A conference layout and seating arrangement method and system based on recommendation algorithm

Abstract

The present invention discloses a conference layout and seating arrangement method and system based on a recommendation algorithm, which relates to the field of intelligent office technology, obtains information feature data; obtains importance scores of conference participants; arranges the conference layout and seating in combination with the obtained importance scores of conference participants; and feeds back the evaluation results to the conference organizer. The present invention can effectively recommend the most suitable seats for each participant, so that key participants can exert the greatest influence at the appropriate time, evaluates the layout effect after the meeting through an effect evaluation algorithm, and feeds back the results to the conference organizer, thereby improving the organizational efficiency of the meeting, reducing the burden on the organizer, and also optimizing the experience of the conference participants and the overall effect of the meeting.

Description

Technical Field

[0001] The present invention relates to the field of intelligent office technology, and in particular to a conference layout and seating arrangement method and system based on a recommendation algorithm. Background Art

[0002] With the acceleration of the pace of modern work, meetings have become an indispensable part of daily work. Especially for formal meetings, there are high requirements for the selection of conference rooms and the seating arrangement of participants, which not only involves the efficiency of the meeting, but also affects the overall quality of the meeting and the experience of the participants. Traditionally, meeting organizers need to go to the meeting place in person to confirm the venue and arrange seats. Although this method is intuitive, it consumes a lot of manpower and time resources, and is prone to errors under high-pressure and busy working conditions, such as conflicts in conference room selection and improper seating arrangements. What is more complicated is that when there is a time conflict in the conference room or temporary personnel adjustments are required, traditional methods are difficult to respond quickly, which in turn affects the smooth progress and final effect of the meeting. Using advanced recommendation algorithms, not only can the selection of conference rooms and seating arrangements be automatically optimized, but the most suitable conference room layout can also be intelligently recommended based on the roles of the participants and the specific needs of the meeting. By analyzing historical meeting data, the frequency and effect of interaction between participants, the best conference room configuration can be predicted and recommended, thereby greatly improving meeting efficiency and satisfaction.

[0003] In the prior art, it is not convenient to automatically analyze the importance and other relevant characteristic data of the meeting participants, and it is not possible to effectively recommend the most suitable seat for each participant. In addition, the traditional conference layout and seating arrangement requires a lot of manual participation. From data collection to analysis to actual layout, each step is time-consuming and prone to errors. It is not convenient to arrange seats according to the positions and roles of the participants, and it is not possible to consider their past interaction history and performance in the meeting, so it is not possible to arrange seats more scientifically, which is not convenient to promote effective communication and exchanges, and reduces the overall quality of the meeting and the satisfaction of the participants. It is also not convenient to evaluate the layout effect after the meeting, and it is not convenient to feed back the results to the meeting organizer, which reduces the organizational efficiency of the meeting, increases the burden on the organizer, and also reduces the experience of the meeting participants and the overall effect of the meeting.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention proposes a conference layout and seating arrangement method and system based on a recommendation algorithm, which solves the problems mentioned in the above background technology that the existing system is not convenient for automatically analyzing the importance and other relevant feature data of conference participants, and cannot effectively recommend the most suitable seats for each participant. In addition, the traditional conference layout and seating arrangement requires a lot of manual participation, and each step from data collection to analysis to actual layout is time-consuming and prone to errors. It is not convenient to arrange seats according to the positions and roles of the participants, and cannot consider their past interaction history and performance in the meeting, so it is not convenient to arrange seats more scientifically, which is not convenient to promote effective communication and exchanges, and reduces the overall quality of the meeting and the satisfaction of the participants. It is also not convenient to evaluate the layout effect after the meeting and it is not convenient to feed back the results to the meeting organizer, thereby reducing the organizational efficiency of the meeting, increasing the burden on the organizer, and also reducing the experience of the conference participants and the overall effect of the meeting.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] According to one aspect of the present invention, a conference layout and seating arrangement method based on a recommendation algorithm is provided, and the conference layout and seating arrangement method based on a recommendation algorithm comprises the following steps:

[0008] S1. Obtain information data of conference participants and pre-process the information data to obtain information feature data;

[0009] S2. Analyze the obtained information feature data using a scoring analysis algorithm to obtain importance scores of the meeting participants;

[0010] S3. Arrange the meeting seats based on the recommendation algorithm and the importance scores of the meeting participants;

[0011] S4. Use the effect evaluation algorithm to evaluate the recommended conference layout and seating arrangement, and feed back the evaluation results to the conference organizer.

[0012] Furthermore, obtaining information data of conference participants and preprocessing the information data to obtain information feature data includes the following steps:

[0013] S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the information data of the conference participants, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values;

[0014] S12, connecting the unprocessed data in the information data of the conference participants to generate a new data table, and associating different data tables through external key values ​​to generate a complete data table, and obtain an accurate data set;

[0015] S13. Extract features from the accurate data set and obtain information feature data.

[0016] Further, using a scoring analysis algorithm to analyze the obtained information feature data to obtain the importance scores of the conference participants includes the following steps:

[0017] S21. Compare the information data obtained from the meeting participants with industry standard professional performance indicators;

[0018] S22. Analyze the key factors that affect the importance of meeting participants and set corresponding evaluation levels;

[0019] S23, training the acquired information feature data of the conference participants through a scoring analysis algorithm, calculating the importance score of the conference participants, and determining whether they are key conference participants;

[0020] S24, normalizing the importance scores obtained by the score analysis algorithm, and calculating the normalized scores;

[0021] S25. The meeting organizer evaluates each key factor at different importance levels to form an importance evaluation matrix;

[0022] S26. Use logical methods to calculate the normalized scores and the importance assessment matrix to obtain a comprehensive importance assessment result;

[0023] S27, judging the relative positions of the conference participants in different importance levels according to the weight values ​​of the comprehensive evaluation results, and determining the importance levels of the conference participants;

[0024] S28, determining whether the importance level of the conference participant reaches a preset threshold, if so, marking it as a key conference participant, if not, treating it as a conference participant of low or medium importance;

[0025] S29. Based on the results of the scoring analysis algorithm and in combination with the suggestions of the meeting organizer, determine the key factors that affect the importance level of the meeting participants.

