Organization member task assessment management system
By leveraging the synergistic effects of task acquisition, intelligent profiling, relationship mapping, and risk identification modules, the problems of data isolation, delayed evaluation, and insufficient risk identification in existing task management systems have been solved. This enables real-time perception and intelligent management of the task execution process, thereby improving the precision and efficiency of organizational management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUIZHOU EXPRESSWAY GRP
- Filing Date
- 2025-12-24
- Publication Date
- 2026-04-14
AI Technical Summary
Existing task management systems cannot deeply integrate multi-source data, cannot provide real-time insights into task and member status, offer static and delayed evaluations, and lack risk identification and intelligent decision support, resulting in high management costs and low efficiency.
Design an organizational member task performance evaluation and management system, including a task collection module, an intelligent profiling module, a relationship graph module, a risk identification module, and a personnel adjustment module. By comprehensively collecting task data, constructing a multi-dimensional capability model, generating a visual graph in real time, dynamically assessing risks, and providing intelligent adjustment suggestions.
It enables real-time perception of the task execution process, dynamic evaluation of members' capabilities, and quantitative early warning of potential risks, thereby improving the level of management refinement and intelligence and optimizing human resource allocation.
Smart Images
Figure CN121860484A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of task management technology, and more specifically to an organizational member task assessment and management system. Background Technology
[0002] In today's organizations, including enterprises, government agencies, public institutions, and large teams, task allocation, execution tracking, and final performance evaluation are core management activities for maintaining organizational effectiveness and driving goal achievement. With the expansion of organizational scale and the increase in business complexity, task management has evolved from simple instruction and result acceptance to a complex and dynamic process involving multiple parallel tasks, multi-member collaboration, and multi-dimensional evaluation. Traditional management models heavily rely on the personal experience of managers at all levels, frequent meetings, and manually compiled reports, resulting in high management costs and difficulty in achieving timeliness, comprehensiveness, and objectivity. To address this challenge, various task management or performance appraisal software systems have emerged and are widely used. These existing technological solutions typically aim to improve management efficiency through digital means, and their common forms include project management systems, task modules in collaborative office platforms, and standalone performance appraisal software.
[0003] Existing technological solutions generally focus on digitizing task workflows. A typical approach is to provide a platform for assigning tasks, setting deadlines, uploading attachments, and updating progress. Managers can create tasks and assign them to specific members, who then provide progress feedback by updating task status, submitting documents, or filling out logs. Regarding performance evaluation, many systems support manual scoring or evaluation by superiors or relevant personnel after task completion. Some more advanced systems also incorporate simple statistical functions, such as calculating task completion rates, tracking delays, and generating basic reports or charts for review. These methods, to some extent, achieve centralized storage of task information and visualization of processes, reducing the burden on managers in information collection and organization.
[0004] However, in-depth analysis reveals that existing technological solutions still have a series of significant problems and limitations in addressing the core needs of complex organizational dynamic task performance management. Firstly, at the data level, the data collected by the systems is often relatively singular and superficial. Most systems can only effectively record the "status points" of task progress, such as "not started," "in progress," and "completed," as well as the final result document, but they fail to capture the large amount of valuable "process data" generated during task execution. For example, in-depth collaborative data such as cross-departmental communication, interactive details of solution discussions, and the iterative revision process of documents during task completion are usually scattered across different communication tools and file platforms, failing to be effectively linked to the task subject and incorporated into the analysis. This results in a one-sided and static depiction of the task execution process, unable to recreate the true and complex overall picture of the work, and even less able to gain insight into the actual behavioral patterns and collaborative effectiveness of members.
[0005] Secondly, existing technologies for evaluating organizational members exhibit significant static and lagging characteristics. Common evaluation methods rely on manual scoring at the end of a cycle or mechanical calculations based on a limited number of quantitative indicators (such as the number of tasks completed or the number of delays). This approach is essentially a "post-event retrospective," failing to dynamically reflect changes in members' abilities and performance during task execution. Evaluation results are heavily influenced by subjective factors and lack a detailed profile of members' professional strengths, efficiency trends, collaborative contributions, and other multidimensional capabilities. Managers struggle to use such evaluation results to accurately diagnose members' abilities and provide development guidance, nor can they obtain data-driven intelligent suggestions on "who is best suited" when assigning new tasks.
[0006] Furthermore, existing technologies are particularly weak in risk identification and early warning. Most systems can only provide simple reminders based on the final deadline, such as issuing notifications when a task is about to expire. However, they lack effective monitoring and assessment mechanisms for potential schedule deviations, quality risks, and chain reactions that may be triggered by dependencies within the task network during task execution. Systems cannot automatically determine whether a minor delay in a task will become a bottleneck for the entire project, nor can they assess whether the current person in charge has the capacity and workload to handle emerging risks. The lack of or overly simplistic risk warnings often results in reactive and delayed management interventions, with action only taken after problems have escalated, frequently leading to unnecessary losses.
