Work suitability estimation system and work suitability estimation method

Abstract

To estimate the propriety degree of a worker by a work propriety degree estimation system while taking a mental burden as an internal element of the worker into consideration.SOLUTION: A work propriety degree estimation system has: a mental burden estimation part which generates a mental burden estimation value by estimating the mental burden on a worker; a work detail estimation part which estimates work details of the worker; a work propriety estimation part which estimates work propriety of the worker based upon the mental burden estimation value and the work details to generate a work propriety degree; and a work improvement plan generation part which generates a work improvement plan based upon the work propriety degree and the mental burden estimation value.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a work suitability estimation system and a work suitability estimation method.

Background Art

[0002] In order to improve work efficiency and reduce errors, for example, there may be a case where it is desired to determine the suitability of each work of a worker and appropriately send an instruction according to the suitability of the work being executed.

[0003] Patent Document 1 discloses an aptitude determination and personnel allocation system characterized by "using a performance index based on work accuracy, speed, stability, and rhythm" as a problem that "it is difficult to use only the processing time of each work as an index for human ability (proficiency) for each work." Thereby, the assignment of each worker to each work can be appropriately determined based on the performance index.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In a conventional system such as Patent Document 1, the determination of the suitability of a worker for each work is determined from external elements that occur when the work is executed, such as the speed of the execution time, the correctness of the work order, and the small number of mistakes. In order to determine the suitability of work using such external elements, a value that should be a standard for distinguishing the suitability for each element is required.

[0006] Conventional systems calculate this by collecting data from highly skilled workers with a high level of proficiency in the task. In other words, conventional systems make it possible to quantitatively compare how smoothly a task was performed compared to a highly skilled worker with a high level of proficiency.

[0007] However, the assessment of work suitability does not include the internal factors of the worker when performing the task. Internal factors refer to the mental burden and fatigue level experienced by the worker. The problem here is that work suitability based on external factors does not necessarily coincide with work suitability based on internal factors.

[0008] For example, if a worker is extremely focused, they may be able to complete even a difficult task without making mistakes and within the required time, but this will increase their mental burden. In such cases, even if they can perform better than required in the short term, it is possible that work efficiency will decline in the long term.

[0009] Furthermore, even for tasks where the worker is highly suitable, there are cases where they may not be able to perform to the required level depending on their physical condition or mental fatigue. In such cases, the risk of performance decline can be detected in advance from internal factors, but it is impossible to detect it from external factors until it becomes apparent.

[0010] Thus, conventional systems determine the suitability of a task based on external factors observed during its execution, making it difficult to detect the mental burden on the worker, the resulting long-term risks, or potential problems that may occur during the task.

[0011] Based on the above challenges, there is a need for technology that determines the suitability of each task by including the internal burden on the worker as a judgment factor, and that determines the suitability of the task from a perspective that more closely matches the worker's subjective experience.

[0012] The objective of the present invention is to estimate a worker's suitability for a task by taking into account the mental load, which is an internal element of the worker, in a work suitability estimation system. [Means for solving the problem]

[0013] A work suitability estimation system according to one aspect of the present invention is characterized by comprising: a sensing data acquisition unit that acquires the worker's biological data and the worker's work data; a mental load estimation unit that estimates the worker's mental load based on the biological data and generates a mental load estimate value; a work content estimation unit that estimates the worker's work content based on the work data; a work suitability estimation unit that estimates the worker's work suitability based on the mental load estimate value and the work content and generates a work suitability score; and a work improvement proposal generation unit that generates work improvement proposals based on the work suitability score and the mental load estimate value. [Effects of the Invention]

[0014] According to one aspect of the present invention, the estimation system can estimate the suitability of a worker by taking into account the mental load, which is an internal element of the worker. [Brief explanation of the drawing]

