Intelligent scheduling and duty system that integrates personnel health dimensions
By identifying and analyzing the health data of on-duty personnel to generate a rating, and combining personnel information and real-time physiological monitoring, the problem of the lack of health dimensions in the existing scheduling system has been solved, thus achieving health and safety assurance and efficient emergency deployment.
Patent Information
- Application Number
- CN202611145042.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-30
- Publication Date
- 2026-11-10
AI Technical Summary
The existing scheduling system fails to effectively incorporate the health of employees into decision-making, leading to forced work in high-intensity positions and causing health and safety incidents.
By identifying and analyzing the structured and unstructured health data of on-duty personnel, a health level is generated. Combined with personnel information and preset verification strategies, personnel are assigned to appropriate reserve groups, and physiological signs are monitored in real time to determine replacement personnel.
It enables precise quantitative assessment of physical condition, ensures the health and safety of personnel, avoids labor disputes and secondary injuries, improves emergency deployment efficiency, and ensures the smooth operation of duty work.
Smart Images

Figure CN123070536A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to data processing technology, and more particularly to an intelligent scheduling method and system that integrates the dimension of human physical health. Background Technology
[0002] As various industries increasingly demand standardized duty roster management, scenarios such as government duty, park operation and maintenance, security duty, engineering inspection, property management shifts, and frontline employee scheduling all require periodic and systematic scheduling management. A scientific and reasonable scheduling plan not only needs to ensure that personnel are in place and operating normally during duty hours for all types of positions, but also needs to take into account the rational allocation of human resources and work efficiency.
[0003] However, in the actual scheduling process, the physical health of the on-duty personnel directly affects their ability to perform the on-duty work at a specific time or intensity. Especially for high-intensity positions such as night shifts, all-night shifts, and high-temperature inspections, if personnel are forced to work when they are not in good physical condition, it is very easy to cause health and safety accidents.
[0004] Therefore, how to incorporate the physical health of personnel into the core considerations of scheduling decisions has become an important technical problem that urgently needs to be solved in this field. Summary of the Invention
[0005] Based on the above problems, this invention is proposed to provide an intelligent scheduling and duty system that integrates the dimension of personnel physical health to overcome or at least partially solve the above problems.
[0006] According to one aspect of the present invention, an intelligent shift scheduling method integrating personnel health dimensions is provided, comprising the following steps: Data identification and parsing are performed on the structured and unstructured health data corresponding to the same on-duty personnel to determine the health level of the corresponding on-duty personnel; Based on the personnel information corresponding to the duty personnel, the duty positions corresponding to the duty personnel are determined, and each duty personnel whose corresponding health level is not lower than the duty position level and whose difference between the health level and the duty position level is within the preset tolerance are assigned to the reserve group corresponding to the same duty position. Based on the preset verification strategy, the on-duty personnel in different reserve groups are verified, and the personnel are scheduled for each suitable personnel. The personnel status is determined based on the physiological characteristics data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
[0007] Optionally, in the method according to the present invention, data identification and data parsing are performed on each structured health data and each unstructured health data corresponding to the same on-duty personnel to determine the health level corresponding to the on-duty personnel, including: Retrieve a preset information type table, which includes various information types and corresponding benchmark words for different information types; Semantic recognition is performed on each structured health data corresponding to the same on-duty personnel. If any text word in each structured health data is the same as any benchmark word included in the preset information type table, the information type corresponding to the benchmark word is determined as the target type. Multi-source heterogeneous data analysis was performed on unstructured health data of the same on-duty personnel to obtain structured taboo labels and structured health scores; The health level of the on-duty personnel is determined based on the target type and structured health score.
[0008] Optionally, in the method according to the present invention, determining the health level of the on-duty personnel based on each target type and structured health score includes: A preset benchmark interval is determined for each target type, and the individual health deduction for each target type is determined based on the deviation between the target information corresponding to each target type determined by each structured health data and the preset benchmark interval. An initial health score is determined based on the individual health deductions, and the health level is determined based on the structured health score and the initial health score. Retrieve the preset taboo level mapping relationship, compare the structured taboo tags with the mapping relationship, and determine the upper limit of the level; The health level is updated based on the aforementioned upper limit.
[0009] Optionally, in the method according to the present invention, verification operations are performed on duty personnel located in different reserve groups based on a preset verification strategy, and personnel scheduling is carried out for each identified suitable personnel, including: The preset verification strategy includes hard verification of employment compliance, soft verification of personnel physical load, and verification of rules specific to special groups; Based on the aforementioned hard verification of employment compliance, soft verification of personnel physical load, and special rule verification for special groups, the on-duty personnel of the reserve group located at each on-duty post are verified to obtain each suitable personnel. Staffing schedules were arranged for the identified suitable personnel.
[0010] Optionally, in the method according to the invention, the method further includes: The verification data for the mandatory verification of employment compliance includes at least the daily working hours, number of consecutive shifts, rest time between shifts, and maximum overtime hours. The data threshold parameters of each verification data for the aforementioned hard verification of employment compliance are pushed and updated in real time. The soft test of personnel physical load includes the cumulative on-duty hours of the test cycle and the cumulative fatigue level; The special group-specific rule verification includes configuring differentiated flexible scheduling rules for elderly on-duty personnel, personnel recovering from injuries or illnesses, and pregnant and breastfeeding personnel. The flexible scheduling rules include prioritizing the allocation of easy shifts, shortening the on-duty hours, and reducing night shifts.
