Labor management system, labor management method, and program

Abstract

To provide a labor management system, a labor management method and a program for enabling a manager to easily and statistically grasp the labor characteristics of the whole job site based on the labor result / load of an individual.SOLUTION: A labor management system includes a data acquisition unit that receives labor achievement information including a daily labor time or a labor content for each worker and incident information including presence or absence of an accident that has occurred during labor of the worker, a labor index generation unit that generates a labor index for each predetermined period from the labor achievement information, a labor characteristic analysis unit that analyzes a correlation between the labor index generated by the labor index generation unit and the incident information, and a labor characteristic presentation unit that presents a labor characteristic including the correlation analyzed by the labor characteristic analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a labor management system, labor management method, and program that uses labor performance information to generate labor indicators, analyze labor characteristics according to labor content, and extract relationships with work-related errors and risks, thereby avoiding labor risks and supporting labor management. [Background technology]

[0002] Labor shortages are a major issue in the logistics industry. In recent years, in order to prevent accidents involving drivers in the transportation industry, efforts have been made to develop and promote safe driving management systems that utilize IoT and sensors to collect driver and vehicle status data in the cloud, and use digital information to quantitatively evaluate driver fatigue and grasp driving conditions in real time. Furthermore, with the revised Labor Standards Act, which aims to improve working conditions, coming into effect in 2024, more appropriate management and improvement of driver working conditions will be required, with a focus on labor information. Furthermore, safety management for on-site workers is required not only in the transportation industry, and similar management methods using IoT and sensors to monitor safety are being considered.

[0003] As a conventional invention of this type, Japanese Patent Application Laid-Open Publication No. 2017-220074 (Patent Document 1) describes a method and device for providing work plan supplementary information, which refers to a memory unit that stores an individual's past work performance and attribute information, performs a process of calculating the individual's fatigue level for each of multiple types of work in a future working time period that includes multiple types of work based on the past work performance and the attribute information, and performs a process of outputting the calculated fatigue level in association with each of the multiple types of work included in the future working time period. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-220074 Summary of the Invention [Problem to be solved by the invention]

[0005] The aforementioned revision of labor standards is expected to improve the working environment for drivers by setting standards for some labor information such as on-duty hours and driving hours. However, even for the same working hours, the workload on drivers varies depending on the work content and time of day, and labor management that takes into account the actual working conditions and labor characteristics based on labor performance data obtained at the driving site is necessary.

[0006] Furthermore, in Patent Document 1, the fatigue level for each type of work during future work hours is calculated based on the work performance and attribute information of a specific individual, but this does not necessarily reflect the overall trend of the work. It is difficult for managers to predict the individual workload of workers (for example, drivers) and understand the work characteristics of the entire work site.

[0007] The present invention aims to provide a labor management system, labor management method, and program that can statistically analyze the labor characteristics of the entire site based on individual labor performance and workload, thereby reducing the labor management burden on managers. [Means for solving the problem]

[0008] In order to solve at least one of the above-mentioned problems, the labor management system of the present invention is configured to have a data acquisition unit that receives labor performance information including daily working hours or labor content for each worker and incident information including whether or not an accident occurred while the worker was working, a labor index generation unit that generates labor indexes for each specified period from the labor performance information, a labor characteristic analysis unit that analyzes the correlation between the labor index generated by the labor index generation unit and the incident information, and a labor characteristic presentation unit that presents labor characteristics including the correlation analyzed by the labor characteristic analysis unit. [Effects of the Invention]

[0009] According to the present invention, accumulated labor performance information is used to generate a new set of indicators that capture the characteristics of the working style of workers (for example, drivers), and by statistically analyzing the labor conditions that lead to accident risks for each labor type and analyzing the labor characteristics for each labor type, it is possible to reduce the burden of labor management on managers, and for example, to provide advice to drivers on improving operation plans, avoid labor conditions that lead to accident risks, and make labor plan creation more efficient.

