JP2020181538A - Employment support device, employment support method, and employment support program - Google Patents

Abstract

To provide an employment support device and the like that can extract optimal countermeasure information while constantly providing feedback by learning countermeasure information together with result information on an action taken according to the countermeasure information when an abnormality occurs in employment of a person with a disability.SOLUTION: An employment support device includes: an individual information acquisition unit 31 that acquires information about each individual with a disability during employment from a sensor; an information extraction unit 34 that determines whether an employment condition of a person with a disability is normal or abnormal based on the information acquired by the individual information acquisition unit 31, and acquires and outputs countermeasure information for the abnormality from a countermeasure model 332 when it is determined to be abnormal; and a learning model construction unit 32 that constructs a learning model using result information indicating a result of an action taken according to the countermeasure information together with the countermeasure information when the information extraction unit 34 determines that it is abnormal.SELECTED DRAWING: Figure 3

Description

The present invention relates to a employment support device or the like that supports a person with a disability so that he / she can work properly.

Employment of persons with disabilities has become a major social problem, and the current situation is that appropriate work is not possible despite the large number of applicants for employment. Especially in the case of people with disabilities, it is more difficult to detect the effects of changes in their physical condition and emotions on work than in healthy people, and it is necessary to have an administrator who is familiar with disabilities to some extent. There are also problems such as a heavy burden and a shortage of human resources.

Regarding the employment of such persons with disabilities, for example, the technique shown in Patent Document 1 is disclosed. The technique shown in Patent Document 1 stores information on possible work types that a person with a disability can work in a person with a disability information database, and when there is a requested work, the work allocation processing unit stores the information on the person with a disability information database. With reference to the stored possible work types of persons with disabilities, when the requested work matches the possible work types of persons with disabilities, the work is assigned to persons with disabilities.

Japanese Unexamined Patent Publication No. 2003-248719

However, as described above, it is more difficult for persons with disabilities to detect the effects of changes in their physical condition and emotions on labor than those of healthy persons. Therefore, matching with the information database for persons with disabilities as shown in Patent Document 1 is appropriate. There is a problem that it is difficult to assign various tasks.

According to the present invention, when an abnormality occurs in the employment of a person with a disability, the optimum coping information can be extracted while always giving feedback by learning the coping information together with the result information of coping according to the coping information. Provide employment support equipment, etc.

The employment support device according to the present invention has an individual information acquisition means for acquiring information about each individual of a disabled person who is working from a sensor, and the working state of the disabled person based on the information acquired by the individual information acquisition means. The information extraction means that determines whether it is normal or abnormal and acquires and outputs the coping information for the abnormality when it is determined to be abnormal, and the information extraction means when it is determined that the information extraction means is abnormal. It is provided with a learning model construction means for constructing the learning model with result information indicating the result of coping according to the coping information together with the coping information.

As described above, in the employment support device according to the present invention, information on each individual of the disabled person during work is acquired from the sensor, and based on the acquired information, it is determined whether the working state of the disabled person is normal or abnormal. However, when it is determined to be abnormal, the coping information for the abnormality is acquired from the learning model and output, and when it is determined to be abnormal, the result information indicating the coping result according to the coping information is used together with the coping information. Since a learning model is constructed, it is possible to obtain the optimum coping information while constantly giving feedback when an abnormality occurs in the employment of a person with a disability.

It is a hardware block diagram of the employment support system using the employment support device which concerns on 1st Embodiment. It is a hardware block diagram of the employment support apparatus which concerns on 1st Embodiment. It is a functional block diagram which shows the structure of the whole employment support apparatus which concerns on 1st Embodiment. It is a figure which shows the structure of the management database in the employment support apparatus which concerns on 1st Embodiment. It is a figure which shows the structure of the registration processing part in the employment support apparatus which concerns on 1st Embodiment. It is a figure which shows the structure of the coping information extraction part in the employment support apparatus which concerns on 1st Embodiment. It is a flowchart which shows the operation of the employment support apparatus which concerns on 1st Embodiment. It is a figure which shows the structure of the management database in the employment support apparatus which concerns on 2nd Embodiment. It is a figure which shows the structure of the management database in the employment support apparatus which concerns on 3rd Embodiment.

