Express industry work satisfaction evaluation method based on productivity model

Abstract

The invention relates to the field of work satisfaction evaluation, and discloses an express industry work satisfaction evaluation method based on a productivity model, and the method comprises the following steps: collecting the work data of a courier, including the workload, the work efficiency and the customer evaluation; collecting emotional data of the courier, wherein the emotional data comprises emotional fluctuations and emotional labels obtained through voice analysis and text analysis; constructing a productivity evaluation model based on the collected work data, and evaluating the work productivity of the courier; constructing an emotion calculation model based on the collected emotion data, and evaluating the emotional state of the courier; calculating the work satisfaction degree of the courier based on the results of the productivity evaluation and the emotional state evaluation; and based on a work satisfaction evaluation result, constructing an optimization algorithm to dynamically adjust the work task and the work time. Through a dynamic evaluation method based on a productivity model, in combination with a multi-dimensional working state score and a real-time feedback mechanism, the accuracy of work satisfaction evaluation is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of job satisfaction evaluation, and in particular to a method for evaluating job satisfaction in the express delivery industry based on a productivity model. Background Art

[0002] With the rapid development of e-commerce, the express delivery industry has become an integral part of society. However, the couriers' work environment and tasks result in high pressure and workload, which directly impacts their job satisfaction and emotional well-being. Currently, many express delivery companies focus on productivity metrics, such as delivery speed and task completion rates, when managing and motivating their couriers. However, these evaluation methods often overlook the couriers' emotional well-being and overall job satisfaction. This leads to couriers experiencing negative emotions in this high-intensity work environment, which in turn impacts their work efficiency and service quality.

[0003] Existing techniques often use a single quantitative metric to assess job satisfaction, failing to fully integrate the emotional fluctuations of couriers with their actual productivity levels. For example, many traditional evaluation methods rely primarily on couriers' work performance (such as delivery time and number of completed orders) to measure their job satisfaction. These methods lack attention to emotional factors and fail to effectively capture the emotional changes that couriers may experience during the work process. Furthermore, existing evaluation models are often static and fail to dynamically adjust in real time to meet the individual needs of different couriers. These shortcomings not only limit the accuracy of the evaluation system but also hinder the personalization and targeted nature of work optimization solutions.

[0004] Furthermore, existing evaluation systems fail to fully integrate multi-source data, ignoring the interplay of multidimensional factors such as work environment, task type, and emotional state. While some advanced models attempt to improve the comprehensiveness of evaluations by incorporating multi-dimensional data inputs, many challenges remain, particularly in processing heterogeneous data from multiple sources and effectively integrating this information. Existing technologies generally lack the ability to flexibly adjust and dynamically optimize couriers' work status in real time.

[0005] Therefore, existing technologies for assessing courier job satisfaction suffer from shortcomings such as insufficient consideration of emotional state and productivity, a lack of dynamic adaptability in assessment models, and limited data fusion processing capabilities. These issues hinder a comprehensive understanding of couriers' actual work experiences and fail to effectively support the development of personalized work optimization and emotional regulation strategies. A more flexible, efficient, and accurate assessment method is urgently needed. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides a job satisfaction evaluation method for the express delivery industry based on a productivity model, which solves the problems that the existing job satisfaction evaluation method for the express delivery industry fails to fully consider the comprehensive impact of the courier's emotional state and productivity, and the evaluation model lacks dynamic adaptability and personalized optimization.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for evaluating job satisfaction in the express delivery industry based on a productivity model, comprising the following steps:

[0008] S1. Collect courier work data, including workload, work efficiency, and customer evaluation;

[0009] S2. Collect the courier’s emotional data, including emotional fluctuations and emotional labels obtained through voice analysis and text analysis;

[0010] S3. Build a productivity evaluation model based on the collected work data to evaluate the couriers’ work productivity;

[0011] S4. Build an affective computing model based on the collected affective data to evaluate the courier’s affective state;

[0012] S5. Calculate the courier’s job satisfaction based on the results of productivity assessment and affective state assessment;

[0013] S6. Based on the job satisfaction evaluation results, build an optimization algorithm to dynamically adjust work tasks and working hours to optimize job satisfaction in real time;

[0014] S7. Adjust the weight coefficient of the evaluation model based on the optimization results to make the evaluation more accurate and form a self-correction mechanism.

[0015] Preferably, the collection of courier work data includes using Internet of Things technology to monitor the courier's package handling volume, delivery time and customer feedback data in real time.

[0016] Preferably, the collecting of courier emotion data further includes analyzing the interaction content between employees and customers through natural language processing technology and extracting emotion tags therefrom.