[0015] [Figure 1] This is an overall block diagram of the mental load and work suitability estimation system for the embodiment. [Figure 2] This is a block diagram showing an example of data acquired by the sensing data acquisition unit. [Figure 3] This is a schematic diagram illustrating the estimation of mental stress using biometric data. [Figure 4] This is a schematic diagram of the estimation of Sago content based on work data. [Figure 5] This is a schematic diagram of an example of a work database. [Figure 6] This is a schematic diagram illustrating the estimated mental load at the elemental work unit level. [Figure 7] This is a schematic diagram of an example of a mental stress database. [Figure 8]It is a schematic diagram of an example of a work appropriateness database. [Figure 9] It is a flowchart when outputting warnings for error potentials by level associated with work appropriateness and mental load in Example 1 as work improvement plans. [Figure 10] It is a conceptual diagram when outputting the work order as a work improvement plan in Example 2. [Figure 11] It is a conceptual diagram when outputting the work standard time as a work improvement plan in Example 3.

Mode for Carrying Out the Invention

[0016] The embodiments will be described in detail with reference to the drawings. However, the present invention is not to be construed as being limited to the description of the embodiments shown below. Those skilled in the art can easily understand that the specific configuration can be changed without departing from the spirit or gist of the present invention.

[0017] In the configuration of the invention described below, the same reference numerals are commonly used for the same parts or parts having the same or similar functions among different drawings, and duplicate explanations may be omitted.

[0018] When there are a plurality of elements having the same or similar functions, they may be described by attaching different subscripts to the same reference numeral. However, when it is not necessary to distinguish between the plurality of elements, the subscripts may be omitted in the description.

[0019] Expressions such as "first", "second", "third", etc. in this specification and the like are attached to identify constituent elements, and do not necessarily limit the number, order, or content thereof. Also, the numbers for identifying constituent elements are used for each context, and the numbers used in one context do not necessarily indicate the same configuration in other contexts. Also, it does not prevent a constituent element identified by a certain number from having the functions of a constituent element identified by another number.

[0020] The positions, sizes, shapes, and ranges of each component shown in drawings, etc., may not represent their actual positions, sizes, shapes, and ranges in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, and ranges disclosed in drawings, etc.

[0021] In this specification, elements expressed in the singular form shall include the plural form unless otherwise clearly indicated in the context.

[0022] Here, "elementary work" refers to each unit element when a series of tasks is divided. For example, in the case of assembly work on a production line, these would include "screw tightening," "parts installation," and "inspection." The method and units of division of elemental work are not necessarily fixed and may be adjusted or changed depending on the content of the work being handled.

[0023] Such technologies can be used, for example, to support workers in factory operations. Worker support systems can be used, for instance, in actual assembly work on a production line. An example will be described below with reference to the drawings. [Examples]

[0024] <Overall System Configuration> Figure 1 is an overall block diagram of the mental load and work suitability estimation system of the embodiment. The mental load / work suitability estimation system 1 includes an execution unit 110 and a database 120. The database 120 stores the processing results from past execution units 110, and the execution unit 110 performs processing while referring to the past processing results stored in the database 120.

[0025] The execution unit 110 includes a sensing data acquisition unit 111, a mental load estimation unit 112, a work content estimation unit 113, a work suitability estimation unit 114, a work improvement proposal generation unit 115, and an output unit 116.

[0026] Database 120 includes a work database 121, a mental stress database 122, and a work suitability database 123.

[0027] The mental load / work suitability estimation system 1, which includes the execution unit 110 and the database 120, can be configured using a general-purpose server. The hardware configuration around the server includes an input device, an output device, a processing unit, and a storage device. In this embodiment, functions such as calculation and control are realized by the processing unit executing a program stored in the storage device, thereby cooperating with other hardware to perform the defined processes, and only this functional block is shown in Figure 1.

[0028] The above configuration may be made up of a single server, or any part of the input device, output device, processing device, and storage device may be made up of other computers connected via a network.