Hereinafter, embodiments of the present invention will be described. In addition, the same elements are designated by the same reference numerals throughout the present embodiment.

(First Embodiment of the present invention)
The employment support device according to the present embodiment will be described with reference to FIGS. 1 to 7. The employment support device according to the present embodiment supports the employment of persons with disabilities, and is particularly difficult for persons with physical disabilities to communicate with, persons with intellectual disabilities, persons with developmental disabilities, persons with mental disabilities who have difficulty in communicating, and persons with mental disabilities. By using machine learning (for example, deep learning), it is possible to allocate appropriate work by AI to persons with disabilities who have multiple mental illnesses.

FIG. 1 is a hardware configuration diagram of a employment support system using the employment support device according to the present embodiment. The employment support system 1 includes a employment support device 10, a sensor unit 11 that senses information about a person with a disability who is a worker, information about a manager who manages the worker, information about a working environment, and the like, and a calculation of the employment support device 10. A display 12 for outputting a result or the like is provided.

The employment support device 10 is a employment recipe model as a learning model that outputs appropriate work information based on employment records when the worker has worked in the past, assuming that the worker is under the control of this device. Has been built. The employment record can include various information about employment such as work that has been performed before and work that is suitable for the work. In addition, a coping model has been constructed as a learning model that outputs appropriate coping information for the abnormality when an abnormality occurs during work. The coping information includes medical information such as the medical history of the person and the characteristics of the disability, and further, if something goes wrong during work, the appropriate coping method, how to take a break, and cautions. It may contain various coping information such as how to eat, how to calm down, and how to calm down.

The sensor unit 11 includes, for example, an image sensor, a temperature sensor, a humidity sensor, a sound sensor, an acceleration sensor, a magnetic sensor, a pressure sensor, a position sensor, various other sensors, and various combinations thereof, and includes heartbeats and blood pressures of workers and managers. , Body temperature, biological information such as voice, position information, movement information, etc. are measured. In addition, if necessary, information on the environment (for example, environmental sound, temperature, humidity, weather, season, sunshine condition, etc.) at the working site is detected. The information measured by the sensor unit 11 is registered in the database of the employment support device 10 and monitored.

When the employment support device 10 determines from the measurement result of the sensor unit 11 that something abnormal has occurred during employment, appropriate coping information is extracted from the coping model and the coping information is taken. The result is fed back to the coping model. That is, the employment support device 10 can always perform machine learning to extract appropriate coping information by AI and deal with it.

As shown in FIG. 1, as result information, external information including daily work report, daily physical condition report / medication report, and information on each individual of the disabled person at work at the workplace is input to the employment support device 10. , It may be reflected in a learning model such as a working recipe model or a coping model.

FIG. 2 is a hardware configuration diagram of the employment support device according to the present embodiment. The computer of the employment support device 10 includes a CPU 21, a RAM 22, a ROM 23, a hard disk (referred to as HD) 24, a communication I / F 25, and an input / output I / F 26. The operating system, program, database, etc. are stored in the ROM 23 and HD 24, and the program is read into the RAM 22 as needed and executed by the CPU 21.

The communication I / F 25 is an interface for performing communication between devices. The input / output I / F 26 is an interface for accepting input from input devices such as a touch panel, keyboard, and mouse, and outputting data to a printer, a display, or the like. The input / output I / F 26 can be connected to a drive compatible with a magneto-optical disk, a removable disk such as a CD-R, a DVD-R, or the like, if necessary. Each processing unit is connected via a bus and exchanges information. The above hardware configuration is just an example and can be changed as needed.