[0010] Problems, configurations, and effects other than those described above will become apparent from the following description of the preferred embodiments of the invention. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a block diagram showing the configuration of a labor management system according to an embodiment of the present invention; [Figure 2] 1 is a flowchart showing an outline of processing performed in a labor management system according to an embodiment of the present invention. [Figure 3] FIG. 10 is a diagram showing an example of labor performance information in an embodiment of the present invention. [Figure 4] FIG. 10 is a diagram illustrating an example of incident information according to an embodiment of the present invention. [Figure 5] 1A and 1B are diagrams illustrating examples of biometric information and subjective information according to an embodiment of the present invention. [Figure 6] 10 is a flowchart illustrating a process performed by a labor index generation unit in an embodiment of the present invention. [Figure 7] FIG. 10 is a diagram showing an example of labor index items in an embodiment of the present invention. [Figure 8] 10 is a flowchart showing processing performed by an additional indicator generation and fusion unit in an embodiment of the present invention. [Figure 9] FIG. 10 is a diagram showing an example of additional index items in the embodiment of the present invention. [Figure 10] 10 is a flowchart illustrating an example of a labor characteristic analysis process according to an embodiment of the present invention. [Figure 11] FIG. 10 is a diagram showing an example of labor type classification in an embodiment of the present invention. [Figure 12A] FIG. 10 is a diagram showing an example of a labor status according to a labor type classification in an embodiment of the present invention. [Figure 12B] FIG. 10 is a diagram showing an example of a labor status according to a labor type classification in an embodiment of the present invention. [Figure 12C] FIG. 10 is a diagram showing an example of a labor status according to a labor type classification in an embodiment of the present invention. [Figure 12D] FIG. 10 is a diagram showing an example of a labor status according to a labor type classification in an embodiment of the present invention. [Figure 12E] FIG. 10 is a diagram showing an example of a labor status according to a labor type classification in an embodiment of the present invention. [Figure 13] FIG. 10 is a diagram showing an example of a labor index base distribution in an embodiment of the present invention. [Figure 14] FIG. 10 is a diagram showing an example of a risk trend analysis for each labor type in an embodiment of the present invention. [Figure 15] 10 is a flowchart illustrating a labor characteristic presentation process according to an embodiment of the present invention. [Figure 16A] FIG. 2 is a diagram showing an example of a screen display of a labor management system according to an embodiment of the present invention. [Figure 16B] FIG. 2 is a diagram showing an example of a screen display of a labor management system according to an embodiment of the present invention. [Figure 16C] FIG. 2 is a diagram showing an example of a screen display of a labor management system according to an embodiment of the present invention. [Figure 17] 10 is a flowchart illustrating an example of processing performed by an individual labor characteristics analysis unit in the embodiment of the present invention. [Figure 18] FIG. 2 is a diagram showing an example of a screen display of a labor management system according to an embodiment of the present invention. [Figure 19] 10 is a flowchart illustrating an example of a labor characteristic analysis process according to an embodiment of the present invention. [Figure 20] FIG. 10 is a diagram illustrating an example of labor type classification in an embodiment of the present invention. [Figure 21] FIG. 10 is a diagram showing an example of identifying factors highly correlated with the occurrence of incidents for each labor type in an embodiment of the present invention. [Figure 22] 10 is an example of a table summarizing the analysis of labor characteristics and average risk for each labor type in an embodiment of the present invention. [Figure 23A] FIG. 10 is a diagram showing an example of labor type classification for each driver in an embodiment of the present invention. [Figure 23B] FIG. 10 is a diagram showing an example of labor type classification for each establishment in an embodiment of the present invention. [Figure 24] FIG. 10 is a diagram showing an example of changes over time in the driver's work type in an embodiment of the present invention. [Figure 25] FIG. 10 is a diagram showing an example of setting labor indicators highly related to risk according to labor types in an embodiment of the present invention. [Figure 26] FIG. 10 is a diagram showing an example of various analyses performed on a specific worker based on risk factors for each labor type in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0013] The examples are illustrative of the present invention, and have been omitted or simplified as appropriate for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise specified, each component may be singular or plural.

[0014] In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings.

[0015] Examples of various types of information may be described using expressions such as "table," "list," and "queue," but the various types of information may also be expressed using data structures other than these. For example, various types of information such as "XX table," "XX list," and "XX queue" may also be expressed as "XX information." When describing identification information, expressions such as "identification information," "identifier," "name," "ID," and "number" are used, but these are interchangeable.

[0016] When there are multiple components with the same or similar functions, they may be described using the same reference numeral with different subscripts. When there is no need to distinguish between these multiple components, the subscripts may be omitted.

[0017] In the embodiments, processing performed by executing a program may be described. Here, a computer executes the program using a processor (e.g., a CPU or a GPU) and performs processing defined by the program using storage resources (e.g., a memory) and interface devices (e.g., a communication port). Therefore, the entity performing the processing by executing the program may be the processor. Similarly, the entity performing the processing by executing the program may be a controller, device, system, computer, or node having a processor. The entity performing the processing by executing the program may be any computing unit, and may include a dedicated circuit that performs specific processing. Here, the dedicated circuit may be, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device).

[0018] A program may be installed on a computer from a program source. The program source may be, for example, a program distribution server or a computer-readable storage medium. When the program source is a program distribution server, the program distribution server may include a processor and storage resources for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. In addition, in the embodiments, two or more programs may be realized as one program, or one program may be realized as two or more programs. [Example]

[0019] <System configuration> First, the system configuration of this embodiment will be described with reference to FIG. As an example, the labor management system 100 of this embodiment is assumed to manage the driving operations of trucks that transport cargo, and collects labor performance information from a labor performance information collection device 20 via a network 10, and collects additional information from an on-board information collection device 30, a biometric information collection device 40, and a subjective information collection device 50. Note that the labor management system 100 may include all or any of the labor performance information collection device 20, the on-board information collection device 30, the biometric information collection device 40, and the subjective information collection device 50. In the following description, the term "user" refers to a worker, which corresponds to a driver in this embodiment. Furthermore, an administrator who manages workers has the authority to check the labor status of specific individuals as a power user in the system.

[0020] The labor performance information collection device 20 includes a labor detail recording unit 21 that records details of labor content, a time attendance information recording unit 22 that records time attendance information for each user, an operation performance linking unit 23, and a user information recording unit 24. The in-vehicle information collection device 30 includes an accident information recording unit 31 and an in-vehicle sensor 32. Accident information is incident information. Incident information includes traffic accidents as well as environmental situation information that may lead to accidents, and is collected by the in-vehicle sensor 32. The biometric information collection device 40 includes a biometric sensor 41 that measures body temperature, heart rate, etc., and acquires and collects biometric information of the user. The subjective information collection device 50 includes a subjective information input unit 51 and collects subjective information input by the user.

[0021] The labor management system 100 is a computer including a processor 110, a memory 120, a storage device 130, an input / output device 140, and a communication device 150.