[0007] Finally, in terms of management decision support, particularly dynamic personnel adjustments and resource allocation, existing technologies offer virtually no substantial assistance. When a task faces risks or requires reinforcement, adjustment decisions typically rely entirely on the manager's personal experience and intuition. The system cannot comprehensively consider the professional suitability of candidate members, their current workload, historical performance, and the overall impact of adjustments on the existing task network to provide a scientifically sound personnel recommendation. This makes personnel adjustment decisions highly uncertain, easily leading to new imbalances or adaptation period problems, and fails to fundamentally optimize the organization's human resource allocation through intelligent means. Summary of the Invention
[0008] The technical problem solved by this invention is to provide an organizational member task assessment and management system that can deeply integrate multi-source data, provide real-time insight into task and member status, accurately quantify and assess risks, and provide intelligent decision support.
[0009] The basic solution provided by this invention is: an organizational member task assessment and management system, including a server, wherein the server includes a task acquisition module, an intelligent profiling module, a relationship graph module, a risk identification module, and a personnel adjustment module; The task acquisition module is used to collect task data and task indicators of each member in the organization during the execution of historical tasks. The task data includes task log data reflecting task progress, task document data reflecting work content, and member interaction data reflecting the collaboration process. The task indicators include importance, complexity, and time urgency. The intelligent profiling module is used to determine the capability profile of each member based on task data. The capability profile includes professional field, task efficiency and collaboration ability. The relationship graph module is used to acquire task data of each task in real time. Based on the current task data and task indicators, tasks are regarded as task nodes and members are regarded as member nodes. According to the preset association relationship between each task, member nodes are mapped to task nodes and the member relationship between member nodes is determined. The member relationship includes cooperation relationship and upstream and downstream relationship, thus obtaining the current task-member relationship graph. The risk identification module is used to determine whether there is an execution deviation in each task based on the current task data. When there is an execution deviation, the deviation risk value of the task node is assessed based on the capability profile of the member nodes associated with the task node and other task nodes that are related to the task node. The personnel adjustment module is used to assess whether the task requires personnel adjustments based on the deviation risk value. When adjustments are needed, the adjustment personnel are selected based on the ability profiles of each member.
[0010] The principles and advantages of this invention are as follows: First, the task acquisition module comprehensively collects logs reflecting progress, documents reflecting content and results, and interactive data reflecting the collaboration process, laying the foundation for all subsequent analyses. The intelligent profiling module analyzes this historical and current data to construct a multi-dimensional quantitative capability model for each member, covering their professional field, execution efficiency, and collaboration ability. The relationship graph module utilizes current task data in real time to abstract tasks and members as nodes in a graph, and establishes connecting edges based on the logical relationships between tasks and the collaborative relationships between members, thereby dynamically generating a visual graph reflecting the overall picture of the organization's current work. When the risk identification module discovers an execution deviation in a task by comparing planned and actual data, it does not view the problem in isolation, but immediately calls the relationship graph to find the members associated with the task and other upstream and downstream tasks, and combines the capability profiles of relevant members to comprehensively assess the cascading risk value that the deviation may cause. Finally, the personnel adjustment module determines whether intervention is needed based on this risk value, and if necessary, intelligently recommends the most suitable adjustment candidates based on the capability profiles of all members.
[0011] Compared to existing technologies, the key advantage of this solution lies in breaking through the limitations of traditional performance evaluation management systems, such as isolated data, static evaluation, and delayed response. Traditional systems may only record task completion status or perform simple post-event scoring, failing to dynamically reflect the dependency risks between tasks or provide data-driven, scientific adjustment suggestions when problems arise. This solution, through the collaboration of various modules, achieves real-time perception of the task execution process, dynamic evaluation of member capabilities, quantitative early warning of potential risks, and intelligent allocation of human resources. It elevates performance evaluation management from a post-event evaluation tool to a proactive management tool for in-process optimization and risk control, greatly improving the refinement and intelligence of organizational management.
[0012] Furthermore, the intelligent profiling module includes a professional scoring module, an efficiency scoring module, and a collaborative scoring module; The professional scoring module is used to identify the content of task document data in historical tasks, determine the task classification tags of each historical task, and determine the experience scores of each member in several professional fields based on the task classification tags of the historical tasks completed by each member. The efficiency scoring module is used to identify the completion cycle, target achievement rate, and delay records of each historical task based on the task log data in the historical tasks, and to determine the task efficiency score of each member based on the completion cycle, target achievement rate, and delay records of the historical tasks completed by each member. The collaboration scoring module is used to identify the collaboration efficiency and the quality of task completion of each member based on member interaction data, and to evaluate the collaboration ability score of each member.
[0013] The principle behind the professional evaluation module is that an individual's professional knowledge and experience are primarily reflected in their past work. Therefore, this module uses technologies such as natural language processing to analyze the content of members' historical task documents, automatically identifying the professional field categories to which the tasks belong, and then statistically analyzing the number and type of tasks completed by members in each field, thereby quantifying their professional experience. The principle behind the efficiency evaluation module is that a member's task execution ability is directly reflected in time-related log data. This module analyzes the completion cycle of historical tasks, whether there were delays, and the achievement of key progress nodes. By calculating timeliness indicators such as average delay rate and progress achievement rate, it objectively measures a member's time management ability and execution reliability. The principle behind the collaboration evaluation module is that work in modern organizations cannot be separated from collaboration, and collaboration ability is reflected in the initiative and effectiveness of the interaction process. This module analyzes interaction data generated by emails, instant messaging, collaborative editing platforms, etc., to identify the frequency of members initiating collaborations, the timeliness of responding to others' requests, and the quality of the tasks ultimately achieved through their collaborations, thereby assessing their contribution as a member of the team.
