Intelligent performance management system for specialized nurses

Abstract

The invention provides an intelligent performance management system for specialized nurses. The intelligent performance management system comprises a human resource module, a medical science and style module, an evaluation and pre-evaluation module, a work quality module, a training and assessment module and a performance module. According to the intelligent performance management system for the specialized nurses, training of career of the specialized nurses is used as guidance, and all-around performance management is achieved. An intimacy index evaluation item containing model prediction based on an audio and language model quantifies a mechanism of a nurse working attitude, quantitative evaluation is performed on the most critical language of a patient and family members thereof for nurse impressions, and more important and objective evaluation factors are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an intelligent performance management system for specialist nurses. Background Art

[0002] The development of specialist nurses aims to optimize the nursing team structure, enhance professional service capabilities, and promote the refinement and specialization of nursing services. It also proposes tiered authorization management and intelligent information management for specialist nurses. Currently, there are many performance management systems, but none specifically tailored to specialist nurses. Many performance management systems simply assess workload and link bonuses, lacking a systematic and comprehensive performance management platform oriented toward career planning for nurses.

[0003] Chinese utility model patent application CN108734377A discloses a nurse performance management system for managing nurses' work performance. However, this invention only unilaterally counts work hours. The scope of specialist nurses' work involves the development of specialized nursing work. This invention is only applicable to the attendance of specialist nurses and does not cover more aspects. Chinese utility model patent application CN110458458A discloses a nursing staff performance management device and method, but the assessment mechanism is too general and not suitable for the assessment of specialist nurses. Chinese utility model patent application CN111768122A discloses a nursing staff performance assessment and evaluation system. This invention significantly improves the assessment scope, but is only suitable for general nurses. For specialist nurses, the assessment scope should be broader and lacks comprehensiveness. Chinese utility model patent application CN119180558A discloses an intelligent clinical nurse performance evaluation system. This invention's greatest advantage is that it makes performance management intelligent, but it is designed at the level of personnel management and does not comprehensively evaluate the complexity of nurses' work, making it even less suitable for specialist nurses.

[0004] Furthermore, current methods for evaluating nurses' medical ethics and professional conduct rely primarily on patient and family feedback and word-of-mouth during the nursing process and consultations, which is not scientifically quantifiable. Given the strained doctor-patient relationship and the increasing public concern about nursing staff's service attitude, recording nurses' daily work language and using it as a key factor in analyzing their medical ethics and professional conduct is crucial for addressing the evaluation component of performance appraisals. Summary of the Invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide an intelligent performance management system for specialist nurses, comprising: The human resources module is used to realize basic information management, human resource matching between each bed in the ward and the medical staff in charge, quality control project management assessment, work scheduling, and patient nursing workload and quality control staff workload statistics; the medical ethics and medical style module is used to manage the medical ethics and medical style evaluation information of specialist nurses; the evaluation information includes letters of praise, banners, complaints and patient satisfaction information, as well as multiple evaluation items of intimacy indicators predicted by the model based on audio and language models; the medical ethics and medical style of specialist nurses are evaluated within the set evaluation period according to the evaluation level corresponding to each evaluation item; the excellence and commendation module is used to evaluate specialist nurses; the work quality module is used to manage the workload information and nursing quality control information of specialist nurses; the training and assessment module is used to manage the training and assessment information of specialist nurses; the performance module is used to manage the performance scoring information of specialist nurses.

[0006] Optionally, the method for obtaining the intimacy index predicted by the model based on the audio and language model includes the following steps: S1 the nurse wears the audio collector before work; S2 collects the work site audio within the preset data collection period, and the nurse collects the voice alone in the room during the period; S3 uses the collected voice as a training set to train the nurse voice recognition model for recognizing different nurse voices, and inputs the work site audio into the trained nurse voice recognition model to call out the spectrum of the corresponding nurse's speech voice; S4 builds a natural speech recognition model and uses the spectrum of the corresponding nurse's speech voice for training to recognize the audio Corresponding text; S5 selects multiple nurses with high intimacy to collect their work-site audio, inputs the trained nurse speech recognition model to call out the spectrum of their speaking voice, and then inputs the spectrum into the trained natural speech recognition model to identify the corresponding text; S6 obtains the work-site audio of the nurse to be tested, and also identifies the corresponding text according to S5, and compares the spectrum corresponding to each different text with the spectrum of the corresponding text of the nurse with high medical ethics. The two types of spectra are normalized in intensity and the peak positions are shifted so that the frequency positions of the corresponding peaks coincide, and the similarity of the intimacy between the two is compared. The higher the similarity of intimacy, the higher the intimacy.

[0007] Optionally, the intimacy similarity is calculated as follows: S6-1 presets the frequency interval and finds multiple points of each of the two types of spectrum peaks with overlapping frequency positions; S6-2 calculates the volume db and the frequency derivative of each point on the multiple spectra corresponding to multiple nurses with high intimacy, and clusters them in the constructed frequency-volume-frequency derivative three-dimensional space; S6-3 embeds the multiple points corresponding to the nurses to be tested in the three-dimensional space, and counts the Mahalanobis distances with each cluster at each frequency; S6-4 obtains the average value of the minimum Mahalanobis distance at each frequency. When the average value of the minimum Mahalanobis distance is less than 1, it indicates a high degree of intimacy, between 1-3, it indicates moderate intimacy, greater than 3 but less than 5, it indicates normal intimacy, and greater than or equal to 5, it indicates indifference.

[0008] It should be understood that there are individual differences in the pronunciation frequency of the same word, but the characteristic bands are similar. Therefore, when comparing the degree of similarity, we shifted the frequency of the nurse to be tested to the same frequency as the selected nurses to compare the waveform shape and volume. That is, for each characteristic peak, we took multiple points at a preset frequency interval and calculated the frequency derivative and decibel distance. Although different people's wave shapes and decibels cannot determine whether a nurse is friendly, the closer their different frequencies are to those of multiple selected nurses, the more statistically significant it is to their degree of friendliness. Since there were also multiple selected nurses, covering different types of friendliness, a scientific quantitative indicator for the evaluation item of friendliness was given based on the total sample size and statistical analysis to characterize the nurses' service attitude and its contribution to the overall medical ethics score. The medical ethics and medical style of specialist nurses are evaluated within the set evaluation period according to the evaluation level corresponding to each evaluation item, including: the number of words in the letter of praise N1, the number of banners N2, the number of complaints N3, the number of words N4, and the patient satisfaction N5, as well as the average value N6 of the Mahalanobis distance corresponding to the intimacy predicted by the model based on audio and language models. The total score S=aN1+bN2-cN3-dN4+eN5+fN6 is calculated, with a+b+c+d+e+f=1, and f>c>d>e>a>b. The total score is sorted in order, and the top 60% are qualified and the rest are unqualified.

[0009] Optionally, the evaluation and commendation module includes: a list generation unit, which is used to obtain evaluation and commendation files and automatically generate evaluation keywords, and automatically generate an evaluation list and selection quantity based on the evaluation keywords; a voting collection unit, which is used to create a voting questionnaire based on the evaluation list and selection quantity generated by the list generation unit, and collect voting data feedback from each voter; and an evaluation and commendation generation unit, which generates an evaluation and commendation reference list based on the voting data.

[0010] Optionally, the work quality module includes a workload management unit and a nursing quality control unit; the workload management unit is used to manage the workload information of specialist nurses, calculate the workload schedule in combination with different nursing operations, and perform workload grade assessment; the workload information includes routine clinical workload, clinical specialist workload, and specialist nursing assistance workload; the nursing quality control unit is connected to the nursing quality control PAD system to achieve quality control, and at the same time assigns points to different levels of quality control.

