Item collaborative management method and system based on artificial intelligence

Abstract

The invention discloses an item collaborative management method and system based on artificial intelligence. The method relates to the technical field of item collaborative management, and comprises the following steps of balance degree quantification, collaborative scheduling intelligent regulation and control and response efficiency intelligent regulation and control. According to the method, the balance degree parameter is obtained by identifying the service interface, and the collaborative adaptation efficiency-resource scheduling balance degree is obtained through quantification; based on the balance degree, judging and executing adaptive efficiency-balance degree intelligent regulation and control, including adaptive adjustment of a transmission quantity threshold value and an interaction frequency; and obtaining response efficiency parameters of a decision link, quantifying to obtain collaborative decision reliability and dynamic response efficiency, judging and executing intelligent regulation and control of the dynamic response efficiency according to the collaborative decision reliability and the dynamic response efficiency, including self-adaptive regulation and control of change of an identification window and iterative update frequency, and finally outputting an optimized item collaborative decision scheme. According to the invention, the real-time response collaboration of matter collaborative management is improved, and the problem of low real-time response collaboration of matter collaborative management in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of matter collaborative management, and particularly relates to a matter collaborative management method and system based on artificial intelligence. BACKGROUND

[0002] In the collaborative start stage, the initiating department combines enterprise or department goals to set collaborative goals by the SMART principle, AI (Artificial Intelligence) analyzes the goal text by natural language processing to check ambiguous and contradictory expressions, determines participating departments and personnel, and clearly defines roles by the RACI matrix, AI analyzes historical data to recommend roles, decomposes the goal into stage tasks, AI calculates task time by the critical path method, and generates a Gantt chart. In the communication and execution stage, the communication frequency is set according to the task urgency, cross-department groups are built, AI classifies and organizes group information and pushes key content, interface personnel submit progress, AI compares the Gantt chart and progress by image recognition, predicts delays and gives early warnings, and when departments have differences, AI provides pre-trial suggestions according to the topic content and historical cases. In the problem solving stage, AI analyzes problem descriptions by machine learning, searches for the root cause and defines responsibilities by searching for cases for urgent problems, and coordinates resources by optimization algorithms. In the achievement solidification stage, AI audits achievements by document comparison, analyzes acceptance opinions, generates a preliminary draft of a review report, classifies knowledge base knowledge, and helps process optimization and standardization by analyzing process indicators.

[0003] For example, the Chinese invention patent with the publication number CN110135803B discloses a matter management method and a blockchain node device, which includes: receiving a to-be-confirmed matter sent by an initiating terminal, and registering the to-be-confirmed matter on a blockchain of a decentralized autonomous organization (DAO) for broadcasting; receiving a selection result submitted by a plurality of first target terminals in the to-be-confirmed matter, and registering the selection result on the blockchain of the DAO for broadcasting, the selection result including an agreement to the to-be-confirmed matter or a disagreement to the to-be-confirmed matter; calling an intelligent contract to determine a first proportion of the agreement to the to-be-confirmed matter in the selection result at any time before the effective time of the to-be-confirmed matter; and in the case that the first proportion reaches a threshold value, executing the to-be-confirmed matter.

[0004] For example, Chinese invention patent CN113537704B discloses a change management system, including: a change acceptance subsystem and a change management subsystem; the change acceptance subsystem includes a time-series task processing module and a pending work order management module; the change management subsystem includes a work order monitoring module, a work order allocation management module, and a time-series task management module; the acceptor confirms the start of work order processing, the completion of work order processing, and the work order transfer through the pending work order management module; the manager sets the time-series tasks for each acceptor through the time-series task management module; the work order monitoring module monitors all currently processed change work orders, expired change work orders, and the completion rate of change work orders; and the work order allocation management module statistically analyzes the duration of change requests for each acceptor and transfers work orders.

[0005] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems: Firstly, at the level of cross-system collaboration and resource scheduling, due to the inconsistent interface specifications between enterprise project management tools and business systems, AI middleware needs to develop independent adapters for dozens of heterogeneous interfaces. This results in system integration cycles lasting several months, poor stability, frequent compatibility failures, and difficulty in forming a unified data view. For the inference needs of multimodal large-scale models with hundreds of billions of parameters, existing scheduling algorithms cannot achieve dynamic balance among multiple objectives such as latency, energy consumption, and cost. This leads to high response latency for critical AI functions during peak periods, and edge devices, constrained by computing resources and power consumption, cannot directly deploy large cloud models. Existing technologies lack efficient model block loading and dynamic update mechanisms, resulting in high power consumption for edge inference, failing to meet the stringent requirements of portable devices. Simultaneously, cloud models cannot absorb edge data feedback in real time to complete self-evolution. Secondly, in the core stage of collaborative decision-making, models trained on single-industry data lack cross-domain transfer capabilities, and deep learning-based recommendation systems lack interpretability. For example, when AI proposes "prioritizing resource allocation to department A," it cannot clearly explain its calculation logic based on historical task completion rates and real-time load, leading managers to reject the decision because they cannot understand its basis. Faced with sudden changes such as the departure of key members or supply chain disruptions, existing algorithms suffer from computational bottlenecks when handling complex tasks that rely on networks. Replanning paths and resource allocation is time-consuming, resulting in low real-time response and collaboration in collaborative management. Summary of the Invention

[0006] To address the technical problem of low real-time response and collaboration in existing collaborative task management technologies, this invention provides an artificial intelligence-based collaborative task management method and system. The technical solution is as follows: On the one hand, an AI-based collaborative management method for tasks is provided. This method includes: S1, identifying the business interfaces required for task collaboration, obtaining balance parameters, and obtaining a collaborative adaptation efficiency-resource scheduling balance based on the balance parameters, used to quantify the adaptation efficiency and resource scheduling balance among collaborative tasks; S2, determining whether to perform intelligent adjustment of the adaptation efficiency-resource scheduling balance based on the collaborative adaptation efficiency-resource scheduling balance. If yes, the task collaboration decision-making process is executed after intelligent adjustment of the adaptation efficiency-resource scheduling balance; otherwise, the task collaboration decision-making process is executed directly. The intelligent adjustment of the adaptation efficiency-resource scheduling balance includes adaptive adjustment of the transmission volume threshold. The system integrates and adaptively adjusts the interaction frequency; S3, it obtains the response efficiency parameters in the collaborative decision-making process, and obtains the reliability of collaborative decision-making and dynamic response efficiency based on the response efficiency parameters. This is used to quantify the reliability of AI decision-making in cross-industry scenarios and the response speed of replanning tasks and resources when facing sudden changes in matters. Based on the reliability of collaborative decision-making and dynamic response efficiency, it determines whether to perform intelligent adjustment of dynamic response efficiency. If so, it outputs the collaborative decision-making scheme after intelligent adjustment of dynamic response efficiency; otherwise, it directly outputs the collaborative decision-making scheme. Intelligent adjustment of dynamic response efficiency includes adaptive adjustment of change recognition window and adaptive adjustment of iteration update frequency.