[0014] Furthermore, the professional scoring module determines the member's experience score using the following formula:
[0015] in This represents member m's experience rating in domain d. This represents the set of tasks belonging to domain d completed by member m. This represents the preset importance weight of task t. This represents the complexity coefficient of the predefined task t. The number of tasks belonging to domain d completed by member m; The efficiency scoring module determines the efficiency score of each member using the following formula:
[0016] in This represents the overall efficiency score of member m. This represents the average progress node achievement rate of member m across all tasks. This represents the average delay rate of member m across all tasks. Subtract 1 from the actual cycle / planned cycle; if negative, take 0. This represents the task efficiency fluctuation coefficient of member m. Task cycle standard deviation / average cycle; , as well as As weight, ; The collaboration scoring module evaluates the k collaborations participated in by member m using the following formula. Determine the team members' collaboration ability rating:
[0017] in This represents the collaboration ability score of member m. This indicates the quality of task completion associated with this collaboration. This represents the number of times member m actively initiated interactions during this collaboration. The total number of interactions in this collaboration λ represents the average response time of the members in this collaboration, and λ is a preset coefficient.
[0018] A member's score in a particular area depends not only on the number of tasks they've completed in that area, but also on the average weight of those tasks. The formula introduces importance weights and complexity coefficients as quality multipliers for each task. It first calculates the weighted average complexity of the tasks completed by the member, then multiplies it by the logarithm of the number of tasks. Completing a high-importance, high-complexity task contributes more to experience than completing multiple simple tasks, while the marginal effect of increasing the number of tasks diminishes, which aligns better with the actual laws of experience growth. For efficiency scoring, the formula comprehensively considers how fast a member completes tasks, how well they control delays, and how consistently they perform. Average progress achievement rate is considered a positive contribution, average delay rate is converted into a negative contribution, and an efficiency fluctuation coefficient is subtracted. This means that a member who completes tasks quickly on average but is frequently severely delayed will score lower than a member with moderate speed but extremely consistent performance, encouraging reliability and predictability. When calculating the contribution of each collaboration, the quality of tasks completed related to that collaboration is used as the basic weight, combined with the proportion of proactive interactions initiated by the member in that collaboration and their response speed. This ensures that only collaborative behaviors that truly contribute to the completion of high-quality tasks receive high scores, avoiding the misleading effect of simply focusing on the number of times someone speaks or how fast they respond.
[0019] Furthermore, the relationship graph module includes a node construction module and a relationship mapping module; The node building module is used to generate task nodes corresponding to each task and member nodes corresponding to each member based on the current task data, and to set task attribute information for task nodes and associate member nodes with their corresponding capability profiles. The relationship mapping module is used to map multiple member nodes to the same task node when a cooperative relationship is identified between members, and to create cooperative relationship edges between these member nodes; when an upstream or downstream relationship is identified between members, the corresponding member nodes are mapped to different task nodes with related relationships.
[0020] Each task is assigned a task node containing attributes such as status and deadline, while each member is assigned a member node associated with their skill profile. The relationship mapping module defines the connection rules between nodes. When the system identifies several members sharing the same task, the mapping module connects these member nodes to the task node, clearly indicating that this is a team task and who the collaborators are. Furthermore, member nodes responsible for subsequent tasks may have upstream / downstream relationships with those responsible for previous tasks due to task handover. Through this mapping, a static task list and personnel list transform into a dynamic relationship network, making hidden task logic and collaboration patterns visible and analyzable.
[0021] Furthermore, the risk identification module includes a deviation detection module and a risk quantification module; The deviation detection module is used to extract the actual progress information and actual completion time from the task log data of the current task node, and compare them with the preset planned progress and preset deadline to calculate the progress deviation rate and the timeliness deviation rate. If the progress deviation rate or the timeliness deviation rate exceeds the preset deviation threshold, it is determined that the task has an execution deviation. The risk quantification module is used to assess the deviation risk value of task nodes with execution deviations:
[0022] in, This represents the deviation risk value of task node t. This indicates the severity of the execution deviation for task t, and is the larger of the schedule deviation rate and the timeliness deviation rate. This indicates the number of downstream task nodes that are associated with this task node. This represents the set of member nodes associated with task node t. The overall ability score of member m is obtained by weighting the scores for professional field, task efficiency, and collaboration ability in the aforementioned ability profile. This represents the preset importance weight of task t. These are the preset weighting coefficients.