[0017] Preferably, the step of evaluating the courier's work productivity includes:

[0018] Determine the contribution of workload, work efficiency, and customer reviews to productivity based on collected work data;

[0019] The courier's work productivity is calculated using the following formula:

[0020] P(t)=α1·W(t)+α2·E w (t)+α3·Cr (t);

[0021] Where P(t) is the courier’s work productivity; W(t) is the workload; E w (t) is work efficiency; C r (t)

[0022] is customer evaluation; α1, α2, α3 are weight coefficients;

[0023] Based on the specific data of workload, work efficiency, and customer evaluation, the weight coefficients α1, α2, and α3 are dynamically adjusted to accurately reflect the courier’s work productivity.

[0024] Preferably, the step of evaluating the courier's emotional state includes:

[0025] Based on the collected emotional data, identify the courier's emotional fluctuations and emotional labels;

[0026] The courier’s emotional state is calculated using the following formula:

[0027] E(t)=β1·ΔE(t)+β2·E s (t);

[0028] Among them, E(t) is the emotional state of the courier; ΔE(t) is the emotional fluctuation; E s (t) is the sentiment label; β1 and β2 are weight coefficients;

[0029] According to the specific data of emotional fluctuations and emotional labels, the weight coefficients β1 and β2 are dynamically adjusted to accurately reflect the emotional state of the courier.

[0030] Preferably, the step of calculating the courier's job satisfaction comprises:

[0031] The courier's job satisfaction is calculated using the following formula:

[0032] S(t)=α·P(t)+β·E(t)+γ·C(t);

[0033] Among them, S(t) is the courier's job satisfaction; P(t) is the productivity evaluation result; E(t) is the emotion evaluation result; C(t) is the external environmental factor; α, β, γ are weight coefficients.

[0034] Preferably, the step of constructing an optimization algorithm to dynamically adjust work tasks and work hours and optimize work satisfaction in real time includes:

[0035] Set the objective function to maximize the courier's job satisfaction. The objective function form is:

[0036]

[0037] Among them, x1 is the work task allocation plan; x2 is the work time arrangement plan; S(t) is the courier's job satisfaction; P(t) is the productivity evaluation result; E(t) is the emotion evaluation result; C(t) is the external environmental factor; α, β, γ are weight coefficients;

[0038] Introducing constraints, including daily work hours, task completion, and fairness distribution indicators;

[0039] Based on historical work data and current satisfaction trends, use machine learning algorithms or heuristic search algorithms to calculate the optimal x1 and x2;

[0040] Dynamically adjust the courier's workload and working hours based on the calculation results;

[0041] Feedback adjustment results are used to update subsequent evaluation processes to achieve real-time optimization.

[0042] Preferably, the step of adjusting the weight coefficient of the evaluation model based on the optimization result includes:

[0043] Collect feedback on couriers’ job satisfaction by analyzing optimized work tasks and work time allocation;

[0044] According to the changing trend of job satisfaction, calculate the error of the current evaluation model:

[0045] ∈(t)=|S current (t)-S predicted (t)|;

[0046] Among them, ∈(t) is the error of the current evaluation model; S current (t) is actual job satisfaction; S predicted (t) is the job satisfaction predicted by the model;

[0047] Based on the error calculation results, the optimization algorithm is used to dynamically adjust the weight coefficients α1, α2, α3, β1, and β2 in the productivity evaluation model and the sentiment evaluation model. The specific adjustment process is as follows:

[0048]

[0049] Among them, η is the learning rate; α i , β j is the weight coefficient of productivity and sentiment model; is the i-th weight coefficient α in the productivity evaluation model of error ∈(t) i The partial derivative of reflects the influence of the weight coefficient on the error; is the jth weight coefficient β in the productivity evaluation model of error ∈(t)j The partial derivative of reflects the influence of the weight coefficient on the error;

[0050] Repeat the above adjustment process until the error ∈(t) is less than the preset threshold, ensuring that the weight coefficient of the evaluation model is accurately adjusted and can effectively reflect the courier's job satisfaction.

[0051] Preferably, the step of forming a self-correction mechanism includes:

[0052] Construct a continuous learning mechanism to analyze the error between the model prediction value and the actual satisfaction level at every preset period Δt to form an error time series data set;

[0053] Use the time sliding window to extract the error sequence {∈(t-Δt),…,∈(t)} of the last n cycles and calculate the average error. The calculation rule is:

[0054]

[0055] in, is the average error; n is the number of cycles used to calculate the average error; k is the index of the error sequence, indicating the error between the current cycle and the past cycle; ∈(tk·Δt) is the error at time tk·Δt, as each error value in the sliding window;

[0056] When the average error When the preset threshold θ is exceeded, the model parameter update mechanism is automatically triggered to readjust the weight coefficient α of the evaluation model i , β j , and record the correction cycle;

[0057] The adjustment frequency and error convergence rate are evaluated through historical correction data, and the learning rate η and window length n are further optimized to form a steady-state adaptive correction cycle.