[0011] Optionally, the training and assessment module includes: a stratified specialist nurse target setting unit, which sets target credits corresponding to specialist nurses at different levels; a stratified specialist nurse competition unit, which is used to manage the application requirements of specialist nurses at various levels; a stratified specialist nurse training plan unit, which is used to import specialist nurse training plans at different levels, connect to the hospital training software to send training notifications, and manage the training process at the same time; a credit and score statistics unit, which is used to manage hospital-level training and continuing education training programs, and to count the corresponding training results, including theoretical assessment results and specialist skill assessment results.

[0012] Optionally, the performance module includes: a monthly performance scoring unit, which is used to implement the monthly performance scoring of specialist nurses; a manual annual evaluation unit, which manages the evaluation results of the head nurses of the wards to which the specialist nurses belong; a peer evaluation unit, which automatically collects evaluation results from personnel in the same ward; an annual performance scoring unit, which is used to implement the year-end performance scoring of specialist nurses; a bonus data unit, which automatically calculates the monthly performance bonus based on the monthly performance score; and calculates the annual performance bonus based on the attendance rate and the number of operations; an annual performance analysis unit, which is used to implement hospital-wide, major department and individual performance analysis, and obtain workload, nursing quality, medical ethics and training analysis forms.

[0013] The system also includes a risk level module, which includes risk level setting and risk level assessment; project scoring and grading settings are formulated according to the operation time and difficulty, including four levels: A, B, C, and D; Level D, low risk: monthly basic bonus, night shift pay / the lowest level; Level C, medium risk: monthly basic bonus, night shift pay / the middle level; Level B, high risk: monthly basic bonus, night shift pay / the high level; Level A, extremely high risk: monthly basic bonus, night shift pay / the highest level.

[0014] The system also includes a teaching module for managing basic teaching information, teaching score settings and teaching workload statistics; basic teaching information includes personal basic information and teaching qualification information; when setting teaching scores, different teaching hours are set according to different teaching categories and teaching numbers; teaching workload statistics include undergraduate or graduate classroom teaching workload, nursing department and specialist teaching workload, and clinical teaching workload. The scientific research module is used to manage projects, patents, papers, guidelines / consensus / group standards, books and scientific research summary workload. The continuing care module is used to manage online consultations, home care, telephone follow-ups, health knowledge lectures, volunteer nursing services, health education manuscript submissions and continuing care summary workload. The public health emergency dispatch module includes in-hospital work support and out-of-hospital work support.

[0015] The intelligent performance management system for specialist nurses in the embodiment of the present invention is guided by the career training of specialist nurses and realizes all-round performance management. Through basic information management and matching of beds with medical staff, the manpower distribution of the ward can be grasped in real time, and personnel can be flexibly deployed according to actual needs to improve work efficiency. The intelligent scheduling system takes into account the qualifications and workload of nurses, automatically generates a reasonable schedule, reduces manual scheduling time, and improves the fairness and scientific nature of scheduling. The workload of nursing patients and quality control personnel is automatically counted to ensure that the data is accurate and timely, providing a reliable basis for management decisions. Through the intimacy index predicted by the model based on audio and language models, the mechanism of nurses' work attitude is quantified, and the language that is the most critical impression of patients and their families on nurses is quantitatively evaluated, realizing more important and objective evaluation factors.

[0016] Detailed quality control project management and assessment help the nursing team promptly identify and address quality issues, ensuring patient safety. A multi-dimensional quantitative evaluation mechanism encourages nurses to adhere to medical ethics, improve service attitudes and quality, and enhance patient satisfaction. Comprehensive records of nurse workload and quality control status allow for real-time monitoring of the nursing service process, ensuring high-quality care.

[0017] The objective and fair evaluation and appraisal system of the present invention stimulates nurses' enthusiasm and initiative in their work and encourages them to pursue excellence. Targeted training programs and regular assessments enhance nurses' professional skills and knowledge levels and promote their career growth. The transparent performance scoring system helps nurses understand their work performance, identify deficiencies, and clarify the direction of their efforts. The system accumulates a large amount of data, providing comprehensive analysis and scientific basis for nursing management decisions, helping managers formulate reasonable strategies. Real-time monitoring of nursing work and timely detection of anomalies enable managers to take prompt measures to ensure the smooth operation of nursing services.

[0018] Based on the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will become more aware of the above and other objects, advantages and features of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the structure of the intelligent performance management system for specialist nurses according to an embodiment of the present invention; Figure 2 This is a schematic diagram of logging into the intelligent performance management system for specialist nurses according to an embodiment of the present invention; Figure 3 Flowchart of a method for obtaining a familiarity index based on model prediction of audio and language models; Figure 4 Schematic diagram of normalization and frequency shift between the character spectra of the speech of the high-intimacy nurse and the speech of the nurse to be recognized; Figure 5 Frequency-volume, frequency derivative three-dimensional space for two high affinity nurses I and II as an example Figure 4 Schematic diagram of clustering and corresponding embedding points of the nurses to be tested, taking the frequency positions to which peaks A and B are shifted as an example. DETAILED DESCRIPTION

[0020] The embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to illustrate the present invention and are not intended to limit the present invention.

[0021] The embodiment of the present invention provides an intelligent performance management system for specialist nurses, such as Figure 1 As shown, the intelligent performance management system for specialist nurses in the embodiment of the present invention may include a human resources module for realizing basic information management, human resources matching between each bed in the ward and the medical staff in charge, quality control project management assessment, work scheduling, and patient nursing workload and quality control staff workload statistics; a medical ethics and medical style module for managing the medical ethics and medical style evaluation information of specialist nurses; the evaluation information includes multiple evaluation items such as letters of praise, banners, complaints, and patient satisfaction information; the medical ethics and medical style of specialist nurses are evaluated within a set evaluation period according to the evaluation level corresponding to each evaluation item; an evaluation module for evaluating and commending specialist nurses; a work quality module for managing the workload information and nursing quality control information of specialist nurses; a training and assessment module The module is used to manage the training and assessment information of specialist nurses; the teaching module is used to manage the basic teaching information of specialist nurses, the setting of teaching workload scores and the statistics of teaching workload; the scientific research module is used to manage the workload of specialist nurses' projects, patents, papers, guidelines / consensus / group standards and books; the continuing care module is used to manage the workload of specialist nurses' online consultation, home care, telephone follow-up, health knowledge lectures, volunteer nursing services, and health education manuscript submissions; the public health emergency dispatch module manages the in-hospital work support and out-of-hospital work support of specialist nurses; the risk level module is divided into risk level setting and risk level assessment, which is used as the basis for the monthly basic bonus and night shift fee classification of the ward; the performance module is used to manage the performance scoring information of specialist nurses. The intelligent performance management system for specialist nurses in the embodiment of the present invention is guided by the training of specialist nurses' careers and realizes all-round performance management. The functions of each module are described in detail below.

[0022] The system of this embodiment may have a login module, such as Figure 2As shown, when using the system of this embodiment for the first time, the user needs to register, that is, enter the name, work number, date of birth (age), date of joining the work (length of service), professional title, department (select), position (select), telephone number and development authority (if the nurse is involved in the first-level quality control of the ward, the user can check the individual and ward quality control; if the nurse is the head nurse of the ward, the user can check the individual and ward quality control + management; if the nurse is the head nurse of the department, the user can select the individual and the included wards; and so on) and wait for the technical department to review and notify the user by SMS. After receiving the SMS, the user can enter the system again to set the password to complete the registration.