3 to 6 are functional block diagrams showing the configuration of the employment support device according to the present embodiment. FIG. 3 shows the overall configuration of the employment support device. The employment support device 10 constructs a employment recipe model based on past employment record information of various persons with disabilities (hereinafter referred to as employment record information 13), and also handles measures including medical information known in advance before employment. A coping model is constructed using information, coping information acquired during work extracted by the information extraction unit 34 described later, result information 14 indicating the result of coping based on the coping information, and the management database described later. The learning model construction unit 32 stored in 33, the individual information acquisition unit 31 that inputs the measurement results from the sensor unit 11 and registers the measurement results in the management database 33, and the working status and employment status of each worker and manager. A management database 33 that stores the measurement results from the sensor unit 11 regarding the environment and stores the learning model (working recipe model, coping model, etc.) constructed by the learning model construction unit 32, and the measurement results measured by the sensor unit 11. Is monitored to determine the presence or absence of an abnormality, and when it is determined that an abnormality has occurred, an information extraction unit 34 that extracts appropriate countermeasure information for the abnormality from the countermeasure model of the management database 33 and presents it on the display 12 Be prepared. The information extraction unit 34 may extract appropriate work information from the employment recipe model based on the employment record information 13 of an individual with a disability who works and present it on the display 12.

In the management database 33, a employment recipe model that outputs appropriate work information based on the employment record information 13 is constructed and stored before the worker comes under control. The employment recipe model is pre-built by aggregating the past employment records and the opinions of experts of various persons with disabilities other than the person in question. However, there is a possibility that the output results of these employment recipe models alone will not be sufficient, so by accumulating and learning more data while working, more appropriate work can be assigned to workers. Is possible. For example, as a result of monitoring biometric information and work results during work for persons with disabilities who were judged to be suitable for clerical work before work, the heart rate and blood pressure increased. If you are seen and are under strong stress, or if you find that the work is not progressing significantly (abnormality has occurred), some coping information will be extracted (details will be described later for the extraction of coping information). The learning model construction unit 32 can be improved by registering the result information such as that such a person with a disability is not actually suitable for clerical work and what other work is suitable for it. Build a mature working recipe model.

Similarly, for example, when it is determined that a worker is under excessive stress during work, coping information for relieving the stress is acquired from the coping model and presented to the manager. At this time, the coping model constructed by the learning model construction unit 32 based on a large amount of data (so-called big data) collected from the individual information acquisition unit 31 is used to provide appropriate coping information (so-called big data) corresponding to the target person with a disability. For example, "put in work to move the body once an hour", "rehydrate", etc.) are extracted. The administrator executes the coping according to the extracted coping information, and passes the result together with the coping information to the learning model construction unit 32 as the result information. The learning model construction unit 32 can perform more accurate machine learning by accumulating new data and the result.

Here, the configuration of each processing unit will be described in more detail. FIG. 4 is a diagram showing the configuration of the management database 33 in the employment support device according to the present embodiment. The management database 33 includes an individual data storage unit 33a that stores measurement information from the sensor unit 11 in chronological order for each worker, a work recipe model 331 that outputs appropriate work information based on the work record information 13, and work. It is provided with a coping model 332 that outputs appropriate coping information for abnormalities and problems that occur inside.

The individual information acquisition unit 31 acquires the measurement information of the sensor unit 11 at all times, periodically, or irregularly and writes it in the individual data storage unit 33. The information extraction unit 34 refers to the measurement information written in the individual data storage unit 33, and monitors the measurement information. Specifically, it monitors the presence or absence of sudden changes in the biological information, location information, movement information, etc. of workers as described above, and determines that an abnormality has occurred when a sudden change occurs under predetermined conditions. To do. Then, the coping information that seems to be appropriate for the abnormality is acquired from the coping model 332 and presented to the administrator. The extracted coping information is passed to the learning model construction unit 32 together with the result information of the coping (for example, 5-step evaluation showing the result of the coping) and the anomaly information about the occurrence of the coping. The model 332 is updated, and in some cases, the working recipe model 331 is updated.

FIG. 5 is a diagram showing a configuration of a learning model construction unit 32 in the employment support device according to the present embodiment. The learning model construction unit 32 is basically a processing unit that constructs the employment recipe model 331 and the coping model 332, and is the past employment record information 13, result information 14, and information extraction unit 34 of other persons with disabilities. A working recipe model 331 is constructed based on the input unit 32a for inputting the abnormality information and the coping information from the above, the employment record information 13 and the like, and the coping information and the coping information regarding the coping information taken for the abnormality and the coping information. It is provided with a construction unit 32b for constructing a coping model 332 by associating all the result information 14 regarding the coping result according to the above.