[0058] The express delivery industry job satisfaction evaluation system based on the productivity model is preferably composed of:

[0059] The data collection module is used to collect the courier's work data in real time, including workload, work efficiency and customer evaluation;

[0060] The emotional data collection module is used to obtain the courier's emotional fluctuations and emotional labels through voice analysis and text analysis;

[0061] A productivity evaluation module, which is used to build a productivity evaluation model based on the collected work data and evaluate the work productivity of couriers;

[0062] The emotion evaluation module is used to build an emotion computing model based on the collected emotion data and evaluate the courier's emotional state;

[0063] A job satisfaction calculation module is used to calculate the courier's job satisfaction based on the results of productivity evaluation and emotional state evaluation;

[0064] Optimization algorithm module, used to dynamically adjust work tasks and working hours based on job satisfaction evaluation results and optimize job satisfaction in real time;

[0065] The weight adjustment module is used to adjust the weight coefficient of the evaluation model based on the optimization results, making the evaluation more accurate and forming a self-correction mechanism;

[0066] The correction mechanism module is used to automatically trigger the self-correction process and update the parameters of the evaluation model based on the error calculation results.

[0067] The present invention provides a method for evaluating job satisfaction in the express delivery industry based on a productivity model. It has the following beneficial effects:

[0068] 1. This invention effectively improves the accuracy of job satisfaction assessments by combining a dynamic assessment method based on a productivity model with a multi-dimensional work status score and real-time feedback mechanism. By considering multiple factors, such as productivity and emotional state, it can more comprehensively reflect the courier's work experience, avoiding the single-perspective assessment perspective of traditional methods, and making the measurement of job satisfaction more objective and accurate.

[0069] 2. This invention utilizes a self-correcting mechanism, combining feedback data to dynamically adjust key coefficients in the evaluation model. This allows for personalized work optimization solutions tailored to the specific circumstances of individual couriers. Through flexible weight adjustments and model updates, each courier's work evaluation is precisely tailored to their individual characteristics, thereby enhancing the effectiveness and personalization of work path selection.

[0070] 3. This invention not only focuses on improving productivity but also mitigates the negative impact of emotional fluctuations on couriers' work efficiency through emotional state regulation. By dynamically adjusting the coefficients of influence between productivity and emotional scores, it can promote work efficiency while ensuring emotional stability, thereby increasing couriers' work enthusiasm and satisfaction.

[0071] 4. This invention combines multiple dimensions, including job satisfaction, emotional state, and productivity, to form a multi-objective optimization system, effectively balancing the relationships between various objectives. Through a self-correcting mechanism, it can achieve comprehensive optimization of job satisfaction and productivity in complex work environments, thereby ensuring optimal performance and emotional stability for couriers under various working conditions.

[0072] 5. This invention utilizes a closed-loop adaptive optimization system called "data-model-decision," ensuring that the system can adjust its evaluation model and optimization plan in real time based on actual work feedback. Through continuous iterative updates and feedback mechanisms, the system ensures that work path selection and optimization strategies remain efficient and adaptable, thereby enhancing the long-term robustness and sustainability of courier job satisfaction assessments. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A diagram showing the steps of the method of the present invention;

[0074] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0075] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0076] Please see the attached Figure 1 The embodiment of the present invention provides a method for evaluating job satisfaction in the express delivery industry based on a productivity model, comprising the following steps:

[0077] S1. Collect courier work data, including workload, work efficiency, and customer evaluation;

[0078] S2. Collect the courier’s emotional data, including emotional fluctuations and emotional labels obtained through voice analysis and text analysis;

[0079] S3. Build a productivity evaluation model based on the collected work data to evaluate the couriers’ work productivity;

[0080] S4. Build an affective computing model based on the collected affective data to evaluate the courier’s affective state;

[0081] S5. Calculate the courier’s job satisfaction based on the results of productivity assessment and affective state assessment;

[0082] S6. Based on the job satisfaction evaluation results, build an optimization algorithm to dynamically adjust work tasks and working hours to optimize job satisfaction in real time;

[0083] S7. Adjust the weight coefficient of the evaluation model based on the optimization results to make the evaluation more accurate and form a self-correction mechanism.

[0084] The following is a detailed description of each step in the method of the present invention, which comprehensively explains the specific implementation principles, technical details and processes of each step.

[0085] Regarding step S1, in this embodiment, the purpose of step S1 is to collect the courier's work data through the smart device. Such data includes but is not limited to the courier's workload, work efficiency, and customer evaluation information.

[0086] During the work process, the mobile terminal devices used by couriers (such as handheld devices, vehicle-mounted terminals, etc.) are connected to the central system to record the relevant information of each delivery task in real time. This information mainly includes:

[0087] Workload data: This refers to the number of delivery tasks or packages a courier completes each workday. Each completed delivery task is recorded as a workload unit, and the system automatically updates workload data. Each delivery task includes detailed information such as the task ID, task start time, task end time, delivery location, and the number of items delivered.