[0022] The memory 120 has software (programs) that have the functions of each of the following parts: a data acquisition unit 121 that acquires various data information; a labor index generation unit 122 that generates labor indexes; an additional index generation / fusion unit 123; a labor characteristic analysis unit 124 that classifies labor types and analyzes labor characteristics for each labor type; a labor characteristic presentation unit 125 that presents the analyzed labor characteristics; and an individual labor characteristic analysis unit 126 for individual judgments; and the functions of each of these parts are realized by the processor 110 executing these programs.

[0023] The storage device 130 contains accumulated labor performance information 131, user information 132, sensor information 133, biometric information 134, in-vehicle information 135, incident information (accident information) 136, subjective information 137, labor index setting information 138 that records the labor indexes to be used set by the administrator, etc. and the types of labor indexes to be displayed on the screen, a labor characteristic aggregation model 139 that aggregates labor characteristics, and labor standard setting information 13A that records guideline standards set by the administrator, etc. (upper limits on working hours and working hours, etc.).

[0024] <Processing details> Next, an outline of the processing performed in the labor management system of this embodiment will be described with reference to the flowchart shown in FIG.

[0025] In step S201, the data acquisition unit 121 acquires the labor performance information, incident information, biometric information, subjective information, etc. accumulated in the labor performance information collection device 20, the in-vehicle information collection device 30, the biometric information collection device 40, and the subjective information collection device 50 via the network 10 using the communication device 150, and performs initial processing such as data cleansing as necessary and stores the information in each database (DB) of the storage device 130.

[0026] In step S202, the acquired labor performance information is organized and integrated to generate various labor indicators for each predetermined period.

[0027] In step S203, additional indicators for each predetermined period that are aligned with the labor index are generated from the acquired additional information such as incident information, biometric information, and subjective information, and are merged with the labor index.

[0028] In step S204, the labor characteristics are analyzed comprehensively based on the labor index, including distribution characteristic analysis, labor standard matching, labor type classification, stratification, and risk trend analysis for each labor index and labor type.

[0029] In step S205, the analysis results required by the user are presented based on the distribution of analyzed labor indicators, risk factors and trends, labor types, labor characteristics for each labor type, and the like.

[0030] In step S206, various labor analysis results are output to a labor characteristics model, and a labor characteristics model is generated or an existing model is updated.

[0031] Here, examples of the above-mentioned labor performance information, incident information, biometric information, and subjective information will be described. Figure 3 shows an example 300 of labor performance information in this embodiment. Labor information-1 (310) is recorded for each driving task, and includes basic labor information such as the identification information of the business establishment (business establishment ID), the identification information of the user (driver) (user ID), the date of work, the number of consecutive days since the previous work, on-duty hours, driving hours, etc.

[0032] The labor information-2 (320) includes each item of detailed work content (loading and unloading, rest, rest, standby, etc.) recorded in the labor detail recording section 21, as well as the start and end times of each item.

[0033] Labor information-3 (330) includes the mileage recorded in the on-board sensor 32 and the operation record linking unit 23, the mileage when loaded with luggage, the mileage when empty, and the like.

[0034] 4 is an example of incident information 400 in this embodiment. An incident is a near-miss situation that could lead to an accident, such as sudden braking or insufficient distance between vehicles, that the user encounters during driving operations. Incidents are used as an accident risk index during driving.

[0035] Incidents that occur during driving are estimated and detected, for example, by the in-vehicle information collection device 30 based on information collected by in-vehicle sensors 32 such as a drive recorder and an acceleration sensor. Incident items include failure to stop temporarily, sudden steering, sudden deceleration, following distance warning, insufficient following distance, impact, forward collision warning, and speeding. From the perspective of eliminating false detections, a step may be added in which a user or administrator checks the information determined to be an incident and accepts input of whether it is a true or false detection.

[0036] 5 shows an example 500 of biometric information and subjective information in this embodiment. The subjective information includes fatigue VAS at the time of arriving at work, sleep VAS at the time of arriving at work, and fatigue VAS at the time of leaving work, which are obtained through subjective evaluations at the time of arriving at work and leaving work. A VAS (Visual Analogue Scale) is a type of index capable of evaluating subjective health information, and uses a visual evaluation scale showing a predetermined numerical range to subjectively select a fatigue level at will, for example, on a scale of values ​​from 0 to 100. In addition to the subjective information received by VAS, biometric information actually measured by the user may also include information such as an average heartbeat interval, a fatigue accumulation index (TP), autonomic nervous balance (LF / HF), blood pressure, body temperature, and oxygen saturation (SpO2), which are measured by a heartbeat sensor or the like.

[0037] Next, a detailed description will be given of each step explained in the flowchart of Fig. 2. Fig. 6 is a flowchart showing an example of the process (corresponding to step S202 in Fig. 2) performed by the labor index generation unit 122 of this embodiment.

[0038] When labor index generation starts (step S600), in step S601, detailed labor information (labor content, total time, number of occurrences, etc.) is aggregated based on the labor performance information, using the user ID and labor date as criteria, to generate a daily basic labor index. Each item of this labor index may be generated in accordance with the items defined in the laws and guidelines related to that labor.

[0039] In step S602, the labor indexes for a predetermined period (weekly, monthly, etc.) are aggregated based on the daily labor indexes to generate an accumulated labor index.

[0040] In step S603, an extended labor index is generated, which includes the mean value, variance, deviation, relative ratio, etc. of the labor index for a predetermined period in order to reflect fluctuations and labor characteristics within the predetermined period.

[0041] In step S604, various labor indices are combined and matched with the user ID and the reference date as indexes to generate table data, which is then stored in a storage device as labor index data.

[0042] FIG. 7 shows an example of the labor index items 700 of the table data generated in step S604 described above. The index information 701 includes a user ID, a business establishment ID, and a labor-base date on which the labor occurred.

