Organization data mining method and system
By collecting and analyzing multi-dimensional data on organizational activities, calculating participation and engagement indices, identifying consensus characteristics of high-performing activities, and generating optimization strategy reports, this approach solves the problems of subjectivity and data isolation in traditional evaluation methods. It achieves objective evaluation and planning guidance for activity effectiveness, thereby improving activity quality and efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-24
- Publication Date
- 2026-04-14
AI Technical Summary
In existing technologies, the evaluation of organizational activity effectiveness lacks systematic and objective measurement standards, resulting in highly subjective evaluations, isolated data, difficulty in reflecting the true effectiveness of activities, and the inability to effectively accumulate experience, leading to large fluctuations in activity quality and making it difficult to replicate and promote best practices.
By collecting multi-dimensional data from organizational activities, we calculate participation and engagement indices, generate comprehensive performance evaluations, and identify consensus characteristics and key element combinations of high-performing activities through data mining to generate optimization strategy reports.
It enables data-driven evaluation of the entire process of organizational activities, improving the objectivity and accuracy of evaluation, providing guidance for activity planning based on historical data, reducing the blind spots in planning work, and improving activity effectiveness and resource utilization efficiency.
Smart Images
Figure CN121859871A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data mining technology, and specifically to an organizational data mining method and system. Background Technology
[0002] In current organizational management practices, evaluating and optimizing the effectiveness of various organizational activities such as meetings, training sessions, and group activities is a crucial yet challenging task. Effective activities can build consensus, enhance capabilities, and facilitate task achievement, thereby boosting overall organizational effectiveness. However, traditional methods of evaluating activity effectiveness generally rely on the subjective summaries and experience-based judgments of organizers or participants, lacking systematic and objective measurement standards and continuous improvement mechanisms. This has become a key bottleneck restricting the improvement of organizational activity quality.
[0003] In existing technologies, the evaluation of organizational activity effectiveness typically employs several methods, all of which have significant limitations. The most common method relies on manual summary reports or simple satisfaction surveys after the activity. Feedback obtained through this method is highly subjective, easily influenced by personal feelings, interpersonal relationships, and even the emotions at the time, making it difficult to reflect the objective effectiveness of the activity. Furthermore, questionnaires are often simply designed, yielding only general conclusions of "satisfied" or "unsatisfied," failing to provide in-depth quantitative analysis of the activity's gains and losses in specific dimensions. A slightly more advanced approach involves collecting basic quantitative indicators, such as activity attendance, the number of tasks completed, or meeting duration. While this method introduces some objective data, the indicators are extremely singular and superficial. It can only answer basic questions like "Did people attend?" and "Was anything done?", completely failing to address the core quality of the activity, such as the level of participant engagement, the depth of interaction and reflection, and the actual impact of the activity on subsequent work. These crude indicators are like measuring only the width of a river, without knowing its depth, flow rate, or water quality, making it impossible to provide a truly effective evaluation of the activity's effectiveness.
[0004] Furthermore, existing evaluation methods are often isolated and fragmented. After an event concludes, its evaluation data is typically archived as a separate report or table, lacking effective correlation and integration with data from other historical events. This makes it difficult for organizers to identify trends in event effectiveness, compare the merits of different event formats, or summarize universal successes and failures from a longitudinal time dimension or a horizontal type dimension. Experience cannot be effectively accumulated, and knowledge cannot be systematically passed on, resulting in each event planning process largely starting afresh, relying on the personal experience and improvisation of individual leaders. This leads to significant fluctuations in event quality and makes it difficult to replicate and promote best practices. Summary of the Invention
[0005] The technical problem solved by this invention is to provide an organizational data mining method and system that can collect data from the entire process of an activity and, through data mining technology, transform messy data into accurate evaluations of activity effects and intelligent guidance for future planning, thereby fundamentally improving the management efficiency and value output of organizational activities.