[0011] Optionally, in the method according to the invention, scheduling personnel for each identified suitable individual includes: Obtain job requirement data for each duty post, prioritize personnel health protection as the highest optimization goal, use meeting job requirement data and balanced manpower allocation as constraints, and use commuting distance, personal affairs arrangements and cross-post support capabilities as auxiliary conditions to generate a duty schedule. The duty roster is sent to the management terminal. When the management terminal sends a confirmation signal based on the duty roster, the duty roster is sent to each employee's terminal.
[0012] Optionally, in the method according to the invention, determining the personnel status based on the collected physiological characteristic data of the matched personnel corresponding to each on-duty attribute includes: Physiological data is acquired by monitoring equipment corresponding to each on-duty attribute of the matched personnel. The physiological data includes heart rate data, real-time fatigue index and continuous on-duty time data. When the heart rate data of any matched personnel exceeds the preset heart rate threshold, or the real-time fatigue index exceeds the preset fatigue threshold, or the continuous on-duty time exceeds the preset duration threshold, the personnel status of that matched personnel is determined to be an emergency state.
[0013] Optionally, in the method according to the present invention, if the personnel status of any of the adapted personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the adapted personnel, including: If the personnel status of any of the aforementioned personnel is determined to be an emergency state, based on the reserve group of the corresponding personnel, each personnel with the standby attribute corresponding to the maximum health level is identified as a target personnel, and the number of personnel corresponding to the target personnel is determined. If the number of personnel is 1, the target personnel will be designated as substitutes. If the number of personnel is greater than 1, determine the cumulative on-duty time of each target personnel, and identify the target personnel with the minimum cumulative on-duty time as substitute personnel.
[0014] Optionally, in the method according to the invention, the method further includes: Based on preset periodic statistics of staff on-duty hours, trends in staff health status, scheduling compliance rate, and post duty completion rate, a health duty analysis report is generated. The newly added data in the current period is stored, and the data correlation pattern between shift length, shift type and health level changes is determined based on multi-period data to generate optimization parameters; The optimization parameters include the mapping relationship between health level and job level, as well as the boundary value of the preset tolerance.
[0015] According to another aspect of the present invention, an intelligent scheduling and duty system integrating the dimension of personnel physical health is provided, comprising: The health level determination module is configured to identify and parse the structured and unstructured health data of the same on-duty personnel to determine the health level of the on-duty personnel. The job grouping module is configured to determine the duty position corresponding to the duty personnel based on the personnel information corresponding to the duty personnel, and to divide the duty personnel whose corresponding health level is not lower than the job level of the duty position and whose difference between the health level and the job level is within a preset tolerance into a reserve group corresponding to the same duty position. The personnel scheduling module is configured to perform verification operations on each on-duty personnel in different reserve groups based on a preset verification strategy, and to schedule personnel for each identified suitable personnel. The substitute determination module is configured to determine the personnel status based on the collected physiological characteristic data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
[0016] According to the present invention, by uniformly identifying and analyzing the multi-source heterogeneous health data of on-duty personnel, a health level is generated, achieving a precise quantitative assessment of physical condition. Furthermore, based on personnel information, on-duty positions are determined, and personnel with health levels not lower than the position level and whose differences are within a preset tolerance range are assigned to the same reserve group. This ensures that the scheduling scheme meets personnel constraints while guaranteeing the health and safety of personnel and sufficient scheduling resources. On this basis, through a preset verification strategy, while ensuring the compliance of the scheduling scheme, differentiated flexible scheduling rules can be configured for special groups, effectively avoiding labor conflicts and secondary injuries to personnel. At the same time, by collecting the physiological characteristics data of on-duty personnel in real time, and quickly determining replacement personnel based on the reserve group when the personnel status is determined to be in an emergency, the efficiency of emergency deployment in case of emergencies is improved, maximizing the protection of the health of on-duty personnel and the smooth operation of the duty. Attached Figure Description
[0017] Figure 1 A flowchart illustrating an intelligent shift scheduling method that integrates personnel health dimensions according to an embodiment of the present invention is shown. Figure 2 A schematic diagram of a preset information type table according to an embodiment of the present invention is shown; Figure 3 A structural block diagram of an intelligent scheduling and duty system that integrates the dimension of human physical health according to another embodiment of the present invention is shown. Detailed Implementation
[0018] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0019] To address the problems existing in the aforementioned background technology, the inventors have proposed the solution of this invention. One embodiment of this invention provides an intelligent shift scheduling method that integrates personnel health dimensions, and this method can be executed on a computing device.
[0020] Figure 1 A flowchart of an intelligent scheduling method for shift work that integrates the dimension of personnel physical health according to an embodiment of the present invention is shown, the method being adapted to be executed in a computing device.
[0021] like Figure 1 As shown, the intelligent shift scheduling method that integrates personnel health dimensions proposed in this embodiment begins with step S102, which includes the following: The structured and unstructured health data of the same on-duty personnel are identified and analyzed to determine the health level of the corresponding on-duty personnel.