[0007] On the other hand, an AI-based collaborative task management system is provided. This system is applied to an AI-based collaborative task management method and includes: a balance quantification module, a collaborative scheduling intelligent control module, and a response efficiency intelligent control module. The balance quantification module identifies the business interfaces required for task collaboration, obtains balance parameters, and calculates the collaborative adaptation efficiency-resource scheduling balance based on these parameters. This balance quantifies the adaptation efficiency and resource scheduling balance among collaborative tasks. The collaborative scheduling intelligent control module determines whether to perform intelligent adjustment based on the collaborative adaptation efficiency-resource scheduling balance. If so, the collaborative task decision-making process is executed after the intelligent adjustment; otherwise, the process is directly executed. In the collaborative decision-making process, the intelligent adjustment of efficiency and balance includes adaptive adjustment of transmission volume threshold and adaptive adjustment of interaction frequency. The intelligent response efficiency adjustment module is used to obtain response efficiency parameters in the collaborative decision-making process. Based on the response efficiency parameters, the reliability of collaborative decision-making and dynamic response efficiency are obtained. This is used to quantify the reliability of AI decision-making in cross-industry scenarios and the response speed of replanning tasks and resources when facing sudden changes in collaborative matters. Based on the reliability of collaborative decision-making and dynamic response efficiency, it is determined whether to perform intelligent dynamic response efficiency adjustment. If so, the collaborative decision-making scheme is output after intelligent dynamic response efficiency adjustment; otherwise, the collaborative decision-making scheme is output directly. Intelligent dynamic response efficiency adjustment includes adaptive adjustment of change recognition window and adaptive adjustment of iteration update frequency.

[0008] Beneficial effects The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. By constructing two core quantitative indicators—collaborative adaptation efficiency and resource scheduling balance, and collaborative decision reliability and dynamic response efficiency—this method achieves multi-dimensional and accurate perception and performance evaluation of the entire process of collaborative management of matters. This method innovatively couples and analyzes underlying parameters such as peak-period service response latency, interface adaptation cycle, and number of heterogeneous interfaces, as well as decision-level parameters such as the time consumption of matter adjustment and the timeliness of resource reallocation, forming a complete system health and intelligence level measurement system, which further improves the real-time response and collaboration of collaborative management of matters.

[0009] 2. By introducing an intelligent control mechanism based on balance offset and response efficiency offset, this method achieves closed-loop adaptive optimization of system resource scheduling and decision-making strategies. It can dynamically adjust data transmission thresholds and interaction frequencies based on real-time status such as concurrency and interface change frequency, effectively balancing system load and collaborative efficiency. At the same time, based on indicators such as data access latency and demand change latency, it adaptively controls the change identification window and decision iteration frequency, significantly improving the adaptability and decision quality in complex environments, and further enhancing the real-time response and collaboration of collaborative management of matters.

[0010] 3. By realizing the intelligent transformation of collaborative task management from passive response to proactive prediction and from static configuration to dynamic optimization, and through a series of algorithms such as parameter coupling, mapping query and compensation correction, key issues such as resource scheduling imbalance and decision response lag in cross-system collaboration have been solved. This ensures stable operation under high load and guarantees the reliability and timeliness of collaborative task decision-making schemes in changing environments, comprehensively improving the intelligence level and operational efficiency of collaborative task management, and further enhancing the real-time response and collaboration of collaborative task management. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating an artificial intelligence-based collaborative management method for tasks, provided as an embodiment of this application; Figure 2 A flowchart illustrating the adaptive adjustment of a change identification window in an AI-based collaborative management method for matters, provided in an embodiment of this application. Figure 3 A flowchart illustrating the adaptive adjustment of the iterative update frequency of an artificial intelligence-based collaborative management method for matters, provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an AI-based collaborative management system for tasks, provided as an embodiment of this application. Detailed Implementation

[0013] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0014] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0015] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0016] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0017] This invention provides an artificial intelligence-based collaborative management method for tasks, such as... Figure 1 The flowchart shown is a collaborative task management method based on artificial intelligence. The processing flow of this method may include the following steps: As the first step of an AI-based collaborative task management method, S1 identifies the business interfaces required for task collaboration, obtains the balance parameter, and obtains the collaboration adaptation efficiency-resource scheduling balance based on the balance parameter. This is used to quantify the adaptation efficiency between tasks and the degree of balance in resource scheduling during task collaboration management.

[0018] It should be noted that by intelligently identifying the various business interfaces required for collaborative tasks and extracting key balance parameters, a comprehensive quantitative indicator, "Collaboration Adaptation Efficiency - Resource Scheduling Balance," was constructed. This effectively solves the technical challenges of low interface adaptation efficiency and resource scheduling imbalance in cross-system collaboration. This indicator enables precise measurement of the system interface efficiency and resource utilization rationality between collaborative tasks, providing a reliable data foundation for subsequent intelligent control, thereby significantly improving the overall efficiency and stability of collaborative task management.

[0019] It's important to explain that the balance parameters include peak-period service response latency, average interface adaptation cycle, and the number of heterogeneous interfaces associated with the task for adaptation. Peak-period service response latency refers to the total time from receiving a user request to returning a complete result during high-load periods (such as peak cross-department task synchronization or end-of-month project progress summary). This peak-period service response latency is calculated by embedding monitoring probes in the front-end (e.g., web page, client) or back-end API gateway of the task collaboration platform, directly recording the initiation and completion timestamps of each AI service request, and calculating the difference. Average interface adaptation cycle refers to the time required to complete adaptation of a single heterogeneous interface (such as the Jira interface for project management tools, the ERP interface for business systems, or the interface for third-party collaboration) to meet the task collaboration requirements. The average development time for adapting to the Lark interface (same as the tool); the "requirement confirmation start time" and "online acceptance completion time" of each interface adaptation task are extracted through the project management tool, the interval between the two time points is calculated, and after statistical period for each interface task, the arithmetic mean of all adaptation tasks is calculated to obtain the average interface adaptation period; the number of heterogeneous interface adaptations associated with the matter refers to the total number of heterogeneous interfaces that need to be adapted with external systems (such as business systems, collaboration tools, etc.) to ensure the normal progress of a single or a type of collaborative matter (such as supply chain emergency collaborative matters); the number of heterogeneous interface adaptations associated with the matter is obtained through the API gateway management platform.