[0006] The basic solution provided by this invention is an organizational data mining method, comprising the following steps: S100. Collect behavioral data from multiple dimensions of members participating in the organization's activities, as well as the activity data for that activity. The behavioral data includes attendance data, interaction data, and task completion data. The activity data includes the activity type and the scale of the activity. S200. Based on behavioral data, determine the effectiveness index of organizational activities. S200 includes the following steps: S210. Calculate the participation index based on the attendance data, wherein the participation index is used to determine the personnel coverage scale of the organized activities; S220. Based on the interaction data and the task completion data, calculate the engagement index of the organizational activity, and the engagement index determines the depth of participation of the participants in the organizational activity. S300. Generate a comprehensive evaluation of the organizational activities based on the participation index and engagement index, and store the comprehensive evaluation of the activities and the activity data in the database. S400: Based on the comprehensive effect evaluation of multiple activities within the cycle and the activity data, identify and analyze the comprehensive effect evaluation under different activity types and scales, identify the consensus characteristics that the comprehensive effect evaluation reaches the preset requirements; and conduct correlation analysis on activity data, participation index, engagement index and comprehensive effect evaluation, and extract the key element combination that affects the comprehensive effect evaluation. S500 generates an optimization strategy report for future organizational activities based on consensus characteristics and key element combinations.
[0007] The principle and advantages of this invention are as follows: By collecting behavioral data of members and attribute data of the activities themselves, and calculating the participation index reflecting the breadth of the activity coverage and the engagement index reflecting the depth of participation based on these data, a comprehensive effect evaluation is generated; then, by mining and analyzing the evaluation data and activity attributes accumulated in historical activities, the common characteristics of high-performing activities and the combination of key elements affecting the effect are identified, and finally, an optimization strategy report is generated to guide the planning of future activities.
[0008] This transforms traditional activity evaluation methods, which rely on subjective summaries and experience-based judgments, into a continuous optimization process based on multi-dimensional objective data and systematic analysis models. Its advantage lies in achieving, for the first time, a data-driven evaluation and optimization of the entire process of organizational activity effectiveness. This not only improves the objectivity and accuracy of evaluations but also provides a basis for activity planning through historical data mining, enabling targeted improvements to activity design and thereby enhancing the overall effectiveness and resource utilization efficiency of organizational activities.
[0009] Furthermore, S100 includes the following steps: S110, collecting attendance data, obtaining the list of members who should attend the event and the actual attendance records, calculating the attendance rate, and obtaining the attendance duration of each member; S120. Collect interaction data, record the number of times members speak, ask questions, answer questions, and participate in voting during the activity, and obtain the interaction count of each member; S130. Collect data on the completion of tasks, and obtain information on the completion status, number of successful submissions, and quality assessment of the preset tasks and topics of the activity. S140. Collect the number of activities, obtain the actual number of participants based on the attendance rate, determine the scale of the activities, and obtain the activity type based on the activity information.
[0010] Abstract behavioral and activity data are broken down into specific, directly obtainable or calculable metrics: attendance data is calculated by comparing the expected attendance list with the actual attendance records, and the actual attendance duration is recorded; interaction data is quantified by recording the number of specific interactive behaviors such as speaking, asking questions, answering, and voting; task completion data is reflected by obtaining information on the completion status, quantity, and quality of tasks or topics; the scale of the activity is determined based on the actual number of attendees, and the activity type is tagged from the activity creation information. This ensures that all collected data is objective, recordable, and verifiable, avoiding subjective descriptions or vague judgments. Its advantage lies in the fact that by clearly defining the specific source and form of each type of data, the entire method has high operability and consistency during implementation, solving the analytical difficulties caused by vague data definitions and inconsistent recording standards in traditional methods, and laying a solid and reliable data foundation for subsequent quantitative calculations and in-depth analysis.
[0011] Furthermore, S210 includes the following steps: S211. The attendance rate is obtained by comparing the actual number of attendees with the number of members who should be present. S212. Calculate the average actual attendance time of members and obtain the average attendance time ratio based on the ratio of the average actual attendance time of members to the total preset duration of the activity. S213. Map the activity size based on the preset size range where the actual number of participants falls; S214. The participation index is obtained by weighting the attendance rate, average attendance duration ratio, and event size: Participation Index = α × Check-in Rate + β × Average Attendance Duration Ratio + γ × Event Scale Coefficient.
