Performance assessment system for medical beauty related personnel
By designing a performance appraisal system for medical beauty-related personnel and using neural network models to automatically perform performance appraisal, the problems of cumbersome manual calculations and human errors in the existing technology are solved, and efficient, accurate and real-time performance appraisal is achieved.
Patent Information
- Application Number
- CN202510146039.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-10
- Publication Date
- 2025-05-30
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing performance appraisal technology relies on manual statistics and calculations by human resources departments or managers, which makes the calculations cumbersome, time-consuming and prone to human errors, and it is difficult to quickly adapt to business changes, affecting the timeliness and effectiveness of the assessment.
Design a performance appraisal system for medical beauty-related personnel, including functional management units, data analysis units, model building units, performance accounting units and trend analysis units, establish performance appraisal models for different functional positions through neural network models, automate data integration and analysis, and generate evaluation and judgment results.
It has achieved automation and real-time performance appraisal of personnel in different positions in the medical beauty industry, reduced human errors, improved the accuracy and fairness of the assessment, and can quickly adapt to business changes and ensure work efficiency and work order.
Smart Images
Figure CN120069665A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of performance appraisal, and particularly relates to a performance appraisal system for personnel related to medical beauty. Background Art
[0002] With the development of the times and the continuous progress of society, performance has become a key concern in enterprises and organizations. Performance usually refers to the effect and quality of an individual or team completing work tasks within a certain period of time. In enterprises and organizations, performance is usually used to measure employees' work performance, so as to evaluate, motivate and manage them. By setting specific and measurable work goals, it helps employees clarify work requirements and expectations, thereby improving work efficiency.
[0003] The existing performance calculation technologies mainly rely on the human resources department or relevant management personnel for statistics and calculation. First, collect the work data of different employees, and then manually formulate different performance calculation methods for employees with different responsibilities. Since it is manually formulated, the formulation criteria are usually relatively simple. According to the principle of more pay for more work, the performance is directly allocated according to the workload.
[0004] However, manual performance calculation requires a large amount of manpower and time. Especially in the case of a large number of employees or complex assessment criteria, the calculation process may become very cumbersome and time-consuming. And because manual calculation involves a large amount of data processing and calculation, it is very easy to make human errors, such as data entry errors, calculation errors, etc. These errors may affect the accuracy and fairness of the assessment results.
[0005] At the same time, the manual performance calculation process may be affected by various subjective factors, such as personal biases, emotional factors, etc. These factors may lead to the assessment results being less objective and fair. With the development and change of enterprise business, the assessment criteria and calculation methods may need to be adjusted and optimized. However, manual performance calculation often has difficulty adapting to these changes quickly, resulting in the timeliness and effectiveness of the assessment results being affected;
[0006] In view of the above technical defects, a solution is proposed now. Summary of the Invention
[0007] The purpose of the present invention is to: construct a performance appraisal system for personnel in different positions in the medical beauty industry, understand the working status of medical practitioners in real time, and adjust the workload of personnel according to the evaluation and judgment results to ensure work efficiency, and then ensure the orderly progress of work.
