Multi-source data fusion production environment emotion management and value creation system

Abstract

The invention relates to a multi-source data fusion production environment emotion management and value creation system, which relates to the field of data processing, and comprises the steps of obtaining an emotion recognition result and an execution task importance level of a target post employee group; retrieving a high-frequency execution task importance level of the same scheme of the first production environment emotion control scheme, and calculating a deviation from the execution task importance level to obtain a first task emotion imbalance coefficient; when the emotion belongs to the negative emotion, or / and the first task emotion imbalance coefficient is greater than or equal to an imbalance coefficient threshold value, obtaining a second production environment emotion control scheme; obtaining an emotion prediction result through the emotion prediction model; and when the emotion is the positive emotion and is smaller than the imbalance coefficient threshold value, carrying out production environment adjustment according to a second production environment emotion control scheme. The technical problem that the overall production efficiency cannot be effectively improved due to the fact that the importance of task execution and the comprehensive influence of the working environment on group emotion are not fully considered in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a production environment emotion management and value creation system for multi-source data fusion. Background Art

[0002] In modern production environments, especially those involving mental labor and labor-intensive production scenarios, the emotions of employees have a significant impact on production efficiency. Traditional emotion management methods mainly focus on the individual level, improving the emotional state of employees through psychological counseling or personal emotion regulation techniques, and fail to fully consider the importance of task execution and the comprehensive impact of the work environment on group emotions. Such one-sided methods may lead to a disconnection between emotion regulation measures and actual production needs, and are unable to effectively improve overall production efficiency and employee job satisfaction. Summary of the Invention

[0003] Aiming at the technical problem in the prior art that due to the fact that emotion management methods mainly focus on the individual level and fail to fully consider the importance of task execution and the comprehensive impact of the work environment on group emotions, resulting in the inability to effectively improve overall production efficiency and employee emotions, the present invention provides a production environment emotion management and value creation system for multi-source data fusion to solve this problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] The present invention provides a production environment emotion management and value creation system for multi-source data fusion, including: obtaining the emotion recognition result of the target position employee group and the importance level of the executed task, where the importance level of the executed task is used to represent the required output per unit time; retrieving the high-frequency executed task importance level of the same scheme in the first production environment emotion control scheme; calculating the deviation between the high-frequency executed task importance level and the importance level of the executed task to obtain the first task emotion disorder coefficient; when the emotion recognition result belongs to negative emotion, or / and the first task emotion disorder coefficient is greater than or equal to the disorder coefficient threshold, updating the first production environment emotion control scheme to obtain the second production environment emotion control scheme; processing the second production environment emotion control scheme and the importance level of the executed task through an emotion prediction model to obtain an emotion prediction result; when the emotion prediction result is positive emotion and the second task emotion disorder coefficient of the second production environment emotion control scheme is less than the disorder coefficient threshold, adjusting the production environment according to the second production environment emotion control scheme.

[0006] The beneficial effects of the present invention are as follows: It can dynamically monitor and adjust the production environment to adapt to the emotional changes of employees and the importance of task execution. When the system detects negative emotions of employees or the task emotion disorder coefficient exceeds the threshold, it will automatically update the emotion control plan and verify the effectiveness of the new plan through the emotion prediction model. Finally, the system adjusts the production environment based on the predicted positive emotions and the lower task emotion disorder coefficient, thereby improving the job satisfaction of employees and the humanization level of overall production while ensuring production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic flow chart of the execution steps of a multi-source data fusion-based production environment emotion management and value creation system provided by the present invention;

[0008] Figure 2 It is a schematic flow chart for determining the importance level of high-frequency execution tasks of a multi-source data fusion-based production environment emotion management and value creation system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0010] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0011] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order to enable any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0012] As Figure 1 shown, an embodiment of the present invention provides a production environment emotion management and value creation system for multi-source data fusion, and the execution steps include:

[0013] S10: Obtain the emotion recognition result of the target position employee group and the importance level of the executed task, where the importance level of the executed task is used to represent the required output per unit time;

[0014] Specifically, the emotion recognition result: refers to the employee emotion state obtained through various technical means (such as facial expression analysis, speech intonation detection, physiological signal monitoring, etc.); the importance level of the executed task: is used to represent the task priority or criticality of the required output per unit time; the target position employee group refers to the employee group of the target position type, and the emotion recognition result represents the mode emotion recognition result of the target position employee group. If the number of employees with negative emotions in the target position employee group is greater than p%, preferably 30%, then the emotion recognition result is negative emotion, otherwise, the emotion recognition result is positive emotion.