[0043] Daily basic labor indicators 702 include on-duty time, driving time, loading and unloading time, rest time, break time, work start time, work end time, etc. In daily work, the same work such as driving and loading and unloading may be performed multiple times, so these are aggregated based on the labor reference date. In addition, an indicator of the number of times may be generated to show the frequency.

[0044] As the monthly accumulated labor index 703, the aggregated values ​​of each item for the month and the number of working days are added to the daily basic labor index 702 to generate accumulated labor indexes such as total hours and number of times. The period here may be a predetermined period such as a week.

[0045] As the extended labor index 704, the average value, variance, difference within a period, etc. of the start time, end time, etc. are generated for the monthly accumulated labor index 703 in order to maintain its fluctuation and characteristics over time. Indicators such as loading / unloading ratio and driving ratio may also be generated to detail the work content.

[0046] FIG. 8 is a flowchart showing an example of the process (corresponding to step S203 in FIG. 2) performed by the additional index generating and integrating unit 123 of this embodiment.

[0047] In step S801, additional information such as incident information, biometric information, and subjective information is obtained from the accumulated data DB.

[0048] In step S802, in conjunction with the generation of the labor index, a daily incident index, a biological index, a subjective index, etc. are generated in accordance with the relevant reference date.

[0049] In step S803, the accumulated labor index for each predetermined period (week, month) of the labor index, and indices such as the average, variance, and amount of change over time of each index that indicates fluctuation are generated.

[0050] In step S804, matching table data is generated using the user ID, reference date, etc. as indexes in accordance with the labor index data, and the generated table data is then held as integrated index data.

[0051] FIG. 9 shows an example of additional index items 900 of the table data generated in step S804 described above. The index information 901 includes a user ID, a business ID, and a labor_reference date. As the incident index 902, a daily total of various incidents, the number of occurrences in a predetermined period (week, month), and the incidence rate averaged over days are generated. Similarly, indices are generated for the subjective assessment VAS information 903 and the biological index 904 on a daily basis and for a predetermined period of time.

[0052] FIG. 10 is a flowchart showing an example of the labor characteristics analysis process (corresponding to steps S204 and S205 in FIG. 2) performed by the labor characteristics analysis unit 124 of this embodiment. In step S1001, a basic analysis is performed based on the labor index data (Figure 7) to understand the actual labor situation and analyze whether the set labor standards (such as maximum driving hours and working hours per month) are being met.

[0053] In step S1002, the correlation between each labor index and the objective variable (incident) is analyzed for the labor index data (Figure 7) and the fusion index data that combines additional indexes such as incident indexes (Figure 9), and the indexes are stratified and related factors and trends are extracted.

[0054] In step S1003, labor types (regularity, start time, core duties, etc.) are extracted and classified based on the labor index data (Figure 7). When confirming the actual labor situation, labor conditions may vary greatly depending on the business establishment and user (driver), so this must be taken into consideration. Figure 11 shows an example of labor type classification, and Figure 12A shows an example of labor conditions based on that classification. Figure 12A is a diagram showing the work status of users with four different labor types ((a), (b), (c), and (d)). The vertical axis represents the date (for one month) and the horizontal axis represents the time (24 hours), and the working hours are shown as a horizontal bar graph. Although not specifically shown in Figure 7, the color, pattern, and width of the bands on the graph are associated with the labor content and displayed as a classification. Enlarged views of these four graphs are shown in Figures 12B to 12E.

[0055] Figure 12A (a) (Figure 12B) shows an example of a work type that mainly involves day shifts, with regular arrival times. Figure 12A (b) (Figure 12C) shows an example of a work situation where mainly involves night shifts and regular arrival times. Figure 12A (c) (Figure 12D) shows an example of a work situation where day and night shifts alternate weekly and arrival times are irregular. Figure 12A (d) (Figure 12E) shows an example of a work situation where mainly involves long hours (driving) and irregular arrival times.

[0056] As such, while there are labor situations where the arrival times are regular, there are also completely irregular types. Even if the arrival times are regular, there are day shift types, night shift types, etc. In some cases, day shifts and night shifts are alternated. Depending on the work content, there are types that focus on local deliveries and loading and unloading work, and there are also types that focus on long-term transportation. Classification of types can be based on labor indicators. Classification can also be done automatically using methods such as decision trees, machine learning, and clustering.

[0057] In step S1004, the labor characteristics for each labor type are analyzed, and in order to analyze trends in risk changes according to fluctuations in indicators for each labor type, the process returns to step S1001 and performs a similar analysis for each labor type, and then a similar analysis for each labor type is performed in step S1002 (see the bold arrows in Figure 10).

[0058] In step S1005, the overall results of each of the above analyses, such as the overall distribution, correlations and trends, and labor type classifications, are stored in a labor characteristic aggregation model in the storage device. Note that the labor characteristic analysis unit 124 may further include a learning unit, and if the correlation is equal to or greater than a predetermined threshold, learning may be performed using labor performance information for each labor index for a predetermined period as an explanatory variable and incident information for the predetermined period as a target variable, to generate a risk estimation model and store it in the labor characteristic aggregation model.

[0059] FIG. 13 shows an example of the basic distribution of labor indices obtained in step S1001, and can be displayed on the screen of the input / output device 140 or the like to be presented to the user. An appropriate interval can be set for each index, and the basic distribution and cumulative ratio can be checked. This makes it possible to determine whether the histogram distribution of the overall data and the set labor standards are met. In addition, the data distribution for each labor type can be presented according to the condition settings.