[0023] 1. Human Resources Module The Human Resources module provides the following five functions: basic information management, human resources matching, quality control project management assessment, work scheduling, and patient and quality control staff workload statistics. Basic information management includes age, gender, length of service, employee number, professional title, position, work experience, educational background, specialist nursing certificates, and skill certificates. Each certificate has a corresponding acquisition date and level. Work experience requires electronic signature confirmation from a qualified head nurse, who then uploads the electronic certificate for review by the technical department. Upon approval, nurses can view the individual's basic information.

[0024] Human Resource Matching: Import the ward's nursing staff ID (replacement numbers must be updated promptly to prevent nurses from joining the next ward). Match bed numbers to primary quality control items, linking bed numbers to primary quality control items to track and evaluate the quality of care for each bed. Statistical methods are used to generate ward human resource maps and tables. This includes analyzing the ward's human resource allocation, such as the number, distribution, and workload of nursing staff, as well as calculating human resource-related costs, such as labor costs and training costs.

[0025] Quality Control Project Management Assessment: 1) Statistically assign quality control project grades based on the time spent on each project: A (highest), B (high), C (medium), D (average). Ward quality control staff will be assessed monthly for their work quality: ① A / project: 40 points, B / project: 30 points, C / project: 20 points, D / project: 10 points; ② Quality Control Effectiveness Scoring: Quality control projects completed without deductions from supervisors: 5 points / project, completed as required but with deductions from supervisors: 3 points / project, and completed not as required (regardless of deductions from supervisors): 0 points / project. 2) Based on the lowest and highest scores of each individual in the ward each month and year, a four-level tier system will be established: D (lowest level), C (medium level), B (higher level), and A (highest level).

[0026] Work Scheduling: Before scheduling, set upper and lower limits for ward human resources (total number of patients, number of critically ill patients, number of beds managed by the responsible nurse, required daily shifts, etc.). If these limits are exceeded, the system automatically sends a text message to the head nurse to remind her to adjust her shift. The system also notifies the head nurse based on the workload standards set by each nurse in the nursing department. The head nurse accesses the scheduling system and selects weekly, biweekly, or monthly scheduling (which can be customized). The system displays information such as the date, time, name, bed number, and time off from the previous week. The head nurse can select the appropriate shift in each column. After scheduling, clicking Save will check the system against the required daily shifts and remind her. The system automatically calculates time off based on the shift. Shifts can be modified to accommodate emergencies such as sick leave or changes in human resources. If a nurse defies the required sick leave, the head nurse must enter a note after modifying the shift. If a nurse defies departmental work arrangements, such as an inter-hospital transfer, the head nurse must enter a note after modifying the shift.

[0027] Statistics on night shifts, patient care workload, and quality control staff grades: 1) Night shift workload target setting: The Nursing Department sets targets based on the nurse specialist's level. The percentage of the ward's annual workload completed is: C1 (junior specialist nurse) ≥ 60%, C2 (intermediate specialist nurse) ≥ 50%, C3 (senior specialist nurse) ≥ 40%, and C4 (specialist nursing expert) ≥ 30%. Calculation method: Night shift workload percentage = 365 x 2 ÷ total number of nurses in the ward (including the head nurse) × 100% × 1.5. A light night shift = 1.5 heavy night shifts (all converted to light night shifts). Night shift workload progress estimate: The previous year's data is used as the denominator, and the current year's actual completion number is used as the numerator to predict the night shift workload progress.

[0028] 2) Targeting the total number of patients nursed: This target is set based on the specialist nurse's grade, with corresponding regulations for the number of night shifts based on the specialist nurse's grade. This prevents specialist nurses from prioritizing research over clinical nursing work, such as night shifts. The Nursing Department can set targets based on the hospital's human resources and medical workload, such as the percentage of annual completion of the ward's workload: C1 and C2 ≥ 60%, C3 and C4 ≥ 50%. Calculation method: Total number of patients nursed (%) = Total number of patients assigned to each responsible nurse ÷ (Total number of patients in the ward ÷ Total number of responsible nurses) × 100%. Nursing workload estimation: Using the previous year's data as the denominator and the current year's actual completion number as the numerator, the total number of patients nursed is projected.

[0029] 3) Target Setting for the Total Number of Critically Ill Patients Caregived: The Nursing Department sets targets based on the specialist nurse level, with annual completion percentages for each ward's workload: C1 ≥ 30%, C2 ≥ 40%, C3 ≥ 50%, and C4 ≥ 55%. Calculation: Critically Ill (%) = Total number of critically ill patients cared for by each responsible nurse ÷ (Total number of critically ill patients in the ward ÷ Total number of responsible nurses) × 100%. Estimate: Use the previous year's data as the denominator and the current year's actual completion number as the numerator to project progress toward the total number of critically ill patients cared for.

[0030] 4) Workload of quality control personnel: Monthly and annual evaluation results: D (lowest level), C (middle level), B (high level), A (highest level).

[0031] 5) The system is connected to the hospital HIS system, automatically extracting the number of night shifts per person, the total number of patients nursed and the number of critically ill patients, and conducting monthly grade assessments based on the number, with D (lowest level), C (middle level), B (high level), and A (highest level). The number of night shifts is assigned based on the number of long night shifts and short night shifts, that is, 1 long night shift = 1.5 short night shifts. At the beginning of each month, the system notifies individuals by text message of the number of night shifts, the total number of patients nursed and the number of critically ill patients, as well as the annual progress and the results of the quality control staff's work grade assessment, and the data is imported into the performance. For the specific process, see Figure 3 .

[0032] 2. Medical Ethics and Medical Style Module The medical ethics and medical style module is used to manage the medical ethics and medical style evaluation information of specialist nurses and can evaluate the comprehensive performance of specialist nurses in terms of professional ethics, work attitude, and patient service. In this embodiment, the evaluation information managed by the medical ethics and medical style module may include an evaluation information management unit for managing multiple evaluation items such as letters of praise, banners, complaints, and patient satisfaction; and a medical ethics and medical style assessment and statistics unit for assessing the medical ethics and medical style of specialist nurses within a set evaluation period based on the evaluation level corresponding to each evaluation item. The quality control officer of the medical ethics and medical style ward has the authority to import letters of praise and banners, enter the patient's name, hospitalization number, the name of the employee being praised, and upload electronic pictures.

[0033] Complaints are received by relevant departments such as the Medical Affairs Office, Outpatient Department, and the Nursing Department. Complaint-related information may include the name, hospitalization number, complainant, and content of the complaint. The system automatically notifies the head nurse of the ward concerned, who then investigates and determines the nature of the complaint to rule out unreasonable patient behavior. If the complaint is false, no department or individual will be linked. If the complaint is true, the head nurse resolves the dispute on-site or by phone, then completes the complaint handling process in the system and conducts a PDCA analysis. For genuine complaints, the third-party department provides feedback on the complaint's effectiveness. If satisfactory, the adjustment is concluded. If not, the system notifies the head nurse to make corrective actions.