[0029] Figure 2 is a block diagram showing an example of data acquired by the sensing data acquisition unit 111. The sensing data acquisition unit 111 consists of sensors for acquiring biometric data 11 necessary for the mental load estimation unit 112 and work data 12 necessary for the work content estimation unit 113.

[0030] For acquiring biometric data 11, one or more types of sensors capable of measuring the worker's internal state, such as electroencephalographs, heart rate monitors, and blood pressure monitors, can be selected. Other options include cameras that can record video, electromyographs, and glasses-type sensors capable of measuring eye movements.

[0031] The following explanation uses an example combining electroencephalography (EEG), heart rate, and gaze as biometric data 11. For acquiring work data 12, one or more types of sensors capable of capturing the worker's movements, such as first-person perspective video or posture / skeletal sensors, can be selected. Furthermore, if the types and order of elemental tasks to be performed are known in advance, that information can be directly acquired as work data 12.

[0032] Furthermore, the sensing data acquisition unit 111 may acquire biometric data 11 and work data 12 from the wearable sensor while the worker, who is fitted with the wearable sensor, is performing a task that includes multiple elemental tasks. The following example will use a first-person perspective video as the work data 12.

[0033] The mental load estimation unit 112 receives biometric data 11 from the sensing data acquisition unit 111 and past mental load information of the same worker from the mental load database 122 of the database 120, and transmits the estimated mental load to the work suitability estimation unit 114 and the work improvement proposal generation unit 115, respectively. It also stores the estimated mental load information in the mental load database 122 of the database 120.

[0034] The work content estimation unit 113 receives work data 12 from the sensing data acquisition unit 111 and transmits the estimated work content to the work suitability estimation unit 114 and the work improvement proposal generation unit 115, respectively. It also stores the estimated work content information in the work database 121 of the database 120.

[0035] The work suitability estimation unit 114 receives information on mental load from the mental load estimation unit 112 and information on work content from the work content estimation unit 113, and estimates the latest work suitability based on past work suitability scores for the relevant worker and task stored in the work suitability database 123 of the database 120. It transmits the newly estimated work suitability to the work improvement proposal generation unit 115. It also updates the work suitability database 123 of the database 120 using the estimated work suitability.

[0036] The work improvement plan generation unit 115 receives information on mental load from the mental load estimation unit 112, work content from the work content estimation unit 113, and work suitability from the work suitability estimation unit 114. Based on past work information for the relevant worker and work stored in the database 120, it generates a work improvement plan optimized for the current state of the worker.

[0037] Examples of work improvement proposals optimized for the current state of workers include suggesting new work methods that reduce worker errors, lessen workload, and improve work efficiency, as well as informing workers of points to be aware of in their current work methods.

[0038] The output unit 116 receives the work improvement proposal generated by the work improvement proposal generation unit 115, determines the format in which to output the proposal, and transmits the output content to an output device installed on a server or the like. The output format may be, for example, audio, video, images, or a combination of multiple formats. The target of the output unit is the worker actually performing the work or the supervisor at the work site.

[0039] <Work content estimation unit> Figure 3 is a schematic diagram of mental load estimation using biometric data 11. The biometric data 11 consists of values ​​measured by each biosensor, extracted as time-series features. Figure 3 shows an example in which an electroencephalograph, heart rate monitor, and eye-tracking sensor are attached to a worker, and the measurement values ​​for each are acquired by the sensing data acquisition unit 111. The acquired measurement values ​​can be used directly as features, or features can be extracted separately using a feature extractor trained through supervised learning. When multiple measurement values ​​are acquired as shown in Figure 3, the measurement values ​​can be combined to create a new single feature.

[0040] Using the extracted features, the mental load estimation unit 112 estimates the mental load over time. The mental load estimation unit 112 can be configured, for example, as a deep neural network (DNN) and trained using supervised learning.