[0060] FIG. 14 shows an example 1400 of risk trend analysis for each labor type obtained in step S1002, including an example 1410 of risk trend analysis using a decision tree, analysis results 1420, and an evaluation (text report) 1430 based on the analysis. These can also be displayed on the screen of the input / output device 140 or the like and presented to the user. Techniques such as decision trees may involve classification of labor types, branching point conditions, and risk comparisons between groups, or the identification of combinations between complex indicators may be documented and compiled as a written report. For a single indicator, the trend of risk change may be presented according to fluctuations in the labor indicator for each labor type. Furthermore, mutual comparisons may be made for each labor type, and risk assessment results and trends may be presented.

[0061] FIG. 15 is a flowchart showing an example of the presentation process (corresponding to step S206 in FIG. 2) performed by the labor characteristic presentation unit 125 of this embodiment.

[0062] When the labor characteristic presentation process is started (step S1500), in step S1501, fusion index data that combines labor indicators obtained by the above-mentioned analysis process with additional indicators such as incident indicators, labor characteristic aggregation models, etc. are accessed, and items that can be presented to the user are displayed on the screen of the input / output device 140, etc.

[0063] In step S1502, the presentation range is specified by the user, such as the entire analysis results, by labor type, by business establishment, or by user.

[0064] In step S1503, further detailed specification of indicators and items to be presented is accepted.

[0065] In step S1504, based on the above-mentioned specified information, a graph, a data list, a text report, etc. of the relevant information is presented on the input / output device 140, etc.

[0066] FIG. 16A is a diagram showing an example of a presentation screen (for a manager) 1600 of the labor management system of this embodiment. The input setting section 1601 sets administrator privileges, accessible databases, the scope of business establishments and users to be targeted, etc. The indicator setting section 1602 allows for the addition or modification of various values ​​required for analysis and standard values ​​for indicators that are set as initial values. The standard setting section 1603 allows for the setting of restriction rules for some labor indicators set by the industry or individual business establishment, such as revised improvement standards. For example, standard values ​​for daily working hours, monthly working hours, daily operating hours, continuous operating hours, etc. can be set, and individual settings can be changed if the upper limit is exceeded. The labor type specification section 1604 allows for the specification of each type and the setting of that analysis, in addition to the default setting which targets the entire analysis.

[0067] Indicator distribution display specification 1605, display items such as histogram distribution and percentages for each indicator (duty time, driving time, loading and unloading time, etc.) can be set, which is useful for managers to grasp the overall labor situation and check for violations of standards (an enlarged view of the display screen is shown in Figure 16B). Risk trend display 1606 displays the analysis results of the overall data and the relationship between labor indicators and risks according to the analysis method (an enlarged view of the display screen is shown in Figure 16C).

[0068] The document report section 1607 presents the results of the analysis, expressing highly relevant trends in text and displaying them to managers, providing new insights and providing reference for scheduling operation plans. Specifically, it outputs quantitative and written explanations of the relationship between labor indicators and risk for each labor type based on the results of statistical analysis of labor conditions, such as "Irregular groups whose arrival times are 2.5 hours or more later than usual have a 1.8 times higher incident incidence rate than groups with regular arrival times," and "Irregular groups with monthly driving hours of 126 hours or more have a 2.2 times higher incident incidence rate." This allows managers to easily understand the meaning and magnitude of risks presented by data and graphs, facilitating the formulation of improvement measures and reducing the burden on labor management. The incident incidence rate displayed here refers to the percentage of incidents occurring per day under the corresponding labor conditions.

[0069] The data list section 1608 displays labor information (number of consecutive days worked, on-duty time, driving time, loading and unloading time), incident information (number of near misses), estimated risk values, etc. in a list, and the user can also narrow down the results or re-sort them according to specified conditions.

[0070] Automatic pick-up 1609 automatically picks up users who have been previously considered high risk, users with high estimated risk values, or users who exceed the limits set in standard setting 1603, and makes it possible to display their work status individually. Also, if necessary, the range can be narrowed down by business establishment selection 1610 and user selection 1611. Also, display order setting 1612 makes it possible to change the sort key settings and user display order.

[0071] The individual document report 1613 presents a summary of the labor type, labor situation, risk estimation, etc. for each set business establishment or user. The data list 1614 displays a list of data to be narrowed down.

[0072] With the above settings, it is possible to display detailed work status 1615 including the occurrence status of near misses for each user in the individual display section, to switch the target establishment or user name, to display periods before and after the target period, etc. It is also possible to display the labor index distribution 1616 and work ratio 1617 of the target establishment or user. It is also possible to generate a written trend report 1618 summarizing the relevant establishment or user.

[0073] As described above, according to this embodiment, by statistically analyzing the labor conditions that lead to accident risks for each labor type and analyzing the labor characteristics for each labor type, it is possible to reduce the burden on managers, provide easy-to-interpret advice for improving operation plans, avoid labor conditions that lead to accident risks, and efficiently optimize labor plans. [Example]

[0074] In the first embodiment, an example is described in which a manager or the like analyzes the labor characteristics of a target business establishment or the entire area and improves labor management and operation plans. In the second embodiment, an example is described in which an individual user can check their own labor characteristics, and a manager can check the labor status of a specific individual.

[0075] Fig. 17 is a flowchart showing an example of processing performed by the individual labor characteristics analysis unit 126 in this embodiment. Note that this flow uses some of the various indices and results generated in the overall labor characteristics analysis described in the first embodiment, and therefore is executed, for example, following the overall labor characteristics analysis process shown in the flowchart in Fig. 2, or after the overall labor characteristics analysis, at a predetermined timing when an individual user (such as a driver) or a manager requires analysis.