[0034] Medical ethics and conduct assessment: A grading system can be used to automatically set the levels of letters of praise and banners: There are 4 levels in total (the system automatically divides the system into four levels based on the total number of letters of praise and banners received): A (highest number), B (high number), C (medium number), D (low number). Scoring criteria: Letters of praise: A: 40 points, B: 30 points, C: 20 points, D: 10 points; Banners: A: 40 points, B: 30 points, C: 20 points, D: 10 points; Complaints are directly rated as D (unqualified). Satisfaction: (Use the satisfaction survey form in each hospital's nursing quality control system to conduct a satisfaction survey using PAD or QR code. Ward quality control satisfaction personnel conduct the following first-, second-, and third-level quality control analysis. Quality control is carried out at the individual level, and data is automatically imported into this system through connection). Satisfaction rating has 4 levels: 100%, 95-99%, 90-94%, and ≤89%. Evaluation is conducted based on the data of the whole year (the system assigns points based on the number of letters of praise, banners and satisfaction, summarizes the data, and automatically divides the system into four levels based on the points. If a nurse has a valid complaint, he or she will be directly rated D, which means unqualified): A: Excellent, B: Good, C: Qualified, D: Unqualified. Those who are unqualified will be disqualified from the annual evaluation and promotion of professional titles. Statistics of medical ethics and medical style: Statistics on the monthly / annual satisfaction of individuals, departments, major departments, and the entire hospital are generated, and statistical charts or statistical tables are generated. The results of the medical ethics and medical style evaluation are announced at the end of each year. The system regularly sends relevant information to personal text messages. See the specific process for details. Figure 4 .

[0035] A quantitative scoring system can also be set up, which is based on the intelligent recognition of nurses' voices and the cluster analysis of waveforms and volume at characteristic frequencies, and an additional evaluation item of intimacy index predicted by the model based on audio and language models is introduced, which specifically includes the following contents: Figure 3 As shown, the method for obtaining the intimacy index based on the model prediction of the audio and language model includes the following steps: S1 nurses should wear the audio collector before working; S2 collects audio at the work site within a preset data collection cycle, and the nurse collects voice alone in the room during the cycle; S3 uses the collected speech as a training set to train a nurse speech recognition model for different nurse voices. It then inputs the worksite audio into the trained nurse speech recognition model to retrieve the spectrum of the corresponding nurse's speech. S4 builds a natural speech recognition model, trained using the spectrum of the nurse's voice to identify the corresponding text in the audio; S5 selects multiple highly friendly nurses to collect audio from their work scenes, inputs the trained nurse speech recognition model to retrieve the spectrum of their speech, and then inputs the spectrum into the trained natural speech recognition model to recognize the corresponding text; S6 obtains the work site audio of the nurse to be tested, and also recognizes the corresponding text according to S5, and compares the spectrum corresponding to each different text with the spectrum of the corresponding text of the nurse with high medical ethics. The two types of spectra are intensity normalized and the peak positions are shifted so that the frequency positions of the corresponding peaks coincide.

[0036] like Figure 4 As shown, the two types of spectrum examples of the corresponding text. The A peak to be measured is shifted to the left and coincides with the peak position of the corresponding high intimacy nurse, and the intimacy similarity between the two is compared. The higher the intimacy similarity, the higher the intimacy. The intimacy similarity is calculated as follows: S6-1 presets the frequency interval so that a peak is taken at Figure 4 The middle is the two points at half height (indicated by numbers 1 and 2 in the figure, and the points for other peaks are taken in the same way). Find multiple points for each of the two types of spectrum peaks whose frequency positions overlap; S6-2 calculates multiple spectra corresponding to multiple high-intimacy nurses ( Figure 4 For each point on the spectrum (including point A, point 1 and point 2 at half height, and other peaks such as point B and half height of peak B), the volume db and the frequency derivative are clustered in the constructed frequency-volume-frequency derivative three-dimensional space; S6-3 embeds the multiple points corresponding to the nurse to be tested in the three-dimensional space, and calculates the Mahalanobis distance with each cluster at each frequency. Figure 5 As shown, multiple spectra of high intimacy nurse I and high intimacy nurse II in frequency-volume and frequency derivative three-dimensional space are Figure 4 Taking the derivatives and volume decibels of three points (i.e., the peak and two points at half-height) at the coincident frequency position corresponding to peaks A and B as an example, we clustered them on two-dimensional planes α and β. The points corresponding to the coincident positions of the nurses under test were embedded in the planes, and the Mahalanobis distances of the clusters with nurses I and II were calculated on planes α and β, respectively. Mahalanobis distances were calculated similarly for planes at other frequency positions.

[0037] S6-4 obtains the average value of the minimum Mahalanobis distance at each frequency, that is, selects the average value of the Mahalanobis distance of the nurse with the highest intimacy who is closest to the nurse to be treated. When the average value of the minimum Mahalanobis distance is less than 1, it indicates high intimacy, between 1-3, moderate intimacy, greater than 3 but less than 5, average intimacy, and greater than or equal to 5, indifference. The medical ethics and medical style of specialist nurses are evaluated within the set evaluation period based on the evaluation level corresponding to each evaluation item. Specifically, the following are obtained: the number of words in the letter of praise N1, the number of banners N2, the number of complaints N3, the number of words N4, and the patient satisfaction N5, as well as the average value N6 of the Mahalanobis distance corresponding to the intimacy predicted by the model based on the audio and language model. The total score is calculated as S=0.03N1+0.02N2-0.3N3-0.1N4+0.05N5+0.5N6, and the candidates are ranked according to the total score. The top 60% are qualified and the rest are unqualified.

[0038] In an optional embodiment of the present invention, data can be sorted before generating statistical graphs or statistical tables, that is, the data can be classified and sorted according to four levels: individual, department, major department, and whole hospital. For each level, calculate the statistical indicators of satisfaction, such as the average value, maximum value, and minimum value. Arrange the data in chronological order (monthly or annually) for subsequent trend analysis. Make a detailed statistical table, listing the satisfaction data of each level at different time points, including the average value, maximum value, minimum value, etc. Compare the satisfaction of different individuals, departments, major departments, and the whole hospital at a specific time point through a bar chart, and intuitively show the differences between the levels. Show the trend of changes in satisfaction of each level over time through a line chart, which helps analyze the fluctuations and long-term changes in satisfaction. Show the distribution of a large amount of data through a heat map, such as the heat map of satisfaction of all departments in the hospital in different months, which can intuitively show which departments have higher or lower satisfaction in which time periods, etc.

[0039] 3. Evaluation and Priority Module In an optional embodiment of the present invention, the evaluation module includes three units: a list generation unit, a vote collection unit, and an evaluation generation unit.

[0040] The list generation unit obtains the evaluation and selection documents, automatically generates evaluation keywords, and automatically generates the selection list and the number of selected personnel based on the evaluation keywords. Optionally, the head nurse can also add or subtract appropriate evaluation terms based on the ward situation. After the final version of the selection terms is generated, the system automatically generates the list and the number of selected personnel.

[0041] The vote collection unit creates a voting questionnaire based on the selected list and the number of selected candidates generated by the list generation unit, and collects voting data from each voter. Specifically, the generated list and the number of selected candidates are automatically imported into the voting system. The generated questionnaire is sent to each individual via text message. After the individual selects a candidate, the questionnaire is fed back to the system. The head nurse reviews the final list.

[0042] The evaluation generation unit generates a list of references for evaluation based on the voting data. Individuals can see the results of the evaluation publicly. After 24 hours, the list is submitted to the higher authorities for further evaluation. Finally, the Nursing Department issues a document indicating the final selection results.

[0043] 4. Work Quality Module The work quality module is mainly used to manage the quality and quantity of work. Specifically, it is divided into two parts: workload management unit and nursing quality control unit.

[0044] The workload management unit manages the workload information of specialist nurses, calculates workload schedules based on different nursing operations, and assesses workload levels. Workload is categorized into routine clinical workload, specialist clinical workload, and specialist nursing assistance workload.