Here, regarding the appropriate work information output from the work recipe model 331 based on the work record information 13, when the worker comes under the control of the work support device 10, the work is assigned based on the work memory information 13. Although it is done, this work assignment has been done by experts and managers based on their knowledge and experience. Therefore, although the accuracy of work allocation is appropriate to some extent, it may not always be suitable at the actual work site, which increases the burden on both the worker and the manager. Therefore, by growing the employment recipe model 331 and constantly updating it, more appropriate employment management and work allocation become possible. In particular, based on the employment recipe model 331 constructed first, the employment recipe model 331 is grown and worked by accumulating abnormality information, coping information and result information at the actual environment level and constantly machine learning them. It is possible to assign less burdensome work by a person or an administrator.

FIG. 6 is a diagram showing a configuration of an information extraction unit 34 in the employment support device according to the present embodiment. The information extraction unit 34 reads and inputs the measurement information of the sensor unit 11 stored in the individual data storage unit 33a at all times, periodically or irregularly, and the information extraction unit 34 is based on the input unit 61 and the input measurement information of the sensor unit 11. An abnormality determination unit 62 that determines whether or not an abnormality has occurred in a worker, and a countermeasure model that appropriately responds to the abnormal information by inputting the abnormal information when it is determined that an abnormality has occurred. In addition to acquiring from 332, when a worker starts working, the acquisition processing unit 63 that acquires appropriate work information etc. for the worker from the working recipe model 331 and the acquired coping information and work information are displayed. It is provided with an output control unit 64 that outputs to 12 and presents it to the administrator, and outputs the abnormal information determined by the abnormality determination unit 62 and the acquired coping information to the learning model construction unit 32 in association with each other.

The work information specified by the employment recipe model 331 based on the employment record information 13 is basically presented to the manager, and the work is performed under the manager, but some workers are not the manager. In some cases, it may be better to present the information to someone other than a doctor, caregiver, assistant, or manager of a public institution. That is, the output control unit 64 may appropriately calculate and output the destination to be output according to the content of the work division and the output result of the working recipe model 331. Further, the output destination may be learned, the output destination model may be constructed, and the output destination may be registered in the management database 33.

The abnormality determination unit 62 monitors, for example, the measurement information for each worker stored in time series, and determines that an abnormality has occurred when a sudden change or peak value of a predetermined value or more appears. When monitoring the measurement information, it is desirable to determine the parameters under predetermined conditions in a complex manner as necessary. For example, it is determined that an abnormality such as an angry state or a trouble has occurred when the place is moved due to an increase in blood pressure, instead of simply moving the place. In addition, it is determined that an abnormality such as an extreme tension state has occurred when the voice is raised as the heart rate rises, not only when the voice is raised.

In addition, in order to improve the accuracy of the determination process in the abnormality determination unit 62, the abnormality state may be learned and an abnormality determination model may be constructed in the management database 33. That is, the configuration may include an abnormality determination model that outputs the presence / absence of an abnormal state and the type of abnormality by inputting the measurement information from the sensor.

When the abnormality determination unit 62 determines that an abnormality has occurred, the acquisition processing unit 63 inputs the abnormality information regarding the generated abnormality and acquires the corresponding appropriate countermeasure information from the countermeasure model 332. The acquired coping information is presented to the administrator by the output control unit 64, and the administrator takes coping according to the coping information. For example, when it is determined that an abnormality in a tension state in which the voice rises as the heart rate rises occurs, the heart rate and the frequency of the voice are input, and appropriate measures are taken to deal with such a state. As information, information (may include priority information) such as "change room to relax", "prompt to go out", and "take a restroom break" is presented to the administrator as output. The administrator selects and executes the actual action to be taken from the presented action information. In addition, the acquisition processing unit 63 acquires work information and the like appropriate for the worker from the work recipe model 331 when the worker starts working. The working work is started based on the work information acquired from the working recipe model 331.