[0041] <Mental load estimation part> Figure 4 is a schematic diagram of work content estimation using work data 12. Work data 12 is extracted as time-series features based on values ​​measured by each work sensor. In Figure 4, a wearable camera capable of recording first-person perspective video is attached to the worker's head, and the sensing data acquisition unit 111 acquires the first-person video. Features are extracted from the acquired first-person video using a pre-trained video feature extractor. When multiple measurements are acquired, the measurements may be combined to create a new single feature.

[0042] Using the extracted features, the work content estimation unit 113 estimates the type of work and the work time for each elemental work. The work content estimation unit 113 can be configured as, for example, a deep neural network (DNN) and trained using supervised learning.

[0043] The work content estimated by the work content estimation unit 113 is stored in the work database 121 of the database 120. Figure 5 is a schematic diagram of an example of a work database.

[0044] In the example in Figure 5, the database is managed in a table format, and for each record, the record ID, worker name, task name, task start time, and estimated task order and duration for each elemental task are stored as data. The record ID is used to distinguish each measured task. Since each elemental task may appear multiple times within the overall task, the estimated task order and duration are stored as a list.

[0045] <Work Suitability Estimation Unit> Figure 6 is a schematic diagram of estimated mental load at the elemental work unit level. Based on the time-series mental load estimated by the mental load estimation unit 112 and the work type and work time at the elemental work unit level estimated by the work content estimation unit 113, the time-series estimated mental load values ​​are divided at the elemental work unit level, and the mental load for each is extracted.

[0046] The final estimated mental load is determined based on the time-series mental load data for each extracted elemental task unit and the past mental load data for the same worker stored in the mental load database 122 of database 120. The average value of the extracted mental loads can be used as the final value, but depending on the worker, there may be a tendency for the estimated mental load to be generally high or generally low.

[0047] Therefore, for example, the average value of the extracted mental load is compared with the average value of the mental load of all records of the same worker stored in the mental load database 122, and the final mental load value is calculated by standardizing the average value of all records to 50. As a result, even if a worker has a generally high or low mental load, the average value of that worker's mental load is treated as the median value of 50, making it possible to calculate mental load without bias for each worker.

[0048] Figure 7 is a schematic diagram of an example of a mental stress database. In the example in Figure 7, the database is managed in a table format, and for each record, the ID and order of the element task to be measured, the minimum value, maximum value, mean and variance of the estimated mental stress, and the final mental stress value are stored as data.

[0049] In the example in Figure 7, the standardized final mental load value is calculated by comparing the minimum, maximum, mean, and variance of the estimated mental load with the accumulated records of the same worker in the past.

[0050] The work suitability estimation unit 114 updates the work suitability scores for each element task stored in the work suitability database 123 to the latest state, based on the final mental load value for each element task estimated by the mental load estimation unit 112 and the work content estimation unit 113.

[0051] Figure 8 is a schematic diagram of an example of a work suitability database. In the example in Figure 8, the database is managed in a table format, and for each record, the worker's name, element work name, work suitability, and estimated number of times are stored as data. The work suitability is determined based on the mental load calculated by the mental load estimation unit 112.

[0052] As shown in the example in Figure 7, when the final mental load value is standardized to a value between 0 and 100, one method for calculating work suitability is to subtract the final mental load value from 100. If a record already exists for the same worker and elemental task combination, that is, if a previously calculated work suitability already exists, the record is updated by overwriting the existing record. In this case, the update is based on the past work suitability, the number of work measurements, and the newly estimated work suitability. Note that the method for calculating work suitability is not limited to the method described above, and other calculation methods that achieve a similar effect may be used.

[0053] In the example in Figure 8, the work suitability score is updated by taking the average of all previously estimated work suitability scores. In this case, the magnitude of the update to the work suitability score decreases as the number of estimations increases. Therefore, it may be better to periodically reset the record for each worker to reflect the worker's latest work suitability score, or to update the work suitability score using the results of up to the most recent N estimations (where N is a natural number).