[0008] To achieve the above purpose, the present invention adopts the following technical solution: a performance appraisal system for personnel related to medical beauty, including a function management unit, a data analysis unit, a model establishment unit, a performance calculation unit, a trend analysis unit and a publicity terminal;
[0009] The functional management unit is used to obtain all functional positions within a medical beauty institution, obtain the basic performance appraisal data based on the job content of the functional positions, and establish personal portraits of functional personnel. At the same time, it obtains the salary structure of the functional positions, calculates the impact value of human resources cost based on the industry salary reference range, and performs weighted fusion on the basic performance appraisal data and the impact value of human resources cost to obtain performance appraisal characteristics and send them to the model establishment unit;
[0010] The model establishment unit is used to obtain the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to the performance appraisal characteristics, establish performance appraisal models corresponding to different functional positions according to the neural network model, and classify and manage the performance appraisal models;
[0011] The data analysis unit includes a data acquisition module and a data analysis module. The data acquisition module is used to formulate a clear work process form to ensure that personnel work is traceable, record and integrate work data into a work data set through the work process form, and at the same time import the personal portraits of functional personnel additionally, and send the performance appraisal parameter set obtained after data fusion to the data analysis module;
[0012] The data analysis module is used to obtain the performance appraisal parameter set, establish a time axis according to the performance appraisal cycle, and at the same time re-sort the performance appraisal parameter set according to the performance appraisal characteristics, mark the specific data in the performance appraisal parameter set on the time axis one by one according to the time records on the work process form to obtain an appraisal process form, and send the appraisal process form to the superior supervisor of the functional personnel for confirmation. After being confirmed by the superior supervisor, an optimized appraisal process form is obtained;
[0013] The performance calculation unit is used to obtain the appraisal process form of the functional personnel, obtain the specific performance appraisal characteristics from the appraisal process form of the functional personnel, and substitute the specific performance appraisal characteristics into the performance appraisal model to which the functional personnel belong to obtain an appraisal evaluation value;
[0014] The trend analysis unit is used to obtain multiple appraisal evaluation values within the appraisal cycle, calculate the evaluation prediction value through the linear trend analysis method, judge the evaluation prediction value according to the preset evaluation judgment range, and generate an evaluation judgment result and send it to the publicity terminal.
[0015] Further, the publicity terminal includes a publicity platform within the medical beauty institution and the personal terminals of the management personnel within the medical beauty institution.
[0016] Further, the specific process of obtaining the basic performance appraisal data is as follows:
[0017] S101. Obtain all functional positions within a medical beauty institution, specifically including the names, employee numbers, and specific positions of the personnel corresponding to the functional positions, and establish personal portraits of functional personnel based on the names and position characteristics of the personnel.
[0018] S102. Obtain the work content of the functional positions. The work content includes working hours, work difficulty coefficient d, task completion content, task standards, and task frequencies, and obtain the basic performance appraisal data including task completion evaluation coefficient F1, work efficiency coefficient F2, and workload evaluation value F3. Then F = (F1, F2, F3).
[0019] Specifically: By comparing the task completion content with the task standards one by one, obtain the task completion evaluation coefficient F1 in the form of a scale.
[0020] The work efficiency coefficient F2 is obtained by the weighted combination of working hours Ti and work difficulty coefficient d, that is where e3 is a preset weight coefficient.
[0021] The workload evaluation value F3 is specifically calculated based on the task frequency and the working hours corresponding to the task frequency, calculate the total working hours of the personal portrait of the functional personnel, and combine the total working hours of the work cycle. Then F3 is the ratio of the total working hours to the total working hours of the work cycle.
[0022] Further, the specific process of obtaining the performance appraisal characteristics is as follows:
[0023] S201. Obtain the salary structure. The salary structure is specifically the starting salary and commission system corresponding to each functional position, and calculate the salary range (Wmin, Wmax) for each personal portrait of the functional personnel according to the salary structure.
[0024] S202. Obtain the industry's salary reference range (W′min, W′max), and calculate the human cost impact value Ui according to the following formula: where e1 and e2 are preset weight coefficients.
[0025] S203. Extract the spatial features Fk in the performance appraisal basic data F through a two-dimensional convolutional filter variant, and aggregate the temporal features Ft in the performance appraisal basic data F through a two-dimensional convolutional filter variant.
[0026] S204. Perform average pooling on the spatial features Fk and temporal features Ft and then splice them. Send the resulting feature map into the fully connected layer, and normalize the output through the Softmax function to obtain the weight coefficient matrix a.
[0027] S205. Multiply the spatial features Fk and temporal features Ft with the weight coefficient matrix a and the human cost impact value Ui to obtain the performance appraisal characteristics F′: F = [Ft, Fk] * a * Ui.
[0028] Further, the specific process of establishing a performance appraisal model corresponding to different functional positions is as follows:
[0029] Obtain historical performance appraisal data and input the historical performance appraisal data into a preset BP neural network model, specifically including:
[0030] S301. Integrate the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to performance appraisal characteristics into a training set, and determine the number of hidden layer nodes of the BP neural network model according to the quantity of the historical performance appraisal data in the training set;
[0031] S302. Output the historical performance appraisal data as a first feature based on the standard normal distribution through the first activation function of the hidden layer, and the activation function is the probability density function based on the standard normal distribution;
[0032] S303. Output the first feature as an assessment value based on the non-standard normal distribution through the second activation function of the output layer, and update the weight value and bias value of the BP neural network model until the value of the cost function of the BP neural network model is minimized.