[0020] The response latency impact value is obtained by correcting the results of the analysis of the response latency reference value and the proportion of service response latency during peak periods using a response latency compensation factor; the adaptation cycle impact value is obtained by correcting the results of the analysis of the adaptation cycle reference value and the proportion of average interface adaptation cycles using an adaptation cycle compensation factor; and the adaptation quantity impact value is obtained by correcting the results of the analysis of the adaptation quantity reference value and the proportion of adaptation quantity of heterogeneous interfaces associated with items using an adaptation quantity compensation factor. The response latency impact value, adaptation cycle impact value, and adaptation quantity impact value are coupled to obtain the collaborative adaptation efficiency-resource scheduling balance. The constraint expression for the collaborative adaptation efficiency-resource scheduling balance is as follows: ; In the formula, S represents the collaborative adaptation efficiency-resource scheduling balance; c1 represents the response delay compensation factor obtained from the item collaborative management database; c2 represents the adaptation cycle compensation factor obtained from the item collaborative management database; c3 represents the adaptation quantity compensation factor obtained from the item collaborative management database; F0 represents the response delay reference value obtained from the item collaborative management database; P0 represents the adaptation cycle reference value obtained from the item collaborative management database; Q0 represents the adaptation quantity reference value obtained from the item collaborative management database; F represents the peak service response delay; P represents the average interface adaptation cycle; and Q represents the number of heterogeneous interfaces associated with the item for adaptation.

[0021] It's important to understand that the more heterogeneous interfaces a task is adapted to, including more complex interfaces (such as SOAP protocol interfaces and financial interfaces requiring customized encryption), the longer the protocol analysis and code development time becomes. Furthermore, when multiple interfaces run in parallel, the more complex interfaces tend to become "bottleneck tasks," slowing down the overall average cycle time and resulting in a longer average interface adaptation cycle. The more heterogeneous interfaces a task is adapted to, the greater the number of interface connections and data cache that need to be maintained simultaneously during peak periods. This leads to a higher proportion of server CPU, memory, and bandwidth resources being consumed, resulting in longer service response latency during peak periods. A longer average interface adaptation cycle also leads to "hidden defects" in the adapted interfaces (such as abnormal data parsing or weak concurrent processing capabilities). Under high-concurrency requests during peak periods, these hidden defects will be exposed (such as frequent "data timeout returns" or "connection interruptions"), forcing the system to trigger a "retry mechanism," increasing data interaction time and further increasing service response latency during peak periods. Meanwhile, there is a negative correlation between peak-period service response latency and collaborative adaptation efficiency-resource scheduling balance. Higher peak-period service response latency is often due to mismatch between computing resources and request load, resulting in a lower peak-period critical AI function latency compliance rate and a smaller collaborative adaptation efficiency-resource scheduling balance. Similarly, there is a negative correlation between average interface adaptation cycle and collaborative adaptation efficiency-resource scheduling balance. A higher average interface adaptation cycle is often due to low interface adaptation efficiency (e.g., complex protocol parsing, low reuse rate, frequent requirement changes), resulting in a lower integration cycle compliance rate and a smaller collaborative adaptation efficiency-resource scheduling balance. Furthermore, there is a negative correlation between the number of heterogeneous interfaces associated with a task and collaborative adaptation efficiency-resource scheduling balance. A greater number of heterogeneous interfaces associated with a task require simultaneous protocol analysis, development, and testing of more interfaces, leading to a longer "integration cycle" in "system integration adaptation efficiency" and a smaller collaborative adaptation efficiency-resource scheduling balance.

[0022] As the second step of an AI-based collaborative management method, S2 determines whether to perform intelligent adjustment of the efficiency-balance of the collaborative adaptation efficiency and resource scheduling. If yes, the collaborative decision-making process is executed after the intelligent adjustment of the efficiency-balance. If no, the collaborative decision-making process is executed directly. The intelligent adjustment of the efficiency-balance includes adaptive adjustment of the transmission volume threshold and adaptive adjustment of the interaction frequency.

[0023] It should be noted that by establishing an intelligent judgment mechanism based on collaborative adaptation efficiency and resource scheduling balance, dynamic optimization and control of the collaborative process are achieved. When the system detects that the collaborative efficiency is not up to standard, it automatically triggers intelligent control strategies that include adjusting transmission volume thresholds and optimizing interaction frequency, effectively solving the problems of rigid resource allocation and low data transmission efficiency in traditional collaborative systems. This closed-loop control mechanism not only ensures the system's operational efficiency under normal conditions but also enables timely self-optimization when anomalies occur, significantly improving the adaptive capability and overall operational efficiency of collaborative management.

[0024] Furthermore, the specific process for determining whether to perform intelligent adjustment of efficiency-balance is as follows: If the collaborative adaptation efficiency-resource scheduling balance is greater than or equal to the balance benchmark value, no intelligent adjustment of the adaptation efficiency-balance will be performed. Otherwise, the transmission volume threshold and interaction frequency will be adaptively adjusted based on the balance offset. The balance offset represents the negative difference between the collaborative adaptation efficiency-resource scheduling balance and the balance benchmark value.

[0025] As further explained in detail, the specific process for adaptive adjustment of the transmission volume threshold is as follows: If the concurrent requests for collaborative tasks during peak periods are less than the lower concurrency reference limit, the system is considered idle. The result of arithmetically averaging the balance offset and the concurrency offset, rounded up, is input into the concurrency-transmission threshold mapping table to obtain the transmission threshold adjustment factor. The current task's data transmission threshold is then multiplied by this adjustment factor to obtain the target task's data transmission threshold. The concurrency offset represents the negative difference between the concurrent requests for collaborative tasks during peak periods and the lower concurrency reference limit. This effectively utilizes idle system resources, supporting larger-scale data exchange demands by appropriately increasing the transmission threshold. Specifically, multiplying the current transmission threshold by the adjustment factor maximizes resource utilization during low-load periods, creating favorable conditions for potential large-scale data transmission tasks. This intelligent adjustment mechanism ensures that system resources are fully utilized during idle periods, avoiding the waste of computing and bandwidth resources.