[0012] This model quantifies and integrates multiple aspects reflecting the scale of an event's reach: attendance rate directly reflects attendance; average attendance duration reflects the duration of participation; and the event size coefficient is a correction value set based on the range of total participants, used to make the participation indices of events of different sizes comparable. For example, large-scale events may naturally have lower interaction depth than small-scale events, and this coefficient balances this. Finally, the three factors are weighted and summed using preset weights to obtain a comprehensive participation index. The breadth of participation is not solely determined by attendance rate; the duration of participation and the event size itself must also be considered, thus constructing a multi-dimensional measurement model. Its advantage lies in overcoming the one-sidedness of traditionally evaluating participation solely based on "attendance rate." By introducing duration and size corrections, it makes the evaluation of participation in different forms and sizes of events more fair and scientific, and can more realistically reflect the actual effect of the event in terms of reach.
[0013] Furthermore, S220 includes the following steps: S221. For each participating member, calculate their individual interaction score according to the preset scoring rules based on their number of speeches, questions, answers, and voting records. After normalizing the individual interaction scores of all participating members, calculate the average score and then correct it according to the interaction benchmark corresponding to the activity type to obtain the interaction intensity index. S222. Based on the completion status of tasks and topics, the number of successful submissions, and quality assessment information, calculate the task completion rate and average quality score, and then sum the two by weight to obtain the task completion index. S223. Based on the interaction intensity index and the task completion index, the engagement index is obtained: Engagement Index = λ × Interaction Intensity Index + μ × Task Completion Index
[0014] The depth of participation is quantified through two core dimensions: members' proactive contributions and task completion. The interaction intensity index quantifies the activity's activity level and quality by setting scoring rules for specific behaviors such as speaking and asking questions, calculating individual scores, averaging them, and then adjusting for different activity types (e.g., seminars and reports have different expected levels of interaction). The task completion index directly quantifies the achievement of the activity's pre-set goals, evaluating both completion rate and quality. Finally, these two indices, representing process input and result delivery respectively, are weighted and combined into an engagement index. This distinguishes between the depth of communication and the outcome of work during the activity. Its advantage lies in breaking through the limitations of traditional methods that only focus on task completion or superficial interaction atmosphere, providing a structured method to comprehensively measure members' substantive engagement in the activity, making the evaluation of the activity's deeper effects more accurate and comprehensive.
[0015] Furthermore, S300 includes the following steps: S310. The participation index and the engagement index are compared with multiple preset evaluation level thresholds to determine their respective evaluation dimension levels. S320. Determine the comprehensive effect evaluation level of the organizational activity based on the evaluation dimension level corresponding to the participation index, the evaluation dimension level corresponding to the engagement index, and the preset comprehensive evaluation rules; wherein, the comprehensive evaluation rules define the mapping relationship between different combinations of evaluation dimension levels and the comprehensive effect evaluation level. S330. Based on the comprehensive effect evaluation level, generate a comprehensive effect evaluation report containing qualitative conclusions and quantitative indicator data.
[0016] A hierarchical mapping rule-based decision-making logic is employed: First, each of the two indices is compared with a preset threshold, transforming them into evaluation dimension levels such as "high," "medium," and "low." Then, based on a predefined comprehensive evaluation rule, the combined levels of the two dimensions are mapped to a final comprehensive effect evaluation level. For example, the rule might stipulate that "high participation and high engagement" corresponds to "excellent," while "high participation but low engagement" corresponds to "good but needs improvement in depth." Finally, a report containing qualitative conclusions and detailed quantitative data is generated based on this level. This avoids the possibility that simple weighted averages might mask specific problems. Through rule-based judgment logic, the structural characteristics of the activity's effectiveness can be more clearly represented. Its advantage lies in making the evaluation result not just a score, but a diagnostic conclusion that can directly point out the activity's strengths and weaknesses in "breadth" and "depth," greatly enhancing the interpretability of the evaluation results and their guiding value for subsequent improvements.