[0015] In detail, the system first collects the emotion state of the target position employees through the integrated emotion recognition technology. At the same time, the system obtains the importance level of each task from the task management system. The collection of this data is crucial because it enables the system to understand the current emotion state of the employees and the priority of the tasks they are dealing with. The consideration of these two important elements lays the foundation for the subsequent analysis of the interaction between the production environment and the employees' emotions.

[0016] Through this process, the system can comprehensively master the emotion state of the employees and the urgency of the tasks, so as to provide data support for subsequent decision-making.

[0017] S20: Retrieve the high-frequency execution task importance level of the same solution of the first production environment emotion control solution;

[0018] Further, as Figure 2 shown, retrieving the high-frequency execution task importance level of the same solution of the first production environment emotion control solution, the execution of step S20 includes:

[0019] S21: The first production environment emotion control solution includes a lighting control sub-solution, an audio-visual type control sub-solution, and an interaction device modality control sub-solution. Among them, the interaction device modality control sub-solution is used to control the interaction statement type between the interaction device and the employees, and the interaction statement type includes relaxation statements, encouragement statements, and warning statements;

[0020] S22: Retrieve the historical execution task record importance level of the same control solution of the lighting control sub-solution, the audio-visual type control sub-solution, and the interaction device modality control sub-solution;

[0021] S23: Conduct a centralized value evaluation on the importance level of the historical execution task records to obtain the importance level of the high-frequency execution tasks.

[0022] Further, retrieve the same control schemes for the lighting control sub-scheme, the audio-visual type control sub-scheme, and the interaction device modality control sub-scheme. Performing step S12 includes:

[0023] S221: The lighting control sub-scheme includes a first lamp brightness list and a first lighting color list. The audio-visual type control sub-scheme includes a first video type list and a first music type list. The interaction device modality control sub-scheme includes a first statement type list;

[0024] S222: Obtain the historical production environment emotion control scheme, where the historical production environment emotion control scheme includes a second lamp brightness list, a second lighting color list, a second video type list, a second music type list, and a second statement type list;

[0025] S223: Construct an environmental control scheme distance evaluation function:

[0026]

[0027] where d i represents the control distance of the i-th list. When i represents the lamp brightness or lighting color, d i is used to calculate the proportion of the number of lamps with a brightness absolute deviation greater than the brightness deviation threshold, or calculate the proportion of the number of lamps with a color RGB absolute deviation greater than the color RGB deviation threshold. When i represents the video type, music type, or statement type, d i is used to calculate the ratio of the number of non-intersecting types to the number of types in the union of types. w i represents the preset weight of the i-th list, and D represents the control distance between the historical production environment emotion control scheme and the first production environment emotion control scheme;

[0028] S224: When the control distance is less than or equal to the control distance threshold, add the historical production environment emotion control scheme to the same control scheme.

[0029] Specifically, the first production environment emotion control plan refers to the current environmental control strategy used to affect employees' emotions, which specifically includes the following sub-plans: Lighting control sub-plan: Manage the lighting settings in the production environment, such as brightness and color; Audio-visual type control sub-plan: Involve the types of music or videos played to affect mood and productivity; Interactive device modality control sub-plan: Control the interaction methods between interactive devices and employees, including different types of interactive statements such as relaxation, encouragement, or warning; The importance level of the historical execution task record of the same control plan refers to the importance level of the tasks that have executed similar emotion control plans in history; Central value evaluation refers to a statistical method used to determine a central value from a dataset, such as the average or median.