[0026] If the concurrent requests for collaborative tasks during peak periods are within the reference range, the system is considered to be in a normal state, and no adaptive adjustment of the transmission threshold is performed. The reference range represents a closed interval formed by the lower and upper limits of the reference range. This avoids performance fluctuations that may result from unnecessary configuration adjustments. By setting a reasonable reference range, the system can maintain optimal performance under normal operating conditions, preventing resource strain due to excessively high thresholds and limiting normal data transmission needs due to excessively low thresholds.

[0027] Adaptive adjustment of transmission volume threshold also includes: If the concurrent requests for collaborative tasks during peak periods exceed the reference concurrency limit, indicating a peak state, the arithmetic average of the balance offset and the concurrency correction, rounded down, is input into the concurrency-transmission threshold mapping table to obtain the transmission threshold reduction factor. The current task's data transmission threshold is then multiplied by this reduction factor to obtain the target task's data transmission threshold. The concurrency correction represents the positive difference between the concurrent collaborative requests for collaborative tasks during peak periods and the reference concurrency limit. Under high load pressure, appropriately lowering the transmission threshold ensures the stable operation of core services. When the system detects that the concurrency exceeds the safety threshold, it automatically limits the data transmission scale of a single request, effectively preventing system overload and ensuring the availability of critical business functions. This protective reduction strategy significantly enhances the system's resilience and fault prevention capabilities.

[0028] In this embodiment, through intelligent querying and dynamic adjustment of the concurrency-transmission threshold mapping table, precise matching between transmission thresholds and the real-time load status of the system is achieved. This solution not only solves the problem of rigid resource allocation in traditional systems but also establishes an adaptive optimization system based on actual operating conditions, enabling the system to automatically maintain optimal operating status under different load conditions, greatly improving the intelligence level and operational efficiency of collaborative task management.

[0029] As further explained in detail, the specific process for adaptive adjustment of interaction frequency is as follows: If the frequency of changes to the collaborative request interface is less than the critical lower limit, the system switches to silent mode. Specifically, the balance offset and change frequency offset are retrieved from the change frequency-interaction frequency mapping table to obtain the interaction frequency reduction amount. The difference between the current task stage data interaction frequency and the interaction frequency reduction amount is rounded up to become the target task stage data interaction frequency. The change frequency offset represents the negative difference between the frequency of changes to the collaborative request interface and the critical lower limit. This effectively reduces system communication overhead during periods of slow demand change, minimizes unnecessary data synchronization and status reports, and allows the collaborative team to focus on the in-depth execution of the current task. By intelligently reducing the interaction frequency, the system significantly reduces resource consumption and improves operational economy while ensuring the flow of core information.

[0030] The frequency of interaction is adaptively adjusted, and it also includes: If the frequency of interface changes for collaborative requests falls within the critical range, no adaptive adjustment of the interaction frequency will be performed. The critical range refers to the closed interval formed by the lower and upper critical limits of the change frequency. This avoids system fluctuations caused by frequent adjustments and ensures optimal collaboration within the scope of normal business changes. By setting reasonable critical ranges, the system provides a stable operating environment for routine business activities, ensuring both the necessary timeliness of information synchronization and avoiding excessive communication from interfering with work efficiency.

[0031] If the frequency of changes to the collaborative request interface exceeds the critical upper limit, the system switches to high-frequency synchronization mode. Specifically, the balance offset and change frequency correction are retrieved from the change frequency-interaction frequency mapping table to obtain the interaction frequency increase. The current event stage data interaction frequency is coupled with the interaction frequency increase, and the result is rounded down to the target event stage data interaction frequency. The change frequency correction represents the positive difference between the change frequency of the collaborative request interface and the critical upper limit. During periods of rapid business change, increasing the data interaction frequency ensures that all collaborating parties can obtain the latest information in a timely manner, effectively avoiding decision-making errors and collaboration gaps caused by information lag. High-frequency synchronization mode significantly enhances the system's agility and responsiveness, providing reliable collaborative support for rapidly iterating business environments.

[0032] In this embodiment, a precise correspondence between changes in business requirements and system interaction frequencies is established through intelligent querying and dynamic adjustment of the change frequency-interaction frequency mapping table. This solution not only solves the problem of rigid interaction frequency configuration in traditional collaborative systems, but also constructs a flexible interaction system based on actual business needs. This enables the system to intelligently adapt to the business characteristics at different stages, optimize resource utilization efficiency while ensuring collaboration quality, and comprehensively improve the intelligence level of collaborative management.

[0033] The third step of this AI-based collaborative management method involves acquiring response efficiency parameters in the collaborative decision-making process. Based on these parameters, the reliability of collaborative decisions and dynamic response efficiency are obtained. These parameters are used to quantify the reliability of AI decisions in cross-industry scenarios and the response speed of replanning tasks and resources when faced with sudden changes. The system determines whether to implement intelligent dynamic response efficiency control based on the reliability of collaborative decisions and the dynamic response efficiency. If so, a collaborative decision-making scheme is output after intelligent dynamic response efficiency control; otherwise, the scheme is output directly. Intelligent dynamic response efficiency control includes adaptive control of the change recognition window and adaptive control of the iteration update frequency.

[0034] It's worth noting that by constructing a quantitative indicator system for "reliability of collaborative decision-making and efficiency of dynamic response," precise evaluation and closed-loop optimization of AI decision-making quality and response speed have been achieved. This mechanism effectively quantifies the decision-making reliability of the AI ​​system in cross-industry scenarios and its ability to respond to sudden changes. When substandard performance is detected, intelligent control strategies, including adjustments to the change recognition window and optimization of iteration update frequency, are automatically triggered. This design significantly improves the decision-making accuracy and responsiveness of the collaborative system in complex and ever-changing environments, ensuring that the final output decision solution is both cross-domain adaptable and meets the business needs of real-time dynamic adjustments, fundamentally enhancing the intelligence level and practical value of AI collaborative management.