[0017] Furthermore, S400 includes the following steps: S410. Preprocess and classify the comprehensive effect evaluation, activity data, participation index and engagement index of each activity stored in the database within the preset period to form an analysis dataset divided by activity type and activity scale. S420. For the subset of activities in the analysis dataset that achieve a preset high evaluation threshold in the comprehensive effect evaluation, perform feature pattern mining to identify consensus features presented in the activity data, participation index and engagement index. S430. Based on the association rule mining algorithm, perform association analysis on the activity data, participation index, engagement index and comprehensive effect evaluation in the analysis dataset, and extract association rules with support and confidence reaching a preset threshold as key element combinations affecting the comprehensive effect evaluation.
[0018] First, historical data is categorized and organized according to activity type and scale, forming a well-structured analytical dataset. Then, for a subset of activities rated as highly effective, feature pattern mining techniques are used to identify recurring common features in activity attributes, participation, and engagement—these are consensus features. Simultaneously, association rule mining algorithms are used to explore stable symbiotic relationships between activity attributes, participation, engagement, and high-evaluation results across the entire dataset—these are key element combinations. By leveraging machine learning and data mining techniques, complex patterns and rules that are difficult for humans to intuitively summarize are automatically and efficiently discovered from a large amount of historical experience. Its advantage lies in transforming the organization's historical experience into coded, transferable explicit knowledge, overcoming the limitations of traditional reliance on the experience summaries of individual leaders, which suffers from bias, randomness, and irreproducibility. This allows insights into the patterns of activity success to be based on comprehensive data analysis, making them more objective and systematic.
[0019] Furthermore, S50 includes the following steps: S510. Based on the consensus characteristics and key element combinations, generate a strategy rule base for different activity types or activity scales; the strategy rule base defines the element conditions that should be prioritized or the feature combinations that should be avoided in activity planning and execution in order to improve the overall effect evaluation. S520. Based on the strategy rule base and the preset type and expected scale of the target new activity, generate a set of preliminary optimization suggestions that includes at least one of the following: form, process, and resource configuration. S530. Associate the preliminary set of optimization suggestions with specific execution cases of historical high-performing activities, and integrate them into a structured template to generate the optimization strategy report.
[0020] A bridge is built to translate analytical findings into practical guidance: First, the mined consensus features and association rules are transformed into a strategy rule base. This rule base clearly indicates which elements should be present or which combinations should be avoided when planning specific types or scales of activities to improve effectiveness. Then, when planning a new activity, the system automatically matches relevant strategy suggestions from the rule base based on its preset type and scale, covering aspects such as activity format, process design, and resource allocation. Finally, these suggestions are combined with historical successful cases that conform to the rules and populated into a structured report template to form the final optimization strategy report. This ensures that the conclusions of data mining do not remain at the analytical level but can directly and specifically provide feedback and guidance for future action plans. Its advantage lies in achieving a closed loop from "post-event analysis" to "pre-event prediction and planning," providing event planners with data-driven decision support that combines principles and case references, significantly reducing the blind spots in planning work and improving the predictability of event success. Attached Figure Description
[0021] Figure 1 This is a schematic diagram of an embodiment of the present invention. Detailed Implementation
[0022] The following detailed description illustrates the specific implementation method: The basic implementation examples are as follows: Figure 1 As shown: An organizational data mining method includes the following steps: S100. Collect behavioral data from multiple dimensions of members participating in the organization's activities, as well as the activity data for that activity. The behavioral data includes attendance data, interaction data, and task completion data. The activity data includes the activity type and the scale of the activity. S200. Based on behavioral data, determine the effectiveness index of organizational activities. S200 includes the following steps: S210. Calculate the participation index based on the attendance data, wherein the participation index is used to determine the personnel coverage scale of the organized activities; S220. Based on the interaction data and the task completion data, calculate the engagement index of the organizational activity, and the engagement index determines the depth of participation of the participants in the organizational activity. S300. Generate a comprehensive evaluation of the organizational activities based on the participation index and engagement index, and store the comprehensive evaluation of the activities and the activity data in the database. S400: Based on the comprehensive effect evaluation of multiple activities within the cycle and the activity data, identify and analyze the comprehensive effect evaluation under different activity types and scales, identify the consensus characteristics that the comprehensive effect evaluation reaches the preset requirements; and conduct correlation analysis on activity data, participation index, engagement index and comprehensive effect evaluation, and extract the key element combination that affects the comprehensive effect evaluation. S500 generates an optimization strategy report for future organizational activities based on consensus characteristics and key element combinations.