[0088] Work efficiency data: This refers to a courier's work efficiency, primarily calculated by comparing the actual duration of each delivery task to the expected duration. The system automatically calculates the scheduled time and the actual completion time for each task, and uses this as a measure of work efficiency.

[0089] Customer review data: After each delivery, customers can rate their service through the system, typically using a star rating or text review. This data is submitted by customers via a mobile app or text message, and the system automatically records each customer rating.

[0090] Through this step, all working data will be uploaded to the central data storage system in real time for data processing and calculation in subsequent steps.

[0091] In this embodiment, step S2 aims to collect the courier's emotional data through various means, including voice and text data. This emotional data is primarily collected through the courier's smart device, which analyzes voice and text to capture their emotional fluctuations during work.

[0092] Voice Data Collection: The system automatically records the conversations between couriers and customers. Whenever a courier communicates with a customer, the system converts the spoken words into text using speech recognition technology. The system also analyzes voice characteristics such as tone, pitch, and speed, and records emotion-related indicators (such as the emotional tendency of the voice).

[0093] Text Data Collection: Textual communications between couriers and customers or colleagues also contain emotional information. The system automatically monitors the content of couriers' messages and collects text chat logs during work. Text data can be collected through SMS, chat apps, or other communication platforms. The system converts these text messages into emotional labels (such as positive, negative, and neutral) and records the timestamp and emotional polarity of each text message.

[0094] All emotional data will be archived in the system and uploaded to the data storage center for emotional data processing and calculation in subsequent steps.

[0095] Regarding step S3, in this embodiment, the purpose of step S3 is to use the work data collected in step S1 to construct a productivity evaluation model through calculation and processing. This model can evaluate the courier's work performance, and the specific implementation method is as follows:

[0096] Workload Calculation: Based on the workload data collected in step S1, the system calculates the courier's daily workload. Workload data includes the number of tasks, task type, and task difficulty. The system assigns different weights to each task based on pre-set task difficulty, ultimately calculating the courier's total workload over a specific time period.

[0097] Work efficiency calculation: For each delivery task, the system calculates the work efficiency by comparing the ratio of actual completion time to scheduled time. The work efficiency formula is:

[0098]

[0099] E(t) represents the work efficiency. The closer its value is to 1, the more efficient the courier is. The system calculates the work efficiency of each task in real time and takes a weighted sum to calculate the daily work efficiency.

[0100] Processing and calculation of customer reviews: The system uses the collected customer rating data to calculate the courier's daily average customer review. Customer reviews are generally rated on a five-point scale, and the system calculates the average of all customer ratings to determine the courier's overall customer review score.

[0101] Productivity score calculation: After comprehensively processing workload, work efficiency and customer evaluation, the system uses weighted summation to obtain the courier's productivity score P(t). The productivity score calculation formula is:

[0102] P(t)=α1·W(t)+α2·E(t)+α3·C(t);

[0103] Where W(t) is workload, E(t) is work efficiency, C(t) is customer evaluation, and α1, α2, and α3 are weight coefficients. The system can dynamically adjust these weight coefficients based on historical data and actual needs to improve the accuracy of the evaluation results.

[0104] Through this step, the system can accurately evaluate the courier's work productivity and provide data support for subsequent satisfaction analysis.

[0105] Regarding step S4, in this embodiment, the purpose of step S4 is to construct an emotional computing model based on the emotional data collected in step S2 through processing and calculation. This model is used to evaluate the emotional state of the courier at work, and is specifically implemented as follows:

[0106] Speech emotion data processing: The system performs sentiment analysis on the speech data collected in step S2. First, the speech is converted into text using speech recognition technology. Then, the sentiment analysis model is used to analyze the converted text to identify emotional tendencies (such as joy, anxiety, fatigue, etc.). During the analysis process, the system further infers the emotional state based on characteristics such as pitch, speaking speed, and tone. The speech emotion score F(t) can be expressed as the following formula:

[0107] F(t) = weighted sum of sentiment analysis results;

[0108] The sentiment analysis results will be scored based on the emotional polarity of the speech (positive, negative, neutral), and the system will continuously optimize the accuracy of speech sentiment analysis through model training.

[0109] Text sentiment data processing: The system uses natural language processing technology to perform sentiment analysis on the collected text data. Specifically, the system will segment each message and match it with the sentiment dictionary, and determine the sentiment polarity (positive, negative, neutral) based on the sentiment words in the text. The text sentiment score T(t) can be calculated using the following formula:

[0110] T(t) = weighted sum of sentiment lexicon matching results;

[0111] The sentiment score of text data is also scored by the weight of sentiment polarity.