[0054] <Work improvement plan generation section / output section> Figure 9 is a flowchart illustrating the process of outputting warnings about error potential at different levels associated with work suitability and mental stress, as work improvement suggestions.

[0055] Based on the current mental load estimated by the mental load estimation unit 112 and the work suitability of the relevant elemental task estimated by the work suitability estimation unit 114, the error potential, which indicates the likelihood of the worker making errors or mistakes while performing the current task, is estimated, and a warning is issued in advance. In the example in Figure 9, the warning level is divided into three stages, and the system constantly estimates which stage of the warning level the worker belongs to based on the suitability of the elemental task being performed and the current state of mental load.

[0056] In the example in Figure 9, work suitability and mental load are estimated on a scale of 0 to 100. A work suitability score of less than 30 indicates low work suitability, and a mental load score greater than 70 indicates high mental load. If neither low work suitability nor high mental load applies, the warning level is estimated to be 0; if one of them applies, the warning level is estimated to be 1; and if both apply, the warning level is estimated to be 2. Depending on the estimated warning level, the output unit will issue an audio alert to the worker. The output unit may also output video, images, or a combination thereof, in addition to audio.

[0057] At warning level 0, the error potential is low, and no warning is issued to the operator by the output unit. At warning level 1, the error potential is moderate, and the output unit issues a warning to the operator once. The warning may include a simple warning sound, or it may include pre-registering points prone to errors in each elemental task in the work database 121 and verbally informing the operator of this information.

[0058] At warning level 2, the error potential is high, and mistakes could occur at any time. The output unit should continuously provide alerts to raise awareness, and depending on the nature of the work, it may also suggest taking a break.

[0059] According to Example 1, while a worker equipped with a wearable sensor is performing a task that includes multiple elemental tasks, it becomes possible to estimate the worker's work content and the mental burden during that task, thereby estimating the worker's suitability for each elemental task, focusing on the worker's internal state.

[0060] This allows for a constant monitoring of a worker's error potential by combining their mental stress level with their suitability for the task. It also makes it possible to warn workers in advance when they are in a state where they are likely to make mistakes or where their work efficiency may decrease. [Examples]

[0061] Example 1 describes a method for outputting error potential alerts at different levels as work improvement suggestions by combining mental load and work suitability. By utilizing the implementation methods of the mental load estimation unit 112, work content estimation unit 113, and work estimation suitability unit 114 in Example 1, it is possible to consider a method for outputting the optimal work sequence as a work improvement suggestion for each worker.

[0062] Figure 10 is a conceptual diagram of how work sequences are output as work improvement proposals. Even for a series of tasks that combine similar elemental tasks, differences in the order of tasks can lead to different mental burdens on the worker.

[0063] In the example in Figure 10, when repeating multiple elemental tasks, worker 1 found that performing the same elemental tasks together resulted in a lower estimated average mental load for each elemental task, while worker 2 found that repeating a series of tasks resulted in a lower estimated average mental load for each elemental task. Similar to worker 2, worker 3 also found that repeating a series of tasks resulted in a lower estimated average mental load for each elemental task, but unlike worker 2, the average mental load decreased further when the order of elemental tasks A and B was reversed.

[0064] In this way, the differences in mental load when the work order is different can be compared using past estimated values ​​stored in the mental load database 122 of database 120. The work improvement proposal generation unit 115 calculates the work order that causes the least mental load for the worker from all the work order patterns that have been measured in the past, and proposes it to the worker in the output unit 116. In the example in Figure 10, the output unit proposes work order (1) to worker 1, work order (2) to worker 2, and work order (3) to worker 3.