[0023] By collecting behavioral data of members and attribute data of the activities themselves, and calculating the participation index reflecting the breadth of the activities and the engagement index reflecting the depth of participation based on these data, a comprehensive effect evaluation is generated. Subsequently, by mining and analyzing the evaluation data and activity attributes accumulated in historical activities, the common characteristics of high-performing activities and the combination of key elements affecting the effect are identified, and finally, an optimization strategy report is generated to guide the planning of future activities.
[0024] This transforms traditional activity evaluation methods, which rely on subjective summaries and experience-based judgments, into a continuous optimization process based on multi-dimensional objective data and systematic analysis models. Its advantage lies in achieving, for the first time, a data-driven evaluation and optimization of the entire process of organizational activity effectiveness. This not only improves the objectivity and accuracy of evaluations but also provides a basis for activity planning through historical data mining, enabling targeted improvements to activity design and thereby enhancing the overall effectiveness and resource utilization efficiency of organizational activities.
[0025] S100 includes the following steps: S110, collecting attendance data, obtaining the list of members who should attend the event and the actual attendance records, calculating the attendance rate, and obtaining the attendance duration of each member; S120. Collect interaction data, record the number of times members speak, ask questions, answer questions, and participate in voting during the activity, and obtain the interaction count of each member; S130. Collect data on the completion of tasks, and obtain information on the completion status, number of successful submissions, and quality assessment of the preset tasks and topics of the activity. S140. Collect the number of activities, obtain the actual number of participants based on the attendance rate, determine the scale of the activities, and obtain the activity type based on the activity information.
[0026] Abstract behavioral and activity data are broken down into specific, directly obtainable or calculable metrics: attendance data is calculated by comparing the expected attendance list with the actual attendance records, and the actual attendance duration is recorded; interaction data is quantified by recording the number of specific interactive behaviors such as speaking, asking questions, answering, and voting; task completion data is reflected by obtaining information on the completion status, quantity, and quality of tasks or topics; the scale of the activity is determined based on the actual number of attendees, and the activity type is tagged from the activity creation information. This ensures that all collected data is objective, recordable, and verifiable, avoiding subjective descriptions or vague judgments. Its advantage lies in the fact that by clearly defining the specific source and form of each type of data, the entire method has high operability and consistency during implementation, solving the analytical difficulties caused by vague data definitions and inconsistent recording standards in traditional methods, and laying a solid and reliable data foundation for subsequent quantitative calculations and in-depth analysis.
[0027] S210 includes the following steps: S211. The attendance rate is obtained by comparing the actual number of attendees with the number of members who should be present. S212. Calculate the average actual attendance time of members and obtain the average attendance time ratio based on the ratio of the average actual attendance time of members to the total preset duration of the activity. S213. Map the activity size based on the preset size range where the actual number of participants falls; S214. The participation index is obtained by weighting the attendance rate, average attendance duration ratio, and event size: Participation Index = α × Check-in Rate + β × Average Attendance Duration Ratio + γ × Event Scale Coefficient.