[0026] Furthermore, analyzing the key factors that affect the importance of meeting participants and setting corresponding evaluation levels includes the following steps:

[0027] S221. Collect various key factors that affect the importance of meeting participants based on the meeting topic and historical activity data of meeting participants;

[0028] S222. Screen and classify the collected key factors that affect the importance of meeting participants, remove duplicate factors, and summarize them into a set of measurable key factors;

[0029] S223. Set weights for each key factor that affects the importance of meeting participants based on industry standards and meeting topics, and set evaluation levels for each key factor;

[0030] S224. Reflect the importance and performance of each key factor in the importance assessment of meeting participants based on the set evaluation level.

[0031] Furthermore, training the acquired information feature data of the conference participants through a scoring analysis algorithm, calculating the importance score of the conference participants, and determining whether they are key conference participants includes the following steps:

[0032] S231, dividing the acquired conference participant information feature data into a training set and a test set;

[0033] S232, based on the training set, training the ensemble learning model by selecting features and feature values ​​related to the importance of the meeting participants;

[0034] S233. Build an integrated learning model consisting of multiple decisions and analyze the importance of meeting participants;

[0035] S234. Using the constructed ensemble learning model, calculate the comprehensive score of each conference participant in the test set, and calculate the importance score for each conference participant based on the comprehensive score;

[0036] S235. According to a preset threshold, use the importance score to determine whether each conference participant is a key conference participant.

[0037] Furthermore, the following steps are included to arrange the seating arrangement for the meeting based on the recommendation algorithm and in combination with the importance scores of the meeting participants:

[0038] S31, calculating the importance scores of the conference participants according to the objective function, and selecting the conference participants with the highest importance as the key conference participants;

[0039] S32, the conference participant performs a global search, calculates the best position of the conference participant in the seat row, and compares it with the current best position;

[0040] S33, updating the seat positions of the conference participants according to the optimization algorithm, and other conference participants perform local search and position adjustment according to the positions of the key conference participants;

[0041] S34, after each round of optimization, evaluate the positions of all meeting participants based on the new seating arrangement and select the best seating arrangement as a new starting point;

[0042] S35. Update importance ratings and seating arrangements based on meeting participants’ feedback and interaction efficiency;

[0043] S36, judging whether the termination condition of the optimization is met, if so, outputting the best seat layout, if not, returning to step S31 to continue the optimization;

[0044] S37, initializing final preparations for the meeting according to the optimal seating layout;

[0045] S38. Continue to optimize the seating layout and importance scores of meeting participants based on actual meeting feedback;

[0046] S39. Evaluate the meeting results. If the predetermined standards are met, fix the seating layout; otherwise, continue to optimize.

[0047] Furthermore, the formula for calculating the importance score of conference participants based on the objective function is:

[0048]

[0049] Among them, M represents the objective function;

[0050] K is represented as the importance membership matrix;

[0051] L represents the set of key participants in the meeting;

[0052] μ ab It is expressed as the importance affiliation of conference participant a to key conference participant b;

[0053] n represents the total number of meeting participants;

[0054] c is represented as the total number of key participants in the meeting;

[0055] x is represented as the fuzzy coefficient;

[0056] d ab It is expressed as the influence distance between meeting participant a and key meeting participant b.

[0057] Further, using the effect evaluation algorithm to evaluate the recommended conference layout and seating arrangement, and feeding back the evaluation results to the conference organizer includes the following steps:

[0058] S41, determining the factor parameters that affect the efficiency of conference interaction, and setting the initial search scope;

[0059] S42, preset an initial value of the evaluation cycle, and preset the number of iterations as a termination condition of the evaluation process;

[0060] S43, comparing the identified factor parameters affecting the meeting interaction efficiency with the known factor parameters for optimizing the meeting layout, and updating the factor parameters according to a preset comparison technology;

[0061] S44. Evaluate the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of interaction efficiency in each meeting through the verification method;

[0062] S45. Calculate the fitness score of each iteration based on the evaluation results of meeting participant satisfaction and interaction efficiency;

[0063] S46, comparing the fitness score after each iteration with the fitness score of the previous iteration, and selecting the factor parameters of the conference layout that have the greatest impact on the conference interaction efficiency and satisfaction as the current optimal solution;

[0064] S47, increasing the initial value of the evaluation cycle, and if the preset maximum number of iterations has been reached, terminating the evaluation process;

[0065] S48. Analyze the effect of the conference layout after the evaluation process is completed, and compare it with the preset conference efficiency and conference participant satisfaction standards to determine whether the conference layout has a significant impact on the conference interaction efficiency and satisfaction. If so, make adjustments; if not, feed back the factor parameters of the current conference layout to the conference organizer as factor parameters affecting the conference interaction efficiency.

[0066] Furthermore, through the verification method, the evaluation of the meeting participant satisfaction and interaction efficiency after comparing the factor parameters of the interaction efficiency of each meeting includes the following steps:

[0067] S441, initializing the first round of evaluation of conference layout and interaction efficiency, and dividing the parameter data set of the factors of conference interaction efficiency into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set.

[0068] S442, training a validation model using the adjusted conference interaction efficiency factor parameters on the training set, and testing the prediction performance of the validation model on the conference participant interaction efficiency and satisfaction on the test set;

[0069] S443. Calculate the generalization error of the verification model according to the actual performance of the factor parameters of conference interaction efficiency on the test set;

[0070] S444, looping step S441 to step S443 until each subset has been used as a test set;

[0071] S445. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of the interaction efficiency of each meeting.