[0022] For example, in this embodiment, the system first collects various health data of the on-duty personnel in a unified manner. Among them, structured health data refers to health-related information with a fixed data format that can be directly identified and processed. It usually exists in the form of numerical values, labels or standardized fields, and may include physical examination numerical indicators, heart rate time series signals and sleep duration records, etc. Unstructured health data refers to health information that does not have a fixed format and cannot be directly identified and quantified automatically. It requires parsing and structural conversion and can include free text medical records, physical examination PDF reports, and medical images, etc. The system identifies and analyzes various types of health data to determine the health level of the corresponding on-duty personnel.
[0023] Furthermore, the aforementioned "data identification and parsing of structured and unstructured health data corresponding to the same on-duty personnel to determine the health level of the corresponding on-duty personnel" also includes the following steps: Retrieve a preset information type table, which includes various information types and corresponding benchmark words for different information types; Semantic recognition is performed on each structured health data corresponding to the same on-duty personnel. If any text word in each structured health data is the same as any benchmark word included in the preset information type table, the information type corresponding to the benchmark word is determined as the target type. Multi-source heterogeneous data analysis was performed on unstructured health data of the same on-duty personnel to obtain structured taboo labels and structured health scores; The health level of the on-duty personnel is determined based on the target type and structured health score.
[0024] For example, in this embodiment, the system retrieves a preset information type table, which records various information types, such as systolic blood pressure, fasting blood glucose, and resting heart rate. It also includes baseline vocabulary corresponding to different information types. For instance, the baseline vocabulary for the information type "fasting blood glucose" includes fasting blood glucose and FBG. Figure 2 As shown; The system performs semantic recognition on structured health data. When the recognized text words match the benchmark words in the preset information type table, the system will first determine the information type corresponding to the benchmark words as the target type, so as to facilitate the subsequent determination of the health level of the on-duty personnel based on the determined target type. However, unstructured health data includes free text medical records, physical examination PDF reports, medical images, time-series physiological data, etc., and the data formats are different. Therefore, it can be uniformly encoded and fused by a multimodal health feature fusion model. The multimodal health feature fusion model has a built-in image encoder and a temporal convolutional network to uniformly encode multi-source heterogeneous data such as time-series physiological data, free text medical records, physical examination PDF reports, and medical images, and outputs a unified health constraint feature vector and maps it to a structured health score, realizing the automated parsing and quantitative evaluation of unstructured health data. For example, physical examination PDF reports and medical images are encoded into image feature vectors by image encoders, heart rate time-series signals output by smart wearable devices are encoded into time-series feature vectors by time-series convolutional networks, and free text of medical records is encoded into text semantic vectors by pre-trained language models. The aforementioned image feature vectors, temporal feature vectors, and text semantic vectors are aligned and fused through a cross-modal attention mechanism. For example, the attention mechanism establishes a correlation between "chest pain" in the text description and "signs of myocardial ischemia" in the image, and establishes a correlation between "abnormally high nocturnal heart rate" in the temporal signal and "history of insomnia" in the text, so as to output a unified health constraint feature vector and map it into a structured health score. The system will also perform semantic recognition on the free text of medical records to determine structured taboo labels, which can be understood as health constraint markers that restrict on-duty personnel from participating in specific types of on-duty positions; For example, in a free text medical record stating, "Patient Zhang, male, 52 years old, presented with chest tightness and shortness of breath. He has a 3-year history of coronary heart disease and underwent coronary artery stent implantation in June 2023. He takes medication regularly after the surgery and currently experiences occasional discomfort in the precordial region after exertion," the structured contraindication label is determined to be cardiovascular contraindication. Finally, the system will determine the health level of the corresponding on-duty personnel based on each target type and structured health score.
[0025] Furthermore, the aforementioned "determining the health level of the corresponding on-duty personnel based on each target type and structured health score" also includes the following steps: A preset benchmark interval is determined for each target type, and the individual health deduction for each target type is determined based on the deviation between the target information corresponding to each target type determined by each structured health data and the preset benchmark interval. An initial health score is determined based on the individual health deductions, and the health level is determined based on the structured health score and the initial health score. Retrieve the preset taboo level mapping relationship, compare the structured taboo tags with the mapping relationship, and determine the upper limit of the level; The health level is updated based on the aforementioned upper limit.