[0033] Further, the specific process of obtaining the appraisal process form is as follows:
[0034] S401. Obtain a set of performance appraisal parameters, and the obtaining of the set of performance appraisal parameters includes the personal portrait of functional personnel and the daily work data of the personal portrait of the functional personnel within the appraisal period;
[0035] S402. Obtain the appraisal period T, establish a time axis with working days as the period segments, and obtain performance appraisal characteristics. The performance appraisal characteristics include task completion evaluation coefficient, work efficiency coefficient, and workload evaluation value. It can be known that the necessary data in the set of performance appraisal parameters are the daily working hours, the number of task items, and the task titles within the appraisal period. And mark the work difficulty coefficient, task completion content, and task standards corresponding to the task titles, and calculate the task frequency according to the number of task items and the appraisal period at the same time;
[0036] S403. Mark the task titles on the time axis according to the corresponding task completion dates, calculate the task completion evaluation coefficient, work efficiency coefficient, and workload evaluation value one by one according to the necessary data in the set of performance appraisal parameters, and mark the specific data one by one below the corresponding task titles on the time axis to obtain the appraisal process form.
[0037] Further, the specific process of generating an evaluation and judgment result is as follows:
[0038] S501. Obtain the historical assessment value yi for the same period in history, and calculate the regression coefficient of the linear regression equation according to the preset influencing factors. Specifically:
[0039] S5011. The influencing factors include the work difficulty coefficient d and the task standard. Obtain industry-related data through the database, and comprehensively evaluate the task standard and the work difficulty coefficient d to obtain the task feasibility coefficient xi.
[0040] S5012. Calculate the regression coefficient b according to the following formula: where n is the number of task feasibility coefficients xi.
[0041] S5013. Calculate the regression coefficient a according to the following formula:
[0042] S5014. It can be known that the linear regression equation is Yi = aY + b.
[0043] S502. Substitute multiple assessment values Y into the linear regression equation to obtain the assessment prediction value Yi.
[0044] S503. Obtain the preset assessment judgment range (Ymin, Ymax). If the assessment prediction value Yi is less than or equal to Ymin, the output assessment judgment result is that the performance tends to be in the rising stage.
[0045] If the assessment prediction value Yi is greater than Ymin and less than Ymax, the output assessment judgment result is that the performance tends to be in the stable stage.
[0046] If the assessment prediction value Yi is less than or equal to Ymin, the output assessment judgment result is that the performance tends to be in the rising stage.
[0047] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0048] The performance appraisal system for medical beauty-related personnel obtains the basic performance appraisal data based on the work content of functional positions in a medical beauty institution, and at the same time integrates the salary structure of functional positions to obtain the performance appraisal characteristics. According to the neural network model, a performance appraisal model corresponding to different functional positions is established. The work data is recorded and integrated into a work data set through a work flow table. After being confirmed by the superior supervisor of the functional personnel, the specific performance appraisal characteristics are substituted into the performance appraisal model to which the functional personnel belong to obtain the assessment value. The assessment prediction value is calculated through the linear trend analysis method, and the assessment prediction value is judged according to the preset assessment judgment range to generate an assessment judgment result, constructing a performance appraisal system for different positions in the medical beauty industry, understanding the working status of medical practitioners in real time, and adjusting the workload of personnel according to the assessment judgment result to ensure work efficiency, and thus ensure that the work is carried out in an orderly manner. Brief Description of the Drawings
[0049] Figure 1 Shows a schematic diagram of the overall structure of the present invention. Detailed Description of the Embodiments
[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0051] Embodiment:
[0052] As Figure 1 shown, a performance appraisal system for medical beauty-related personnel includes a function management unit, a data analysis unit, a model establishment unit, a performance calculation unit, a trend analysis unit, and a publicity terminal;
[0053] The function management unit is used to obtain all function positions in a medical beauty institution, obtain performance appraisal basic data based on the work content of the function positions and establish personal portraits of function personnel. At the same time, obtain the salary structure of the function positions, calculate the human cost impact value based on the industry wage reference range, and perform weighted fusion on the performance appraisal basic data and the human cost impact value to obtain performance appraisal features and send them to the model establishment unit;