[0076] <Step S1700> By entering the specified user information and issuing the individual labor characteristics analysis command, the individual labor characteristics analysis is started.

[0077] <Steps S1701 and S1702> The individual labor performance data (individual labor performance information) of the designated user is acquired according to the set labor indicator items and stored in a specified storage unit (database), and various individual labor indicators such as on-duty time, driving time, and loading and unloading time for each specified period such as daily, weekly, or monthly are generated.If there are additional indicators such as individual user's vital measurement indicators, individual biological information such as VAS, individual incident information including incident information, and individual subjective information, individual additional indicators are generated and merged with the individual labor indicators.

[0078] <Step S1703> A labor characteristics aggregation model obtained by analyzing a large-scale database including multiple business locations and users is introduced, and the data of individual users is compared with existing labor types analyzed using overall data, and the labor type that is closest to the data of the individual user is selected from the existing labor types and classified.

[0079] <Step S1704> Individual labor data is analyzed individually to determine the labor status of individual users and estimate risks such as near misses, based on the relationship between labor indicators and labor risks for classified labor types.

[0080] <Step S1705> Individual analysis results are compared with overall trends and distributions, and individual labor conditions are summarized to provide individual feedback reports, etc. For example, a report is presented that specifically identifies labor risks along with a fact-based summary such as, "User A has recently been working mainly on ultra-long-distance transportation. Monthly driving time exceeds 150 hours. Compared to all drivers, this length of driving time is in the top 5%. There is a tendency for labor risks to increase due to long driving hours, so caution is required."

[0081] 18 is a diagram showing an example of the presentation screen of the labor management system in this embodiment. In user settings 1801, an individual's user ID and other information are set, enabling access to the individual's labor data. Age, gender, authentication code, and other information can also be set as necessary.

[0082] Indicator settings 1802, it is possible to set or change the indicators you want to access. Other data linkage 1803 allows linkage with VAS information and biometric data, and also makes it possible to display other linked device information and data. Display settings 1804 allow various screen displays, ranges, items, etc. Individual document report 1805 displays individual document reports. Comparison with overall 1806 makes it possible to compare individual data with overall trends.

[0083] In the graph display section 1807, each item is displayed using each setting section and on-screen adjustment button. For example, it is possible to display details of an individual's work status within a specified period, fluctuations over time in specified indicators, and the proportion of work content. It is also possible to present estimated results of risks in today's work and alerts indicating whether or not caution is required. In addition, it is possible to present analyzed labor status, labor type, short-term and long-term trends, points requiring caution, advice, etc. in a document report 1808 for individuals.

[0084] As described above, according to this embodiment, individual users (drivers) can check their own work characteristics, etc., and managers of users (drivers) can check the work status of specific individuals as power users of this system. [Example]

[0085] In this embodiment, a modified example of the analysis process of labor characteristics performed by the labor characteristics analysis unit 124 in the first embodiment will be described. This embodiment is an alternative to the analysis process method shown in Fig. 10, and is suitable for cases where the accumulated large-scale labor data includes multiple business establishments with various different labor types.

[0086] Due to the diversity of labor practices at each business location, analyzing the entire large amount of accumulated labor data can make it difficult to grasp labor characteristics and risk trends. On the other hand, analyzing the labor characteristics of all business locations individually can result in a huge amount of analysis, and the analyzed trends can become too individualized to the characteristics unique to each business location.

[0087] Therefore, in this embodiment, we first consider overall labor characteristics and classify labor types into several types by system according to actual work performance. Then, we verify the validity and interpretability of the classified labor types, adjust the classification labor indicators (mainly long-term labor indicators) and classification model to be used as needed, and determine the specific labor types to be used in the analysis. We then perform a stratification analysis on the determined labor types, compare risk factors between groups according to each labor type, and analyze the relationship between labor indicators and incidents within the group, thereby identifying labor factors that increase the incidence of incidents.

[0088] FIG. 19 shows a processing flowchart of this embodiment. <Step S1901> As in step S1001 of Figure 10, a basic analysis is performed on the labor index data (Figure 7) to understand the actual labor situation and analyze whether the set labor standards (such as maximum driving hours and working hours per month) are being met.

[0089] <Step S1902> Systematically classify labor types based on labor index data (mainly long-term labor indexes). Labor type classification is performed automatically using methods such as decision trees, machine learning, and clustering.

[0090] <Step S1903> The validity of the labor characteristics for each labor type classified in step S1902 is analyzed, and it is confirmed whether there are any problems with the classification results in step S1902. This confirmation process may be performed automatically by the labor characteristics analysis unit 124 based on predetermined rules, or the classification results may be presented to the user and the user's judgment accepted. If there are no problems with the classification results (Yes in FIG. 19), proceed to step S1904. If there are any problems (No in FIG. 19), return to step S1902 and adjust the classification model by changing the classification conditions (number of categories, indexes used for classification, etc.), repeating this process until valid classification results are obtained. The labor type classification model may be periodically re-trained and updated in response to changes in the business characteristics of the business establishment being analyzed and the increase in collected data.

[0091] An example of labor type classification in this modified example is shown in Figure 20. Here, based on monthly labor indicators that reflect the actual labor conditions of drivers over a long period of time, labor is classified into four types: M1 (group with regular fixed work schedules), M2 (group with regular rotating shifts), M3 (group with regular fixed shifts and long loading and unloading hours), and M4 (group with irregular long-term operation).