[0026] For example, in this embodiment, the system first determines the preset benchmark interval corresponding to each target type. For example, the benchmark interval for systolic blood pressure is [90, 140] mmHg, and the benchmark interval for fasting blood glucose is [3.9, 6.1] mmol / L. For each target type, the system determines the target information corresponding to each target type based on the structured health data, i.e. the actual measurement value, and then calculates the individual health deduction based on the deviation of the target information from the benchmark interval. Specifically, the difference between the target information and the median of the benchmark interval is calculated first. Then, the absolute value of the calculated result is divided by the half-width of the benchmark interval to obtain the deviation. The deviation is used to characterize the relative degree of deviation of the target information from the benchmark interval. The larger the deviation, the more serious the abnormality of the health indicator. Then, the system multiplies the calculated deviation by the influence weight corresponding to the target type to obtain the single health deduction for the target type. The influence weight can be preset according to the degree of influence of each health indicator on the personnel's duty ability. For health indicators that directly affect the safety of night duty or the ability to perform high-intensity work, such as cardiovascular indicators, their influence weight can be higher than that of other types of indicators, so that different health indicators with the same degree of deviation can reflect different constraints in the health level assessment. For example, if a staff member's measured systolic blood pressure is 155 mmHg, and the preset baseline range for systolic blood pressure is [90, 140] mmHg, then the midpoint of the range is 115 mmHg, the half-width of the range is 25 mmHg, and the deviation is |155| / 25 mmHg. 115 / 25=1.6. If the impact weight of abnormal systolic blood pressure is 2.0, then the single health deduction for this target type is 1.6×2.0=3.2 points. The system sums up all individual health deductions to obtain the total deduction score, and then calculates the difference between the preset total score and the total deduction score to obtain the initial health score. Next, the structured health score and the initial health score are weighted and summed to obtain the current score. The specific weights can be set according to the actual situation. This embodiment does not limit this. The number of health levels can also be determined based on actual needs. For example, the health level can be divided into five levels. Different health levels correspond to different current score intervals. Then, the health level is determined based on the current score interval in which the current score is located. Next, the system retrieves the preset contraindication level mapping relationship. Based on the preset contraindication level mapping relationship, it can determine the level upper limit corresponding to each structured contraindication label. For example, the level upper limit corresponding to the contraindication of coronary heart disease in the preset contraindication level mapping relationship is level 3. Then, the health level is updated according to the level upper limit. For example, if the determined health level is greater than the upper limit, the upper limit will be taken as the final health level; otherwise, the initial health level will be maintained so that staff with organic lesions or clear contraindications will not be assigned to high-intensity positions and will have a certain degree of adaptability.
[0027] Step S104 includes the following: Based on the personnel information corresponding to the duty personnel, the duty positions corresponding to the duty personnel are determined, and the duty personnel whose corresponding health level is not lower than the duty position level and whose difference between the health level and the duty position level is within the preset tolerance are assigned to the reserve group corresponding to the same duty position.
[0028] For example, in this embodiment, the system obtains the personnel information of the on-duty personnel, including job skills and qualifications, years of service, leave permissions, duty shifts that are prohibited due to physical conditions, and age and gender, etc. The system filters the set of positions that on-duty personnel can be competent for based on their job skills and qualifications. For example, a person holding a high-voltage electrician certificate can be competent for the power distribution room on-duty position but not for the fire control room position. Positions during leave are removed based on leave permissions. Positions that are prohibited from being on duty are blocked based on physical restrictions. For example, if there is a restriction on night shifts, all night shift positions are blocked. The job matching priority is adjusted based on years of service, age, and gender. The longer the years of service, the higher the priority for matching complex jobs. For example, when the age is over 55, the priority of high-intensity jobs is reduced and the priority of low-intensity jobs is increased. After the above screening and adjustment, the associated job of the on-duty personnel is determined. If the health level is divided into five levels according to physical endurance, with health level 5 representing the best level, then the job level is also divided into five levels according to the intensity of duty, with job level 5 representing the strongest intensity. Therefore, the health level of on-duty personnel cannot be lower than the job level. For example, on-duty personnel with a health level of 4 can be matched with job levels of 1-4 but cannot be matched with on-duty positions with a job level of 5. However, to avoid excessive restrictions that lead to insufficient scheduling resources, the system can be set with a preset tolerance, such as setting the preset tolerance to level 1. Therefore, the system will assign all on-duty personnel whose health level is not lower than the job level of the on-duty position and whose health level is within the preset tolerance to the reserve group corresponding to the same on-duty position. This can not only maximize the protection of the health and safety of on-duty personnel, but also avoid the situation of insufficient scheduling resources.
[0029] Step S106 includes the following: Based on the preset verification strategy, the on-duty personnel in different reserve groups are verified, and the selected suitable personnel are assigned shifts.
[0030] For example, in this embodiment, the system performs a preset verification strategy on each on-duty personnel in different reserve groups to determine the appropriate personnel to perform on-duty duties, and schedules the personnel for each appropriate personnel to further enhance the health and rationality on the basis of ensuring compliance with employment regulations.
[0031] Furthermore, the aforementioned "performing verification operations on on-duty personnel in different reserve groups based on a preset verification strategy, and scheduling personnel for each identified suitable personnel" also includes the following steps: The preset verification strategy includes hard verification of employment compliance, soft verification of personnel physical load, and verification of rules specific to special groups; The verification data for the mandatory verification of employment compliance includes at least the daily working hours, number of consecutive shifts, rest time between shifts, and maximum overtime hours. The data threshold parameters of each verification data for the aforementioned hard verification of employment compliance are pushed and updated in real time. The soft test of personnel physical load includes the cumulative on-duty hours of the test cycle and the cumulative fatigue level; The special group-specific rule verification includes configuring differentiated flexible scheduling rules for elderly on-duty personnel, personnel recovering from injuries or illnesses, and personnel who are pregnant or breastfeeding. The flexible scheduling rules include prioritizing the allocation of less strenuous shifts, shortening the on-duty hours, and reducing night shifts. Based on the aforementioned hard verification of employment compliance, soft verification of personnel physical load, and special rule verification for special groups, the on-duty personnel of the reserve group located at each on-duty post are verified to obtain each suitable personnel. Staffing schedules were arranged for the identified suitable personnel.