[0028] This model quantifies and integrates multiple aspects reflecting the scale of an event's reach: attendance rate directly reflects attendance; average attendance duration reflects the duration of participation; and the event size coefficient is a correction value set based on the range of total participants, used to make the participation indices of events of different sizes comparable. For example, large-scale events may naturally have lower interaction depth than small-scale events, and this coefficient balances this. Finally, the three factors are weighted and summed using preset weights to obtain a comprehensive participation index. The breadth of participation is not solely determined by attendance rate; the duration of participation and the event size itself must also be considered, thus constructing a multi-dimensional measurement model. Its advantage lies in overcoming the one-sidedness of traditionally evaluating participation solely based on "attendance rate." By introducing duration and size corrections, it makes the evaluation of participation in different forms and sizes of events more fair and scientific, and can more realistically reflect the actual effect of the event in terms of reach.
[0029] S220 includes the following steps: S221. For each participating member, calculate their individual interaction score according to the preset scoring rules based on their number of speeches, questions, answers, and voting records. After normalizing the individual interaction scores of all participating members, calculate the average score and then correct it according to the interaction benchmark corresponding to the activity type to obtain the interaction intensity index. S222. Based on the completion status of tasks and topics, the number of successful submissions, and quality assessment information, calculate the task completion rate and average quality score, and then sum the two by weight to obtain the task completion index. S223. Based on the interaction intensity index and the task completion index, the engagement index is obtained: Engagement Index = λ × Interaction Intensity Index + μ × Task Completion Index
[0030] The depth of participation is quantified through two core dimensions: members' proactive contributions and task completion. The interaction intensity index quantifies the activity's activity level and quality by setting scoring rules for specific behaviors such as speaking and asking questions, calculating individual scores, averaging them, and then adjusting for different activity types (e.g., seminars and reports have different expected levels of interaction). The task completion index directly quantifies the achievement of the activity's pre-set goals, evaluating both completion rate and quality. Finally, these two indices, representing process input and result delivery respectively, are weighted and combined into an engagement index. This distinguishes between the depth of communication and the outcome of work during the activity. Its advantage lies in breaking through the limitations of traditional methods that only focus on task completion or superficial interaction atmosphere, providing a structured method to comprehensively measure members' substantive engagement in the activity, making the evaluation of the activity's deeper effects more accurate and comprehensive.
[0031] S300 includes the following steps: S310. The participation index and the engagement index are compared with multiple preset evaluation level thresholds to determine their respective evaluation dimension levels. S320. Determine the comprehensive effect evaluation level of the organizational activity based on the evaluation dimension level corresponding to the participation index, the evaluation dimension level corresponding to the engagement index, and the preset comprehensive evaluation rules; wherein, the comprehensive evaluation rules define the mapping relationship between different combinations of evaluation dimension levels and the comprehensive effect evaluation level. S330. Based on the comprehensive effect evaluation level, generate a comprehensive effect evaluation report containing qualitative conclusions and quantitative indicator data.
[0032] A hierarchical mapping rule-based decision-making logic is employed: First, each of the two indices is compared with a preset threshold, transforming them into evaluation dimension levels such as "high," "medium," and "low." Then, based on a predefined comprehensive evaluation rule, the combined levels of the two dimensions are mapped to a final comprehensive effect evaluation level. For example, the rule might stipulate that "high participation and high engagement" corresponds to "excellent," while "high participation but low engagement" corresponds to "good but needs improvement in depth." Finally, a report containing qualitative conclusions and detailed quantitative data is generated based on this level. This avoids the possibility that simple weighted averages might mask specific problems. Through rule-based judgment logic, the structural characteristics of the activity's effectiveness can be more clearly represented. Its advantage lies in making the evaluation result not just a score, but a diagnostic conclusion that can directly point out the activity's strengths and weaknesses in "breadth" and "depth," greatly enhancing the interpretability of the evaluation results and their guiding value for subsequent improvements.
[0033] The S400 includes the following steps: S410. Preprocess and classify the comprehensive effect evaluation, activity data, participation index and engagement index of each activity stored in the database within the preset period to form an analysis dataset divided by activity type and activity scale. S420. For the subset of activities in the analysis dataset that achieve a preset high evaluation threshold in the comprehensive effect evaluation, perform feature pattern mining to identify consensus features presented in the activity data, participation index and engagement index. S430. Based on the association rule mining algorithm, perform association analysis on the activity data, participation index, engagement index and comprehensive effect evaluation in the analysis dataset, and extract association rules with support and confidence reaching a preset threshold as key element combinations affecting the comprehensive effect evaluation.