[0030] The system needs to review historical data to identify similar plans to the current emotion control plan and record the importance levels of these plans when they are executed. Specifically, the system will analyze the historical execution of each sub-plan (lighting, audio-visual, interactive device), and evaluate the performance of these plans when dealing with tasks of different importance levels; Through central value evaluation, the system can determine the importance levels of the high-frequency tasks executed in history under similar plans, and this information is crucial for understanding whether the current emotion control plan can effectively handle the current task, ensuring that the environmental settings match the task requirements.

[0031] Exemplarily, assume the plan includes playing light music in the work area to improve mood and productivity. The system will review historical data to see which types of tasks (such as emergency error repair or regular function development) are executed most frequently when light music is played, and record the importance levels of these tasks; If the historical data shows that high-priority error repair tasks are executed most frequently when light music is played, the system will determine the importance levels of these tasks and use them as the importance levels of the high-frequency execution tasks of the current plan, enabling the system to evaluate whether the current emotion control plan is suitable for the priority of the current task and ensuring that the environmental settings are consistent with the needs and goals of the team.

[0032] Furthermore, the retrieval process of the same control plan is as follows:

[0033] Term explanation: The lighting control sub-plan includes the first lamp brightness list and the first light color list; The audio-visual type control sub-plan includes the first video type list and the first music type list; The interactive device modality control sub-plan includes the first statement type list; The historical production environment emotion control plan includes the second lamp brightness list, the second light color list, the second video type list, the second music type list, and the second statement type list; The environmental control plan distance evaluation function is used to quantify the difference between two emotion control plans; The control distance threshold is a preset threshold used to determine whether two plans are similar enough.

[0034] Specific process:

[0035] The system will evaluate the function according to the environmental control plan distance: Among them, d i Represents the control distance of the i-th list. When i represents the lamp brightness or light color, d i Is used to calculate the proportion of the number of lamps with an absolute brightness deviation greater than the brightness deviation threshold, or to calculate the proportion of the number of lamps with an absolute RGB color deviation greater than the RGB color deviation threshold. When i represents the film and television type, music type or statement type, d i Is used to calculate the ratio of the number of non-intersecting types to the number of union types, w i Represents the preset weight of the i-th list. D represents the control distance between the historical production environment emotion control plan and the first production environment emotion control plan; compare the control plan distance between the current production environment emotion control plan and the historical plan. If the calculated control distance is less than or equal to the preset threshold, the historical plan will be regarded as similar to the current plan and included in further analysis.

[0036] Exemplarily:

[0037] Current production environment emotion control plan: Lamp brightness list: [70%, 80%, 90%]; Light color list (RGB): [(255, 0, 0), (0, 0, 255), (0, 255, 0)]; Film and television type list: [Documentary, Comedy]; Music type list: [Jazz, Pop]; Statement type list: [Encouragement, Warning].

[0038] Historical production environment emotion control plan: Second lamp brightness list: [65%, 75%, 85%]; Second light color list (RGB): [(255, 0, 0), (0, 0, 255), (255, 255, 0)]; Second film and television type list: [Documentary, Action]; Second music type list: [Jazz, Rock];

[0039] Second statement type list: [Encouragement, Relaxation];

[0040] Preset list weight: Lamp brightness: 0.2; Light color: 0.2; Film and television type: 0.3; Music type: 0.2; Statement type: 0.1.

[0041] Control distance threshold: 0.1

[0042] Step 1: Calculate the control distance of each list

[0043] Lamp brightness: Absolute deviation: |70 - 65| = 5%, |80 - 75| = 5%, |90 - 85| = 5%. Proportion of the number of lamps exceeding the threshold: Since all deviations are 5%, which is lower than the 10% threshold, the proportion is 0%.