[0023] The deviation detection module continuously monitors the real-time progress of the task, calculating the deviation rate between actual and planned progress, and the deviation rate between actual completion time and planned deadline, and comparing them with preset thresholds. Once either deviation rate exceeds the threshold, the system determines that the task has an execution deviation requiring attention. The risk quantification module takes the more severe deviation between progress and timeliness as the basis for deviation severity. Next, using a relationship graph, it quickly finds the number of downstream tasks for the task node. This number, after logarithmic processing, represents the potential propagation impact range of the deviation. Then, it summarizes the comprehensive ability scores of all members responsible for the task. The stronger the member's ability, the stronger their ability to cope with and compensate for deviations, and therefore the risk should be correspondingly reduced. This score is used to represent the risk increment caused by insufficient ability. Finally, all these factors are multiplied by the importance weight of the task itself, because the deviation of an important task obviously has a higher risk than the same deviation of a minor task. Compared with common risk identification methods in existing technologies, the advantage of this solution is that it achieves dynamic quantification and classification of risk. Traditional systems may simply highlight or issue simple reminders when a task is delayed, but they cannot tell managers how urgent the delay is, how much other work it will affect, or whether it is within the current manager's control. This solution, through quantified risk values, prioritizes deviations in different tasks, enabling managers to clearly identify which are high-risk issues requiring immediate resource allocation and which are low-risk fluctuations that can be addressed later or resolved by current staff. This allows for efficient and precise allocation of limited management resources.
[0024] Furthermore, the relationship graph module also includes a member load calculation module, and the member load technology module includes a task set module and a load calculation module; The task set module is used to extract all task nodes associated with member node c based on the task-member relationship graph generated by the relationship graph module, thus forming the current task set of that member. ; The load calculation module is used to calculate the load of the set. For each task, calculate its load weight:
[0025] in The preset importance weights for task t, To preset the complexity coefficient, Time urgency coefficient
[0026] The deadline for the task. The current date is 'k', and 'k' is a preset sensitivity parameter. Preset weighting coefficients; Calculate the workload rate of member c based on the load weight of the current task set:
[0027] Where M represents the set of all members, j represents the j-th member, and e represents a very small number to prevent the denominator from being 0.
[0028] By using a relationship graph, all tasks currently handled by each member are captured, forming their to-do list. For each task on the list, the workload calculation module does not treat them as equal burdens, but rather evaluates their weight from three dimensions: task importance, task complexity, and task time urgency. Importance weights and complexity coefficients are usually inherent attributes set when the task is created. The time urgency coefficient is mapped to a value between 0 and 1, characterized by an accelerated increase in urgency rather than a linear increase as the deadline approaches, which aligns with the actual psychological pressure and resource allocation patterns people face towards deadlines. The weighted sum of the scores from these three dimensions yields the workload weight for that task. A member's current total workload is the sum of the workload weights of all their current tasks. Finally, to ensure fair comparisons within the organization, each member's total workload is divided by the largest total workload among all members to obtain their normalized workload rate. The advantage of this scheme is that it greatly improves the scientific rigor and fairness of member workload assessment. Traditional management methods may only consider how many tasks an individual is simultaneously responsible for, but cannot distinguish the vast difference in workload between handling five simple, trivial tasks and handling two major, challenging projects. This solution uses a quantitative model to identify hidden high-load members who, although their workload may be small, bear high importance, high complexity, and are nearing their deadlines. This provides a crucial data foundation for subsequent personnel adjustments and task allocation, effectively preventing key members from being overwhelmed by new tasks due to misjudgment of their workload, or allowing certain members to remain underutilized for extended periods.
[0029] Furthermore, the personnel adjustment module includes an adjustment decision module and a personnel matching module; The adjustment decision module is used to assess whether personnel adjustments are needed for the task based on the deviation risk value. If the deviation risk value is greater than a preset high-risk threshold, it is determined that personnel adjustments are needed immediately. If the deviation risk value is within the preset medium risk range, a comprehensive evaluation is conducted by combining the remaining time of the task, the current member's load rate, and the key indicators of the task, and an adjustment necessity score is calculated. If the score exceeds the preset threshold, it is determined that adjustment is required. If the deviation risk value is lower than the preset low-risk threshold, it is determined that no personnel adjustment is needed at this time. The personnel matching module is used to calculate the matching degree between each member c and the task t:
[0030] in, This represents the similarity between member c's professional domain profile and task t's professional domain requirements. and These represent the normalized task efficiency score and collaboration ability score, respectively. This indicates the current workload rate of the members. , which represents the preset weight.
[0031] The system categorizes tasks into high, medium, and low risk levels and implements different decision-making strategies for each. For high-risk tasks, indicating a serious problem that could spread rapidly, the system immediately determines that personnel adjustments are necessary and initiates an intervention process. For low-risk tasks, the system considers the deviation to be within a controllable range, and the current person in charge is likely to resolve it independently; therefore, adjustments are deemed unnecessary to avoid unnecessary organizational disruption. For medium-risk tasks, a comprehensive assessment is initiated to calculate an adjustment necessity score. This score considers the remaining time for the task (the tighter the timeframe, the more cautious the adjustment should be), the workload of the current responsible member (if the member is already very busy, they may be unable to salvage the situation, increasing the necessity for adjustment; if the workload is light, more time may be allocated), and the task's key performance indicators. Only when the comprehensive score exceeds a preset threshold does the system determine that adjustment is necessary. Attached Figure Description
[0032] Figure 1 This is a schematic diagram of an embodiment of the present invention. Detailed Implementation
[0033] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: An organizational member task performance evaluation and management system includes a server, which includes a task acquisition module, an intelligent profiling module, a relationship graph module, a risk identification module, and a personnel adjustment module. The task acquisition module is used to collect task data and task indicators of each member in the organization during the execution of historical tasks. The task data includes task log data reflecting task progress, task document data reflecting work content, and member interaction data reflecting the collaboration process. The task indicators include importance, complexity, and time urgency. The intelligent profiling module is used to determine the capability profile of each member based on task data. The capability profile includes professional field, task efficiency and collaboration ability. The relationship graph module is used to acquire task data of each task in real time. Based on the current task data and task indicators, tasks are regarded as task nodes and members are regarded as member nodes. According to the preset association relationship between each task, member nodes are mapped to task nodes and the member relationship between member nodes is determined. The member relationship includes cooperation relationship and upstream and downstream relationship, thus obtaining the current task-member relationship graph. The risk identification module is used to determine whether there is an execution deviation in each task based on the current task data. When there is an execution deviation, the deviation risk value of the task node is assessed based on the capability profile of the member nodes associated with the task node and other task nodes that are related to the task node. The personnel adjustment module is used to assess whether the task requires personnel adjustments based on the deviation risk value. When adjustments are needed, the adjustment personnel are selected based on the ability profiles of each member.