[0034] First, historical data is categorized and organized according to activity type and scale, forming a well-structured analytical dataset. Then, for a subset of activities rated as highly effective, feature pattern mining techniques are used to identify recurring common features in activity attributes, participation, and engagement—these are consensus features. Simultaneously, association rule mining algorithms are used to explore stable symbiotic relationships between activity attributes, participation, engagement, and high-evaluation results across the entire dataset—these are key element combinations. By leveraging machine learning and data mining techniques, complex patterns and rules that are difficult for humans to intuitively summarize are automatically and efficiently discovered from a large amount of historical experience. Its advantage lies in transforming the organization's historical experience into coded, transferable explicit knowledge, overcoming the limitations of traditional reliance on the experience summaries of individual leaders, which suffers from bias, randomness, and irreproducibility. This allows insights into the patterns of activity success to be based on comprehensive data analysis, making them more objective and systematic.
[0035] S50 includes the following steps: S510. Based on the consensus characteristics and key element combinations, generate a strategy rule base for different activity types or activity scales; the strategy rule base defines the element conditions that should be prioritized or the feature combinations that should be avoided in activity planning and execution in order to improve the overall effect evaluation. S520. Based on the strategy rule base and the preset type and expected scale of the target new activity, generate a set of preliminary optimization suggestions that includes at least one of the following: form, process, and resource configuration. S530. Associate the preliminary set of optimization suggestions with specific execution cases of historical high-performing activities, and integrate them into a structured template to generate the optimization strategy report.
[0036] A bridge is built to translate analytical findings into practical guidance: First, the mined consensus features and association rules are transformed into a strategy rule base. This rule base clearly indicates which elements should be present or which combinations should be avoided when planning specific types or scales of activities to improve effectiveness. Then, when planning a new activity, the system automatically matches relevant strategy suggestions from the rule base based on its preset type and scale, covering aspects such as activity format, process design, and resource allocation. Finally, these suggestions are combined with historical successful cases that conform to the rules and populated into a structured report template to form the final optimization strategy report. This ensures that the conclusions of data mining do not remain at the analytical level but can directly and specifically provide feedback and guidance for future action plans. Its advantage lies in achieving a closed loop from "post-event analysis" to "pre-event prediction and planning," providing event planners with data-driven decision support that combines principles and case references, significantly reducing the blind spots in planning work and improving the predictability of event success.
[0037] 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. A method for organizing data mining, characterized in that: Includes the following steps: S100. Collect behavioral data from multiple dimensions of members participating in the organization's activities, as well as the activity data for that activity. The behavioral data includes attendance data, interaction data, and task completion data. The activity data includes the activity type and the scale of the activity. S200. Based on behavioral data, determine the effectiveness index of organizational activities. S200 includes the following steps: S210. Calculate the participation index based on the attendance data, wherein the participation index is used to determine the personnel coverage scale of the organized activities; S220. Based on the interaction data and the task completion data, calculate the engagement index of the organizational activity, and the engagement index determines the depth of participation of the participants in the organizational activity. S300. Generate a comprehensive evaluation of the organizational activities based on the participation index and engagement index, and store the comprehensive evaluation of the activities and the activity data in the database. S400. Based on the comprehensive effect evaluation of multiple activities within the cycle and the activity data, identify and analyze the comprehensive effect evaluation under different activity types and scales, identify the consensus characteristics that the comprehensive effect evaluation reaches the preset requirements; and conduct correlation analysis on activity data, participation index, engagement index and comprehensive effect evaluation, and extract the key element combination that affects the comprehensive effect evaluation. S500 generates an optimization strategy report for future organizational activities based on consensus characteristics and key element combinations.