[0044] Light color (RGB): Current solution vs. historical solution: Color 1: (255, 0, 0) vs. (255, 0, 0) → same; Color 2: (0, 0, 255) vs. (0, 0, 255) → same; Color 3: (0, 255, 0) vs. (255, 255, 0) → different; Number of different colors: 1; Total number of colors: 3; Proportion of the number of lamps with RGB absolute deviation greater than the threshold: 1 / 3 ≈ 0.333.

[0045] Film and television type: Current solution vs. historical solution: Documentary is the same, but comedy vs. action is not. Number of non-intersecting types: 1 (action); Ratio of the number of non-intersecting types to the number of types in the union: 1 / 3 ≈ 0.333.

[0046] Music type: Current solution vs. historical solution: Jazz is the same, but pop vs. rock is different. Number of non-intersecting types: 1 (rock), Ratio of the number of non-intersecting types to the number of types in the union: 1 / 3 ≈ 0.333.

[0047] Statement type: Current solution vs. historical solution: Encouragement is the same, but warning vs. relaxation is different. Number of non-intersecting types: 1 (relaxation), Ratio of the number of non-intersecting types to the number of types in the union: 1 / 3 ≈ 0.333

[0048] Step 2: Application Adjust the ratio: For each list, calculate the adjusted proportion: Lamp brightness: Light color: Film and television type: Music type: Statement type:

[0049] Step 3: According to Calculate the weighted control distance, approximately 0.2

[0050] Step 4: Compare with the control distance threshold. Control distance = 0.2, control distance threshold = 0.1. Since 0.2 > 0.1, the historical solution will not be added to the similar control solutions.

[0051] Through this process, the system can identify historical solutions similar to the current emotion control solution, so as to use the execution data of these solutions to evaluate their potential effectiveness in the current situation.

[0052] S30: Calculate the deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the first task emotion disorder coefficient;

[0053] Further, calculate the deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the first task emotional disorder coefficient. The execution of step S30 includes:

[0054] S31: According to the absolute deviation calculation function: |A1 - A2|, calculate the absolute deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the first importance level deviation, where A1 represents the importance level of the high-frequency execution task and A2 represents the importance level of the execution task;

[0055] S32: According to the relative deviation calculation function: Calculate the relative deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the second importance level deviation;

[0056] S33: Calculate the ratio of the first importance level deviation to the second importance level deviation, and set it as the first task emotional disorder coefficient.

[0057] Specifically, the term explanation: The importance level of the high-frequency execution task (A1) represents the importance level of the task that has been frequently executed historically under a specific emotion control scheme; the importance level of the execution task (A2) represents the importance level of the current execution task; the absolute deviation: the absolute difference between A1 and A2; the relative deviation The first task emotional disorder coefficient, the ratio of the absolute deviation to the relative deviation, represents the degree of mismatch between the environment and the task.

[0058] Exemplarily, it is known that: the importance (A1) of the high-frequency execution task is 7; the importance (A2) of the execution task is 9. Calculate the absolute deviation = ∣A1 - A2∣ = ∣7 - 9∣ = 2, calculate the relative deviation, ln(A1 / A2) = ln(7 / 9) = -0.2513, and then take the absolute value as 0.2513. Finally, calculate the first task emotional disorder coefficient = 2 / 0.2513 = 7.96.

[0059] Through the first task emotional disorder coefficient, the system can quantify the degree of mismatch between the current task and the historical high-frequency tasks, so as to adjust the production environment when necessary to optimize the employees' emotions and production efficiency.

[0060] S40: When the emotion recognition result belongs to a negative emotion, or / and the first task emotional disorder coefficient is greater than or equal to the disorder coefficient threshold, update the first production environment emotion control scheme to obtain the second production environment emotion control scheme;

[0061] Specifically, the imbalance coefficient threshold: a preset boundary. When this boundary is reached or exceeded, the update of the emotion control scheme is triggered. Continuing with the previous example, when the emotion recognition result belongs to a negative emotion and assuming the threshold is 5, the first task emotion imbalance coefficient = 7.96 > 5, indicating that the task emotion imbalance coefficient exceeds the threshold. The system should update the production environment emotion control scheme to better adapt to the current high-priority task, thereby reducing emotion imbalance and optimizing production efficiency. Preferably, the first production environment emotion control scheme can be randomly updated.