[0045] Clinical Routine Workload Statistics Process (data is obtained by scanning PDAs in the mobile nurse work system): Routine Workload Item Setting: Select nursing procedures related to the specialty, such as intravenous infusions and injections. Set routine workload targets based on the specialist nurse's appointment level: C1 ≥ 60%, C2 ≥ 50%, C3 ≥ 40%, and C4 ≥ 30%. Routine Workload Progress: Calculation Method: Annual Routine Workload (%) = Total Routine Workload per Responsible Nurse ÷ (Total Routine Workload for All Wards ÷ Total Number of Responsible Nurse) × 100%. Estimate: Using the previous year's data as the denominator, the system automatically calculates an individual's annual routine workload progress chart. Routine Workload Grading: The Nursing Department assigns a monthly routine workload score based on the duration and difficulty of each procedure. Each score multiplied by the number of procedures is the total monthly routine workload score for each nurse. The system categorizes nurses across the hospital into grades based on their overall scores: D (lowest level), C (mid-level), B (higher level), and A (highest level).

[0046] Clinical Specialty Workload Statistics Process (data is obtained by scanning PDAs in the mobile nurse work system): Specialty Workload (operations that require a qualification certificate) Entries: Select nursing procedures related to the specialty, such as diabetic foot dressing changes and PICC maintenance. The Nursing Department sets specialty workload targets based on the specialist nurse's appointment level: C1 ≥ 30%, C2 ≥ 40%, C3 ≥ 50%, and C4 ≥ 60%. Specialty Workload Progress: Calculation Method: Annual Specialty Workload (%) = Total Specialty Workload per Specialty Nurse ÷ (Total Specialty Workload for All Wards ÷ Total Number of Specialty Nurses) × 100%. Estimate: Using the previous year's data as the denominator, the system automatically calculates the individual's annual specialty workload progress chart.

[0047] Specialist Workload Rating: The Nursing Department assigns a monthly specialist workload score based on the duration and difficulty of each task. Each task's score multiplied by the number of tasks represents each nurse's total monthly specialist workload score. The system categorizes the scores of all nurses in the hospital into grades: D (lowest level), C (mid-level), B (high-level), and A (highest level). Specialist Nursing Assistance Workload Process: Specialist Projects (C2-C4 personnel are eligible for this qualification): Preparation of specialist health education prescriptions, case management, and specialty projects is primarily performed through individual system entry: hosting and participating. Levels are recorded, such as national, provincial, municipal, university / hospital / nursing department commendations or exchanges. Lectures at specialist lecture halls, community seminars, or hospital training sessions are also eligible for C2-C4 personnel.

[0048] 1) Notifications are published to the personal system at different levels. The system notifies the individual via SMS, and the individual uploads photos after completion.

[0049] 2) The system is divided into four tiers based on quantity: D (lowest), C (middle), B (high), and A (highest). Specialist nursing (remote consultation) C3 and C4 personnel are eligible. Connect to the nursing consultation system and import data. The system is divided into four tiers based on quantity: D (lowest), C (middle), B (high), and A (highest). Workload statistics {monthly / yearly}: Regular workload: quantity, monthly grade, and workload completion rate (yearly); Specialist workload: quantity, monthly grade, and workload completion rate (yearly); Specialist nursing assistance workload: number of consultations, grade, and number of specialist projects (and effectiveness) (monthly / yearly); number and grade of lectures in specialist classrooms, community lectures, or hospital training programs (monthly / yearly). The system sends this data to individuals via text message at the beginning of the next month.

[0050] The nursing quality control unit integrates with the nursing quality control PAD system to implement quality control and assign scores to different levels of quality control. The nursing quality control process consists of two parts: setting up quality control deductions and quality control statistics. Quality control personnel at all levels use a dedicated nursing quality control PAD system (quality control items vary between hospitals) to conduct quality control. This system integrates with the nursing quality control PAD system. Quality control personnel are assigned specific responsibilities during the nursing quality control system analysis, and this system connects to this system to export data. The nursing department assigns scores to different levels of quality control. For example, level 1 quality control is ward quality control, level 2 quality control is within the department, and level 3 quality control is at the nursing department or hospital level. Quality control issues are attributed to individual nurses and the number of times they occur. The system automatically counts the number of level 1 quality control deductions for the ward and categorizes them into four levels: A (least frequent), B (medium frequent), C (highest frequent), and D (highest frequent). Scoring is then applied to each level. Specifically, the following applies: Level 1 quality control: D: -1.5, C: -1, B: -0.5, A: 0; Level 2 quality control: D: -2.5, C: -1.5, B: -1, A: 0; Level 3 quality control: D: -2.5, C: -1.5, B: -1, A: 0. For principle violations (e.g., failure to strengthen verification after verification of an adverse event is verified to be related to personal behavior), a 5-point deduction will be applied regardless of the level. Quality control statistics are divided into level 1, 2, and 3 quality control grading and quality control summary statistics. Level 1, 2, and 3 quality control grading method: The system extracts the number of level 1, 2, and 3 quality control units, and categorizes the grading into four levels: D (lowest level), C (middle level), B (highest level), and A (highest level). Quality control summary statistics: Quality control statistics can be viewed in layers, accompanied by graphs or tables, and the data can be exported. The system sends the data to individuals via text message at the beginning of the next month.

[0051] 5. Training and Assessment Module The training and assessment module is a stratified specialist nurse training and assessment module, which includes: a stratified specialist nurse goal setting unit, a stratified specialist nurse competition unit, a stratified specialist nurse training plan unit, and a credit and grade statistics unit.

[0052] Tiered Specialist Nurse Training Target Setting Unit: Target credits are set and intelligently adjusted based on analysis of the previous year's year-end performance data (the following Category I and II credits are set according to the national continuing education credit level, and Category III credits refer to in-hospital training): C4: Class I ≥10 points, Class II ≥6 points, Class III ≥9 points; C3: Class I ≥8 points, Class II ≥4 points, Class III ≥13 points; C2: Class I ≥5 points, Class II ≥2 points, Class III ≥18 points; C1: Class I ≥5 points, Class II ≥0 points, Class III ≥20 points.

[0053] Credits: The total number of learning sessions for the entire year is 31 (including online sessions), including 15 in the Nursing Department, 4 in general departments, and 12 in specialist departments or wards. C4: Lectures or presided over professional learning sessions / ward rounds ≥ 2 times (2 points will be deducted for each missed session); Participation in various professional ward rounds and learning sessions ≥ 9 times; C3: Lectures or presided over professional learning sessions / ward rounds ≥ 1 time (2 points will be deducted for each missed session); Participation in professional ward rounds and learning sessions ≥ 13 times; C2: Participation in professional ward rounds and learning sessions ≥ 18 times; C1: Participation in professional ward rounds and learning sessions ≥ 20 times.