[0092] <Step S1904> Comprehensive analysis is performed by stratifying each labor type, comparing risks between labor types, analyzing the correlation between each labor indicator within a labor type and the objective variable (incident), identifying highly correlated risk factors, and extracting trends.

[0093] The comprehensive analysis in this step can be performed from various perspectives. For example, Figure 21 shows an example in which labor types are stratified, labor indicator factors highly correlated with incident occurrence for each labor type are identified, and the risk of incident occurrence according to fluctuations in labor conditions is displayed. Here, for each classified labor type, the correlation between each labor indicator within the labor type and the incident occurrence rate is confirmed, and labor factors that increase the incident occurrence rate depending on the labor type are identified. Then, in analyzing the correlation between each labor indicator and the incident occurrence rate, the labor indicators are divided into appropriate subgroups, and the incident occurrence rate for data within the corresponding labor conditions is calculated. In addition, fluctuations in the incident occurrence rate are analyzed in accordance with changes in the value of each labor indicator, and the presence or absence of a strong correlation and its trend are analyzed.

[0094] For example, for the labor type M1, which involves fixed, regular shifts, an increase in monthly driving hours, an increase in monthly driving distance, insufficient (short) intervals between shifts, and an earlier monthly start time for work (early morning shifts) are considered to be factors that increase the incident rate. Furthermore, for the labor type M4, which involves irregular, long-duration driving, an insufficient interval between shifts and late arrivals to work are considered to be factors that increase the incident rate. In particular, a significant insufficiency in intervals between shifts (less than eight hours) has been observed, resulting in a sharp increase in the incident rate. For drivers who operate irregular, long-duration driving, ensuring sufficient rest time is extremely important for risk reduction. For each labor type, an alert such as "Caution Required" may be displayed when a high incident rate is observed, based on the actual working conditions.

[0095] Furthermore, as shown in FIG. 22, the labor characteristics and average risk of each labor type may be analyzed and the summary may be compiled in a table.

[0096] Labor types can be classified for each driver and each business location based on labor data accumulated over a long period of time. Figure 23A shows an example of classification results for each driver, and Figure 23B shows an example of classification results for each business location. Labor types for each business location and driver are confirmed, and their labor characteristics are analyzed. Specifically, labor types for each work day and over the long term (month) are aggregated, the proportion of each labor type is calculated, and the labor type with the highest proportion for each business location and driver is designated as the labor type that represents the work content (representative labor type). When confirming the representative labor type for each business location and driver, a percentage threshold (e.g., 50%) can be set, and if no labor type exceeds the threshold, the representative labor type can be determined as indeterminate. Furthermore, changes in the work content and work types can be monitored and compared according to changes in these labor types over time.

[0097] Additionally, the incident occurrence status of each business office and each driver is checked according to each classified representative labor type. As shown in Figure 23A, labor types vary depending on the driver, and even for the same driver, the labor type may change depending on the time period. Furthermore, as shown in Figure 23B, there are differences in labor types between business offices, and between drivers within the same business office. Furthermore, by presenting these analysis results in accordance with the management authority of the user using this labor management system, it is possible to provide more appropriate labor management feedback.

[0098] Figure 24 shows an example of the change in a driver's labor type over time. In January 2024, the driver primarily worked regular, fixed shifts (M1). However, due to busy periods, the driver's labor type changed to irregular, long-distance driving (M4) from the end of January through February. As such, even the same driver's labor type may change over time. By presenting the associated labor characteristics and associated risk factors according to the driver's labor type, labor management appropriate to the actual labor situation can be provided. Furthermore, when the labor type changes, advice can be provided to the driver or manager, such as changes in the items requiring attention due to unusual work or the need for more caution due to unfamiliarity. In this way, the time-series fluctuations and proportions of work content and / or labor type can be analyzed in accordance with the time-series fluctuations for each business establishment and / or worker, and labor characteristics tailored to typical labor types can be presented, along with the presence or absence of changes in labor type. This process may be performed by the individual labor characteristics analysis unit 126.

[0099] Furthermore, labor indicators highly correlated with risk and risk estimation may be selected according to the labor type classified for each business establishment and each worker. Figure 25 shows an example of setting labor indicators highly correlated with risk according to labor type. Based on the results of identifying factors highly correlated with incident occurrence for each labor type shown in Figure 21, highly correlated labor indicators that meet certain criteria, such as those with a correlation coefficient of 0.8 or higher with the incident occurrence rate, are selected, and related risk (labor) factors for each labor type are set. Labor indicators highly correlated with the corresponding risks are compared according to the labor type classified for each business establishment and each worker shown in Figures 23A, 23B, and 24. Furthermore, detailed labor conditions are used to determine whether the corresponding labor indicators meet high risk thresholds and whether a warning alert is issued. Furthermore, for workers or business establishments with uncertain labor types or limited data, a common risk indicator may be used for judgment. Furthermore, as shown in FIG. 25, in addition to determining whether or not a high-risk condition applies, the incident occurrence rate may be estimated based on multiple labor indicators using techniques such as decision trees and multiple regression.

[0100] Figure 26 shows various analyses of the monthly labor characteristics (individual labor performance information) of a specific worker based on the risk factors for each labor type shown in Figure 25. In the example shown in the figure, monthly labor indicators highly related to risk are selected for user ID 1023, and risk-related indicators and deviations from thresholds are extracted. Specifically, the number of incidents (occurrences), interval time (rest time, hours), estimated incident rate (occurrences / day), whether or not monthly operating hours exceeded the threshold (140 hours) (Yes: 1 / No: 0), whether or not interval time fell short of the threshold (9 hours) (Yes: 1 / No: 0), whether or not on-duty time exceeded the threshold (Yes: 1 / No: 0), and whether or not departure occurred earlier than the threshold time (Yes: 1 / No: 0) are displayed. In this way, by extracting and displaying the work status for each user, outputting the deviation from the threshold, and outputting the estimated risk, the manager can plan a work schedule while taking into consideration the incident occurrence rate for that user. Note that this process may be performed by the individual work characteristics analysis unit 126.