[0062] S50: Through the emotion prediction model, process the second production environment emotion control scheme and the importance level of the executed task to obtain an emotion prediction result;

[0063] Furthermore, through the emotion prediction model, processing the second production environment emotion control scheme and the importance level of the executed task to obtain an emotion prediction result, the execution steps include:

[0064] Collect production environment emotion control record scheme data, executed task importance level record data, and emotion type record data, and set them as emotion prediction model construction data;

[0065] Using the emotion type record data as supervision, and using the production environment emotion control record scheme data and the executed task importance level record data as inputs, retrieve the emotion prediction model construction data to train a classifier to obtain the emotion prediction model.

[0066] Furthermore, using the emotion type record data as supervision, and using the production environment emotion control record scheme data and the executed task importance level record data as inputs, retrieve the emotion prediction model construction data to train a classifier to obtain the emotion prediction model, the execution steps include:

[0067] Configure the number of classification sub - classifiers, where the number of classification sub - classifiers is 3 times the number of emotion types;

[0068] Divide the emotion prediction model construction data equally according to the number of classification sub - classifiers to obtain K groups of emotion prediction model construction data;

[0069] Perform K times of sampling with replacement on the K groups of emotion prediction model construction data to obtain a first emotion prediction model construction data set. Using the emotion type record data as supervision, and using the production environment emotion control record scheme data and the executed task importance level record data as inputs, train a first classifier;

[0070] Until the K - group emotion prediction model construction data is sampled K times with replacement to obtain the K - th emotion prediction model construction data set, using the emotion type record data as supervision and the production environment emotion control record scheme data and the execution task importance level record data as inputs, train the K - th classification sub - classifier;

[0071] Construct a fully - connected function to combine the first classification sub - classifier to the K - th classification sub - classifier to obtain the emotion prediction model. The fully - connected function is used to take the output mode type of the first classification sub - classifier to the K - th classification sub - classifier as the output of the emotion prediction model.

[0072] Specifically, the emotion prediction model is an intelligent model used to predict employees' emotional responses based on production environment factors and task parameters. Its specific construction process is as follows:

[0073] Data collection: The production environment emotion control record scheme data represents the emotion control schemes implemented in the historical production environment; the execution task importance level record data represents the importance level of historical tasks; the emotion type record data represents the emotional responses of employees associated with the above data points.

[0074] Construction of the emotion prediction model: Data splitting: Split the collected data into a training set, a validation set, and a test set, usually in the ratio of 70%, 15%, 15%; ensure that the data splitting maintains the distribution balance of emotion types to avoid training bias; Feature engineering: Extract relevant features from production environment and task data, such as lighting level (high, medium, low or cold, mild, warm), music rhythm (fast, medium, slow), etc.; Encode categorical variables (such as music type) using one - hot encoding or label encoding; Model selection: Select a convolutional neural network (CNN); Use the cross - entropy loss function for training. When the accuracy is greater than or equal to the accuracy threshold, the precision is greater than or equal to the precision threshold, and the recall rate is greater than or equal to the recall rate threshold, the emotion prediction model converges.

[0075] Furthermore, preferably in the embodiment of the present application, by means of an ensemble model, the stability of emotion prediction is further improved. The detailed configuration process is as follows: Configure the number of classification sub - classifiers to be 3 times the number of emotion types; Divide the emotion prediction model construction data equally according to the number of classification sub - classifiers to obtain K groups of emotion prediction model construction data, where K is the number of classification sub - classifiers; Repeat this action K times, then obtain K K - group emotion prediction model construction data sets, and then train the first classification sub - classifier to the K - th classification sub - classifier in the above - mentioned model training manner; Construct a fully - connected function to take the output mode type of the first classification sub - classifier to the K - th classification sub - classifier, and combine the first classification sub - classifier to the K - th classification sub - classifier to obtain the emotion prediction model.