[0035] It needs to be explained that the response efficiency parameters include the comparison-to-be-compared collaborative adaptation efficiency - resource scheduling balance, the time taken to adjust for sudden changes in the matter, and the response time for the reallocation of resources in the matter management system. Specifically, the comparison-to-be-compared collaborative adaptation efficiency - resource scheduling balance refers to the newly acquired collaborative adaptation efficiency - resource scheduling balance recorded as the comparison-to-be-compared collaborative adaptation efficiency - resource scheduling balance if intelligent adjustment of adaptation efficiency - balance has been performed; otherwise, the current collaborative adaptation efficiency - resource scheduling balance is recorded as the comparison-to-be-compared collaborative adaptation efficiency - resource scheduling balance. The time taken to adjust for sudden changes in the matter refers to the complete time span from the initial discovery of a sudden change in the matter's progress (such as the departure of a core member, equipment failure, urgent adjustments to customer needs, etc., unforeseen events that affect the normal progress of the matter) to the output of an executable new decision plan (such as reassigning a responsible person, adjusting task assignments, switching to backup equipment, etc.). The "sudden change" marker is extracted from the logs of the matter collaboration management system. The corresponding records are used to locate the "first mark change time" (the starting point of change identification) and the "time when the plan status changes to 'confirmed'" (the end point of plan output). The time difference between the two is calculated to obtain the time consumed for adjusting sudden changes in the matter. The response time of resource reallocation in matter management refers to the total time consumed from initiating a resource adjustment request to the actual arrival of resources and updating the matter decision plan when resources need to be adjusted due to sudden changes in the matter (such as equipment failure, personnel departure) or schedule deviations (such as a task being delayed, resulting in idle resources). The "resource adjustment request creation time" (the starting point of request initiation) and the "time when the resource status changes to 'allocated to matter'" (the end point of resource arrival) are extracted from the resource scheduling system logs. The time difference between the two is calculated to obtain the response time of resource reallocation in matter management.

[0036] The balance degree compensation factor is used to correct the results of the analysis of the ratio of the balance degree to the resource scheduling balance degree and the balance degree reference value in the collaborative adaptation efficiency of the comparison, thus obtaining the balance degree impact value. The adjustment time compensation factor is used to correct the results of the analysis of the adjustment time reference value and the proportion of adjustment time for sudden changes in matters, thus obtaining the adjustment time impact value. The response time compensation factor is used to correct the results of the analysis of the response time reference value and the proportion of response time for the reallocation of resources in matter management, thus obtaining the response time impact value. The balance degree impact value, adjustment time impact value, and response time impact value are coupled to obtain the collaborative decision reliability and dynamic response efficiency. The specific constraint expressions for collaborative decision reliability and dynamic response efficiency are as follows: ; In the formula, R represents the reliability of collaborative decision-making and the efficiency of dynamic response; n1 represents the balance compensation factor obtained from the collaborative management database; n2 represents the adjustment time compensation factor obtained from the collaborative management database; n3 represents the response time compensation factor obtained from the collaborative management database; E0 represents the balance reference value obtained from the collaborative management database; M0 represents the adjustment time reference value obtained from the collaborative management database; X0 represents the response time reference value obtained from the collaborative management database; E represents the collaborative adaptation efficiency to be compared - resource scheduling balance; M represents the adjustment time for sudden changes in the matter; and X represents the response time of the resource reallocation for the matter management.

[0037] It should be noted that the higher the efficiency of collaborative adaptation and resource scheduling balance, the more complete the heterogeneous interface adaptation (such as seamless integration with ERP, HR, and task management system interfaces), and the more timely the data synchronization (such as real-time updates of employee skill data and task lists). When sudden changes occur (such as the departure of core members), there is no need to manually retrieve data across systems; the required information (such as the tasks the member is responsible for and the skill matching degree of backup personnel) can be quickly obtained directly through the adaptation interface, reducing the time spent on data preparation and the time spent on adjusting sudden changes. The higher the efficiency of collaborative adaptation and resource scheduling balance, the more timely the resource status data is synchronized to the task collaboration platform. When a resource reallocation request is initiated (such as allocating allocated equipment), the real-time inventory of resources (such as whether there is available equipment in the warehouse and the location of the equipment) can be viewed directly through the platform, without the need for manual telephone confirmation, reducing the time spent on resource availability confirmation and lowering the response time of task management resource reallocation. The longer the time spent on adjusting sudden changes means that when sudden changes occur (such as the departure of core members), the manual retrieval of data across systems is prolonged, and the response time of task management resource reallocation is longer. Meanwhile, the efficiency of collaborative adaptation – resource scheduling balance – is positively correlated with the reliability of collaborative decision-making and dynamic response efficiency. The higher the efficiency of collaborative adaptation – resource scheduling balance, the more complete the core data required for decision-making (such as task progress, remaining resources, and cross-departmental dependencies) can be obtained through the adaptation interface, avoiding decision-making bias due to data gaps, and thus increasing the reliability of collaborative decision-making and dynamic response efficiency. The time spent on sudden changes and adjustments to matters is negatively correlated with the reliability of collaborative decision-making and dynamic response efficiency. The longer the time spent on sudden changes and adjustments to matters, the longer the data preparation time, and the lower the reliability of collaborative decision-making and dynamic response efficiency. The response time of resource reallocation for matters is also negatively correlated with the reliability of collaborative decision-making and dynamic response efficiency. The longer the response time of resource reallocation for matters, the longer the response time becomes when resources need to be reallocated due to sudden changes (such as equipment failure), and the lower the reliability of collaborative decision-making and dynamic response efficiency.

[0038] Furthermore, the specific steps for determining whether to perform intelligent dynamic response efficiency control are as follows: if the collaborative decision reliability and dynamic response efficiency are greater than or equal to the response efficiency benchmark value, then intelligent dynamic response efficiency control is not performed; otherwise, adaptive control of the change identification window and adaptive control of the iteration update frequency are performed based on the response efficiency offset. The response efficiency offset represents the negative difference between the collaborative decision reliability and dynamic response efficiency and the response efficiency benchmark value.

[0039] It is necessary to understand that, such as Figure 2The diagram shown is a flowchart of the adaptive adjustment process of the change identification window in an artificial intelligence-based collaborative management method for matters provided in this application embodiment. The specific logic is as follows: if the real-time data access delay of a matter is lower than or equal to the access delay reference value, no adaptive adjustment of the change identification window is performed. If the real-time data access delay of a matter is higher than the access delay reference value, the identification window gain factor is obtained by querying the access delay-identification window mapping table based on the response efficiency offset and the access delay correction amount. The identification window gain factor is multiplied by the current matter change identification window to obtain the target value of the matter change identification window.

[0040] As further detailed, the specific process for adaptive adjustment of the change recognition window is as follows: If the real-time data access latency for a given item is lower than or equal to the access latency reference value, no adaptive adjustment of the change recognition window will be performed. When the data flow remains smooth and information synchronization is timely, a fixed recognition window can provide a consistent change recognition experience, avoiding fluctuations in the recognition strategy caused by unnecessary configuration adjustments. This design ensures the system's operational stability under normal data synchronization conditions and provides a reliable time-dimensional benchmark for change recognition.