[0034] First, the task acquisition module comprehensively collects logs reflecting progress, documents reflecting content and results, and interactive data reflecting the collaboration process, laying the foundation for all subsequent analyses. The intelligent profiling module analyzes this historical and current data to build a multi-dimensional quantitative capability model for each member, covering their professional field, execution efficiency, and collaboration ability. The relationship graph module uses current task data in real time to abstract tasks and members as nodes in a graph, establishing connections based on the logical relationships between tasks and the collaborative relationships between members, thereby dynamically generating a visual graph reflecting the overall picture of the organization's current work. When the risk identification module discovers an execution deviation in a task by comparing planned and actual data, it does not view the problem in isolation but immediately calls the relationship graph to find members associated with the task and other upstream and downstream tasks, and combines the capability profiles of relevant members to comprehensively assess the potential cascading risks caused by the deviation. Finally, the personnel adjustment module determines whether intervention is needed based on this risk value, and if necessary, intelligently recommends the most suitable replacement personnel based on the capability profiles of all members.
[0035] Compared to existing technologies, the key advantage of this solution lies in breaking through the limitations of traditional performance evaluation management systems, such as isolated data, static evaluation, and delayed response. Traditional systems may only record task completion status or perform simple post-event scoring, failing to dynamically reflect the dependency risks between tasks or provide data-driven, scientific adjustment suggestions when problems arise. This solution, through the collaboration of various modules, achieves real-time perception of the task execution process, dynamic evaluation of member capabilities, quantitative early warning of potential risks, and intelligent allocation of human resources. It elevates performance evaluation management from a post-event evaluation tool to a proactive management tool for in-process optimization and risk control, greatly improving the refinement and intelligence of organizational management.
[0036] The intelligent profiling module includes a professional scoring module, an efficiency scoring module, and a collaborative scoring module. The professional scoring module is used to identify the content of task document data in historical tasks, determine the task classification tags of each historical task, and determine the experience scores of each member in several professional fields based on the task classification tags of the historical tasks completed by each member. The efficiency scoring module is used to identify the completion cycle, target achievement rate, and delay records of each historical task based on the task log data in the historical tasks, and to determine the task efficiency score of each member based on the completion cycle, target achievement rate, and delay records of the historical tasks completed by each member. The collaboration scoring module is used to identify the collaboration efficiency and the quality of task completion of each member based on member interaction data, and to evaluate the collaboration ability score of each member.
[0037] The principle behind the professional evaluation module is that an individual's professional knowledge and experience are primarily reflected in their past work. Therefore, this module uses technologies such as natural language processing to analyze the content of members' historical task documents, automatically identifying the professional field categories to which the tasks belong, and then statistically analyzing the number and type of tasks completed by members in each field, thereby quantifying their professional experience. The principle behind the efficiency evaluation module is that a member's task execution ability is directly reflected in time-related log data. This module analyzes the completion cycle of historical tasks, whether there were delays, and the achievement of key progress nodes. By calculating timeliness indicators such as average delay rate and progress achievement rate, it objectively measures a member's time management ability and execution reliability. The principle behind the collaboration evaluation module is that work in modern organizations cannot be separated from collaboration, and collaboration ability is reflected in the initiative and effectiveness of the interaction process. This module analyzes interaction data generated by emails, instant messaging, collaborative editing platforms, etc., to identify the frequency of members initiating collaborations, the timeliness of responding to others' requests, and the quality of the tasks ultimately achieved through their collaborations, thereby assessing their contribution as a member of the team.
[0038] The professional scoring module determines a member's experience score using the following formula:
[0039] in This represents member m's experience rating in domain d. This represents the set of tasks belonging to domain d completed by member m. This represents the preset importance weight of task t. This represents the complexity coefficient of the predefined task t. The number of tasks belonging to domain d completed by member m; The efficiency scoring module determines the efficiency score of each member using the following formula:
[0040] in This represents the overall efficiency score of member m. This represents the average progress node achievement rate of member m across all tasks. This represents the average delay rate of member m across all tasks. Subtract 1 from the actual cycle / planned cycle; if negative, take 0. This represents the task efficiency fluctuation coefficient of member m. Task cycle standard deviation / average cycle; , as well as As weight, ; The collaboration scoring module evaluates the k collaborations participated in by member m using the following formula. Determine the team members' collaboration ability rating:
[0041] in This represents the collaboration ability score of member m. This indicates the quality of task completion associated with this collaboration. This represents the number of times member m actively initiated interactions during this collaboration. The total number of interactions in this collaboration λ represents the average response time of the members in this collaboration, and λ is a preset coefficient.