[0112] Construction of the emotion calculation model: By combining the speech emotion score F(t) and the text emotion score T(t), the system obtains a comprehensive emotion score E emotion (t). The specific calculation formula is:

[0113] E emotion (t) = β1·F(t) + β2·T(t);

[0114] Among them, E emotion(t) is the comprehensive sentiment score; β1 and β2 are the weight coefficients for voice and text sentiment scores. Through the accumulation of historical sentiment data and model training, the system can automatically adjust the weight coefficients to further optimize the accuracy of the sentiment score.

[0115] Emotional Trend Analysis: By processing historical emotional data, the system can analyze the changing trends of couriers' emotional states. Combined with couriers' productivity scores, the system can identify the relationship between couriers' emotional fluctuations and work performance, providing more comprehensive data support for job satisfaction assessments.

[0116] Through this step, the system can achieve a comprehensive assessment of the courier's emotional state, thereby providing data support for subsequent job satisfaction analysis.

[0117] Regarding step S5, in this embodiment, the primary purpose of step S5 is to ultimately calculate the courier's job satisfaction score by combining the productivity assessment and sentiment calculation results from steps S3 and S4. Specifically, step S5 involves combining the previously obtained work productivity score with the sentiment score output by the sentiment calculation model, and calculating the courier's overall job satisfaction using a specific weighting method.

[0118] First, the system calculates the productivity score P(t) in step S3, which is obtained by weighted summation of workload, work efficiency and customer evaluation. This score reflects the courier's work performance in a specified time period. In step S4, the system uses the sentiment analysis algorithm to analyze the courier's voice and text data to obtain the emotional state score E emotion (t), this score reflects the courier’s emotional state during the same time period. The emotional state score is based on the courier’s mood fluctuations, such as anxiety, fatigue, and joy, which have a certain impact on the courier’s overall work performance.

[0119] In this embodiment, when calculating job satisfaction, the system uses a comprehensive evaluation formula to combine the productivity score P(t) and the emotion score E(t) into a comprehensive evaluation formula. emotion (t) Perform weighted fusion. The formula for weighted fusion is:

[0120] S(t)=α1·P(t)+α2·E emotion (t);

[0121] Where S(t) is the courier’s job satisfaction score at time t; P(t) is the productivity score; E emotion (t) is the sentiment score; α1 and α2 are the weight coefficients of the importance of productivity score and sentiment score respectively.

[0122] Depending on specific implementation requirements, the system can adjust these two weighting factors based on different business scenarios. For example, if a courier's emotional state has a greater impact on their work performance in certain situations, the system can appropriately increase the weight of the emotional score, while conversely, it can prioritize the productivity score. These weighting factors can be automatically adjusted through learning and feedback from historical data to ensure the accuracy and flexibility of the evaluation results.

[0123] To ensure the accuracy of the assessment results, the system also conducts trend analysis on the courier's historical data. Specifically, the system dynamically analyzes the courier's job satisfaction score S(t) over a period of time to capture trends in their work performance and emotional fluctuations. The results of these trend analyses provide data support for subsequent personalized management measures. For example, if a courier's emotional state remains consistently low over a certain period, and their work productivity score falls below expectations, the system can provide personalized reminders or improvement suggestions to help the courier adjust their mood or optimize their work methods.

[0124] In this embodiment, the system also manages couriers in different levels based on the job satisfaction scores. Through comprehensive analysis of satisfaction scores, the system can identify couriers with excellent work performance, as well as those who may be experiencing work difficulties or emotional fluctuations. Based on different score ranges, the system will provide different management and optimization suggestions to further improve job satisfaction.

[0125] In summary, step S5 combines work productivity scores with emotion calculation results to comprehensively assess couriers' job satisfaction. This satisfaction score comprehensively reflects the courier's work performance and emotional state, providing a scientific data basis for subsequent work optimization and management. This solution not only allows the system to dynamically assess individual couriers' job satisfaction but also provides companies with more effective personalized management solutions.

[0126] Regarding step S6, in this embodiment, the core of step S6 is to optimize the algorithm based on the courier's job satisfaction score S(t) and the emotion score E(t). emotion (t), automatically generating personalized optimization recommendations. To achieve this goal, the optimization algorithm not only considers the division of scoring intervals but also involves using mathematical models to quantitatively analyze the couriers' work status and emotional fluctuations. Based on this analysis, the system generates specific optimization strategies to improve the couriers' work efficiency and emotional stability.

[0127] In this embodiment, the optimization algorithm is based on multi-level analysis and weighted calculation, and dynamically adjusts the optimization suggestions through formulas. The core formula of the algorithm is based on the courier's job satisfaction score S(t) and the emotion score E emotion(t), and the weight coefficient set in the algorithm to guide the generation of the optimization strategy.