[0072] According to another aspect of the present invention, a conference layout and seating arrangement system based on a recommendation algorithm is also provided. The conference layout and seating arrangement system based on a recommendation algorithm includes:

[0073] The data acquisition module is used to acquire the information data of the conference participants and pre-process the information data to obtain information feature data;

[0074] A data analysis module is used to analyze the obtained information feature data using a scoring analysis algorithm to obtain importance scores of conference participants;

[0075] A recommendation layout module is used to arrange the meeting layout and seating based on a recommendation algorithm and in combination with the importance scores of the meeting participants;

[0076] An effect evaluation module is used to evaluate the recommended conference layout and seating arrangement using an effect evaluation algorithm and to feed back the evaluation results to the conference organizer;

[0077] Among them, the data acquisition module is connected with the recommended layout module through the data analysis module, and the recommended layout module is connected with the effect evaluation module.

[0078] The beneficial effects of the present invention are:

[0079] 1. The present invention automatically analyzes the importance and other relevant feature data of conference participants, so that the most suitable seat can be effectively recommended for each participant. It not only takes into account the interaction potential between participants, but also optimizes the meeting process so that key participants can exert the greatest influence at the right time. By assigning an importance score to each participant, the organizer can allocate conference resources more scientifically, thereby ensuring that the most important interactions and discussions in the meeting can take place efficiently. The recommendation algorithm is not only based on the position and role of the participant, but also takes into account his past interaction history and performance in the meeting, so as to arrange seats more scientifically, promote effective communication and exchanges, and improve the overall quality of the meeting and the satisfaction of the participants. The layout effect after the meeting is evaluated through the effect evaluation algorithm, and the results are fed back to the meeting organizer, thereby improving the organizational efficiency of the meeting, reducing the burden on the organizer, and also optimizing the experience of the conference participants and the overall effect of the meeting.

[0080] 2. The present invention, through in-depth analysis of the information features of conference participants and importance scoring, can accurately identify key participants and arrange them in the most suitable positions in the meeting, which not only optimizes the communication lines of the meeting, but also ensures the effective transmission of key information and efficient discussion. By comparing the information of conference participants with industry standards and analyzing key influencing factors through scoring analysis algorithms, organizers can obtain a data-supported decision-making basis, which helps to scientifically formulate conference strategies and reduce subjective judgment errors. Through continuous scoring and evaluation level settings, it can dynamically adapt to changes in conference participants and quickly adjust seating arrangements to ensure that the conference layout always remains in the optimal state, thereby greatly improving the overall satisfaction and participation of the meeting and making the meeting results more effective.

[0081] 3. The present invention calculates the importance scores of conference participants through an objective function and selects the most important participants as key figures, which can ensure that the decision-making process is focused on the people who most influence the results of the meeting, thereby improving the effectiveness of meeting decisions. The seat positions are continuously updated through the optimization algorithm, so that the seat layout always remains in the most optimized state, and it can be flexibly adjusted according to the actual situation of the meeting, thereby improving the overall interactive quality and efficiency of the meeting, thereby improving the organizational efficiency of the meeting and the interactive quality of the participants.

[0082] 4. The present invention adapts to the specific needs and changes of the meeting and ensures the effectiveness of the final layout by setting the initial search range and evaluation cycle, as well as the continuous iteration process. The verification method and the preset comparison technology can accurately evaluate and compare the various factors that affect the interaction efficiency of the meeting, so as to ensure that the selected layout maximizes the satisfaction and interaction efficiency. By comparing the actual performance data with the model, calculating the generalization error and fitness score, the meeting layout can be adjusted in real time. After the evaluation cycle, the effect of the meeting layout will be compared with the preset efficiency and satisfaction standards, which not only ensures the actual effect of the meeting layout, but also provides valuable feedback for the meeting organizer, thereby improving the organizational efficiency of the meeting and the experience of the participants, and through continuous optimization and feedback, the scientificity and accuracy of the meeting layout adjustment are increased. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0084] Figure 1 is a flow chart of a conference layout and seating arrangement method based on a recommendation algorithm according to an embodiment of the present invention;

[0085] Figure 2 The present invention is a block diagram of a conference layout and seating arrangement system based on a recommendation algorithm according to an embodiment of the present invention.

[0086] In the figure:

[0087] 1. Data acquisition module; 2. Data analysis module; 3. Recommended layout module; 4. Effect evaluation module. DETAILED DESCRIPTION

[0088] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0089] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0090] According to an embodiment of the present invention, a conference layout and seating arrangement method and system based on a recommendation algorithm are provided.

[0091] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the conference layout and seating arrangement method based on the recommendation algorithm according to an embodiment of the present invention, the conference layout and seating arrangement method based on the recommendation algorithm includes the following steps:

[0092] S1. Obtain information data of conference participants and pre-process the information data to obtain information feature data;

[0093] Specifically, the information data includes:

[0094] Basic personal information: name, position or role, department or team, contact information, etc.

[0095] Professional background and experience: educational background, work experience, professional skills, industry certifications, etc.

[0096] Historical performance and contributions: past performance in similar meetings, contributions to the company or projects, historical performance evaluations, etc.

[0097] Interaction preferences and styles: communication style (e.g. proactive, reflective, etc.), leadership style (e.g. democratic, authoritative, etc.), decision-making preferences (e.g. data-driven, intuitive, etc.).

[0098] Relationship network and influence: social network position within the organization, relationships with other participants (such as superiors, colleagues, partners, etc.), status and influence in the industry.

[0099] Participation and activity: frequency of attendance at meetings, level of activity in meetings, attention paid to meeting topics, and willingness to participate.

[0100] Other relevant information: Personal development goals and expectations, knowledge of and interest in the conference topic, available resources and time (e.g., whether you travel frequently).

[0101] S2. Analyze the obtained information feature data using a scoring analysis algorithm to obtain importance scores of the meeting participants;

[0102] Specifically, importance ratings reflect the criticality of participants in the meeting and their potential contribution to the achievement of meeting goals.

[0103] Specifically, the importance score includes:

[0104] Position and role: The participant's position and role in the organization. Senior managers and decision makers usually score higher.

[0105] Professional knowledge and experience: Participants’ professional background, work experience, and their expertise and skills in the relevant field.

[0106] Historical performance and contributions: How the participant has performed in past meetings, as well as their contributions and achievements to the project.