[0042] A member's score in a particular area depends not only on the number of tasks they've completed in that area, but also on the average weight of those tasks. The formula introduces importance weights and complexity coefficients as quality multipliers for each task. It first calculates the weighted average complexity of the tasks completed by the member, then multiplies it by the logarithm of the number of tasks. Completing a high-importance, high-complexity task contributes more to experience than completing multiple simple tasks, while the marginal effect of increasing the number of tasks diminishes, which aligns better with the actual laws of experience growth. For efficiency scoring, the formula comprehensively considers how fast a member completes tasks, how well they control delays, and how consistently they perform. Average progress achievement rate is considered a positive contribution, average delay rate is converted into a negative contribution, and an efficiency fluctuation coefficient is subtracted. This means that a member who completes tasks quickly on average but is frequently severely delayed will score lower than a member with moderate speed but extremely consistent performance, encouraging reliability and predictability. When calculating the contribution of each collaboration, the quality of tasks completed related to that collaboration is used as the basic weight, combined with the proportion of proactive interactions initiated by the member in that collaboration and their response speed. This ensures that only collaborative behaviors that truly contribute to the completion of high-quality tasks receive high scores, avoiding the misleading effect of simply focusing on the number of times someone speaks or how fast they respond.
[0043] The relation graph module includes a node construction module and a relation mapping module; The node building module is used to generate task nodes corresponding to each task and member nodes corresponding to each member based on the current task data, and to set task attribute information for task nodes and associate member nodes with their corresponding capability profiles. The relationship mapping module is used to map multiple member nodes to the same task node when a cooperative relationship is identified between members, and to create cooperative relationship edges between these member nodes; when an upstream and downstream relationship is identified between members, the corresponding member nodes are mapped to different task nodes with related relationships.
[0044] Each task is assigned a task node containing attributes such as status and deadline, while each member is assigned a member node associated with their skill profile. The relationship mapping module defines the connection rules between nodes. When the system identifies several members sharing the same task, the mapping module connects these member nodes to the task node, clearly indicating that this is a team task and who the collaborators are. Furthermore, member nodes responsible for subsequent tasks may have upstream / downstream relationships with those responsible for previous tasks due to task handover. Through this mapping, a static task list and personnel list transform into a dynamic relationship network, making hidden task logic and collaboration patterns visible and analyzable.
[0045] The risk identification module includes a deviation detection module and a risk quantification module; The deviation detection module is used to extract the actual progress information and actual completion time from the task log data of the current task node, and compare them with the preset planned progress and preset deadline to calculate the progress deviation rate and the timeliness deviation rate. If the progress deviation rate or the timeliness deviation rate exceeds the preset deviation threshold, it is determined that the task has an execution deviation. The risk quantification module is used to assess the deviation risk value of task nodes with execution deviations:
[0046] in, This represents the deviation risk value of task node t. This indicates the severity of the execution deviation for task t, and is the larger of the schedule deviation rate and the timeliness deviation rate. This indicates the number of downstream task nodes that are associated with this task node. This represents the set of member nodes associated with task node t. The overall ability score of member m is obtained by weighting the scores for professional field, task efficiency, and collaboration ability in the aforementioned ability profile. This represents the preset importance weight of task t. These are the preset weighting coefficients.
[0047] The deviation detection module continuously monitors the real-time progress of the task, calculating the deviation rate between actual and planned progress, and the deviation rate between actual completion time and planned deadline, and comparing them with preset thresholds. Once either deviation rate exceeds the threshold, the system determines that the task has an execution deviation requiring attention. The risk quantification module takes the more severe deviation between progress and timeliness as the basis for deviation severity. Next, using a relationship graph, it quickly finds the number of downstream tasks for the task node. This number, after logarithmic processing, represents the potential propagation impact range of the deviation. Then, it summarizes the comprehensive ability scores of all members responsible for the task. The stronger the member's ability, the stronger their ability to cope with and compensate for deviations, and therefore the risk should be correspondingly reduced. This score is used to represent the risk increment caused by insufficient ability. Finally, all these factors are multiplied by the importance weight of the task itself, because the deviation of an important task obviously has a higher risk than the same deviation of a minor task. Compared with common risk identification methods in existing technologies, the advantage of this solution is that it achieves dynamic quantification and classification of risk. Traditional systems may simply highlight or issue simple reminders when a task is delayed, but they cannot tell managers how urgent the delay is, how much other work it will affect, or whether it is within the current manager's control. This solution, through quantified risk values, prioritizes deviations in different tasks, enabling managers to clearly identify which are high-risk issues requiring immediate resource allocation and which are low-risk fluctuations that can be addressed later or resolved by current staff. This allows for efficient and precise allocation of limited management resources.