[0054] The specific process of obtaining the performance appraisal basic data is as follows:
[0055] S101. Obtain all function positions in a medical beauty institution. The function positions include management personnel, service personnel, logistics personnel, and surgical physicians, specifically including the names, employee numbers, and specific positions of the personnel corresponding to the function positions, and establish personal portraits of function personnel according to the names of the personnel and the position characteristics;
[0056] S102. Obtain the work content of the function positions. The work content includes working hours, work difficulty coefficient d, task completion content, task standards, and task frequencies. The performance appraisal basic data obtained includes task completion evaluation coefficient F1, work efficiency coefficient F2, and workload evaluation value F3, then F=(F1, F2, F3);
[0057] Specifically: By comparing the task completion content with the task standards one by one, obtain the task completion evaluation coefficient F1 in the form of a scale;
[0058] The work efficiency coefficient F2 is obtained by weighted combination of the working hours Ti and the work difficulty coefficient d, that is where e3 is a preset weight coefficient;
[0059] The workload evaluation value F3 specifically calculates the total working hours of the personal portrait of functional personnel based on the task frequency and the working hours corresponding to the task frequency, and combines the total working hours of the working cycle. Then F3 is the ratio of the total working hours to the total working hours of the working cycle.
[0060] The specific process of obtaining the performance appraisal characteristics is as follows:
[0061] S201. Obtain the salary structure, which is specifically the starting salary and commission system corresponding to each functional position. Calculate the salary range (Wmin, Wmax) for the personal portrait of each functional personnel according to the salary structure;
[0062] S202. Obtain the salary reference range (W′min, W′max) in the industry, and calculate the human cost impact value Ui according to the following formula: Where e1 and e2 are preset weight coefficients. The human cost impact value reflects the impact degree of the human cost of the medical beauty institution on the evaluation of the personal portrait of functional personnel. The larger the human cost impact value, the greater the impact of the performance appraisal result of the personal portrait of this functional personnel by the human cost. On the contrary, the smaller the human cost impact value, the smaller the impact of the performance appraisal result of the personal portrait of this functional personnel by the human cost;
[0063] S203. Extract the spatial feature Fk in the performance appraisal basic data F through the two-dimensional convolutional filter variant, and aggregate the temporal feature Ft in the performance appraisal basic data F through the two-dimensional convolutional filter variant;
[0064] S204. Perform average pooling on the spatial feature Fk and the temporal feature Ft and then splice them. Send the obtained feature map after splicing into the fully connected layer, and normalize the output through the Softmax function to obtain the weight coefficient matrix a,
[0065] S203. Multiply the spatial feature Fk and the temporal feature Ft with the weight coefficient matrix a and the human cost impact value Ui to obtain the performance appraisal feature F′: F = [Ft, Fk] * a * Ui.
[0066] The model establishment unit is used to obtain the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to the performance appraisal characteristics, establish performance appraisal models corresponding to different functional positions according to the neural network model, and classify and manage the performance appraisal models;
[0067] The specific process of establishing performance appraisal models corresponding to different functional positions is as follows:
[0068] Obtain historical performance appraisal data, and input the historical performance appraisal data into a preset BP neural network model. Before the BP neural network model generates an appraisal value that conforms to a normal distribution from the historical performance appraisal data through a probability density function, it also includes constructing a BP neural network model, specifically including:
[0069] S301. Obtain the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to the performance appraisal characteristics, integrate them into a training set, and determine the number of hidden layer nodes of the BP neural network model according to the quantity of the historical performance appraisal data in the training set;
[0070] S302. Output the historical performance appraisal data as a first feature based on the standard normal distribution through the first activation function of the hidden layer. The activation function is the probability density function based on the standard normal distribution;
[0071] S303. Output the first feature as an appraisal value based on the non-standard normal distribution through the second activation function of the output layer, and update the weight values and bias values of the BP neural network model until the value of the cost function of the BP neural network model is minimized.