[0054] Hiring units for tiered specialist nurses (specific requirements for recruitment are determined by each hospital): Recruitment is held once every three years. The Nursing Department publishes recruitment information, and individuals submit their applications. The Nursing Department announces the interview personnel, time, location, and PPT preparation requirements. The list of candidates will be finalized 24 hours after the review results are announced and will be notified to individuals via SMS. Requirements for each tier: C0: Preparatory specialist nurses: N2 level, published one article within three years, annual performance score ≥ xx points (the system is divided into different levels according to the lowest and highest performance scores of nurses who meet the standards in the hospital); C1: Junior specialist nurse: Possess a specialist nurse certificate (national, Chinese, provincial, municipal, or hospital level), publish one Category F article within three years; annual performance score of xx to xx points; C2: Intermediate Specialist Nurse: Possess a Specialist Nurse Certificate (national, Chinese, provincial, municipal, or hospital level), publish one Category E article within three years, obtain one patent (invention, utility model, software copyright, or design patent) within three years, and have an annual performance score of xx to xx points. C3: Senior Specialist Nurse: Possess a Specialist Nurse Certificate (national, Chinese, provincial, or municipal), publish one Category D article within three years; obtain one research project (municipal or hospital level) within three years; annual performance score of xx to xx points; C4: Nursing Expert: Possess a specialist nurse certificate (national or Chinese level), publish one SCI article within three years; obtain one research project (national, Chinese or provincial level) within three years; ≥xx points.

[0055] Tiered Specialist Nurse Training Plan Unit (intelligently adjusted based on analysis of previous year-end performance data): Departmental Education Supervisors develop tiered specialist nurse training plans; Head Instructors of major departments develop tiered specialist nurse training plans for major departments; and the Nursing Department Training Department develops tiered specialist nurse training plans. Training plans at different levels are imported and integrated with hospital training software such as the Jingyi 512 system. Training notifications are issued by the Jingyi 512 system, and after a training session or lecture, participants sign in by scanning a QR code using the Jingyi 512 system. Data is directly sent to in-hospital training statistics.

[0056] The Credit and Grade Statistics unit manages hospital-level training and continuing education programs and compiles corresponding training results, including theoretical assessment scores and specialized skills assessment scores. Credit Statistics: Hospital-level training statistics (Category III credits) display the number and content of credits after data import. Continuing education training statistics (Category I and II credits): Continuing education programs and links are regularly sent according to training requirements, allowing students to register and pay through the links. After completing a training session, take a screenshot of the medical education management system and upload the image. The system will then identify the credits and display the statistics.

[0057] Training assessment results statistics: This system integrates with hospital training software, such as the Jingyi 512 system. Each assessment result from the Jingyi 512 system is imported into this system, divided into theoretical assessment and specialized skill assessment. The averaged data represents the year-end theoretical and specialized skill assessment results. Those who are unable to take the exam due to special reasons and have the nursing department's approval must confirm their absence; otherwise, the system defaults to a score of 0. All data systems will send the data to individuals via text message at the beginning of the next month.

[0058] The employment conditions for specialist nurses, the conditions for applying for professional titles and the details of various training mentioned in the embodiments of the present invention may be adjusted according to the conditions of local medical institutions.

[0059] 6. Performance Module The performance module includes monthly performance rating unit, manual annual evaluation unit, peer evaluation unit, annual performance rating unit, bonus data unit and annual performance analysis unit.

[0060] The monthly performance rating unit is used to implement the monthly performance rating of specialist nurses, as shown in the following table.

[0061]

[0062]

[0063]

[0064] In an optional embodiment of the present invention, monthly performance evaluation may be conducted according to the following rule: total performance score = basic score + workload score + quality score + additional score.

[0065] Basic points include: Professional title: points are awarded based on professional title level. Seniority: points are awarded based on years of service. Job discipline: points are awarded based on different disciplinary items. Specialist nurse level: points are awarded based on specialist nurse level.

[0066] Workload scores include: Night shift workload: count the number of night shifts. Total number of patients nursed: score is given based on the total number of patients nursed. Routine workload: score is given based on the quantity and quality of routine work completed. Total number of critically ill patients nursed: score is given based on the level of the number of critically ill patients nursed. Specialist workload: score is given based on the level of specialist work completed. Remote consultation volume: score is given based on the level of the number of consultations participated in. Ward quality control officer work: score is given based on the level of the ward quality control officer. Monthly basic bonus: the monthly basic bonus is used as the base, and a certain ratio is set to convert it into a score.

[0067] The quality score includes: satisfaction and nursing quality control. Different satisfaction levels and different nursing quality control levels correspond to different scores.

[0068] Additional points will be awarded based on the specific content of the additional points, such as commendations, papers, nurses aged 50 or above who continue to work night shifts and reach a certain number, etc. The system will automatically extract data for evaluation.

[0069] The manual annual evaluation unit manages the evaluation results of the head nurses of the wards to which the specialist nurses are assigned. The manual annual evaluation can be conducted by the head nurses of the wards themselves. The evaluation criteria are: 1) Adherence to medical ethics standards and relevant medical ethics regulations, and implementation of the "Nursing Regulations." Compliance with national laws and regulations, as well as hospital and nursing department rules and regulations: Excellent (1 point), Good (0.5 point), Poor (0 point); 2) Fulfillment of job responsibilities, implementation of core systems, relevant regulations, and requirements. Timely completion of nursing-related tasks at all levels: Good implementation (2.4 points), moderate implementation (1.8 points), average (1.2 points), basic implementation (0.6 points), and failure to implement (0 point). 3) Implementation of disease nursing routines: Completion of work: Good (1 point), Average (0.5 point), Poor (0 point); 4) Implementation of core systems and nursing operating procedures, and proactive reporting of nursing adverse events: Good implementation (3 points), moderate implementation (1.5 points), Average (1 point), Poor (0.5 point), and False reporting or concealment of adverse events: 0 point. The above assessment results can be stored in the manual annual assessment unit.

[0070] The peer review unit automatically collects evaluation results from staff in the same ward. The system automatically sends them to other staff in the ward for peer review. The evaluation criteria are: 2 points for positive reviews, 1 point for average reviews, and 0 points for negative reviews. The system calculates the average score as the individual score.

[0071] Details of the annual performance rating system are shown in the table below.

[0072]

[0073]

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088]

[0089]

[0090]

[0091]

[0092]

[0093] For the bonus data unit, the system calculates the monthly bonus based on the monthly performance score by multiplying the number of points by the score. For example, this month's bonus for specialist nurses across the hospital is 250,000 yuan. There are 50 specialist nurses in the hospital, and the total number of points earned is 4,230. 250,000 ÷ 4,230 ≈ 59.10 yuan per point. If a specialist nurse earns 93 points, she will receive a monthly bonus of 93 points x 59.10 yuan per point = 5,496.3 yuan, and so on. The annual performance bonus is calculated by multiplying the number of points by the score x the attendance rate. For example, if a specialist nurse earns 78 points, the bonus is 102 yuan per point, and her attendance rate is 50%. The annual bonus for this specialist nurse is: 78 points x 102 yuan per point x 50% = 3,978 yuan.

[0094] The annual performance analysis unit includes hospital-wide, department-wide, and individual performance analyses. Specific analysis forms are categorized into workload, nursing quality, medical ethics, and training. The system analyzes acquired data and identifies individuals requiring key attention and training. A questionnaire survey is conducted based on a list of individuals who fall short of target performance in various metrics. This identifies areas with low teaching performance. The training department then conducts assessments of these instructors and sets appropriate training goals. Based on this data, the system intelligently analyzes specialty theory, specialty skills, teaching, scientific research, chronic disease management, laws, regulations, rules, and regulations, and team training, creating a training outline to inform the following year's training plan. See the table below for details.

[0095]

[0096]

[0097]

[0098] All data are notified to individuals via SMS. In addition to the above, the intelligent performance management system for specialist nurses in the embodiment of the present invention is also provided with a risk level module, a teaching module, a scientific research module, a continuing care module and a public health emergency dispatch module.