[0048] The relationship graph module also includes a member load calculation module, and the member load technology module includes a task set module and a load calculation module. The task set module is used to extract all task nodes associated with member node c based on the task-member relationship graph generated by the relationship graph module, thus forming the current task set of that member. ; The load calculation module is used to calculate the load of the set. For each task, calculate its load weight:
[0049] in The preset importance weights for task t, To preset the complexity coefficient, Time urgency coefficient
[0050] The deadline for the task. The current date is 'k', and 'k' is a preset sensitivity parameter. Preset weighting coefficients; Calculate the workload rate of member c based on the load weight of the current task set:
[0051] Where M represents the set of all members, j represents the j-th member, and e represents a very small number to prevent the denominator from being 0.
[0052] By using a relationship graph, all tasks currently handled by each member are captured, forming their to-do list. For each task on the list, the workload calculation module does not treat them as equal burdens, but rather evaluates their weight from three dimensions: task importance, task complexity, and task time urgency. Importance weights and complexity coefficients are usually inherent attributes set when the task is created. The time urgency coefficient is mapped to a value between 0 and 1, characterized by an accelerated increase in urgency rather than a linear increase as the deadline approaches, which aligns with the actual psychological pressure and resource allocation patterns people face towards deadlines. The weighted sum of the scores from these three dimensions yields the workload weight for that task. A member's current total workload is the sum of the workload weights of all their current tasks. Finally, to ensure fair comparisons within the organization, each member's total workload is divided by the largest total workload among all members to obtain their normalized workload rate. The advantage of this scheme is that it greatly improves the scientific rigor and fairness of member workload assessment. Traditional management methods may only consider how many tasks an individual is simultaneously responsible for, but cannot distinguish the vast difference in workload between handling five simple, trivial tasks and handling two major, challenging projects. This solution uses a quantitative model to identify hidden high-load members who, although their workload may be small, bear high importance, high complexity, and are nearing their deadlines. This provides a crucial data foundation for subsequent personnel adjustments and task allocation, effectively preventing key members from being overwhelmed by new tasks due to misjudgment of their workload, or allowing certain members to remain underutilized for extended periods.
[0053] The personnel adjustment module includes an adjustment decision module and a personnel matching module; The adjustment decision module is used to assess whether personnel adjustments are needed for the task based on the deviation risk value. If the deviation risk value is greater than a preset high-risk threshold, it is determined that personnel adjustments are needed immediately. If the deviation risk value is within the preset medium risk range, a comprehensive evaluation is conducted by combining the remaining time of the task, the current member's load rate, and the key indicators of the task, and an adjustment necessity score is calculated. If the score exceeds the preset threshold, it is determined that adjustment is required. If the deviation risk value is lower than the preset low-risk threshold, it is determined that no personnel adjustment is needed at this time. The personnel matching module is used to calculate the matching degree between each member c and the task t:
[0054] in, This represents the similarity between member c's professional domain profile and task t's professional domain requirements. and These represent the normalized task efficiency score and collaboration ability score, respectively. This indicates the current workload rate of the members. , which represents the preset weight.
[0055] The system categorizes tasks into high, medium, and low risk levels and implements different decision-making strategies for each. For high-risk tasks, indicating a serious problem that could spread rapidly, the system immediately determines that personnel adjustments are necessary and initiates an intervention process. For low-risk tasks, the system considers the deviation to be within a controllable range, and the current person in charge is likely to resolve it independently; therefore, adjustments are deemed unnecessary to avoid unnecessary organizational disruption. For medium-risk tasks, a comprehensive assessment is initiated to calculate an adjustment necessity score. This score considers the remaining time for the task (the tighter the timeframe, the more cautious the adjustment should be), the workload of the current responsible member (if the member is already very busy, they may be unable to salvage the situation, increasing the necessity for adjustment; if the workload is light, more time may be allocated), and the task's key performance indicators. Only when the comprehensive score exceeds a preset threshold does the system determine that adjustments are necessary.
[0056] The above are merely embodiments of the present invention. Commonly known structures and characteristics are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are aware of all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, under the guidance of this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.
Claims
1. An organizational member task performance evaluation and management system, characterized in that: The server includes a task acquisition module, an intelligent profiling module, a relationship graph module, a risk identification module, and a personnel adjustment module. The task acquisition module is used to collect task data and task indicators of each member in the organization during the execution of historical tasks. The task data includes task log data reflecting task progress, task document data reflecting work content, and member interaction data reflecting the collaboration process. The task indicators include importance, complexity, and time urgency. The intelligent profiling module is used to determine the capability profile of each member based on task data. The capability profile includes professional field, task efficiency and collaboration ability. The relationship graph module is used to acquire task data of each task in real time. Based on the current task data and task indicators, tasks are regarded as task nodes and members are regarded as member nodes. According to the preset association relationship between each task, member nodes are mapped to task nodes and the member relationship between member nodes is determined. The member relationship includes cooperation relationship and upstream and downstream relationship, thus obtaining the current task-member relationship graph. The risk identification module is used to determine whether there is an execution deviation in each task based on the current task data. When there is an execution deviation, the deviation risk value of the task node is assessed based on the capability profile of the member nodes associated with the task node and other task nodes that are related to the task node. The personnel adjustment module is used to assess whether the task requires personnel adjustments based on the deviation risk value. When adjustments are needed, the adjustment personnel are selected based on the ability profiles of each member.