[0065] According to the embodiment 2 described above, for a worker who performs the same task multiple times in different orders, the mental load estimation unit 112 estimates the mental load at each execution, and by comparing the magnitude of the mental load at each execution, the work improvement plan generation unit 115 creates an optimal work order plan for the worker for the same task, which is then output by the output unit 116. [Examples]

[0066] Example 1 describes a method for outputting error potential alerts at different levels as work improvement suggestions by combining mental load and work suitability. By utilizing the implementation methods of the mental load estimation unit 112, work content estimation unit 113, and work estimation suitability unit 114 in Example 1, it is possible to consider a method for outputting the optimal estimated work time for each worker as a work improvement suggestion.

[0067] Figure 11 is a conceptual diagram of how estimated work times are output as work improvement proposals. For tasks where standard estimated work times are set for each element of work, it is possible to update the estimated work time according to the worker's suitability for the task. Tasks with high suitability are likely to be completed in a shorter time than the standard time, while tasks with low suitability are likely to be completed in a longer time than the standard time.

[0068] Therefore, based on the standard estimated work time for each elemental task, the estimated time for tasks with a high level of suitability will be shortened, and the estimated time for tasks with a low level of suitability will be lengthened to allow more time to be allocated to them. In this way, the overall estimated work time will be updated.

[0069] In the example in Figure 11, for each worker, the average suitability score for the entire task is calculated from the suitability score for each element task. A score above the average suitability score is judged as high suitability, and a score below the average suitability score is judged as low suitability. For sets of tasks where the suitability score is high or low compared to the average, weighting is applied to each task by considering two factors: the ± of the suitability score from the average, and the standard estimated work time.

[0070] Depending on the weighting, the target work time is reduced by 5% in sets with higher than average accuracy, and extended by 5% in sets with higher than average accuracy. The 5% value for reduction and extension of the total work time is adjustable. In this way, the work improvement plan generation unit 115 generates an optimized target work time for each worker, and the output unit 116 notifies the worker by voice or image, enabling the worker to perform the work with a time allocation that is more suitable for them.

[0071] According to Embodiment 3, for a worker performing a task for which a standard work time has been set for each elemental task, the work improvement proposal generation unit 115 creates an optimal work time for the worker based on the mental load estimated by the mental load estimation unit 112 and the work suitability estimated by the work suitability estimation unit 114, and outputs this to the output unit 116.

[0072] In the above embodiment, the sensing data acquisition unit acquires biometric data and work data of a worker performing a task that includes multiple elemental tasks, and estimates the mental load, which is the worker's internal burden. The mental load estimation unit estimates the mental load from the biometric data acquired by the sensing data acquisition unit.

[0073] Using the mental load estimated by the mental load estimation unit and the past work suitability scores for the relevant elemental tasks stored in the database, the work suitability estimation unit generates optimized work improvement plans for each worker based on the work suitability score for each elemental task and the current mental load.

[0074] According to the above embodiment, by combining information on work suitability and mental load, it becomes possible to provide warnings about potential mistakes and errors based on past work suitability information and current mental state, as well as to present optimized work time estimates for each worker.

[0075] Furthermore, by comparing the mental burden on the same worker when they perform tasks in different order, it is possible to suggest the optimal work order for each worker. [Explanation of Symbols]

[0076] 1. Mental Load and Work Suitability Estimation System 110 Execution Unit 120 databases 111 Sensing data acquisition unit 112 Mental load estimation section 113 Work Content Estimation Department 114 Work Suitability Estimation Unit 115 Work improvement plan generation department 116 Output section 121 Work Database 122 Mental Stress Database 123 Work Suitability Database

Claims

1. A sensing data acquisition unit that acquires the worker's biometric data and the worker's work data, A database for storing past work information for the aforementioned worker, The processing device includes a mental load estimation unit that estimates the mental load of the worker based on the biological data and generates a mental load estimate value, The processing apparatus includes a work content estimation unit that estimates the work content of the worker based on the work data, The processing device includes a work suitability estimation unit that estimates the current work suitability of the worker based on the estimated mental load, the work content, and past work information stored in the database, and generates a work suitability score. The processing device includes a work improvement proposal generation unit that generates a work improvement proposal optimized for the current state of the worker based on the work suitability, the estimated mental load, and past work information stored in the database, An output unit that outputs the aforementioned work improvement proposal, A work suitability estimation system characterized by having the following features.