[0076] S60: When the emotion prediction result is a positive emotion and the second task emotion imbalance coefficient of the second production environment emotion control plan is less than the imbalance coefficient threshold, adjust the production environment according to the second production environment emotion control plan.

[0077] Specifically, when the emotion prediction result is a positive emotion and the second task emotion imbalance coefficient of the second production environment emotion control plan is less than the imbalance coefficient threshold, adjust the production environment according to the second production environment emotion control plan to ensure that the adjustment of the production environment is consistent with the employees' emotional state and task requirements, thereby optimizing the overall working environment and enhancing employee satisfaction and production efficiency.

[0078] Further, the execution steps further include:

[0079] When the emotion prediction result is a positive emotion and the second task emotion imbalance coefficient of the second production environment emotion control plan is greater than or equal to the imbalance coefficient threshold, update the second production environment emotion control plan;

[0080] When the preset number of updates is reached and there is still no production environment emotion control plan with an imbalance coefficient less than the threshold, obtain the set of updated production environment emotion control plans and the set of recorded task emotion imbalance coefficients;

[0081] Using the task emotion imbalance coefficient as the fitness value, optimize the set of updated production environment emotion control plans to obtain a target production environment emotion control plan with an imbalance coefficient less than the threshold for production environment adjustment.

[0082] Specifically, when the emotion prediction result is a positive emotion and the second task emotion imbalance coefficient of the second production environment emotion control plan is greater than or equal to the imbalance coefficient threshold, update the second production environment emotion control plan. When the preset number of updates is reached and there is still no production environment emotion control plan with an imbalance coefficient less than the threshold, obtain the set of updated production environment emotion control plans and the set of recorded task emotion imbalance coefficients, and use the task emotion imbalance coefficient as the fitness value for the system to optimize the updated plans; the goal is to find the best plan with a task emotion imbalance coefficient lower than the threshold. Once the best plan is found, the system will implement this plan in the production environment to optimize employee emotions and production efficiency. Through this process, the system ensures that even if the initial update fails to fully solve the problem, it can find the best production environment emotion control plan through continuous iteration and optimization.

[0083] Further, taking the task emotion disorder coefficient as the fitness value, optimize the updated set of production environment emotion control schemes to obtain a target production environment emotion control scheme smaller than the disorder coefficient threshold for production environment adjustment. The execution steps include:

[0084] Based on the environment control scheme distance evaluation function, combined with the control scheme distance threshold, group the updated set of production environment emotion control schemes to obtain multiple groups of updated production environment emotion control schemes;

[0085] According to the task emotion disorder coefficient, respectively extract multiple updated production environment emotion control schemes corresponding to the minimum values of the disorder coefficients of multiple groups of updated production environment emotion control schemes;

[0086] Taking the multiple updated production environment emotion control schemes as the target, perform distance reduction update on the updated production environment emotion control schemes that are not in this group to obtain an extended production environment emotion control scheme;

[0087] When the emotion disorder coefficient of the extended production environment emotion control scheme is less than the disorder coefficient threshold, obtain the target production environment emotion control scheme; otherwise, perform cyclic optimization.

[0088] Specifically, the control scheme distance threshold is used as the boundary for grouping schemes. When the control scheme distance is greater than the control scheme distance threshold, they cannot be divided into one group; otherwise, they can be divided into one group. Based on the environment control scheme distance evaluation function, combined with the control scheme distance threshold, group the updated set of production environment emotion control schemes to obtain multiple groups of updated production environment emotion control schemes; for each group, identify the scheme with the minimum disorder coefficient, and these schemes are the ones that best match the task requirements within their respective groups; taking the scheme with the minimum disorder coefficient in each group as the target, adjust other schemes to be closer to these target schemes. This adjustment aims to reduce their distance from the target schemes, thereby potentially reducing the minimum value of the disorder coefficient; recalculate the disorder coefficient of each updated scheme; if the disorder coefficient is lower than the threshold, this scheme becomes the target production environment emotion control scheme and is implemented in the production environment; if no scheme has a disorder coefficient lower than the threshold, repeat the optimization process (cyclic optimization).