2. The organizational data mining method according to claim 1, characterized in that: S100 includes the following steps: S110. Collect attendance data, obtain the list of members who should attend the event and the actual attendance records, calculate the attendance rate, and obtain the attendance duration of each member; S120. Collect interaction data, record the number of times members speak, ask questions, answer questions, and participate in voting during the activity, and obtain the interaction count of each member; S130. Collect data on the completion of tasks, and obtain information on the completion status, number of successful submissions, and quality assessment of the preset tasks and topics of the activity. S140. Collect the number of activities, obtain the actual number of participants based on the attendance rate, determine the scale of the activities, and obtain the activity type based on the activity information.
3. The organizational data mining method according to claim 2, characterized in that: S210 includes the following steps: S211. The attendance rate is obtained by comparing the actual number of attendees with the number of members who should be present. S212. Calculate the average actual attendance time of members and obtain the average attendance time ratio based on the ratio of the average actual attendance time of members to the total preset duration of the activity. S213. Map the activity size based on the preset size range where the actual number of participants falls; S214. The participation index is obtained by weighting the attendance rate, average attendance duration ratio, and event size: Participation Index = α × Check-in Rate + β × Average Attendance Duration Ratio + γ × Event Scale Coefficient.
4. The organizational data mining method according to claim 3, characterized in that: S220 includes the following steps: S221. For each participating member, calculate their individual interaction score according to the preset scoring rules based on their number of speeches, questions, answers, and voting records. After normalizing the individual interaction scores of all participating members, calculate the average score and then correct it according to the interaction benchmark corresponding to the activity type to obtain the interaction intensity index. S222. Based on the completion status of tasks and topics, the number of successful submissions, and quality assessment information, calculate the task completion rate and average quality score, and then sum the two by weight to obtain the task completion index. S223. Based on the interaction intensity index and the task completion index, the engagement index is obtained: Engagement Index = λ × Interaction Intensity Index + μ × Task Completion Index 5. The organizational data mining method according to claim 4, characterized in that: S300 includes the following steps: S310. The participation index and the engagement index are compared with multiple preset evaluation level thresholds to determine their respective evaluation dimension levels. S320. Determine the comprehensive effect evaluation level of the organizational activity based on the evaluation dimension level corresponding to the participation index, the evaluation dimension level corresponding to the engagement index, and the preset comprehensive evaluation rules; wherein, the comprehensive evaluation rules define the mapping relationship between different combinations of evaluation dimension levels and the comprehensive effect evaluation level. S330. Based on the comprehensive effect evaluation level, generate a comprehensive effect evaluation report containing qualitative conclusions and quantitative indicator data.
6. The organizational data mining method according to claim 5, characterized in that: The S400 includes the following steps: S410. Preprocess and classify the comprehensive effect evaluation, activity data, participation index and engagement index of each activity stored in the database within the preset period to form an analysis dataset divided by activity type and activity scale. S420. For the subset of activities in the analysis dataset that achieve a preset high evaluation threshold in the comprehensive effect evaluation, perform feature pattern mining to identify consensus features presented in the activity data, participation index and engagement index. S430. Based on the association rule mining algorithm, perform association analysis on the activity data, participation index, engagement index and comprehensive effect evaluation in the analysis dataset, and extract association rules with support and confidence reaching a preset threshold as key element combinations affecting the comprehensive effect evaluation.
7. The organizational data mining method according to claim 6, characterized in that: S50 includes the following steps: S510. Based on the consensus characteristics and key element combinations, generate a strategy rule base for different activity types or activity scales; the strategy rule base defines the element conditions that should be prioritized or the feature combinations that should be avoided in activity planning and execution in order to improve the overall effect evaluation. S520. Based on the strategy rule base and the preset type and expected scale of the target new activity, generate a set of preliminary optimization suggestions that includes at least one of the following: form, process, and resource configuration. S530. Associate the preliminary set of optimization suggestions with specific execution cases of historical high-performing activities, and integrate them into a structured template to generate the optimization strategy report.
8. An organizational data mining system, characterized in that: An organizational data mining method according to any one of claims 1-7 was used.