2. The organizational member task assessment management system according to claim 1, characterized in that: The intelligent profiling module includes a professional scoring module, an efficiency scoring module, and a collaborative scoring module. The professional scoring module is used to identify the content of task document data in historical tasks, determine the task classification tags of each historical task, and determine the experience scores of each member in several professional fields based on the task classification tags of the historical tasks completed by each member. The efficiency scoring module is used to identify the completion cycle, target achievement rate, and delay records of each historical task based on the task log data in the historical tasks, and to determine the task efficiency score of each member based on the completion cycle, target achievement rate, and delay records of the historical tasks completed by each member. The collaboration scoring module is used to identify the collaboration efficiency and the quality of task completion of each member based on member interaction data, and to evaluate the collaboration ability score of each member.
3. The organizational member task assessment management system according to claim 2, characterized in that: The professional scoring module determines a member's experience score using the following formula: in This represents member m's experience rating in domain d. This represents the set of tasks belonging to domain d completed by member m. This represents the preset importance weight of task t. This represents the complexity coefficient of the predefined task t. The number of tasks belonging to domain d completed by member m; The efficiency scoring module determines the efficiency score of each member using the following formula: in This represents the overall efficiency score of member m. This represents the average progress node achievement rate of member m across all tasks. This represents the average delay rate of member m across all tasks. Subtract 1 from the actual cycle / planned cycle; if negative, take 0. This represents the task efficiency fluctuation coefficient of member m. Task cycle standard deviation / average cycle; , as well as As weight, ; The collaboration scoring module evaluates the k collaborations participated in by member m using the following formula. Determine the team members' collaboration ability rating: in This represents the collaboration ability score of member m. This indicates the quality of task completion associated with this collaboration. This represents the number of times member m actively initiated interactions during this collaboration. The total number of interactions in this collaboration λ represents the average response time of the members in this collaboration, and λ is a preset coefficient.
4. The organizational member task assessment and management system according to claim 3, characterized in that: The relation graph module includes a node construction module and a relation mapping module; The node building module is used to generate task nodes corresponding to each task and member nodes corresponding to each member based on the current task data, and to set task attribute information for task nodes and associate member nodes with their corresponding capability profiles. The relationship mapping module is used to map multiple member nodes to the same task node when a cooperative relationship is identified between members, and to create cooperative relationship edges between these member nodes. When an upstream or downstream relationship is identified among members, the corresponding member nodes are mapped to different task nodes with the same relationship.
5. The organizational member task assessment management system according to claim 4, characterized in that: The risk identification module includes a deviation detection module and a risk quantification module; The deviation detection module is used to extract the actual progress information and actual completion time from the task log data of the current task node, and compare them with the preset planned progress and preset deadline to calculate the progress deviation rate and the timeliness deviation rate. If the progress deviation rate or the timeliness deviation rate exceeds the preset deviation threshold, it is determined that the task has an execution deviation. The risk quantification module is used to assess the deviation risk value of task nodes with execution deviations: in, This represents the deviation risk value of task node t. This indicates the severity of the execution deviation for task t, and is the larger of the schedule deviation rate and the timeliness deviation rate. This indicates the number of downstream task nodes that are associated with this task node. This represents the set of member nodes associated with task node t. The overall ability score of member m is obtained by weighting the scores for professional field, task efficiency, and collaboration ability in the aforementioned ability profile. This represents the preset importance weight of task t. These are the preset weighting coefficients.
6. The organizational member task assessment and management system according to claim 5, characterized in that: The relationship graph module also includes a member load calculation module, and the member load technology module includes a task set module and a load calculation module. The task set module is used to extract all task nodes associated with member node c based on the task-member relationship graph generated by the relationship graph module, thus forming the current task set of that member. ; The load calculation module is used to calculate the load of the set. For each task, calculate its load weight: in The preset importance weights for task t, To preset the complexity coefficient, Time urgency coefficient The deadline for the task. The current date is 'k', and 'k' is a preset sensitivity parameter. Preset weighting coefficients; Calculate the workload rate of member c based on the load weight of the current task set: Where M represents the set of all members, j represents the j-th member, and e represents a very small number to prevent the denominator from being 0.
7. The organizational member task assessment and management system according to claim 6, characterized in that: The personnel adjustment module includes an adjustment decision module and a personnel matching module; The adjustment decision module is used to assess whether personnel adjustments are needed for the task based on the deviation risk value. If the deviation risk value is greater than a preset high-risk threshold, it is determined that personnel adjustments are needed immediately. If the deviation risk value is within the preset medium risk range, a comprehensive evaluation is conducted by combining the remaining time of the task, the current member's load rate, and the key indicators of the task, and an adjustment necessity score is calculated. If the score exceeds the preset threshold, it is determined that adjustment is required. If the deviation risk value is lower than the preset low-risk threshold, it is determined that no personnel adjustment is needed at this time. The personnel matching module is used to calculate the matching degree between each member c and the task t: in, This represents the similarity between member c's professional domain profile and task t's professional domain requirements. and These represent the normalized task efficiency score and collaboration ability score, respectively. This indicates the current workload rate of the members. , which represents the preset weight.