[0041] If the real-time data access latency for a given item exceeds the access latency reference value, the identification window gain factor is obtained by querying the access latency-identification window mapping table based on the response efficiency offset and the access latency correction amount. This identification window gain factor is then multiplied by the current item change identification window to obtain the target value for the item change identification window. The access latency correction amount represents the positive difference between the real-time data access latency and the access latency reference value. When data synchronization is delayed, the identification window is appropriately extended to compensate for the time difference in information transmission, effectively preventing missed change detections due to incomplete data arrival. The intelligent expansion of the window ensures that even under conditions of poor data flow, the system can still accurately identify changes based on more complete time-series data, significantly improving the system's robustness and decision reliability under abnormal operating conditions.

[0042] In this embodiment, a dynamic matching relationship between data timeliness and recognition sensitivity is established by intelligently querying the access delay-recognition window mapping table. This design not only solves the problem of insufficient adaptability caused by the fixed recognition window in traditional systems, but also constructs an elastic recognition system based on the health status of the data flow, enabling the change recognition mechanism to adapt to different data environments and maintain optimal system performance while ensuring recognition accuracy.

[0043] It is necessary to understand that, such as Figure 3The diagram shows an iterative update frequency adaptive adjustment flowchart of an AI-based collaborative management method for items provided in this application. The specific logic is as follows: If the item requirement change delay is lower than or equal to the change delay reference value, no iterative update frequency adaptive adjustment is performed. If the item requirement change delay is higher than the change delay reference value, the response efficiency offset and change delay correction are input into the change delay-update frequency mapping table for querying to obtain the update frequency adjustment factor. It is then determined whether the update frequency adjustment factor is greater than the update frequency adjustment threshold. If so, the frequency adjustment offset is input into the change delay-update frequency mapping table for querying to obtain the update frequency reduction factor. The update frequency reduction factor is multiplied by the current item collaborative decision-making scheme iterative update frequency to obtain the target item collaborative decision-making scheme iterative update frequency. If not, the frequency adjustment correction is input into the change delay-update frequency mapping table for querying to obtain the update frequency increase factor. The update frequency increase factor is multiplied by the current item collaborative decision-making scheme iterative update frequency to obtain the target item collaborative decision-making scheme iterative update frequency.

[0044] As a further explanation, the specific process of iterative frequency adaptive control is as follows: If the delay for a change in requirements is less than or equal to a reference value, no adaptive adjustment of the iteration update frequency will be performed. This reflects the principle of "not interfering with normal operations." When the requirement change process is smooth and decision-making information can be obtained in a timely manner, a fixed iteration rhythm can provide the collaborative team with a stable work cycle, avoiding planning chaos caused by frequent adjustments. This maintenance mechanism ensures that the team can advance its work according to the established rhythm under normal business conditions, maintaining the stability and predictability of the collaborative process.

[0045] If the delay for changing the requirement is higher than the reference value for the delay, the response efficiency offset and the delay correction amount are entered into the delay-update frequency mapping table for querying to obtain the update frequency adjustment factor. It is then determined whether the update frequency adjustment factor is greater than the update frequency adjustment threshold. The delay correction amount represents the positive difference between the delay for changing the requirement and the reference value for the delay.

[0046] If so, the frequency adjustment offset is input into the change delay-update frequency mapping table for querying, obtaining the update frequency reduction factor. This reduction factor is then multiplied by the current collaborative decision-making scheme iteration update frequency to obtain the target collaborative decision-making scheme iteration update frequency. The frequency adjustment offset represents the positive difference between the update frequency adjustment factor and the update frequency adjustment threshold. Precise control is achieved through a two-layer judgment mechanism. First, the system obtains the update frequency adjustment factor from the mapping table based on the response efficiency offset and change delay correction amount. This design comprehensively considers system performance and business latency. The subsequent threshold judgment mechanism reflects the refined management philosophy of control: when the adjustment factor exceeds the threshold, it indicates a serious blockage in the change process, and the system reduces the iteration frequency by querying the reduction factor. This conservative strategy effectively avoids ineffective decisions based on incomplete information, reduces resource waste and decision turbulence, and ensures the team focuses its efforts on clearly defined tasks.

[0047] If not, the frequency adjustment correction amount is input into the change delay-update frequency mapping table for querying to obtain the update frequency adjustment factor. This adjustment factor is then multiplied by the current collaborative decision-making scheme iteration update frequency to obtain the target collaborative decision-making scheme iteration update frequency. The frequency adjustment correction amount represents the negative difference between the update frequency adjustment factor and the update frequency adjustment threshold. The iteration frequency is increased by querying the adjustment factor. This proactive strategy maintains sufficient decision-making agility in a low-latency environment, adapting to continuously flowing new demands through more frequent scheme adjustments. This two-way control mechanism prevents blind iteration during severe congestion while ensuring timely response during low-latency periods, demonstrating the maturity of the system's intelligent management.

[0048] In this embodiment, an intelligent correlation between business change efficiency and decision iteration frequency is established through cascading queries of the change latency-update frequency mapping table. This solution effectively solves the problem of the iteration frequency being out of sync with the actual situation in traditional systems, and constructs a flexible iteration system based on the health status of business flows. This allows the decision update rhythm to adapt to different business process states, optimizing resource utilization efficiency while ensuring decision quality.

[0049] like Figure 4The diagram shown is a structural schematic of an AI-based collaborative management system provided in this application embodiment, including: a balance quantification module, a collaborative scheduling intelligent control module, and a response efficiency intelligent control module. The balance quantification module is used to identify the business interfaces required for collaborative tasks, obtain balance parameters, and obtain the collaborative adaptation efficiency-resource scheduling balance based on the balance parameters. This balance is used to quantify the adaptation efficiency and resource scheduling balance among collaborative tasks in collaborative task management. The collaborative scheduling intelligent control module is used to determine whether to perform intelligent control based on the collaborative adaptation efficiency-resource scheduling balance. If yes, the collaborative task decision-making process is executed after intelligent control; otherwise, the collaborative task decision-making process is executed directly. The system includes intelligent adjustment of efficiency and balance, which includes adaptive adjustment of transmission volume threshold and adaptive adjustment of interaction frequency. The intelligent response efficiency adjustment module is used to obtain response efficiency parameters in the collaborative decision-making process. Based on the response efficiency parameters, it obtains the reliability of collaborative decision-making and dynamic response efficiency. This is used to quantify the reliability of AI decision-making in cross-industry scenarios and the response speed of replanning tasks and resources when facing sudden changes in matters. Based on the reliability of collaborative decision-making and dynamic response efficiency, it determines whether to perform intelligent dynamic response efficiency adjustment. If so, it outputs the collaborative decision-making scheme after intelligent dynamic response efficiency adjustment; otherwise, it directly outputs the collaborative decision-making scheme. Intelligent dynamic response efficiency adjustment includes adaptive adjustment of change recognition window and adaptive adjustment of iteration update frequency.