[0107] Networks and influence: The actor’s social network position within the organization, as well as their influence and authority within the industry or organization.

[0108] Participation and activity: The frequency and activity of participants in the meeting, as well as their attention to and willingness to participate in the meeting topics.

[0109] Interaction preferences and styles: Participants’ communication and leadership styles, as well as their decision-making preferences and interaction patterns.

[0110] Other relevant factors: Personal factors that may affect the effectiveness of the meeting, such as personal development goals, interest in the meeting topic, and available resources.

[0111] S3. Arrange the meeting seats based on the recommendation algorithm and the importance scores of the meeting participants;

[0112] S4. Use the effect evaluation algorithm to evaluate the recommended conference layout and seating arrangement, and feed back the evaluation results to the conference organizer.

[0113] Preferably, obtaining the information data of the conference participants and preprocessing the information data to obtain the information feature data includes the following steps:

[0114] S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the information data of the conference participants, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values;

[0115] S12, connecting the unprocessed data in the information data of the conference participants to generate a new data table, and associating different data tables through external key values ​​to generate a complete data table, and obtain an accurate data set;

[0116] S13. Extract features from the accurate data set and obtain information feature data.

[0117] It should be explained that, for example, there is an Excel table containing participant information, including the participant's name, position, years of work experience, etc. Table) or data cleaning tools (such as Python's Pandas library) to identify and delete completely duplicate records. For missing years of work, use the mean or median for interpolation, or use model prediction (such as K-nearest neighbors or regression models) to estimate missing values. Use statistical methods (such as box plots) to identify abnormal years of work, and then manually check whether these abnormal values ​​are reasonable or whether they are data entry errors. Then, there is a CSV file containing the participants' social media activity data. Use SQL's JOIN operation or Pandas' merge function to merge the two data sets through the participant's name as an external key value. The merged data may contain duplicate columns (such as name). Use pivot or aggregation functions to eliminate duplication and ensure the uniqueness of the data. Finally, get a clean and complete data set. Use correlation analysis or model-based feature selection methods to identify the most useful features, perform one-hot encoding on categorical features, standardize or normalize numerical features, and construct new features based on business logic. For example, calculate the participant's work experience level based on years of work.

[0118] Preferably, analyzing the obtained information feature data using a scoring analysis algorithm to obtain the importance scores of the conference participants includes the following steps:

[0119] S21. Compare the information data obtained from the meeting participants with industry standard professional performance indicators;

[0120] S22. Analyze the key factors that affect the importance of meeting participants and set corresponding evaluation levels;

[0121] S23, training the acquired information feature data of the conference participants through a scoring analysis algorithm, calculating the importance score of the conference participants, and determining whether they are key conference participants;

[0122] S24, normalizing the importance scores obtained by the score analysis algorithm, and calculating the normalized scores;

[0123] S25. The meeting organizer evaluates each key factor at different importance levels to form an importance evaluation matrix;

[0124] S26, using a logical method (i.e., a fuzzy operation operator) to calculate the normalized score (i.e., the weight vector) and the importance evaluation matrix (i.e., the fuzzy relationship matrix) to obtain a comprehensive importance evaluation result;

[0125] S27, judging the relative positions of the conference participants in different importance levels according to the weight values ​​of the comprehensive evaluation results, and determining the importance levels of the conference participants;

[0126] S28, determining whether the importance level of the conference participant reaches a preset threshold, if so, marking it as a key conference participant, if not, treating it as a conference participant of low or medium importance;

[0127] S29. Based on the results of the scoring analysis algorithm and in combination with the suggestions of the meeting organizer, determine the key factors that affect the importance level of the meeting participants.

[0128] It needs to be explained that, for example, there is a data set containing the positions, years of work experience and performance evaluations of the participants. The industry average years of work experience and average performance evaluation are used as benchmarks to calculate the relative performance of each participant. Based on the participant data, factors such as position, years of work experience, and performance evaluation are identified. A scoring analysis algorithm is used to identify key factors. Three evaluation levels of high, medium, and low are set according to the importance of the factors. Then, the scoring analysis algorithm (i.e., the fuzzy isolation forest algorithm) is used to train the ensemble learning model. The trained ensemble learning is used to predict new participant data to obtain importance scores. The maximum and minimum normalization method is used to scale the scores to between 0 and 1 to ensure the comparability of the scores. ,The organizer scores the importance of each factor at different levels based on experience, and constructs a matrix in which rows represent factors, columns represent importance levels, and the value in the cell represents the importance score of the factor at that level. Finally, the weight vector (normalized score) and the fuzzy relationship matrix (evaluation matrix) are operated using operators in fuzzy logic (such as maximum-minimum combination) to obtain the comprehensive evaluation results of each participant. According to the component values ​​of the comprehensive evaluation results, the participants are assigned to the corresponding importance levels, and an importance score threshold is set. If the participant's score exceeds the threshold, it is marked as a key meeting participant. The key factors are determined using feature importance analysis and organizer feedback.

[0129] Preferably, analyzing the key factors affecting the importance of conference participants and setting corresponding evaluation levels includes the following steps:

[0130] S221. Collect various key factors that affect the importance of meeting participants based on the meeting topic and historical activity data of meeting participants;

[0131] S222. Screen and classify the collected key factors that affect the importance of meeting participants, remove duplicate factors, and summarize them into a set of measurable key factors;

[0132] S223. Set weights for each key factor that affects the importance of meeting participants based on industry standards and meeting topics, and set evaluation levels for each key factor;

[0133] S224. Reflect the importance and performance of each key factor in the importance assessment of meeting participants based on the set evaluation level.

