of the task to be executed .

4. The big data control system based on artificial intelligence and blockchain according to claim 3, characterized in that The high-risk task identification module is used to mark high-risk tasks according to the failure risk probability, including: Set the risk probability threshold ; Compare the failure risk probability of the task to be executed with ; If , the task to be executed is recorded as a high-risk task.

5. The big data control system based on artificial intelligence and blockchain according to claim 1, characterized in that The execution time calculation module is used to calculate the required execution duration of the task to be executed based on the execution speed of historical similar tasks and in combination with the current state of the task to be executed, including: Obtain the execution speed of historical similar tasks, calculate the average value, and use the result as the average execution speed; For any task to be executed, evaluate the workload required from the current state to the completion of the task, and record it as the execution workload; Calculate the execution workload ÷ average execution speed, and record the result as the execution duration.

6. The big data control system based on artificial intelligence and blockchain according to claim 1, characterized in that The scheduling strategy dynamic adjustment module is used to dynamically adjust the task scheduling strategy within a fixed scheduling period and arrange the execution of high-risk tasks in batches, including: Dividing the scheduling period into multiple execution stages according to task categories, and each execution stage corresponds to a different task category; Obtain the number of high-risk tasks in each execution stage , where i represents different execution stages; Sort in ascending order, and denote the execution phases corresponding to the number of high-risk tasks in ascending order as ; Obtain the reference execution time set for the scheduling period , , , where is the total available execution time in the scheduling period, and m is the number of execution phases; Set the time adjustment range in the execution phase ; Adjust the execution time in the execution phase : ； ； ； Among them, is an adjustment coefficient.

7. The big data control system based on artificial intelligence and blockchain according to claim 6, characterized in that The scheduling strategy dynamic adjustment module is used to dynamically adjust the task scheduling strategy within a fixed scheduling period and arrange the execution of high-risk tasks in batches, including: According to the execution time in the execution phase Calculate the batches into which the tasks to be executed are divided: Obtain the execution stage Obtain the execution duration of all tasks to be executed at , calculate the average value, and record the result as the average execution duration ; Calculate the maximum number of tasks to be executed in the current execution stage during the current scheduling period , where is the floor symbol; Obtain the execution phase The number of all tasks to be executed ; If , then the batches into which the tasks to be executed on are divided are Set the high-risk quantity threshold; Detect the quantity of high-risk tasks in any batch. If the quantity is greater than or equal to the high-risk quantity threshold, then halve the quantity of tasks executed in the batch.

8. The big data control system based on artificial intelligence and blockchain according to claim 1, characterized in that, The blockchain storage module includes: Data preprocessing unit: used to standardize and structurally encapsulate the recorded data to generate corresponding data hash values; Transaction packaging unit: used to package the data during a single adjustment task scheduling cycle to form a blockchain data, and add a timestamp, signature authentication, and system node identifier; On-chain synchronization unit: used to broadcast the packaged data to the blockchain network to complete distributed consensus and on-chain storage of the data; Data query and traceability unit: used to support rapid retrieval and traceability of historical on-chain data according to time, task category, task identifier, and scheduling cycle; Privacy and security protection unit: used to desensitize the task identifier and executor characteristic information, and store the encrypted anonymous identifier.

Images