[0032] For example, in this embodiment, the preset verification strategy includes hard verification of employment compliance, soft verification of personnel physical burden, and verification of rules specific to special groups. The verification data for the hard verification of employment compliance includes at least the daily working hours, the number of consecutive shifts, the rest time between shifts, and the maximum overtime hours. The system will push and update the threshold parameters of each verification data for the hard verification of employment compliance in real time. For example, the data threshold parameters of each verification data on which the hard verification of employment compliance is based are pushed and updated in real time by the scheduling and health RAG knowledge base. The scheduling and health RAG knowledge base is divided into three independent vector bases: labor rules vector base, job intensity historical scheduling vector base, and personnel health and duty sequence correlation vector base. The system is configured to automatically capture the latest labor rule changes daily and store them in a quantitative database. During verification, the system employs a multi-path recall mechanism, which simultaneously retrieves the latest rules from the labor rule vector library and extracts compliance verification threshold parameters, such as the daily working hours threshold and the consecutive shift days threshold; retrieves historical shift data for similar positions from the historical shift scheduling vector library to assist in determining the level of job intensity; and retrieves historical health and shift correlation patterns for similar personnel from the personnel health and shift sequence correlation vector library to assist in calibrating the physical load threshold, thereby achieving real-time updates and dynamic calibration of the verification threshold parameters. When changes in labor rules lead to changes in thresholds, such as when revisions to labor rules reduce the maximum daily working hours from 8 hours to 7 hours, the system automatically uses the latest threshold parameters for verification without manual modification, thus offering a certain degree of accuracy and convenience. The soft test of personnel physical load is an assessment of the long-term physical endurance of on-duty personnel, including the cumulative on-duty hours of the test cycle and the cumulative fatigue level. If the cumulative on-duty hours of the on-duty personnel exceed the upper limit or the cumulative fatigue level exceeds the warning line, the on-duty personnel will be rescheduled and will not participate in the current cycle's scheduling. The special group-specific rule verification includes configuring differentiated flexible scheduling rules for elderly on-duty personnel, personnel recovering from injuries or illnesses, and personnel who are pregnant or breastfeeding. The flexible scheduling rules include prioritizing the allocation of less strenuous shifts, shortening the on-duty hours, and reducing night shifts. For example, when the on-duty personnel are 55 years of age or older, they are assigned to day shifts with a single shift not exceeding 4 hours and continuous shifts not exceeding 3 days; when the on-duty personnel are in the recovery period from injury or illness, they are only assigned to low-intensity positions at level 4 or below with a single shift not exceeding 4 hours and night shifts are prohibited; when the on-duty personnel are pregnant or breastfeeding, they are only assigned to day shift positions, night shifts and overtime are prohibited, and a single shift does not exceed 6 hours. The system will verify each on-duty personnel in the reserve group at each on-duty post based on hard verification of employment compliance, soft verification of personnel physical load, and special rule verification for special groups, so as to configure differentiated scheduling protection measures for different groups of people, obtain suitable personnel, and then schedule personnel for each determined suitable personnel.
[0033] Furthermore, the aforementioned "scheduling of personnel for the identified suitable candidates" also includes the following steps: Obtain job requirement data for each duty post, prioritize personnel health protection as the highest optimization goal, use meeting job requirement data and balanced manpower allocation as constraints, and use commuting distance, personal affairs arrangements and cross-post support capabilities as auxiliary conditions to generate a duty schedule. The duty roster is sent to the management terminal. When the management terminal sends a confirmation signal based on the duty roster, the duty roster is sent to each employee's terminal.
[0034] For example, in this embodiment, the system obtains the job requirements data for each duty post, including the duty period, such as 22:00-06:00; the number of people on duty, such as at least 2 people; the job level, such as level 3; the division of day and night shifts, such as night shift; the priority of emergency tasks, such as responding to a sudden fire is the highest priority; and the duty requirements during holidays, such as being on duty 24 hours a day during the Spring Festival. The system prioritizes the health and safety of personnel as its highest optimization goal. This means that the health level and real-time physical condition of on-duty personnel are the primary considerations. Personnel with higher health levels are given priority for assignment to high-intensity positions. Personnel with contraindication labels are not eligible to participate in the scheduling of corresponding positions. The system uses the data on job requirements as a hard constraint, such as ensuring that the number of personnel on duty is not less than the minimum requirement, that on-duty personnel have the skills and qualifications required for the corresponding position, and that contraindication labels do not conflict with job attributes. For example, those who are contraindicated for night shifts are not scheduled for night shifts. It will also use the balanced distribution of manpower as a soft constraint to avoid some people being overworked while others are idle. At the same time, it will use commuting distance, personal affairs arrangements and cross-job support capabilities as auxiliary conditions to select the best among multiple feasible scheduling schemes. That is, under the premise of prioritizing health and meeting hard constraints, the plan that minimizes the total commuting distance, minimizes conflicts between employees' personal affairs, and maximizes the utilization rate of multi-skilled personnel is selected first, thereby generating a duty schedule to ensure that the schedule meets the needs of on-duty personnel while protecting their health. The system will push the generated duty roster to the management terminal. After the management personnel review and confirm that it is correct, the system will simultaneously distribute the duty roster to the management backend, employee terminal and office announcement terminal to complete the unified release of the duty information. Employees can view their personal duty details through the employee terminal and click to confirm before officially starting their duty work.