[0128] Based on the combination of job satisfaction score and sentiment score, the system makes optimization strategy decisions based on the preset score threshold. The generation of the optimization strategy can be expressed by the following formula:

[0129] For couriers with low job satisfaction and high emotional volatility:

[0130]

[0131] Where ΔP(t) is the adjustment of work productivity; ΔE emotion (t) is the adjustment amount of the emotional state; β1 and β2 are the corresponding adjustment weight coefficients.

[0132] This formula means that when job satisfaction is low and emotional fluctuations are large, the system will focus on emotional intervention and appropriately reduce task load.

[0133] For couriers with high job satisfaction and low emotional volatility:

[0134]

[0135] Among them, ΔT(t) is the optimization adjustment of the task; ΔP(t) is the adjustment of work productivity; γ1 and γ2 are the weight coefficients of task adjustment.

[0136] In this case, the system will focus on optimizing the couriers' task allocation and improving work efficiency.

[0137] In this embodiment, the optimization algorithm generates a personalized optimization strategy for couriers through the following steps:

[0138] First, obtain the courier’s job satisfaction score S(t) and sentiment score E from step S5. emotion (t). These two rating values ​​serve as input to the optimization algorithm.

[0139] Then, the system calculates the job satisfaction score S(t) and the sentiment score E(t). emotion (t) is divided into thresholds to determine the courier’s current working status. For example, if S(t) is lower than a certain threshold, and E emotion (t) shows high emotional fluctuations, the system will think that the courier’s condition is poor and needs to be optimized.

[0140] Next, based on the score classification, the optimization algorithm calculates the corresponding adjustment amount according to the above formula and determines the optimization strategy based on the adjustment amount. For example, in the case of low job satisfaction and high emotional volatility, the system will take measures such as increasing rest time and adjusting workload to alleviate emotional stress and improve work efficiency.

[0141] Finally, the system generates specific optimization suggestions based on the calculation results and feeds them back to the courier. These suggestions include adjusting work tasks, optimizing routes, and emotional counseling.

[0142] In this embodiment, step S6 uses an optimization algorithm to comprehensively analyze the courier's job satisfaction and emotional scores, providing them with a personalized work optimization plan. Through dynamic weighted calculation and optimization strategy generation, the system effectively improves the courier's work performance and emotional state, enhancing work efficiency and stability, and ensuring the real-time and personalized nature of the entire optimization process.

[0143] In step S7, in this embodiment, the system dynamically adjusts the evaluation model's weight coefficients based on the optimization results, creating a self-correcting mechanism to improve the accuracy and personalization of courier job satisfaction assessments. In practice, the evaluation model analyzes couriers' productivity scores, sentiment scores, and work feedback, adjusting correlation coefficients in real time to optimize the model's accuracy and adaptability.

[0144] First, the evaluation model evaluates the courier’s working status through a multi-dimensional scoring system, which includes productivity score P(t) and emotional state score E(t). emotion (t). These scores reflect the courier's work efficiency and emotional fluctuations respectively. In order to comprehensively consider the impact of productivity and emotional state on job satisfaction, the system assigns corresponding weight coefficients α1 and α2 to each score, so that the comprehensive satisfaction score S(t) is expressed as the following formula:

[0145]

[0146] Among them, S(t) new This is the adjusted overall job satisfaction score; and These are dynamically adjusted weight coefficients. Based on the courier's feedback and work performance, the system will adjust these weight coefficients in real time to ensure that the evaluation results accurately reflect the courier's actual work status.

[0147] In this embodiment, the system evaluates the effectiveness of the evaluation model by calculating the error ∈(t) of the current evaluation model. This error reflects the difference between the actual job satisfaction and the model's prediction. Specifically, the error ∈(t) is calculated as follows:

[0148] ∈(t)=|S current (t)-S predicted (t)|;

[0149] Among them, ∈(t) is the error of the current evaluation model; S current(t) is actual job satisfaction; S predicted (t) is the job satisfaction predicted by the model;

[0150] By continuously monitoring and calculating this error, the system can evaluate the model's performance in each cycle and adjust the model parameters accordingly.

[0151] When the error reaches the preset threshold, the system will adjust the weight coefficients in the evaluation model through the optimization algorithm. Specifically, the system uses the following formula to dynamically adjust the weight coefficients:

[0152]

[0153] Among them, η is the learning rate; α i , β j is the weight coefficient of productivity and sentiment model; is the i-th weight coefficient α in the productivity evaluation model of error ∈(t) i The partial derivative of reflects the influence of the weight coefficient on the error; is the jth weight coefficient β in the productivity evaluation model of error ∈(t) j The partial derivative of reflects the influence of the weight coefficient on the error.

[0154] In addition, the system also uses time sliding window technology to further optimize the evaluation model by extracting the error sequence of the last n cycles and calculating the average error. The calculation formula for the average error is:

[0155]

[0156] in, is the average error; n is the number of cycles used to calculate the average error; k is the index of the error sequence, indicating the error between the current cycle and the past cycle; ∈(tk·Δt) is the error at time tk·Δt, as each error value in the sliding window.