[0134] It needs to be explained that, for example, a conference on artificial intelligence technology is being organized, and data on the performance of participants in similar conferences in the past are collected, such as the number of speeches, the number of suggestions made, the group discussions participated in, etc., and key factors related to the theme of the conference are identified, such as expertise in the field of artificial intelligence, relevant project experience, etc., and factors that are irrelevant to the theme of the conference or irrelevant to the participants' importance assessment are removed. The remaining factors are classified by type, such as professional background, historical performance, interactive ability, etc., and then the expert scoring method, hierarchical analysis method (AHP) or data analysis methods (such as principal component analysis) are used to determine the weight of each factor, and an evaluation level is set for each factor, such as high, medium, and low. Finally, the key factor evaluation level of each participant is combined with its weight to calculate a comprehensive evaluation.

[0135] Preferably, training the acquired conference participant information feature data through a scoring analysis algorithm, calculating the importance score of the conference participant, and determining whether the conference participant is a key conference participant includes the following steps:

[0136] S231, dividing the acquired conference participant information feature data into a training set and a test set;

[0137] S232, based on the training set, training the ensemble learning model by selecting features and feature values ​​related to the importance of the meeting participants;

[0138] S233, construct an integrated learning model consisting of multiple decisions (i.e., multiple isolated trees) and analyze the importance of meeting participants;

[0139] S234. Use the constructed ensemble learning model (i.e., the isolation forest model) to calculate the comprehensive score of each conference participant in the test set, and calculate the importance score for each conference participant based on the comprehensive score;

[0140] S235. According to a preset threshold, use the importance score to determine whether each conference participant is a key conference participant.

[0141] Specifically, during the training process, the data points are divided into two subsets according to the selected eigenvalue (one containing data points less than or equal to the eigenvalue, and the other containing data points greater than the eigenvalue), and a split operation is performed; this process is recursively repeated for each subset until the stopping condition is met (such as the subset size reaches a predetermined threshold and the depth of the tree reaches the maximum value).

[0142] It needs to be explained that, for example, there is a CSV file containing features such as participant positions, years of work experience, performance evaluation, etc., and a stratified sampling or random sampling method is used to divide the data set into a training set (e.g., 70%) and a test set (e.g., 30%). Features that are highly correlated with the importance of meeting participants, such as positions, performance evaluation, etc., are selected. A random forest algorithm is used to construct an ensemble learning model (i.e., an isolation forest model). The random forest consists of multiple decision trees, each of which is trained on a different subset of the data. The feature importance output by the ensemble learning model is used to analyze which factors have a significant impact on the importance of meeting participants. Finally, the ensemble learning model outputs a comprehensive score for each participant in the test set, which reflects the importance of the participant. If the participant's comprehensive score exceeds the threshold, it is marked as a key meeting participant.

[0143] Preferably, arranging the meeting seats based on the recommendation algorithm and in combination with the obtained importance scores of the meeting participants includes the following steps:

[0144] S31, calculating the importance scores of the conference participants according to the objective function (i.e., the objective function in the fuzzy C-means clustering algorithm), and selecting the conference participants with the highest importance as the key conference participants;

[0145] S32, the conference participant performs a global search, calculates the best position of the conference participant in the seat row, and compares it with the current best position;

[0146] S33, updating the seat positions of the conference participants according to the optimization algorithm (i.e., the wolf pack algorithm), and other conference participants perform local search and position adjustment according to the positions of the key conference participants;

[0147] S34, after each round of optimization, evaluate the positions of all meeting participants according to the new seating arrangement and select the best seating arrangement as a new starting point;

[0148] S35. Update importance ratings and seating arrangements based on meeting participants’ feedback and interaction efficiency;

[0149] S36, judging whether the optimization termination condition is met, if so, outputting the best seat layout, if not, returning to step S31 to continue optimization;

[0150] S37, initializing final preparations for the meeting according to the optimal seating layout;

[0151] S38. Continue to optimize the seating layout and importance scores of meeting participants based on actual meeting feedback;

[0152] S39. Evaluate the meeting results. If the predetermined standards are met, fix the seating layout; otherwise, continue to optimize.

[0153] It needs to be explained that, for example, there is a data set containing participant characteristics, and the fuzzy C-means algorithm is used to cluster the participants. The membership degree of each participant to each cluster represents its importance. The importance score of each participant is calculated based on the membership degree, and the entire possible seating layout space is searched to find the best seating arrangement. The social behavior of wolves is simulated to optimize the problem solution. The optimal solution is searched through the roles of leader, follower and explorer. Local search is performed around key participants to find a better seating arrangement. The evaluation function is designed according to the meeting goals (such as interaction efficiency, line of sight clarity, etc.), and the seating layout with the highest evaluation score is selected as the starting point for a new round of optimization. The opinions of the participants are collected through questionnaires or direct feedback. Finally, the seating positions of the participants are adjusted according to the feedback, the meeting venue and seats are arranged according to the optimal seating layout, the seating layout and participant scores are adjusted according to real-time feedback, and the effect of the meeting is evaluated according to the meeting goals. If the meeting effect meets the predetermined standards, the current seating layout is fixed.

[0154] Specifically, the recommendation algorithm is a hybrid recommendation algorithm that integrates the wolf pack algorithm and fuzzy clustering. In a data-sparse environment, it is difficult for traditional collaborative filtering recommendations to find reliable similar users for target users, which affects the recommendation results. Therefore, it is proposed to use item-based collaborative filtering recommendations for sparse matrices to fill data to ensure data integrity. Then, the fuzzy C-means clustering algorithm optimized by the wolf pack algorithm is added to the traditional collaborative filtering algorithm to find reliable neighbor users, and refer to their historical data to form a recommendation list. After filtering the items that the target user has interacted with, the final recommendation list is formed. In the data processing process, the data relationship between items is fully mined according to the item-based collaborative filtering algorithm, and the zero value of the original matrix is ​​filled to reduce data sparsity; from the user's perspective, the relevant neighbor set is screened according to the size of the fuzzy clustering membership to expand the search range of relevant users; the wolf pack algorithm is introduced into fuzzy clustering, and the global search advantage of the wolf pack algorithm is used to improve the accuracy of finding similar users.