[0035] Step S108 includes the following: The personnel status is determined based on the physiological characteristics data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
[0036] For example, in this embodiment, when the personnel are on duty, that is, when they have the attribute of being on duty, the system will collect the physiological data of the personnel on duty, including heart rate data, real-time fatigue index and continuous on-duty time data, etc. The system analyzes the collected physiological data to determine the status of the corresponding personnel. If the system determines that a personnel is in an emergency, it means that the personnel is not suitable to continue their shift. At this time, the system will select a replacement personnel based on the reserve group of the corresponding personnel. This ensures the safety of personnel, the absence of vacancies in the duty positions, and the smooth operation of the shift work.
[0037] Furthermore, the aforementioned "determining personnel status based on the collected physiological data of each on-duty personnel" also includes the following steps: Physiological data is acquired by monitoring equipment corresponding to each on-duty attribute of the matched personnel. The physiological data includes heart rate data, real-time fatigue index and continuous on-duty time data. When the heart rate data of any matched personnel exceeds the preset heart rate threshold, or the real-time fatigue index exceeds the preset fatigue threshold, or the continuous on-duty time exceeds the preset duration threshold, the personnel status of that matched personnel is determined to be an emergency state.
[0038] For example, in this embodiment, the system obtains physiological data through monitoring devices corresponding to each on-duty attribute of the matched personnel. The monitoring devices can be smart wearable devices, such as smart bracelets, smart badges, etc. The system collects heart rate data and continuous on-duty time of on-duty personnel in real time through monitoring equipment. It also collects and monitors activity level and body movement frequency to calculate real-time fatigue index. The normal threshold range of various physiological signs can be set individually based on historical health data. For example, the heart rate warning threshold of the fit personnel with a history of cardiovascular disease is lower than that of healthy fit personnel to ensure more accurate warning. If any on-duty personnel's heart rate data is consistently higher than the preset heart rate threshold, such as a heart rate higher than 120 beats / minute for 5 consecutive minutes, or if the real-time fatigue index is greater than the preset fatigue threshold, such as a maximum score of 100 points and a preset fatigue threshold of 80 points, or if the continuous on-duty time exceeds the preset time threshold, such as a continuous on-duty time of more than 8 hours, the system determines that the personnel is in an emergency state. In addition, the adapted employees can also submit reports of physical discomfort based on natural language through the corresponding employee terminal. For example, if the system receives a report from Zhang San that says "I have a bad headache and want to ask for leave", the system will perform semantic recognition on the report. For example, it will extract entity information such as the person's name as Zhang San and the symptoms of discomfort as headache. At this time, it will also determine that the adapted employee is in an emergency, which has a certain degree of flexibility.
[0039] Furthermore, the aforementioned "if the personnel status of any of the adapted personnel is determined to be in an emergency state, a substitute personnel shall be determined based on the reserve group of the corresponding adapted personnel" also includes the following steps: If the personnel status of any of the aforementioned personnel is determined to be an emergency state, based on the reserve group of the corresponding personnel, each personnel with the standby attribute corresponding to the maximum health level is identified as a target personnel, and the number of personnel corresponding to the target personnel is determined. If the number of personnel is 1, the target personnel will be designated as substitutes. If the number of personnel is greater than 1, determine the cumulative on-duty time of each target personnel, and identify the target personnel with the minimum cumulative on-duty time as substitute personnel.
[0040] For example, in this embodiment, when the system determines that the personnel status of any adaptable person is in an emergency state, it first determines the reserve group to which the adaptable person belongs. In order to enable the subsequently determined substitute personnel to be more competent in the substitute duty work, the system will determine each adaptable person with the waiting attribute corresponding to the maximum health level as the target personnel and determine the number of personnel corresponding to the target personnel. For example, if the maximum health level in the reserve group is level 4, then each adaptable person with a health level of 4 will be determined as the target personnel. If the number of personnel is 1, the system will directly identify the target personnel as the substitute personnel. If the number of target personnel is greater than 1, the system will further determine the cumulative on-duty time of each target personnel in the current scheduling cycle, and then identify the target personnel with the minimum cumulative on-duty time as the substitute personnel, so as to achieve a balanced allocation of manpower. Finally, the system will push the finalized replacement personnel to the management end. The management personnel can view the replacement personnel through the review interface, confirm them with one click, and then execute the shift change operation. This embodiment determines substitute personnel by prioritizing those with the best health level and then those with the shortest cumulative shift time. This approach ensures that the physical requirements of the substitute positions are met while achieving a balanced distribution of manpower, demonstrating its feasibility.
[0041] Furthermore, the above method also includes the following steps: Based on preset periodic statistics of staff on-duty hours, trends in staff health status, scheduling compliance rate, and post duty completion rate, a health duty analysis report is generated. The newly added data in the current period is stored, and the data correlation pattern between shift length, shift type and health level changes is determined based on multi-period data to generate optimization parameters; The optimization parameters include the mapping relationship between health level and job level, as well as the boundary value of the preset tolerance.