[0157] When the average error When a preset threshold is exceeded, the system automatically triggers a self-correction mechanism to readjust the parameters in the evaluation model. This process allows the weighting coefficients in the productivity and sentiment models to be adjusted in real time based on courier feedback and work performance, ensuring that optimization recommendations always meet the actual needs of couriers.

[0158] During the self-correction process, the system continuously monitors the couriers' job satisfaction scores and emotional state, adjusting the weighting coefficients based on real-time feedback. Each adjusted score serves as the basis for the next adjustment, ensuring that the optimization plan remains consistent with the couriers' work status.

[0159] Through the above process, the system can realize the weight coefficient adjustment and self-correction mechanism based on the optimization results, so that the evaluation model can continuously adapt to the working environment and the personalized needs of couriers, and ultimately achieve continuous optimization and personalized improvement of job satisfaction evaluation.

[0160] In general, the present invention realizes the multi-dimensional dynamic optimization of couriers' job satisfaction, emotional state and productivity through a job satisfaction evaluation method for the express delivery industry based on a productivity model, combined with a dynamically adjusted evaluation model and a self-correction mechanism.

[0161] The express delivery industry job satisfaction evaluation system based on the productivity model described below and the express delivery industry job satisfaction evaluation method based on the productivity model described above can be referenced to each other.

[0162] Please see the attached Figure 2 The present invention also provides a system for evaluating job satisfaction in the express delivery industry based on a productivity model, comprising:

[0163] The data collection module is used to collect the courier's work data in real time, including workload, work efficiency and customer evaluation;

[0164] The emotional data collection module is used to obtain the courier's emotional fluctuations and emotional labels through voice analysis and text analysis;

[0165] A productivity evaluation module, which is used to build a productivity evaluation model based on the collected work data and evaluate the work productivity of couriers;

[0166] The emotion evaluation module is used to build an emotion computing model based on the collected emotion data and evaluate the courier's emotional state;

[0167] A job satisfaction calculation module is used to calculate the courier's job satisfaction based on the results of productivity evaluation and emotional state evaluation;

[0168] Optimization algorithm module, used to dynamically adjust work tasks and working hours based on job satisfaction evaluation results and optimize job satisfaction in real time;

[0169] The weight adjustment module is used to adjust the weight coefficient of the evaluation model based on the optimization results, making the evaluation more accurate and forming a self-correction mechanism;

[0170] The correction mechanism module is used to automatically trigger the self-correction process and update the parameters of the evaluation model based on the error calculation results.

[0171] The system of this embodiment can be used to execute the above method embodiments, and its principles and technical effects are similar, so they will not be repeated here.

[0172] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating job satisfaction in the express delivery industry based on a productivity model, characterized by: The following steps are involved: S1. Collect courier work data, including workload, work efficiency, and customer evaluation; S2. Collect the courier’s emotional data, including emotional fluctuations and emotional labels obtained through voice analysis and text analysis; S3. Build a productivity evaluation model based on the collected work data to evaluate the couriers’ work productivity; S4. Build an affective computing model based on the collected affective data to evaluate the courier’s affective state; S5. Calculate the courier’s job satisfaction based on the results of productivity assessment and affective state assessment; S6. Based on the job satisfaction evaluation results, build an optimization algorithm to dynamically adjust work tasks and working hours to optimize job satisfaction in real time; S7. Adjust the weight coefficient of the evaluation model based on the optimization results to make the evaluation more accurate and form a self-correction mechanism.

2. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The collection of courier work data includes using Internet of Things technology to monitor the courier's package handling volume, delivery time and customer feedback data in real time.

3. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The collecting of courier emotion data further includes analyzing the interaction content between employees and customers through natural language processing technology and extracting emotion tags therefrom.

4. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The steps of evaluating the courier's work productivity include: Determine the contribution of workload, work efficiency, and customer reviews to productivity based on collected work data; The courier's work productivity is calculated using the following formula: P(t)=α1·W(t)+α2·E w (t)+α3·C r (t); Where P(t) is the courier’s work productivity; W(t) is the workload; E w (t) is work efficiency; C r (t) is the customer evaluation; α1, α2, α3 are weight coefficients; Based on the specific data of workload, work efficiency, and customer evaluation, the weight coefficients α1, α2, and α3 are dynamically adjusted to accurately reflect the courier’s work productivity.

5. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The step of evaluating the courier's emotional state includes: Based on the collected emotional data, identify the courier's emotional fluctuations and emotional labels; The courier’s emotional state is calculated using the following formula: E(t)=β1·ΔE(t)+β2·E s (t); Among them, E(t) is the emotional state of the courier; ΔE(t) is the emotional fluctuation; E s (t) is the sentiment label; β1 and β2 are weight coefficients; According to the specific data of emotional fluctuations and emotional labels, the weight coefficients β1 and β2 are dynamically adjusted to accurately reflect the emotional state of the courier.

6. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The steps of calculating the courier's job satisfaction include: The courier's job satisfaction is calculated using the following formula: S(t)=α·P(t)+β·E(t)+γ·C(t); Among them, S(t) is the courier's job satisfaction; P(t) is the productivity evaluation result; E(t) is the emotion evaluation result; C(t) is the external environmental factor; α, β, γ are weight coefficients.

7. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The steps of constructing an optimization algorithm to dynamically adjust work tasks and work hours and optimize work satisfaction in real time include: Set the objective function to maximize the courier's job satisfaction. The objective function form is: Among them, x1 is the work task allocation plan; x2 is the work time arrangement plan; S(t) is the courier's job satisfaction; P(t) is the productivity evaluation result; E(t) is the emotion evaluation result; C(t) is the external environmental factor; α, β, γ are weight coefficients; Introducing constraints, including daily work hours, task completion, and fairness distribution indicators; Based on historical work data and current satisfaction trends, use machine learning algorithms or heuristic search algorithms to calculate the optimal x1 and x2; Dynamically adjust the courier's workload and working hours based on the calculation results; Feedback adjustment results are used to update subsequent evaluation processes to achieve real-time optimization.

8. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The step of adjusting the weight coefficient of the evaluation model based on the optimization result includes: Collect feedback on couriers’ job satisfaction by analyzing optimized work tasks and work time allocation; According to the changing trend of job satisfaction, calculate the error of the current evaluation model: ∈(t)=|S current (t)-S predicted (t)|; Among them, ∈(t) is the error of the current evaluation model; S current (t) is actual job satisfaction; S predicted (t) is the job satisfaction predicted by the model; Based on the error calculation results, the optimization algorithm is used to dynamically adjust the weight coefficients α1, α2, α3, β1, and β2 in the productivity evaluation model and the sentiment evaluation model. The specific adjustment process is as follows: Among them, η is the learning rate; α i , β j is the weight coefficient of productivity and sentiment model; is the i-th weight coefficient α in the productivity evaluation model of error ∈(t) i The partial derivative of reflects the influence of the weight coefficient on the error; is the jth weight coefficient β in the productivity evaluation model of error ∈(t) j The partial derivative of reflects the influence of the weight coefficient on the error; Repeat the above adjustment process until the error ∈(t) is less than the preset threshold, ensuring that the weight coefficient of the evaluation model is accurately adjusted and can effectively reflect the courier's job satisfaction.

9. The method for evaluating job satisfaction in the express delivery industry based on a productivity model according to claim 1, characterized in that: The steps of forming a self-correction mechanism include: Construct a continuous learning mechanism to analyze the error between the model prediction value and the actual satisfaction level at every preset period Δt to form an error time series data set; Use the time sliding window to extract the error sequence {∈(t-Δt),…,∈(t)} of the last n cycles and calculate the average error. The calculation rule is: in, is the average error; n is the number of cycles used to calculate the average error; k is the index of the error sequence, indicating the error between the current cycle and the past cycle; ∈(tk·Δt) is the error at time tk·Δt, as each error value in the sliding window; When the average error When the preset threshold θ is exceeded, the model parameter update mechanism is automatically triggered to readjust the weight coefficient α of the evaluation model i , β j , and record the correction cycle; The adjustment frequency and error convergence rate are evaluated through historical correction data, and the learning rate η and window length n are further optimized to form a steady-state adaptive correction cycle.

10. A system for evaluating job satisfaction in the express delivery industry based on a productivity model, for executing a method for evaluating job satisfaction in the express delivery industry based on a productivity model as claimed in any one of claims 1 to 9, characterized in that: include: The data collection module is used to collect the courier's work data in real time, including workload, work efficiency and customer evaluation; The emotional data collection module is used to obtain the courier's emotional fluctuations and emotional labels through voice analysis and text analysis; A productivity evaluation module, which is used to build a productivity evaluation model based on the collected work data and evaluate the work productivity of couriers; The emotion evaluation module is used to build an emotion computing model based on the collected emotion data and evaluate the courier's emotional state; A job satisfaction calculation module is used to calculate the courier's job satisfaction based on the results of productivity evaluation and emotional state evaluation; Optimization algorithm module, used to dynamically adjust work tasks and working hours based on job satisfaction evaluation results and optimize job satisfaction in real time; The weight adjustment module is used to adjust the weight coefficient of the evaluation model based on the optimization results, making the evaluation more accurate and forming a self-correction mechanism; The correction mechanism module is used to automatically trigger the self-correction process and update the parameters of the evaluation model based on the error calculation results.

Images