[0050] In this embodiment, a complete intelligent closed-loop optimization system for collaborative task management is established by constructing three core modules: balanced quantification, intelligent control of collaborative scheduling, and intelligent control of response efficiency. The balanced quantification module accurately measures the system's adaptability and the balance of resource scheduling, providing a reliable data foundation for intelligent decision-making. The intelligent control of collaborative scheduling dynamically adjusts transmission thresholds and interaction frequencies based on quantification results, effectively solving the resource allocation optimization problem in cross-system collaboration. The intelligent control of response efficiency significantly improves the reliability of AI decision-making in cross-industry scenarios and its responsiveness to sudden changes through adaptive control of change recognition windows and iteration frequencies. The organic whole formed by these three modules achieves end-to-end optimization from system resource scheduling to intelligent decision output, completely changing the outdated model of traditional collaborative management that relies on manual experience configuration, and significantly improving the intelligence level, system stability, and business adaptability of collaborative task management.

[0051] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the above functions can be divided into different functional modules to complete all or part of the functions described above.

[0052] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0053] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units, located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0054] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0055] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to the solution, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0056] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A collaborative task management method based on artificial intelligence, characterized in that, Includes the following steps: S1, by identifying the business interfaces required for task collaboration, obtains the balance parameter, and based on the balance parameter, obtains the collaboration adaptation efficiency-resource scheduling balance, which is used to quantify the adaptation efficiency between task collaborations and the degree of balance in resource scheduling in task collaboration management. S2, determine whether to perform intelligent adjustment of adaptation efficiency-balance based on the collaborative adaptation efficiency-resource scheduling balance. If yes, then execute the collaborative decision-making step after the intelligent adjustment of adaptation efficiency-balance. If no, then directly execute the collaborative decision-making step. The intelligent adjustment of adaptation efficiency-balance includes adaptive adjustment of transmission volume threshold and adaptive adjustment of interaction frequency. S3. Obtain response efficiency parameters in the collaborative decision-making process. Based on the response efficiency parameters, obtain the reliability of collaborative decision-making and dynamic response efficiency. Used to quantify the reliability of AI decision-making in cross-industry scenarios and the response speed of replanning tasks and resources when facing sudden changes in matters. Determine whether to perform intelligent adjustment of dynamic response efficiency based on the reliability of collaborative decision-making and dynamic response efficiency. If yes, output the collaborative decision-making scheme after intelligent adjustment of dynamic response efficiency. If no, directly output the collaborative decision-making scheme. The intelligent adjustment of dynamic response efficiency includes adaptive adjustment of change recognition window and adaptive adjustment of iteration update frequency.

2. The collaborative management method for tasks based on artificial intelligence as described in claim 1, characterized in that, The balance parameters include peak service response latency, average interface adaptation cycle, and the number of heterogeneous interfaces associated with events for adaptation. The response delay impact value is obtained by correcting the response delay reference value and the peak service response delay ratio analysis results by using a response delay compensation factor. The results of the analysis of the adaptation cycle reference value and the average interface adaptation cycle ratio are corrected by the adaptation cycle compensation factor to obtain the adaptation cycle impact value. The results of the analysis of the proportion of adaptation quantity of heterogeneous interface adaptation quantity related to the item are corrected by the adaptation quantity compensation factor to obtain the adaptation quantity impact value. By coupling the impact values ​​of response latency, adaptation cycle, and number of adaptations, we obtain the collaborative adaptation efficiency-resource scheduling balance. The specific process for determining whether to perform intelligent adjustment of adaptation efficiency-balance is as follows: If the collaborative adaptation efficiency-resource scheduling balance is greater than or equal to the balance benchmark value, no intelligent adjustment of the adaptation efficiency-balance will be performed. Otherwise, the transmission volume threshold and interaction frequency will be adaptively adjusted based on the balance offset. The balance offset represents the degree of negative deviation between the collaborative adaptation efficiency-resource scheduling balance and the balance benchmark value.

3. The collaborative management method for tasks based on artificial intelligence as described in claim 2, characterized in that, The specific process for adaptively adjusting the transmission volume threshold is as follows: If the concurrent requests for collaborative tasks during peak periods are less than the lower limit of the concurrency reference, it is determined to be in an idle state. Then, the result of the arithmetic average of the balance offset and the concurrency offset, rounded up, is input into the concurrency-transmission threshold mapping table to obtain the transmission threshold adjustment factor. The current task's data transmission threshold and the transmission threshold adjustment factor are multiplied to obtain the target task's data transmission threshold. The concurrency offset represents the degree of negative deviation between the concurrent requests for collaborative tasks during peak periods and the lower limit of the concurrency reference. If the concurrent requests for collaborative tasks during peak periods are within the concurrency reference range, it is determined to be in a normal state, and no adaptive adjustment of the transmission volume threshold is performed. The concurrency reference range refers to the closed interval formed by the lower limit of the concurrency reference and the upper limit of the concurrency reference.

4. The collaborative management method for tasks based on artificial intelligence as described in claim 3, characterized in that, The adaptive adjustment of the transmission volume threshold also includes: If the concurrent requests for collaborative tasks during peak periods exceed the reference upper limit of concurrency, it is determined to be in a peak state. Then, the result of the arithmetic average of the balance offset and the concurrency correction is rounded down and input into the concurrency-transmission threshold mapping table to obtain the transmission threshold adjustment factor. The current data transmission threshold and the transmission threshold adjustment factor are multiplied to obtain the target data transmission threshold. The concurrency correction represents the degree of positive deviation between the concurrent requests for collaborative tasks during peak periods and the reference upper limit of concurrency.