[0042] For example, in this embodiment, the system calculates the on-duty time of personnel, the trend of changes in personnel health status, the scheduling compliance rate, and the post duty completion rate according to a preset period, and generates a health duty analysis report. For example, if the preset period can be one month, then the staff on-duty time is the cumulative on-duty hours in that month, the health status change trend is the health level change curve and fatigue accumulation trend in that month, the scheduling compliance rate is the employment compliance verification pass rate and the rule matching rate for special groups, and the post duty completion rate is the on-duty personnel compliance rate and the number of post vacancies, thereby generating a health duty analysis report for managers to review. The system will store the newly added data for the current period, including the current shift schedule, records of changes in personnel health status, compliance verification results, and duty completion status, into the Shift Health RAG knowledge base and store it in a vectorized format. Among them, the scheduling plan data is stored in the historical scheduling vector library of job intensity, and the health change data is stored in the personnel health and duty time sequence correlation vector library, so that the scheduling data and health feedback data of each cycle are persistently saved and quantified. The system then uses multi-period data mining to identify the data correlation patterns between shift duration, shift type, and changes in employee health status, and generates optimization parameters. For example, the analysis found that after two consecutive night shifts at the level 3 health grade, the proportion of people with health indicators such as blood pressure decreased by 78%, while when they were only assigned day shifts at the level 4-5 job grade, the proportion was only 12%. Based on this, the matching weight of night shifts for people with chronic diseases was automatically reduced. For example, analysis of historical data revealed that outdoor inspection positions during the high-temperature period in summer require significantly more physical exertion for personnel with a health level below 2 than in other seasons. Based on this, the tolerance range boundary value for summer was automatically lowered. The system will feed back the generated optimization parameters for the health level assessment and matching of the next scheduling cycle, thus enabling the system to continuously and autonomously iterate. The system will de-identify all collected health privacy data, and store the names, employee numbers, health scores, and contraindication labels of the on-duty personnel separately. Only the anonymization identifier is retained in the health data, and then the de-identified data is encrypted and stored. The system also sets tiered data access permissions. For example, ordinary managers can only view the names and shifts of employees in the work schedule, but cannot view health scores and contraindication labels. Senior managers can view complete health data, and HR personnel can only view the summary statistics of physical examinations, ensuring that employees' health privacy data is not leaked or misused.
[0043] According to the present invention, by uniformly identifying and analyzing the multi-source heterogeneous health data of on-duty personnel, a health level is generated, achieving a precise quantitative assessment of physical condition. Furthermore, based on personnel information, on-duty positions are determined, and personnel with health levels not lower than the position level and whose differences are within a preset tolerance range are assigned to the same reserve group. This ensures that the scheduling scheme meets personnel constraints while guaranteeing the health and safety of personnel and sufficient scheduling resources. On this basis, through a preset verification strategy, while ensuring the compliance of the scheduling scheme, differentiated flexible scheduling rules can be configured for special groups, effectively avoiding labor conflicts and secondary injuries to personnel. At the same time, by collecting the physiological characteristics data of on-duty personnel in real time, and quickly determining replacement personnel based on the reserve group when the personnel status is determined to be in an emergency, the efficiency of emergency deployment in case of emergencies is improved, maximizing the protection of the health of on-duty personnel and the smooth operation of the duty.
[0044] Another embodiment of the present invention provides an intelligent shift scheduling system that integrates the dimension of personnel physical health. Figure 3 Its corresponding system block diagram includes: The health level determination module is configured to identify and parse the structured and unstructured health data of the same on-duty personnel to determine the health level of the on-duty personnel. The job grouping module is configured to determine the duty position corresponding to the duty personnel based on the personnel information corresponding to the duty personnel, and to divide the duty personnel whose corresponding health level is not lower than the job level of the duty position and whose difference between the health level and the job level is within a preset tolerance into a reserve group corresponding to the same duty position. The personnel scheduling module is configured to perform verification operations on each on-duty personnel in different reserve groups based on a preset verification strategy, and to schedule personnel for each identified suitable personnel. The substitute determination module is configured to determine the personnel status based on the collected physiological characteristic data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
[0045] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages is for the purpose of disclosing preferred embodiments of the invention.
[0046] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0047] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof.
[0048] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.
[0049] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components.
[0050] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.
[0051] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.
[0052] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.
[0053] Although the invention has been described with respect to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and edibility purposes, and not for the purpose of explaining or limiting the subject matter of the invention.
Claims
1. A smart shift scheduling method that integrates the dimension of personnel physical health, characterized in that, include: Data identification and parsing are performed on the structured and unstructured health data corresponding to the same on-duty personnel to determine the health level of the corresponding on-duty personnel; Based on the personnel information corresponding to the duty personnel, the duty positions corresponding to the duty personnel are determined, and each duty personnel whose corresponding health level is not lower than the duty position level and whose difference between the health level and the duty position level is within the preset tolerance are assigned to the reserve group corresponding to the same duty position. Based on the preset verification strategy, the on-duty personnel in different reserve groups are verified, and the personnel are scheduled for each suitable personnel. The personnel status is determined based on the physiological characteristics data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
2. The method according to claim 1, characterized in that, Data identification and parsing are performed on the structured and unstructured health data corresponding to the same on-duty personnel to determine the health level of the corresponding on-duty personnel, including: Retrieve a preset information type table, which includes various information types and corresponding benchmark words for different information types; Semantic recognition is performed on each structured health data corresponding to the same on-duty personnel. If any text word in each structured health data is the same as any benchmark word included in the preset information type table, the information type corresponding to the benchmark word is determined as the target type. Multi-source heterogeneous data analysis was performed on unstructured health data of the same on-duty personnel to obtain structured taboo labels and structured health scores; The health level of the on-duty personnel is determined based on the target type and structured health score.