2. The aforementioned work includes multiple component tasks, The work content estimation unit is determined by the processing device, The work order of multiple elemental tasks and the work time for each elemental task are estimated. The mental load estimation unit is controlled by the processing device, For each of the aforementioned elemental tasks, the estimated mental load is generated, The work suitability estimation unit is determined by the processing device, The work suitability estimation system according to claim 1, characterized in that it generates the work suitability score for each of the aforementioned elemental tasks.

3. The sensing data acquisition unit is, The work suitability estimation system according to claim 1, characterized in that it acquires the biometric data and work data while the worker is performing the work using a wearable sensor attached to the worker.

4. The aforementioned work improvement proposal generation unit is controlled by the processing device, Based on the aforementioned suitability for the task and the estimated mental load, the error potential that may occur during the current task is predicted for each level for the worker currently performing the task. The output unit is, The operator is presented with warning information corresponding to the level of the error potential. The aforementioned work improvement proposal generation unit is controlled by the processing device, The work suitability estimation system according to claim 1, characterized in that it predicts the error potential for each level by determining whether the work suitability and the estimated mental load each exceed a predetermined threshold.

5. The output unit is, The work suitability estimation system according to claim 4, characterized in that the worker is presented with warning information, such as cautionary information or information regarding a suggestion to take a break.

6. The aforementioned work improvement proposal generation unit is controlled by the processing device, Based on the estimated mental load, determine the optimal sequence of the elemental tasks for the worker. The output unit is, The work sequence is proposed to each of the aforementioned workers. The aforementioned work improvement proposal generation unit is controlled by the processing device, The work suitability estimation system according to claim 2, characterized in that, for workers who perform the same task multiple times in different work sequences, the work sequence with the smallest estimated mental load is determined as the optimal work sequence for the worker by comparing the magnitude of the estimated mental load for each work sequence.

7. The aforementioned work improvement proposal generation unit is controlled by the processing device, For each elemental task for which a standard work time is set, the worker performing the task is given the optimal work time for that worker as a work guideline based on the work suitability. The output unit is, The estimated work time is proposed for each worker. The aforementioned work improvement proposal generation unit is controlled by the processing device, For each worker, the average suitability score for the entire task is calculated from the suitability score for each element task. If the average suitability is above the above, the work suitability is determined to be high. If the average suitability is below the above-mentioned level, it is determined that the work suitability is low. The work suitability estimation system according to claim 2, characterized in that it shortens the estimated work time for tasks with a high degree of work suitability and extends the estimated work time for tasks with a low degree of work suitability to generate the estimated work time as the work improvement plan.

8. The output unit is, The work suitability estimation system according to claim 1, characterized in that it outputs the aforementioned work improvement proposals in the form of audio, video, or images.

9. A method for estimating work suitability using a work suitability estimation system having a processing unit, a database for accumulating past work information for workers, and an output unit, A sensing data acquisition step in which the worker's biometric data and the worker's work data are acquired by a sensor, The processing apparatus performs a mental load estimation step, which involves estimating the mental load of the worker based on the biological data and generating a mental load estimate value, The processing apparatus performs a work content estimation step of estimating the work content of the worker based on the work data, The processing device performs a work suitability estimation step, which estimates the current work suitability of the worker based on the estimated mental load, the work content, and past work information stored in the database, and generates a work suitability score. The processing device performs a work improvement plan generation step, which generates a work improvement plan optimized for the current state of the worker based on the work suitability, the estimated mental load, and past work information stored in the database. The output step includes outputting the work improvement proposal to the output unit, A method for estimating work suitability, characterized by having the following features.

Images