[0099] VII. Risk Level Module The risk level module includes risk level settings and risk level assessment results. Risk level setting: Different wards have varying workloads due to the types of diseases they encounter. A unified risk level assessment across wards facilitates fairer bonus allocations, with higher bonus amounts allocated to wards with heavier workloads. The Nursing Department assigns a unified score based on the number of critically ill patients, the number of nursing levels (e.g., 1 special-grade nurse, 10 first-grade nurses, 20 second-grade nurses, and 10 third-grade nurses), the number of surgeries, and the number of infusions performed, based on the duration and difficulty of each procedure. Individual hospitals can customize their scoring based on their specific circumstances. The system connects to the medical order system within the hospital's HIS system to automatically export order entries. The head nurse selects the department responsible for issuing orders based on the department's scope, such as ward xx, quality control room xx, or day clinic xx. The system categorizes AD levels based on the highest and lowest scores, ultimately intelligently determining the final level. The Nursing Department has the authority to set an update frequency, such as three months (assessment results from January to March are applied to April to June). Risk level assessment results: (the hospital sets the specific amount based on its own income): Level D: Low risk: monthly basic bonus, night shift pay / lowest level; Level C: Medium risk: monthly basic bonus, night shift pay / mid-level; Level B: High risk: monthly basic bonus, night shift pay / high level; Level A: Extremely high risk: monthly basic bonus, night shift pay / highest level.

[0100] 8. Teaching Module The teaching module is used to manage basic teaching information, teaching score settings and teaching workload statistics.

[0101] Basic teaching information, including personal information and teaching qualifications. The system automatically generates: name, age, and work number; classroom teaching qualification certificate input: name, acquisition date, and upload certificate image; clinical teaching qualification input: name, acquisition date, and upload certificate image; thesis advisor qualification input: name, acquisition date, and upload certificate image. The system will display the information after waiting for confirmation from the Nursing Department and Training Department. Teaching score settings: different teaching hours are set according to different teaching categories and teaching numbers. Specific information can be imported through the Nursing Department and Training Department.

[0102] 1) Applicants with departmental classroom teaching: Undergraduate and graduate classroom teaching: 1.5 points for 10 or more hours, 1.25 points for 8-9 hours, 1 point for 6-7 hours, 0.75 points for 4-5 hours, 0.5 points for 2-3 hours, and 0.25 points for 1 hour; 2) Applicants with nursing departments and specialized teaching: Applicants who teach nursing training departments and undergraduate and specialized professional lectures (including in-service, continuing education, internship, and specialized base students): 1.5 points for 10 or more hours, 1.25 points for 8-9 hours, 1 point for 6-7 hours, 0.75 points for 4-5 hours, 0.5 points for 2-3 hours, and 0.25 points for 1 hour; Those with clinical teaching: 3) Undertaking clinical teaching: 1.5 points for teaching ≥10 people, 1.25 points for 8-9 people, 1.0 points for 6-7 people, 0.75 points for 4-5 people, 0.5 points for 2-3 people, and 0.25 points for 1 person; 4) Being hired as a thesis advisor for undergraduate students of a designated medical school is awarded 1.5 points; being a full-time advisor for other interns is awarded 1 point; For departments without clinical teaching: 0.5 points for those who have been engaged in nursing work for ≥5 years and have participated in clinical teacher training courses and passed the assessment; 5) Teaching continuing education: Presiding over continuing education projects: 2 points at the national level and 1 point at the provincial level.

[0103] Teaching workload statistics include undergraduate or graduate classroom teaching workload, nursing department and specialist teaching workload, and clinical teaching workload. Undergraduate or graduate classroom teaching workload: The hospital teaching department is connected to this system to import classroom teaching workload: class time, location, content, etc., and also import teaching accidents and the number of students with negative reviews. Nursing department and specialist teaching workload: The nursing department training department is connected to this system to import teaching workload: class time, location, content, etc., and also import teaching accidents and the number of students with negative reviews. Specialist teaching supervisors enter teaching workload in this system: class time, location, content, etc., and also enter teaching accidents and the number of students with negative reviews.

[0104] Clinical Teaching Workload: Ward supervisors enter their teaching workload into the system, including student name, school, and number of weeks of teaching. They also record teaching incidents and the number of negative student reviews. Once the system receives this information, a text message will be sent to the individual within 2 hours. Continuing Education Teaching Workload: Individuals enter the meeting name, number, and level (select using the drop-down list), and upload a photo of the meeting letter. Wait for confirmation from the Nursing Department and Training Department before the information is displayed.

[0105] IX. Scientific Research Module The research module manages projects, patents, papers, guidelines / consensus / group standards, books, and research summary workload. Projects: Individuals enter the project name, project number, approval date, name of the lead researcher, names and levels of participating researchers, and submit project approval documents and project rankings. Patents: Individuals enter the patent number, name, approval date, and upload the patent certificate. Papers: Individuals enter the paper title, journal, impact factor, word count, and time of publication, and upload the cover, table of contents, full text, and back cover. Guidelines / consensus / group standards: Individuals enter the guideline / consensus / group standard title and time of publication, and upload supporting documentation. Books: Individuals enter the book title, publisher, word count, and time of publication, and upload the cover, table of contents, and back cover. All of the above require approval by the relevant intelligent components before they can be displayed in the research summary workload, and the data is automatically imported into the performance report.

[0106] 10. Continuing Care Module The continuing care module is used to manage online consultations, home care, telephone follow-up, health knowledge lectures, volunteer nursing services, health education manuscript submissions and continuing care summary workload.

[0107] Online Consultation (referring to the hospital app): This online consultation (referring to the hospital app) is available to C3 and C4 personnel. This service automatically exports data through the hospital app. The system categorizes the consultation into four levels: D (lowest level), C (middle level), B (higher level), and A (highest level). Home Care: For home care, the user enters the content, time, and name of the person performing the consultation. Screenshots and images can be uploaded to the Nurse's Appointment app. Telephone Follow-up: This service automatically exports data through the hospital's nursing management follow-up system. The system categorizes the consultation into four levels: D (lowest level), C (middle level), B (higher level), and A (highest level). Health Lecture: The nursing department enters the topic, participants, time, and location of the health lecture. The nurse takes a photo and uploads it after the lecture. The nurse awaits the nursing department's confirmation and evaluation of the results. The head nurse enters the topic, participants, time, and location of the ward's health lecture. The nurse takes a photo and uploads it after the lecture. The head nurse awaits the head nurse's confirmation and evaluation of the results. Volunteer Nursing: The user enters the content, time, and name of the person performing the consultation. Screenshots and images can be uploaded to the Nurse's Appointment app. Health education manuscript submission: Personal input: Content, time, person name, etc., and upload images from the hospital app. Continuing care workload summary: Displays the number and level of online consultations; the number of home care; the number and level of telephone follow-up visits; the number, level, and effectiveness of health knowledge lectures; the number of volunteer nursing services; and the number of health education manuscripts accepted.

[0108] 11. Public Health Emergency Dispatch Module The public health emergency dispatch module includes in-hospital work support and out-of-hospital work support. The in-hospital work support is completed by the head nurse entering the personnel list and the system to record attendance. The relevant workload is the average workload of the ward and personal data is entered; the out-of-hospital work support is completed by the nursing department entering the personnel list and the system to record attendance. The relevant workload can be the average workload of the entire hospital. The intelligent performance management system for specialist nurses in the embodiment of the present invention is connected to the hospital HIS system, the nursing quality control system (quality control section, consultation section, telephone follow-up section and satisfaction section), the face recognition clocking system and the hospital APP system (online consultation), and the nursing department quality control APP system (various nursing quality controls and satisfaction).