The output control unit 64 presents coping information and work information appropriate to the worker to the administrator, and extracts (or informs the administrator) the abnormality information regarding the occurrence of the abnormality in order to update the learning model of the management database 33. The coping information (selectively input) is sent to the learning model construction unit 32 to update the learning model. At the same time, the result information indicating the result of the administrator executing the countermeasure is input to the learning model construction unit 32, and the learning model is updated in association with the abnormality information and the countermeasure information sent from the output control unit 64. By constructing a learning model with these latest data, the learning model will constantly grow and highly accurate information can be acquired.

For example, in the above example, coping information is presented in the order of priority of "1. Change room to relax", "2. Encourage going out", and "3. Take a restroom break", and the administrator actually " 1. Suppose you execute "Change room to relax". As a result, when the tension state is not resolved at all, for example, 1 of the 5-grade evaluation (worst result) is transmitted in association with the above-mentioned abnormality information and coping information, and the learning model is updated. To. As a result, when the same abnormality occurs next time, the above result information is taken into consideration, for example, "1. Encourage going out", "2. Take a restroom break", "3. Change the room to relax". The coping information is presented in the order of priority. That is, since the coping effect was not effective in "1. Change the room to relax", the priority is lowered, and AI will give priority to other coping information and recommend it.

In this way, by constantly updating the learning model with actual coping information and result information and performing machine learning, more appropriate coping information can be extracted and presented.

The information of the individual data storage unit 33a of the management database 33 may be used as the result information. That is, in the case of the above-mentioned five-stage evaluation, the arbitrary opinion of the administrator may be reflected. Therefore, by associating the information of the individual data storage unit 33a as objective data, a more accurate result can be obtained. It becomes possible to make information. In other words, even if the manager evaluates with 5 (best result) on a 5-point scale, if there is no improvement in the condition (biological information, etc.) of the workers dealt with, the evaluation given by the manager is low. It may be possible to make corrections to the other side.

In addition, AI may be used to determine whether or not an abnormality has occurred, and whether or not an abnormality has been effectively dealt with, or it may be determined by an expert or administrator. You may ask your family to make a decision. That is, even if a state that seems abnormal at first glance occurs, it may be judged that it is normal as a normal behavior at home. In such a case, the judgment of the family such as parents, siblings, and children at home may be prioritized. In addition, as a family, you can get a sense of security because you can hear about the working people. The family may be contacted, for example, by taking an image of what seems to be an abnormality in the moving image and sending it, or by verbally communicating it.

Next, the operation of the employment support device according to the present embodiment will be described. FIG. 7 is a flowchart showing the operation of the employment support device according to the present embodiment. As a premise of operation, the base of learning models such as employment recipe model 331 and coping model 332 has been constructed to some extent based on past achievements, and based on the output result of employment recipe model 331, it has already been given to workers. Is assigned work and is actually working. First, individual information such as biological information and working status is measured by the sensor unit 11 for each worker, and stored in the individual data storage unit 33a in chronological order (S1). The abnormality determination unit 62 determines whether or not an abnormality has occurred in the working state based on the information stored in the individual data storage unit 33a (S2). If it is determined that no abnormality has occurred, the working status will be continuously monitored. When it is determined that an abnormality has occurred, the acquisition processing unit 63 acquires appropriate countermeasure information from the countermeasure model 332 based on the abnormal information regarding the abnormal that has occurred (S3). The output control unit 64 outputs the acquired coping information to the display 12 and presents it to the administrator (S4). Further, the output control unit 64 passes the abnormality information regarding the generated abnormality and the acquired coping information to the learning model construction unit 32, and the learning model construction unit 32 updates the coping model 332 (S5). At the same time, the evaluation of the coping with the abnormality performed by the manager and the family is passed to the learning model construction unit 32 as the result information 14, and the learning model construction unit 32 updates the learning model.