[0155] Preferably, the formula for calculating the importance score of the conference participants according to the objective function is:

[0156]

[0157] Where M represents the objective function;

[0158] K is represented as the importance membership matrix;

[0159] L represents the set of key participants in the meeting;

[0160] μ ab It is expressed as the importance affiliation of conference participant a to key conference participant b;

[0161] n represents the total number of meeting participants;

[0162] c is represented as the total number of key participants in the meeting;

[0163] x is represented as the fuzzy coefficient;

[0164] d ab It is expressed as the influence distance between meeting participant a and key meeting participant b.

[0165] Preferably, using an effect evaluation algorithm to evaluate the recommended conference layout and seating arrangement, and feeding back the evaluation results to the conference organizer includes the following steps:

[0166] S41, determining the factor parameters that affect the efficiency of conference interaction, and setting the initial search scope;

[0167] S42, preset an initial value (usually 0 or 1) of the evaluation period (i.e., preset a time counter), and preset the number of iterations as a termination condition of the evaluation process;

[0168] Specifically, a time counter is a counting variable used to track the iteration process in an algorithm or program. In optimization and computational tasks, a time counter is used to monitor the number of iterations that an algorithm has executed and decide when to stop the iteration process.

[0169] Specifically, the termination conditions include that the time recorded by the time counter reaches a preset maximum value and the number of iterations of the optimization algorithm reaches a preset maximum number.

[0170] S43, comparing the identified factor parameters affecting the meeting interaction efficiency with the known factor parameters for optimizing the meeting layout, and updating the factor parameters according to a preset comparison technology;

[0171] S44, evaluating the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of interaction efficiency in each meeting through a validation method (i.e., k-fold cross validation);

[0172] Specifically, k-fold cross validation is a machine learning model evaluation method, which refers to dividing the collected factor parameter data set of wind speed change pattern into k subsets, one of which is used as a validation set, and the remaining k-1 subsets are used as training sets.

[0173] S45. Calculate the fitness score of each iteration based on the evaluation results of meeting participant satisfaction and interaction efficiency;

[0174] S46, comparing the fitness score after each iteration with the fitness score of the previous iteration, and selecting the factor parameters of the conference layout that have the greatest impact on the conference interaction efficiency and satisfaction as the current optimal solution;

[0175] S47, increasing the initial value of the evaluation cycle, and if the preset maximum number of iterations has been reached, terminating the evaluation process;

[0176] S48. Analyze the effect of the conference layout after the evaluation process is completed, and compare it with the preset conference efficiency and conference participant satisfaction standards to determine whether the conference layout has a significant impact on the conference interaction efficiency and satisfaction. If so, make adjustments; if not, feed back the factor parameters of the current conference layout to the conference organizer as factor parameters affecting the conference interaction efficiency.

[0177] It needs to be explained that, for example, the impact of the layout of the conference room on the meeting efficiency is being analyzed, and factors that may affect the interaction efficiency are identified, such as seat distance, seat angle, screen position, etc. A reasonable initial search range is set for each factor, for example, the seat distance can be from 1 meter to 5 meters, the evaluation period is set to 1 day, the number of iterations is set to 10, and a t-test or variance analysis is used to compare the differences between the two groups of parameters. Different subsets are used alternately as validation sets and training sets. Questionnaires or observations are used to evaluate the satisfaction of participants. The satisfaction score and the interaction efficiency indicator are combined to calculate the fitness score. After each iteration, the fitness scores are compared and the factor parameter combination with the highest score is selected. After each iteration, the value of the time counter is increased and the evaluation is stopped when 10 iterations are reached. Finally, statistical analysis methods are used to evaluate the effect of the meeting layout and compare the actual effect with the preset standards (such as industry average satisfaction).

[0178] Specifically, the evaluation algorithm is an SVM parameter selection method based on an improved bird flock optimization algorithm, which is a strategy for applying nature-inspired algorithms to machine learning parameter optimization. In this method, an improved bird flock optimization algorithm is used to select or optimize SVM parameters to improve the performance of the model.

[0179] Specifically, SVM is a supervised learning algorithm based on the principle of structural risk minimization. It uses expected risk minimization as the evaluation criterion and aims to obtain a decision function with high generalization ability through finite sample training, that is, to find an optimal hyperplane to completely separate the samples under the condition of linear separability.

[0180] Specifically, the improved bird flock optimization algorithm refers to an improvement and variant of the traditional particle swarm optimization algorithm (Particle Swarm Optimization, PSO). The particle swarm optimization algorithm is an optimization technology based on swarm intelligence, which simulates the social behavior of bird flocks or fish schools to solve optimization problems.

[0181] Specifically, the improved bird flock optimization algorithm includes the following improvements:

[0182] Improvements in speed and position update rules: In standard PSO, the movement of particles is based on their best historical position and the best position of the entire group. Improved algorithms may use different rules to adjust the speed and position of particles to improve convergence speed and avoid falling into local optimality.

[0183] Parameter adjustment and control: Improved algorithms may include dynamic adjustment mechanisms for PSO parameters such as inertia weight, individual best and group best learning factors to balance exploration (global search) and exploitation (local search) during the search process.

[0184] Customization to adapt to specific problems: For specific types of problems (such as nonlinear problems, multi-objective problems, etc.), the improved bird flock optimization algorithm may be specially designed to solve these problems more effectively.

[0185] Preferably, by means of a verification method, evaluating the satisfaction and interaction efficiency of conference participants after comparing the factor parameters of interaction efficiency of each conference includes the following steps:

[0186] S441, initializing the first round of evaluation of conference layout and interaction efficiency, and dividing the parameter data set of the factors of conference interaction efficiency into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set.

[0187] S442, training a validation model using the adjusted conference interaction efficiency factor parameters on the training set, and testing the prediction performance of the validation model on the conference participant interaction efficiency and satisfaction on the test set;

[0188] S443. Calculate the generalization error of the verification model (i.e., the SVM model) based on the actual performance of the factor parameters of the conference interaction efficiency on the test set;

[0189] Specifically, calculating the generalization error of the validation model refers to calculating the prediction error of the SVM model on the test set.

[0190] S444, looping step S441 to step S443 until each subset has been used as a test set;

[0191] S445. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of the interaction efficiency of each meeting.