[0072] The data analysis unit includes a data acquisition module and a data analysis module. The data acquisition module is used to formulate a clear work process form to ensure that personnel work is traceable. Record and integrate the work data into a work data set through the work process form, and at the same time additionally import the personal portraits of functional personnel. After data fusion, a performance appraisal parameter set is sent to the data analysis module;
[0073] The data analysis module is used to obtain the performance appraisal parameter set, establish a time axis according to the performance appraisal cycle, and at the same time re-comb the performance appraisal parameter set according to the performance appraisal characteristics. Mark the specific data in the performance appraisal parameter set on the time axis one by one according to the time records on the work process form to obtain an appraisal process form, and send the appraisal process form to the superior supervisor of the functional personnel for confirmation. After confirmation by the superior supervisor, an optimized appraisal process form is obtained;
[0074] The specific process of obtaining the appraisal process form is as follows:
[0075] S401. Obtain the performance appraisal parameter set. Obtaining the performance appraisal parameter set includes the personal portrait of the functional personnel and the daily work data of the personal portrait of the functional personnel within the appraisal cycle;
[0076] S402. Obtain the assessment period T, establish a timeline with working days as the period segments, obtain the performance assessment characteristics, which include the task completion assessment coefficient, work efficiency coefficient, and workload assessment value. It can be known that the necessary data in the performance assessment parameter set are the daily working hours, the number of task items, and the task titles within the assessment period. And mark the work difficulty coefficient, task completion content, and task standards corresponding to the task titles. At the same time, calculate the task frequency according to the number of task items and the assessment period;
[0077] S403. Mark the task titles on the timeline according to the corresponding task completion dates. Calculate the task completion assessment coefficient, work efficiency coefficient, and workload assessment value one by one according to the necessary data in the performance assessment parameter set, and mark the specific data one by one below the corresponding task titles on the timeline to obtain the assessment process form.
[0078] The performance calculation unit is used to obtain the assessment process form of the functional personnel, and obtain the specific performance assessment characteristics from the assessment process form of the functional personnel, and substitute the specific performance assessment characteristics into the performance assessment model to which the functional personnel belong to obtain the assessment value;
[0079] The trend analysis unit is used to obtain multiple assessment values within the assessment period, calculate the assessment prediction value through the linear trend analysis method, and judge the assessment prediction value according to the preset assessment judgment range to generate an assessment judgment result and send it to the publicity terminal.
[0080] The specific process of generating the assessment judgment result is as follows:
[0081] S501. Obtain the historical assessment values yi of the same period in history, and calculate the regression coefficients of the linear regression equation according to the preset influencing factors. Specifically:
[0082] S5011. The influencing factors include the work difficulty coefficient d and the task standards. Obtain the industry-related data through the database, and comprehensively evaluate the task standards and the work difficulty coefficient d to obtain the task implementability coefficient xi;
[0083] S5012. Calculate the regression coefficient b according to the following formula: where n is the number of task implementability coefficients xi;
[0084] S5013. Calculate the regression coefficient a according to the following formula:
[0085] S5014. It can be known that the linear regression equation is Yi = aY + b;
[0086] S502. Substitute multiple assessment values Y into the linear regression equation to obtain the assessment prediction value Yi;
[0087] S503. Obtain the preset evaluation and judgment range (Ymin, Ymax). If the evaluation prediction value Yi is less than or equal to Ymin, the output evaluation and judgment result is that the performance tends to be in the rising stage;
[0088] If the evaluation prediction value Yi is greater than Ymin and less than Ymax, the output evaluation and judgment result is that the performance tends to be in the stable stage;
[0089] If the evaluation prediction value Yi is less than or equal to Ymin, the output evaluation and judgment result is that the performance tends to be in the rising stage.
[0090] The public display terminal shown includes a public display platform within a medical beauty institution and the personal terminal of the management personnel within the medical beauty institution.