[0109] The intelligent performance management system for specialist nurses in this embodiment of the present invention has the following beneficial effects: 1) The performance system provides comprehensive, fair, and impartial assessments; 2) The performance system provides transparent assessments; 3) The performance system displays the progress of work completed; 4) The performance system facilitates the development of appropriate training plans; 5) The performance system helps focus on the training of key personnel; and 6) The performance system helps specialist nurses plan their careers.

[0110] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent performance management system for specialist nurses, characterized by: include: The human resources module is used to manage basic information, match the human resources of each ward bed with the medical staff in charge, evaluate quality control project management, schedule work, and calculate the workload of nursing patients and quality control staff; The medical ethics and medical style module is used to manage the medical ethics and medical style evaluation information of specialist nurses; the evaluation information includes letters of praise, banners, complaints, patient satisfaction information, and multiple evaluation items of the intimacy index predicted by the audio and language model; the medical ethics and medical style of specialist nurses are evaluated within a set evaluation period based on the evaluation level corresponding to each evaluation item; The evaluation module is used to evaluate the excellence of specialist nurses; Work quality module, used to manage the workload information of specialist nurses and nursing quality control information; Training and assessment module, used to manage the training and assessment information of specialist nurses; The performance module is used to manage the performance rating information of specialist nurses. The method for obtaining the intimacy index predicted by the model based on the audio and language model includes the following steps: S1 nurses should wear the audio collector before working; S2 collects audio at the work site during the preset data collection cycle, and the nurse collects voice alone in the room during the cycle; S3 uses the collected speech as a training set to train a nurse speech recognition model for different nurse voices. It then inputs the worksite audio into the trained nurse speech recognition model to retrieve the spectrum of the corresponding nurse's speech. S4 builds a natural speech recognition model, trained using the spectrum of the nurse's voice to identify the corresponding text in the audio; S5 selects multiple highly friendly nurses to collect audio from their work scenes, inputs the trained nurse speech recognition model to retrieve the spectrum of their speech, and then inputs the spectrum into the trained natural speech recognition model to recognize the corresponding text; S6 obtains the on-site audio of the nurse to be tested, and similarly identifies the corresponding text according to S5. The spectrum corresponding to each different text is compared with the spectrum of the corresponding text of the nurse with high medical ethics. The two types of spectra are intensity normalized and the peak positions are shifted so that the frequency positions of the corresponding peaks coincide. The intimacy similarity between the two is compared. The higher the intimacy similarity, the higher the intimacy. The medical ethics and medical style of specialist nurses are evaluated within the set evaluation period according to the evaluation level corresponding to each evaluation item, including: the number of words in the letter of praise N1, the number of banners N2, the number of complaints N3, the number of words N4, and the patient satisfaction N5, as well as the average value N6 of the Mahalanobis distance corresponding to the intimacy predicted by the model based on audio and language models. Calculate the total score S = aN1+bN2-cN3-dN4+eN5+fN6, a+b+c+d+e+f=1, and f>c>d>e>a>b. Sort by the total score. The top 60% pass and the rest fail.

2. The system according to claim 1, wherein: The intimacy similarity is calculated as follows: S6-1 presets the frequency interval and finds multiple points of two types of spectrum peaks with overlapping frequency positions; S6-2 calculates the volume db and the frequency derivative at each point on multiple spectra corresponding to multiple nurses with high intimacy, and performs clustering in the constructed frequency-volume-frequency derivative three-dimensional space; S6-3 embeds the multiple points corresponding to the nurse to be tested in a three-dimensional space, and calculates the Mahalanobis distance with each cluster at each frequency; S6-4 obtains the average value of the minimum Mahalanobis distance at each frequency. When the average value of the minimum Mahalanobis distance is less than 1, it indicates a high degree of intimacy; between 1 and 3, it indicates a moderate degree of intimacy; greater than 3 but less than 5, it indicates a normal degree of intimacy; and greater than or equal to 5, it indicates a cold degree of intimacy. The evaluation module includes: A list generation unit is used to obtain evaluation documents and automatically generate evaluation keywords, and automatically generate the selection list and the number of selections based on the evaluation keywords; A voting collection unit is used to create a voting questionnaire based on the selection list and the number of selections generated by the list generation unit, and collect voting data fed back by each voter; The evaluation generation unit generates a reference list for evaluation based on the voting data.

3. The system according to claim 1, wherein: The work quality module includes a workload management unit and a nursing quality control unit; The workload management unit is used to manage the workload information of specialist nurses, calculate the workload schedule based on different nursing operations, and perform workload level assessment; the workload information includes clinical routine workload, clinical specialist workload, and specialist nursing assistance workload; The nursing quality control unit is connected to the nursing quality control PAD system to achieve quality control and assign scores to different levels of quality control.

4. The system according to claim 1, wherein: The training and assessment modules include: A unit for setting the target for stratified specialist nurses, which sets target credits corresponding to specialist nurses at different levels; The tiered specialist nurse competition unit is used to manage the application requirements for specialist nurses at all levels; The hierarchical specialist nurse training plan unit is used to import specialist nurse training plans at different levels, connect to the hospital training software to send training notifications, and manage the training process; The credit and grade statistics unit is used to manage college-level training and continuing education training programs, and to compile statistics on the corresponding training results, including theoretical assessment results and professional skills assessment results.

5. The system according to claim 1, wherein: The performance module includes: Monthly performance rating unit, used to implement monthly performance ratings for specialist nurses; The manual annual evaluation unit manages the evaluation results of the head nurses of the wards to which the specialist nurses belong; Peer evaluation unit, which automatically collects evaluation results from staff in the same ward; Annual performance rating unit, used to implement the year-end performance rating of specialist nurses; Bonus data unit, automatically calculates monthly performance bonus based on monthly performance score; calculates annual performance bonus based on full attendance rate and number of operations; The annual performance analysis unit is used to conduct performance analysis of the entire hospital, major departments and individuals, and obtain workload, nursing quality, medical ethics and training analysis forms.

6. The system according to any one of claims 1 to 5, characterized in that The system also includes a risk level module, which includes risk level setting and risk level assessment; Develop project scoring and grading settings based on operation time and difficulty, including four levels: A, B, C, and D; Level D, low risk: monthly basic bonus, night shift pay / lowest level; Level C, medium risk: monthly basic bonus, night shift pay / mid-range; Level B, high risk: monthly basic bonus, night shift pay / high-level; Level A, extremely high risk: monthly basic bonus, night shift pay / highest level.

7. The system according to any one of claims 1 to 5, characterized in that The system also includes a teaching module for managing basic teaching information, teaching score settings and teaching workload statistics; Basic teaching information includes personal basic information and teaching qualification information; When setting teaching points, different teaching hours should be set according to different teaching categories and teaching numbers; Teaching workload statistics include undergraduate or graduate classroom teaching workload, nursing department and specialty teaching workload, and clinical teaching workload.

8. The system according to any one of claims 1 to 5, characterized in that The system also includes a scientific research module for managing projects, patents, papers, guidelines / consensus / group standards, books and scientific research summary workload.

9. The system according to any one of claims 1 to 5, characterized in that The system also includes a continuing care module for managing online consultations, home care, telephone follow-up, health knowledge lectures, volunteer nursing services, health education manuscript submissions and continuing care summary workload.

10. The system according to any one of claims 1 to 5, characterized in that The system also includes a public health emergency dispatch module, including in-hospital work support and out-of-hospital work support.

Images