[0192] It needs to be explained that, for example, there is a data set containing parameters of conference interaction efficiency factors. The data set is divided into k subsets using k-fold cross validation. In the first round, one subset is selected as the test set and the remaining subsets are used as training sets. The training set is then used to train the SVM model. The predictive performance of the model, such as interaction efficiency and satisfaction, is evaluated on the test set. The error is calculated by comparing the SVM model predicted value and the actual value. Different subsets are repeatedly used as test sets and the remaining subsets are used as training sets to ensure that each subset has a chance to be used as a test set to improve the accuracy of the evaluation. The generalization errors of all rounds are added together and then divided by the number of rounds. Finally, the average of the generalization errors calculated in all rounds is obtained as the overall evaluation of the satisfaction and interaction efficiency of the conference participants after the factor parameters of each conference interaction efficiency are compared.

[0193] According to another embodiment of the present invention, Figure 2 As shown, a conference layout and seating arrangement system based on a recommendation algorithm is also provided, and the conference layout and seating arrangement system based on a recommendation algorithm includes:

[0194] Data acquisition module 1, used to acquire information data of conference participants and pre-process the information data to obtain information feature data;

[0195] Data analysis module 2, used to analyze the obtained information feature data using a scoring analysis algorithm to obtain importance scores of conference participants;

[0196] The recommendation layout module 3 is used to arrange the layout of the meeting based on the recommendation algorithm and the importance scores of the meeting participants;

[0197] The effect evaluation module 4 is used to evaluate the recommended conference layout and seating arrangement using an effect evaluation algorithm, and to feed back the evaluation result to the conference organizer;

[0198] The data acquisition module 1 is connected to the recommended layout module 3 via the data analysis module 2 , and the recommended layout module 3 is connected to the effect evaluation module 4 .

[0199] In summary, with the help of the above technical scheme of the present invention, the present invention can accurately identify key participants and arrange them in the most suitable position in the meeting through in-depth analysis of the information characteristics of the conference participants and importance scoring, which not only optimizes the communication dynamics of the meeting, but also ensures the effective transmission of key information and the efficient discussion. By comparing the information of the conference participants with the industry standards and analyzing the key influencing factors through the scoring analysis algorithm, the organizer can obtain a data-supported decision-making basis, which is helpful to scientifically formulate conference strategies and reduce subjective judgment errors. Through continuous scoring and evaluation level settings, it can dynamically adapt to the changes of conference participants and quickly adjust the seating arrangement to ensure that the conference layout always maintains the optimal state, thereby greatly improving the overall satisfaction and participation of the meeting and making the meeting results more effective. The present invention calculates the importance scores of conference participants through the objective function and selects the most important participants as key figures, which can ensure that the decision-making process is focused on the people who most affect the results of the meeting, thereby improving the effectiveness of the meeting decision, and continuously updates the seat position through the optimization algorithm, so that the seat layout always maintains the optimal state, and is flexibly adjusted according to the actual situation of the meeting, which improves the interactive quality and efficiency of the overall meeting, thereby improving the organizational efficiency of the meeting and the interactive quality of the participants. The present invention adapts to the specific needs and changes of the meeting by setting the initial search range and evaluation cycle, as well as the continuous iterative process, to ensure the effectiveness of the final layout. The verification method and the preset comparison technology can accurately evaluate and compare the various factors affecting the efficiency of meeting interaction, so as to ensure that the selected layout maximizes the satisfaction and interaction efficiency. By comparing the actual performance data with the model, calculating the generalization error and fitness score, the meeting layout can be adjusted in real time. After the evaluation cycle is over, the effect of the meeting layout will be compared with the preset efficiency and satisfaction standards, which not only ensures the actual effect of the meeting layout, but also provides valuable feedback for the meeting organizer, thereby improving the organizational efficiency of the meeting and the experience of the participants, and through continuous optimization and feedback, the scientificity and accuracy of the meeting layout adjustment are increased.

[0200] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A conference layout and seating arrangement system based on a recommendation algorithm, characterized in that: The conference layout seating system includes: The data acquisition module is used to acquire the information data of the conference participants and pre-process the information data to obtain information feature data; The information data includes professional background and experience, historical performance and contributions, interaction preferences and style, participation and activity, and knowledge and interest in the conference topic; A data analysis module is used to analyze the obtained information feature data using a scoring analysis algorithm to obtain importance scores of conference participants; A recommendation layout module is used to arrange the meeting layout and seating based on a recommendation algorithm and in combination with the importance scores of the meeting participants; An effect evaluation module is used to evaluate the recommended conference layout and seating arrangement using an effect evaluation algorithm and to feed back the evaluation results to the conference organizer; The method of arranging the meeting seats based on the recommendation algorithm and combining the importance scores of the meeting participants comprises the following steps: S31, calculating the importance scores of the conference participants according to the objective function, and selecting the conference participants with the highest importance as the key conference participants; S32, the conference participant performs a global search, calculates the best position of the conference participant in the seat row, and compares it with the current best position; S33, updating the seat positions of the conference participants according to the optimization algorithm, and other conference participants perform local search and position adjustment according to the positions of the key conference participants; S34, after each round of optimization, evaluate the positions of all meeting participants based on the new seating arrangement and select the best seating arrangement as a new starting point; S35. Update importance ratings and seating arrangements based on meeting participants’ feedback and interaction efficiency; S36, judging whether the optimization termination condition is met, if so, outputting the best seat layout, if not, returning to step S31 to continue optimization; S37, initializing final preparations for the meeting according to the optimal seating layout; S38. Continue to optimize the seating layout and importance scores of meeting participants based on actual meeting feedback; S39. Evaluate the meeting effect. If it meets the predetermined standard, fix the seating layout. Otherwise, continue to optimize. The formula for calculating the importance score of conference participants according to the objective function is: ； in, M It is expressed as the objective function; K It is expressed as an importance membership matrix; L Represented as a set of key participants in the meeting; Indicate as a conference participant a Key participants in the meeting b The importance of membership; n Expressed as the total number of meeting participants; c Expressed as the total number of key participants in the meeting; x It is expressed as fuzzy coefficient; Indicate as a conference participant a Meeting with key participants b The influence distance between them.