[0091] Based on the work content of functional positions within a medical beauty institution, this invention obtains the basic data for performance appraisal. At the same time, by integrating the salary structure of functional positions, it obtains the performance appraisal characteristics. According to the neural network model, it establishes a performance appraisal model corresponding to different functional positions. Through the work process form, it records and integrates the work data into a work data set. After being confirmed by the superior supervisor of the functional personnel, it substitutes the specific performance appraisal characteristics into the performance appraisal model to which the functional personnel belong to obtain the appraisal value. It calculates the evaluation prediction value through the linear trend analysis method, and judges the evaluation prediction value according to the preset evaluation and judgment range to generate the evaluation and judgment result. It constructs a performance appraisal system for different positions of personnel in the medical beauty industry, understands the working status of medical practitioners in real time, can adjust the workload of personnel according to the evaluation and judgment result to ensure work efficiency, and thus can ensure the orderly progress of work.
[0092] The setting of the size of the interval and threshold is for the convenience of comparison. Regarding the size of the threshold, it depends on the amount of sample data and the number of base numbers set by those skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantified values.
[0093] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation;
[0094] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.
Claims
1. A performance appraisal system for medical cosmetology related personnel, characterized in that: It includes functional management unit, data analysis unit, model building unit, performance accounting unit, trend analysis unit and public announcement terminal; The functional management unit is used to obtain all functional positions in the medical beauty institution, and obtain the basic data of performance appraisal based on the work content of the functional positions and establish the personal portrait of the functional personnel. At the same time, it obtains the salary structure of the functional positions, calculates the human cost impact value based on the salary reference range in the industry, and obtains the performance appraisal characteristics after weighted fusion of the basic data of performance appraisal and the human cost impact value and sends it to the model building unit; The model building unit is used to obtain the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to the performance appraisal characteristics, establish performance appraisal models corresponding to different functional positions based on the neural network model, and classify and manage the performance appraisal models; The data analysis unit includes a data acquisition module and a data analysis module. The data acquisition module is used to formulate a clear work flow table to ensure that the work of personnel is recorded. The work flow table is used to record and integrate the work data into a work data set. At the same time, the personal portrait of the functional personnel is additionally imported. After data fusion, the performance appraisal parameter set is obtained and sent to the data analysis module; The data analysis module is used to obtain a performance appraisal parameter set, and establish a timeline according to the performance appraisal cycle, and at the same time re-sort the performance appraisal parameter set according to the performance appraisal characteristics, and mark the specific data in the performance appraisal parameter set on the timeline one by one according to the time record on the work flow table, and obtain the appraisal process table, and send the appraisal process table to the superior of the functional personnel for confirmation, and obtain the optimized appraisal process table after confirmation by the superior; The performance accounting unit is used to obtain the appraisal process table of the functional personnel, and obtain the specific performance appraisal characteristics from the appraisal process table of the functional personnel, and substitute the specific performance appraisal characteristics into the performance appraisal model to which the functional personnel belong to obtain the appraisal evaluation value; The trend analysis unit is used to obtain multiple assessment evaluation values within the assessment period, calculate the assessment prediction value through the linear trend analysis method, judge the assessment prediction value according to the preset assessment judgment range, and generate the assessment judgment result to be sent to the public display terminal.
2. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The public disclosure terminals shown include the public disclosure platform within the medical beauty institution and the personal terminals of the managers within the medical beauty institution.
3. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The specific process of obtaining the basic data of performance appraisal is as follows: S101. Obtain all functional positions in the medical beauty institution, including the names, work numbers and specific positions of the personnel corresponding to the functional positions, and establish personal portraits of the functional personnel based on the names and position characteristics; S102, obtaining the work content of the functional position, wherein the work content includes working hours, work difficulty coefficient d, task completion content, task standard and task frequency, and obtaining basic performance appraisal data including task completion evaluation coefficient F1, work efficiency coefficient F2 and workload evaluation value F3, then F = (F1, F2, F3); Specifically: by comparing the task completion content with the task standard one by one, the task completion evaluation coefficient F1 is obtained in the form of a scale; The work efficiency coefficient F2 is obtained by weighted combination of work time Ti and work difficulty coefficient d, that is, Where e3 is the preset weight coefficient; The workload assessment value F3 is calculated based on the total working hours of the functional personnel's personal portrait according to the task frequency and the working hours corresponding to the task frequency. Combined with the total duration of the work cycle, F3 is the ratio of the total working hours to the total duration of the work cycle.
4. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The specific process of obtaining performance appraisal characteristics is as follows: S201, obtaining a salary structure, wherein the salary structure specifically includes a starting salary and commission system corresponding to each functional position, and calculating a salary range (Wmin, Wmax) for each functional personnel's personal profile according to the salary structure; S202. Obtain the salary reference range (W′min, W′max) in the industry, and calculate the labor cost impact value Ui according to the following formula: Where e1 and e2 are preset weight coefficients; S203, extracting spatial features Fk in the performance appraisal basic data F through a two-dimensional convolution filter variant, and aggregating temporal features Ft in the performance appraisal basic data F through a two-dimensional convolution filter variant; S204, the spatial feature Fk and the temporal feature Ft are average-pooled and concatenated, the concatenated feature map is sent to the fully connected layer, and the output is normalized by the Softmax function to obtain the weight coefficient matrix a. S205. Multiply the spatial feature Fk and the temporal feature Ft with the weight coefficient matrix a and the human cost impact value Ui to obtain the performance appraisal feature F′: F = [Ft, Fk]*a*Ui.
5. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The specific process of establishing performance appraisal models corresponding to different functional positions is as follows: Obtaining historical performance evaluation data and inputting the historical performance evaluation data into a preset BP neural network model specifically includes: S301, obtaining the personal portraits of functional personnel corresponding to all functional positions and the historical performance appraisal data corresponding to the performance appraisal characteristics, integrating them into a training set, and determining the number of hidden layer nodes of the BP neural network model according to the number of historical performance appraisal data in the training set; S302, outputting the historical performance evaluation data as a first feature based on a standard normal distribution through a first activation function of a hidden layer, wherein the activation function is a probability density function based on a standard normal distribution; S303. Output the first feature as an assessment value based on a non-standard normal distribution through the second activation function of the output layer, and update the weight value and bias value of the BP neural network model until the value of the cost function of the BP neural network model is minimized.
6. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The specific process of obtaining the assessment flow chart is as follows: S401, obtaining a performance appraisal parameter set, wherein the obtained performance appraisal parameter set includes a personal portrait of the functional personnel and daily work data of the personal portrait of the functional personnel during the appraisal period; S402, obtaining the assessment cycle T, establishing a timeline with working days as the cycle segment, and obtaining performance assessment characteristics, which include task completion assessment coefficient, work efficiency coefficient and workload assessment value. It can be seen that the necessary data in the performance assessment parameter set are the daily working hours, number of task items and task titles within the assessment cycle, and the work difficulty coefficient, task completion content and task standard are marked according to the task title, and the task frequency is calculated according to the number of task items and the assessment cycle; S403. Mark the task title on the timeline according to the corresponding task completion date, calculate the task completion evaluation coefficient, work efficiency coefficient and workload evaluation value one by one according to the necessary data in the performance appraisal parameter set, and mark the specific data one by one under the corresponding task title on the timeline to obtain the appraisal process table.
7. The performance appraisal system for medical cosmetology related personnel according to claim 1 is characterized in that: The specific process of generating the evaluation and judgment results is as follows: S501. Obtain the historical assessment value yi for the same period in history, and calculate the regression coefficient of the linear regression equation according to the preset influencing factors. Specifically: S5011. The influencing factors include the work difficulty coefficient d and the task standard. The industry-related data is obtained through the database, and the task standard and the work difficulty coefficient d are comprehensively evaluated to obtain the task feasibility coefficient xi. S5012. Calculate the regression coefficient b according to the following formula: Where n is the number of task implementable coefficients xi; S5013. Calculate the regression coefficient a according to the following formula: S5014, it can be known that the linear regression equation Yi=aY+b; S502, substituting multiple assessment evaluation values Y into a linear regression equation to obtain an assessment prediction value Yi; S503, obtaining a preset evaluation judgment range (Ymin, Ymax), if the evaluation prediction value Yi is less than or equal to Ymin, then the output evaluation judgment result is that the performance tends to rise; If the evaluation prediction value Yi is greater than Ymin and less than Ymax, the output evaluation judgment result is that the performance tends to be stable; If the evaluation prediction value Yi is less than or equal to Ymin, the output evaluation judgment result is that the performance tends to rise.