[0089] Through this iterative optimization process, the system can quickly determine the best production environment emotion control scheme to ensure the efficiency of environment adjustment.

[0090] The multi-source data fusion-based production environment emotion management and value creation system provided by the embodiments of the present invention has at least the following technical effects:

[0091] It can dynamically monitor and adjust the production environment to adapt to the emotional changes of employees and the importance and difficulty of task execution. When the system detects that the negative emotions of employees or the task emotion disorder coefficient exceeds the threshold, it will automatically update the emotion control plan and verify the effectiveness of the new plan through the emotion prediction model. Finally, the system adjusts the production environment according to the predicted positive emotions and the lower task emotion disorder coefficient, so as to improve the job satisfaction of employees and the humanization level of overall production while ensuring production efficiency.

[0092] Those skilled in the art should understand that the embodiments of the present invention can be provided as a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0094] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0095] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0096] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts.

[0097] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A production environment emotion management and value creation system based on multi-source data fusion, characterized in that: The implementation steps include: Obtaining emotion recognition results and task importance levels of target position employee groups, where the task importance levels are used to characterize the required output per unit time; Retrieve the importance level of high-frequency execution tasks of the same solution of the first production environment emotion control solution; Calculating the deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the first task emotion disorder coefficient; When the emotion recognition result belongs to a negative emotion, or / and the emotion disorder coefficient of the first task is greater than or equal to the disorder coefficient threshold, the first production environment emotion control scheme is updated to obtain a second production environment emotion control scheme; Processing the second production environment emotion control scheme and the execution task importance level through the emotion prediction model to obtain an emotion prediction result; When the emotion prediction result is a positive emotion and the second task emotion disorder coefficient of the second production environment emotion control scheme is less than the disorder coefficient threshold, the production environment is adjusted according to the second production environment emotion control scheme.

2. The system according to claim 1, characterized in that Retrieving the importance level of high-frequency execution tasks of the same solution of the first production environment emotion control solution, the execution steps include: The first production environment emotion control scheme includes a lighting control sub-scheme, an audio-visual type control sub-scheme and an interactive device modal control sub-scheme, wherein the interactive device modal control sub-scheme is used to control the interactive statement types between the interactive device and the employees, and the interactive statement types include relaxation statements, encouragement statements and warning statements; Retrieving the importance level of historical execution task records of the same control scheme of the lighting control sub-scheme, the audio and video type control sub-scheme and the interactive device modality control sub-scheme; The importance levels of the historically executed task records are evaluated by centralized value to obtain the importance levels of the frequently executed tasks.

3. The system according to claim 2, characterized in that Retrieving the same control scheme of the lighting control sub-scheme, the audio and video type control sub-scheme and the interactive device modality control sub-scheme, the execution steps include: The lighting control sub-scheme includes a first lamp brightness list and a first lighting color list, the audio and video type control sub-scheme includes a first video type list and a first music type list, and the interactive device modality control sub-scheme includes a first sentence type list; Obtaining a historical production environment mood control scheme, wherein the historical production environment mood control scheme includes a second lamp brightness list, a second light color list, a second film and television type list, a second music type list, and a second sentence type list; Construct the environmental control scheme distance evaluation function: Among them, d i Represents the control distance of the i-th list. When i represents the brightness or color of the lamp, d i It is used to calculate the proportion of lamps with absolute brightness deviation greater than the brightness deviation threshold, or the proportion of lamps with absolute color RGB deviation greater than the color RGB deviation threshold. When i represents the type of film and television, music or sentence, d i Used to calculate the ratio of the number of type non-intersections to the number of type unions, w i represents the preset i-th list weight, D represents the control distance between the historical production environment emotion control scheme and the first production environment emotion control scheme; When the control distance is less than or equal to a control distance threshold, the historical production environment emotion control scheme is added to the same control scheme.