5. The collaborative management method for tasks based on artificial intelligence as described in claim 2, characterized in that, The specific process for adaptive adjustment of interaction frequency is as follows: If the frequency of changes to the collaborative requirement interface is less than the critical lower limit of the change frequency, the system switches to silent mode. Specifically, the balance offset and the change frequency offset are queried from the change frequency-interaction frequency mapping table to obtain the interaction frequency reduction amount. The difference between the current event stage data interaction frequency and the interaction frequency reduction amount is rounded up to obtain the target event stage data interaction frequency. The change frequency offset represents the degree of negative deviation between the change frequency of the collaborative requirement interface and the critical lower limit of the change frequency.

6. The collaborative management method for tasks based on artificial intelligence as described in claim 5, characterized in that, The adaptive adjustment of interaction frequency also includes: If the frequency of changes to the collaborative request interface is within the critical interval of the change frequency, no adaptive adjustment of the interaction frequency will be performed. The critical interval of the change frequency refers to the closed interval formed by the lower critical limit and the upper critical limit of the change frequency. If the frequency of changes to the collaborative requirement interface for a matter exceeds the critical upper limit of the change frequency, the system switches to a high-frequency synchronization mode. Specifically, the balance offset and the change frequency correction are queried from the change frequency-interaction frequency mapping table to obtain the interaction frequency increase. The current data interaction frequency of the matter stage is coupled with the interaction frequency increase, and the result is rounded down to the target data interaction frequency of the matter stage. The change frequency correction represents the degree of positive deviation between the change frequency of the collaborative requirement interface for a matter and the critical upper limit of the change frequency.

7. The collaborative management method for tasks based on artificial intelligence as described in claim 1, characterized in that, The response efficiency parameters include the collaborative adaptation efficiency to be compared - resource scheduling balance, the time consumed for adjusting sudden changes in matters, and the response time of resource reallocation for matters management. The balance compensation factor is used to correct the results of the analysis of the ratio of the collaborative adaptation efficiency-resource scheduling balance of the comparison pair to the balance reference value, so as to obtain the balance influence value. By adjusting the time compensation factor, the results of the analysis of the proportion of adjustment time to the reference value of adjustment time and the adjustment time of sudden changes in the matter are corrected to obtain the impact value of adjustment time. By correcting the response time reference value and the result of the response time ratio analysis of the reallocation of task management resources by the response time compensation factor, the impact value of response time is obtained. By coupling the impact values ​​of balance degree, adjustment time, and response time, we can obtain the reliability of collaborative decision-making and the efficiency of dynamic response. The specific steps for determining whether to perform dynamic response efficiency intelligent control are as follows: If the reliability of collaborative decision-making and the dynamic response efficiency are greater than or equal to the baseline value of response efficiency, then no intelligent adjustment of dynamic response efficiency will be performed. Otherwise, adaptive adjustment of change identification window and adaptive adjustment of iteration update frequency will be performed based on response efficiency offset. The response efficiency offset represents the degree of negative deviation between the reliability of collaborative decision-making and the dynamic response efficiency and the baseline value of response efficiency.

8. The collaborative management method for tasks based on artificial intelligence as described in claim 7, characterized in that, The specific process for adaptive adjustment of the change recognition window is as follows: If the real-time data access delay for a given item is lower than or equal to the access delay reference value, no adaptive adjustment of the change recognition window will be performed. If the real-time data access delay of an item is higher than the access delay reference value, the identification window gain factor is obtained by querying the access delay-identification window mapping table based on the response efficiency offset and the access delay correction amount. The identification window gain factor is multiplied by the current item change identification window to obtain the target value of the item change identification window. The access delay correction amount represents the degree of positive deviation between the real-time data access delay of the item and the access delay reference value.

9. The collaborative management method for tasks based on artificial intelligence as described in claim 7, characterized in that, The specific process for adaptive adjustment of the iterative update frequency is as follows: If the delay for changing the requirements of a matter is lower than or equal to the reference value for the delay, then no adaptive adjustment of the iteration update frequency will be performed. If the delay of the change of the requirement is higher than the reference value of the change delay, the response efficiency offset and the change delay correction amount are input into the change delay-update frequency mapping table for querying to obtain the update frequency adjustment factor. It is then determined whether the update frequency adjustment factor is greater than the update frequency adjustment threshold. The change delay correction amount represents the degree of positive deviation between the change delay of the requirement and the reference value of the change delay. If so, the frequency adjustment offset is input into the change delay-update frequency mapping table for querying to obtain the update frequency reduction factor. The update frequency reduction factor is then multiplied by the current collaborative decision-making scheme iteration update frequency to obtain the target collaborative decision-making scheme iteration update frequency. The frequency adjustment offset represents the degree of positive deviation between the update frequency adjustment factor and the update frequency adjustment threshold. If not, the frequency adjustment correction amount is input into the change delay-update frequency mapping table for querying to obtain the update frequency increase factor. The update frequency increase factor is then multiplied by the current collaborative decision-making scheme iteration update frequency to obtain the target collaborative decision-making scheme iteration update frequency. The frequency adjustment correction amount represents the degree of negative deviation between the update frequency adjustment factor and the update frequency adjustment threshold.

10. A system applying the AI-based collaborative management method for tasks as described in any one of claims 1-9, comprising a balanced quantification module, a collaborative scheduling intelligent control module, and a response efficiency intelligent control module: in, The measurement module is used to obtain the balance parameter by identifying the business interface required for task collaboration, and obtain the collaboration adaptation efficiency-resource scheduling balance based on the balance parameter. This is used to quantify the adaptation efficiency between task collaborations and the balance in resource scheduling during task collaboration management. The intelligent control module for collaborative scheduling is used to determine whether to perform intelligent control of adaptation efficiency-balance based on the collaborative adaptation efficiency-resource scheduling balance. If yes, the collaborative decision-making process is executed after the intelligent control of adaptation efficiency-balance. If no, the collaborative decision-making process is executed directly. The intelligent control of adaptation efficiency-balance includes adaptive adjustment of transmission volume threshold and adaptive adjustment of interaction frequency. The intelligent response efficiency control module is used to acquire response efficiency parameters in the collaborative decision-making process, and obtain the reliability of collaborative decision-making and dynamic response efficiency based on the response efficiency parameters. It is used to quantify the reliability of AI decision-making in cross-industry scenarios and the response speed of replanning tasks and resources when facing sudden changes in matters during collaborative management. Based on the reliability of collaborative decision-making and dynamic response efficiency, it determines whether to perform intelligent dynamic response efficiency control. If so, the collaborative decision-making scheme is output after intelligent dynamic response efficiency control; otherwise, the collaborative decision-making scheme is output directly. The intelligent dynamic response efficiency control includes adaptive control of the change recognition window and adaptive control of the iteration update frequency.

Images