3. The method according to claim 2, characterized in that, Based on each target type and structured health score, the health level of the corresponding on-duty personnel is determined, including: A preset benchmark interval is determined for each target type, and the individual health deduction for each target type is determined based on the deviation between the target information corresponding to each target type determined by each structured health data and the preset benchmark interval. An initial health score is determined based on the individual health deductions, and the health level is determined based on the structured health score and the initial health score. Retrieve the preset taboo level mapping relationship, compare the structured taboo tags with the mapping relationship, and determine the upper limit of the level; The health level is updated based on the aforementioned upper limit.
4. The method according to claim 1, characterized in that, Based on a preset verification strategy, verification operations are performed on duty personnel in different reserve groups, and personnel scheduling is carried out for each identified suitable personnel, including: The preset verification strategy includes hard verification of employment compliance, soft verification of personnel physical load, and verification of rules specific to special groups; Based on the aforementioned hard verification of employment compliance, soft verification of personnel physical load, and special rule verification for special groups, the on-duty personnel of the reserve group located at each on-duty post are verified to obtain each suitable personnel. Staffing schedules were arranged for the identified suitable personnel.
5. The method according to claim 4, characterized in that, The method further includes: The verification data for the mandatory verification of employment compliance includes at least the daily working hours, number of consecutive shifts, rest time between shifts, and maximum overtime hours. The data threshold parameters of each verification data for the aforementioned hard verification of employment compliance are pushed and updated in real time. The soft test of personnel physical load includes the cumulative on-duty hours of the test cycle and the cumulative fatigue level; The special group-specific rule verification includes configuring differentiated flexible scheduling rules for elderly on-duty personnel, personnel recovering from injuries or illnesses, and pregnant and breastfeeding personnel. The flexible scheduling rules include prioritizing the allocation of easy shifts, shortening the on-duty hours, and reducing night shifts.
6. The method according to claim 4, characterized in that, Staffing schedules will be arranged for the identified suitable personnel, including: Obtain job requirement data for each duty post, prioritize personnel health protection as the highest optimization goal, use meeting job requirement data and balanced manpower allocation as constraints, and use commuting distance, personal affairs arrangements and cross-post support capabilities as auxiliary conditions to generate a duty schedule. The duty roster is sent to the management terminal. When the management terminal sends a confirmation signal based on the duty roster, the duty roster is sent to each employee's terminal.
7. The method according to claim 1, characterized in that, The personnel status is determined based on the collected physiological characteristic data of the matched personnel corresponding to each on-duty attribute, including: Physiological data is acquired by monitoring equipment corresponding to each on-duty attribute of the matched personnel. The physiological data includes heart rate data, real-time fatigue index and continuous on-duty time data. When the heart rate data of any matched personnel exceeds the preset heart rate threshold, or the real-time fatigue index exceeds the preset fatigue threshold, or the continuous on-duty time exceeds the preset duration threshold, the personnel status of that matched personnel is determined to be an emergency state.
8. The method according to claim 7, characterized in that, If the personnel status of any of the aforementioned suitable personnel is determined to be in an emergency state, replacement personnel are determined based on the reserve group corresponding to the suitable personnel, including: If the personnel status of any of the aforementioned personnel is determined to be an emergency state, based on the reserve group of the corresponding personnel, each personnel with the standby attribute corresponding to the maximum health level is identified as a target personnel, and the number of personnel corresponding to the target personnel is determined. If the number of personnel is 1, the target personnel will be designated as substitutes. If the number of personnel is greater than 1, determine the cumulative on-duty time of each target personnel, and identify the target personnel with the minimum cumulative on-duty time as substitute personnel.
9. The method according to claim 5, characterized in that, The method further includes: Based on preset periodic statistics of staff on-duty hours, trends in staff health status, scheduling compliance rate, and post duty completion rate, a health duty analysis report is generated. The newly added data in the current period is stored, and the data correlation pattern between shift length, shift type and health level changes is determined based on multi-period data to generate optimization parameters; The optimization parameters include the mapping relationship between health level and job level, as well as the boundary value of the preset tolerance.
10. An intelligent shift scheduling system that integrates the dimension of personnel physical health, characterized in that, include: The health level determination module is configured to identify and parse the structured and unstructured health data of the same on-duty personnel to determine the health level of the on-duty personnel. The job grouping module is configured to determine the duty position corresponding to the duty personnel based on the personnel information corresponding to the duty personnel, and to divide the duty personnel whose corresponding health level is not lower than the job level of the duty position and whose difference between the health level and the job level is within a preset tolerance into a reserve group corresponding to the same duty position. The personnel scheduling module is configured to perform verification operations on each on-duty personnel in different reserve groups based on a preset verification strategy, and to schedule personnel for each identified suitable personnel. The substitute determination module is configured to determine the personnel status based on the collected physiological characteristic data of the matched personnel corresponding to each on-duty attribute. If the personnel status of any matched personnel is determined to be an emergency state, a substitute personnel is determined based on the reserve group corresponding to the matched personnel.