4. The system according to claim 1, characterized in that Calculating the deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain the first task emotional disorder coefficient, the execution steps include: Compute the function in terms of absolute deviation: | A1-A2 | , calculating the absolute deviation between the high-frequency execution task importance level and the execution task importance level, and obtaining a first importance level deviation, wherein A1 represents the high-frequency execution task importance level, and A2 represents the execution task importance level; Calculate the function based on relative deviation: Calculating the relative deviation between the importance level of the high-frequency execution task and the importance level of the execution task to obtain a second importance level deviation; The ratio of the first importance level deviation to the second importance level deviation is calculated and set as the first task emotion disorder coefficient.

5. The system of claim 1, wherein: The emotion prediction model is used to process the emotion control scheme of the second production environment and the importance level of the execution task to obtain an emotion prediction result. The execution steps include: Collect production environment emotion control record plan data, execution task importance record data and emotion type record data, and set them as emotion prediction model construction data; Taking the emotion type record data as supervision, taking the production environment emotion control record plan data and the execution task importance level record data as input, the emotion prediction model is retrieved to build data to train a classifier, and the emotion prediction model is obtained.

6. The system according to claim 5, characterized in that Taking the emotion type record data as supervision, taking the production environment emotion control record scheme data and the execution task importance level record data as input, calling the emotion prediction model construction data training classifier, and obtaining the emotion prediction model, the execution steps include: Configure the number of classifiers, wherein the number of classifiers is three times the number of emotion types; Dividing the emotion prediction model construction data equally according to the number of classifiers to obtain K groups of emotion prediction model construction data; Perform K times of sampling with replacement on the K groups of emotion prediction model construction data to obtain a first emotion prediction model construction data set, and train a first classifier using the emotion type record data as supervision and the production environment emotion control record scheme data and the execution task importance level record data as input; Until the K groups of emotion prediction model construction data are sampled K times with replacement, a Kth emotion prediction model construction data set is obtained, and the emotion type record data is used as supervision, and the production environment emotion control record scheme data and the execution task importance level record data are used as input to train the Kth classifier; Construct a fully connected function, merge the first classifiers up to the K-th classifier, and obtain the emotion prediction model, wherein the fully connected function is used to take the output mode type of the first classifiers up to the K-th classifier as the output of the emotion prediction model.

7. The system according to claim 3, characterized in that The execution steps also include: When the emotion prediction result is a positive emotion, and the emotion disorder coefficient of the second task of the second production environment emotion control scheme is greater than or equal to the disorder coefficient threshold, updating the second production environment emotion control scheme; When the preset number of updates is exceeded and no production environment emotion control solution less than the imbalance coefficient threshold value is found, an updated production environment emotion control solution set and a recording task emotion imbalance coefficient set are obtained; Taking the task emotion disorder coefficient as the fitness value, the updated production environment emotion control scheme set is optimized to obtain a target production environment emotion control scheme that is less than the disorder coefficient threshold to adjust the production environment.

8. The system according to claim 7, characterized in that Taking the task emotion disorder coefficient as the fitness value, optimizing the updated production environment emotion control solution set, obtaining a target production environment emotion control solution less than the disorder coefficient threshold to adjust the production environment, the execution steps include: Based on the environmental control scheme distance evaluation function, the updated production environment emotion control scheme set is grouped in combination with the control scheme distance threshold to obtain multiple groups of updated production environment emotion control schemes; According to the task emotion disorder coefficient, extracting multiple updated production environment emotion control schemes corresponding to multiple minimum values ​​of the disorder coefficients of multiple groups of updated production environment emotion control schemes respectively; Taking the multiple updated production environment emotion control schemes as targets, updating the updated production environment emotion control schemes outside the group with reduced distances to obtain an expanded production environment emotion control scheme; When the emotion disorder coefficient of the expanded production environment emotion control scheme is less than the disorder coefficient threshold, the target production environment emotion control scheme is obtained, otherwise, the optimization is cyclically searched.

Images