[0101] <Step S1905> The overall distribution, correlation / trend, risk estimation model, labor type classification model, etc. obtained in the comprehensive analysis in step S1904 above are saved in a labor characteristic aggregation model in the storage device, and this analysis process ends (S1906).

[0102] As explained above, according to this embodiment, the labor performance information is classified into predetermined labor types based on labor indicators for a predetermined period, and the correlation between the labor indicators and the incident information is analyzed according to the labor type. Therefore, even in cases where the large amount of accumulated labor data includes multiple business establishments with different labor types, appropriate analysis can be performed. [Explanation of symbols]

[0103] 10: Network 20: Labor performance information collection device 30: In-vehicle information collection device 40: Biometric information collection device 50: Subjective information collection device 100: Labor management system 110: Processor 120:Memory 130: Storage device 140: Input / output device 150:Communication equipment

Claims

1. A labor management system, a data acquisition unit that receives labor performance information including the daily working hours or work content of the laborer and incident information including whether or not an accident occurred during the laborer's work; a labor index generation unit that generates a labor index for each predetermined period from the labor performance information; a labor characteristic analysis unit that analyzes the correlation between the labor index generated by the labor index generation unit and the incident information; a labor characteristic presentation unit that presents labor characteristics including the correlation analyzed by the labor characteristic analysis unit; A labor management system comprising:

2. The labor management system according to claim 1, A labor management system characterized in that the labor performance information is labor information related to driving work, and the incident information includes information on incidents that occur during driving.

3. The labor management system according to claim 1, A labor management system characterized in that the labor index generation unit generates the labor index based on items defined in labor-related laws and guidelines.

4. The labor management system according to claim 1, A labor management system characterized in that the labor index generation unit generates an extended labor index including the average value, variance value, deviation value, and relative ratio of each labor index for each specified period.

5. The labor management system according to claim 1, A labor management system characterized in that the labor characteristics analysis unit analyzes the labor characteristics for each labor type classified based on the labor status of the worker.

6. The labor management system according to claim 1, A labor management system characterized in that the labor characteristics analysis unit classifies the labor performance information into specified labor types based on the labor indicators for each specified period, and analyzes the correlation between the labor indicators and the incident information according to the labor type.

7. The labor management system according to claim 6, A labor management system characterized in that the labor characteristic analysis unit identifies labor index factors that are highly correlated with incident occurrence for each classified labor type, and presents the risk of incident occurrence according to changes in labor conditions.

8. The labor management system according to claim 6, The labor management system is characterized in that the labor characteristics analysis unit analyzes the time-series fluctuations and proportions of work content and / or labor type for each business establishment and / or worker, and presents labor characteristics that match representative labor types and whether or not there is any fluctuation in labor type.

9. The labor management system according to claim 6, A labor management system characterized in that the labor characteristics analysis unit selects labor indicators that are highly correlated with risk and estimates risk according to the labor types classified for each business establishment and / or each worker.

10. The labor management system according to claim 1, The labor characteristics analysis unit further has a learning unit, and when the correlation is equal to or greater than a predetermined threshold, the learning unit performs learning using the labor performance information for each labor indicator for the specified period as an explanatory variable and the incident information for the specified period as a target variable, thereby generating a risk estimation model.

11. The labor management system according to claim 1, Further comprising an individual labor characteristics analysis unit, The data acquisition unit receives individual labor performance information of the laborer to be analyzed and individual incident information indicating whether or not an incident occurred during the labor of the laborer, The labor index generation unit generates an individual labor index for each predetermined period for each laborer from the individual labor performance information, A labor management system characterized in that the individual labor characteristic analysis unit analyzes the correlation between the individual labor index generated by the labor index generation unit and the individual incident information.

12. The labor management system according to claim 11, The labor management system is characterized in that it has a storage unit that stores the individual labor performance information.

13. The labor management system according to claim 11, A labor management system characterized by outputting, upon reception from a user, the results of an analysis of the correlation between the individual labor indicators of the target laborer and the individual incident information.

14. A labor management method in a labor management system, The labor management system includes a data acquisition unit, a labor index generation unit, a labor characteristic analysis unit, and a labor characteristic presentation unit, a step of receiving, by the data acquisition unit, labor performance information including the laborer's daily working hours or labor content, and incident information indicating whether or not an incident occurred during the laborer's work; generating a labor index for each predetermined period from the labor performance information by the labor index generating unit; a step of analyzing a correlation between the generated labor index and the incident information by the labor characteristic analysis unit; a step of presenting a labor characteristic including the correlation by the labor characteristic presenting unit; A labor management method comprising:

15. Computer, a data acquisition unit that receives labor performance information including the daily working hours or labor content of a laborer and incident information indicating whether or not an incident occurred during the laborer's work; a labor index generation unit that generates a labor index for each predetermined period from the labor performance information; a labor characteristic analysis unit that analyzes the correlation between the labor index generated by the labor index generation unit and the incident information; a labor characteristic presentation unit that presents labor characteristics including the correlation analyzed by the labor characteristic analysis unit; A program to function as a

Images