2. A conference layout and seating arrangement system based on a recommendation algorithm according to claim 1, characterized in that: The method of obtaining the information data of the conference participants and preprocessing the information data to obtain the information feature data includes the following steps: S11, obtaining duplicate data, missing values ​​and abnormal values ​​of the information data of the conference participants, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values; S12, connecting the unprocessed data in the information data of the conference participants to generate a new data table, and associating different data tables through external key values ​​to generate a complete data table, and obtain an accurate data set; S13. Extract features from the accurate data set and obtain information feature data.

3. A conference layout and seating arrangement system based on a recommendation algorithm according to claim 1, characterized in that: The step of analyzing the obtained information feature data using a scoring analysis algorithm to obtain the importance scores of the conference participants includes the following steps: S21. Compare the information data obtained from the meeting participants with industry standard professional performance indicators; S22. Analyze the key factors that affect the importance of meeting participants and set corresponding evaluation levels; S23, training the acquired information feature data of the conference participants through a scoring analysis algorithm, calculating the importance score of the conference participants, and determining whether they are key conference participants; S24, normalizing the importance scores obtained by the score analysis algorithm, and calculating the normalized scores; S25. The meeting organizer evaluates each key factor at different importance levels to form an importance evaluation matrix; S26. Use logical methods to calculate the normalized scores and the importance assessment matrix to obtain a comprehensive importance assessment result; S27, judging the relative positions of the conference participants in different importance levels according to the weight values ​​of the comprehensive evaluation results, and determining the importance levels of the conference participants; S28, determining whether the importance level of the conference participant reaches a preset threshold, if so, marking it as a key conference participant, if not, treating it as a conference participant of low or medium importance; S29. Based on the results of the scoring analysis algorithm and in combination with the suggestions of the meeting organizer, determine the key factors that affect the importance level of the meeting participants.

4. A conference layout and seating arrangement system based on a recommendation algorithm according to claim 3, characterized in that: The analysis of the key factors affecting the importance of conference participants and setting corresponding evaluation levels includes the following steps: S221. Collect various key factors that affect the importance of meeting participants based on the meeting topic and historical activity data of meeting participants; S222. Screen and classify the collected key factors that affect the importance of meeting participants, remove duplicate factors, and summarize them into a set of measurable key factors; S223. Set weights for each key factor that affects the importance of meeting participants based on industry standards and meeting topics, and set evaluation levels for each key factor; S224. Reflect the importance and performance of each key factor in the importance assessment of meeting participants based on the set evaluation level.

5. The conference layout and seating arrangement system based on recommendation algorithm according to claim 3, characterized in that: The method of training the acquired conference participant information feature data by using a scoring analysis algorithm, calculating the importance score of the conference participant, and determining whether the conference participant is a key conference participant includes the following steps: S231, dividing the acquired conference participant information feature data into a training set and a test set; S232, based on the training set, training the ensemble learning model by selecting features and feature values ​​related to the importance of the meeting participants; S233. Build an integrated learning model consisting of multiple decisions and analyze the importance of meeting participants; S234. Using the constructed ensemble learning model, calculate the comprehensive score of each conference participant in the test set, and calculate the importance score for each conference participant based on the comprehensive score; S235. According to a preset threshold, use the importance score to determine whether each conference participant is a key conference participant.

6. A conference layout and seating arrangement system based on a recommendation algorithm according to claim 1, characterized in that: The method of evaluating the recommended conference layout and seating arrangement by using the effect evaluation algorithm and feeding back the evaluation result to the conference organizer comprises the following steps: S41, determining the factor parameters that affect the efficiency of conference interaction, and setting the initial search scope; S42, preset an initial value of the evaluation cycle, and preset the number of iterations as a termination condition of the evaluation process; S43, comparing the identified factor parameters affecting the meeting interaction efficiency with the known factor parameters for optimizing the meeting layout, and updating the factor parameters according to a preset comparison technology; S44. Evaluate the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of interaction efficiency in each meeting through the verification method; S45. Calculate the fitness score of each iteration based on the evaluation results of meeting participant satisfaction and interaction efficiency; S46, comparing the fitness score after each iteration with the fitness score of the previous iteration, and selecting the factor parameters of the conference layout that have the greatest impact on the conference interaction efficiency and satisfaction as the current optimal solution; S47, increasing the initial value of the evaluation cycle, and if the preset maximum number of iterations has been reached, terminating the evaluation process; S48. Analyze the effect of the conference layout after the evaluation process is completed, and compare it with the preset conference efficiency and conference participant satisfaction standards to determine whether the conference layout has a significant impact on the conference interaction efficiency and satisfaction. If so, make adjustments; if not, feed back the factor parameters of the current conference layout to the conference organizer as factor parameters affecting the conference interaction efficiency.

7. A conference layout and seating arrangement system based on a recommendation algorithm according to claim 6, characterized in that: The verification method for evaluating the meeting participant satisfaction and interaction efficiency after comparing the factor parameters of each meeting interaction efficiency includes the following steps: S441, initializing the first round of evaluation of conference layout and interaction efficiency, and dividing the parameter data set of the factors of conference interaction efficiency into several subsets. In each round, one subset is selected as a test set, and the union of all the remaining subsets is used as a training set. S442, training a validation model using the adjusted conference interaction efficiency factor parameters on the training set, and testing the prediction performance of the validation model on the conference participant interaction efficiency and satisfaction on the test set; S443. Calculate the generalization error of the verification model according to the actual performance of the factor parameters of conference interaction efficiency on the test set; S444, looping step S441 to step S443 until each subset has been used as a test set; S445. Obtain an average value of the generalization errors calculated in all rounds as an overall evaluation of the meeting participants' satisfaction and interaction efficiency after comparing the factor parameters of the interaction efficiency of each meeting.

Images