The measurement result acquired by the individual information acquisition unit 31 may be passed to the learning model construction unit 32 as objective result information. Further, if necessary, not only the coping model 332 but also the working recipe model 331 may be updated at the same time. That is, if the abnormal state continues for a long period of time, or if it does not improve at all even if various measures are taken, there may be a problem in the work division assigned at the beginning. That is, since the learning of the working recipe model 331 may be insufficient, the working recipe model 331 is updated by using the abnormality information, the result information, the coping information, etc. in order to grow the working recipe model 331. You may do so. Furthermore, it is desirable to constantly update the learning model in order to learn that it is normal even in the normal state, instead of updating the learning model only when an abnormality occurs.

Returning to FIG. 7, it is determined whether or not to continue the management (S6), and if it continues, the process returns to step S1. If it does not continue, the process ends.

As described above, in the employment support device according to the present embodiment, information on each individual of the disabled person during work is acquired from the sensor, and based on the acquired information, whether the working state of the disabled person is normal or abnormal is determined. When it is judged and it is judged to be abnormal, the coping information for the abnormality is acquired from the learning model and output, and the learning model is updated with the result information indicating the result of coping according to the coping information together with the coping information. When an abnormality occurs in a person's employment, it is possible to extract optimal coping information while always giving feedback.

In addition, if necessary, in order to build a learning model that outputs appropriate work information based on information on the previous working condition of the person with a disability before the person with a disability starts working, the past working condition is referred to. , People with disabilities can start working in the most comfortable condition possible.

Furthermore, if necessary, the result information includes the information acquired by the individual information acquisition unit 31 when the response information is dealt with, so that the result information based on the objective information acquired by the sensor is obtained. be able to.

(Second Embodiment of the present invention)
The employment support device according to the present embodiment will be described with reference to FIG. The employment support device according to the present embodiment is based on the employment support device according to the first embodiment, and when an abnormality occurs, the measurement information of the manager at that time and / or the environmental information at the work place are also included. By acquiring and learning at the same time, it is possible to acquire coping information corresponding to an abnormality that has occurred with higher accuracy. In this embodiment, the description overlapping with the first embodiment will be omitted.

FIG. 8 is a diagram showing a configuration of a management database 33 in the employment support device according to the present embodiment. In addition to the configuration of the management database 33 shown in FIG. 4, the manager information storage unit 33c that stores biological information such as heartbeat, blood pressure, body temperature, and voice, position information, and movement information of the manager, and working work. It is provided with an environmental information storage unit 33d that stores information on the environment (for example, environmental sound, temperature, humidity, weather, season, sunshine condition, etc.) at the site. The learning model is the same as the case of the first embodiment, and includes a working recipe model 331 and a coping model 332.

The abnormality determination unit 62 of the information extraction unit 34 determines whether or not an abnormality has occurred based on the information of the individual data storage unit 33a, and when it is determined that an abnormality has occurred, the abnormality is generated together with the abnormality information. The information of the administrator information storage unit 33c and the information of the environment information storage unit 33d at the timing of occurrence are read from the management database 33 and passed to the output control unit 64. Then, when the output control unit 64 passes the abnormality information and the coping information to the learning model construction unit 32, the output control unit 64 also passes the information of the administrator information storage unit 33c and the information of the environment information storage unit 33d. When updating the coping model 332 based on the abnormality information, the coping information, and the result information, the learning model construction unit 32 also registers the information of the administrator information storage unit 33c and the information of the environment information storage unit 33d.

In the present embodiment, as described above, the configuration may have both the administrator information storage unit 33c and the environmental information storage unit 33d, or may have only one of them. When only one of them is provided, the learning of the coping model 332 is also a learning model that considers the information of either one.

The learning model construction unit 32 constructs a learning model in which the information of the administrator information storage unit 33c and / or the information of the environment information storage unit 33d is added in addition to the abnormality information, the coping information, and the result information. The information in the administrator information storage unit 33c is information about the administrator and is not direct measurement information of the worker, but in the case where some abnormality occurs in the worker, it is linked with the behavior and behavior of the manager. I often do it. For example, if the manager pays attention to the mistakes of the worker without consideration, the worker on the side of the attention may be extremely frightened. In such a case, it is necessary to take measures such as devising a method of attention or another measure, and it is possible to acquire appropriate measures information by repeating the above-mentioned machine learning.

The same applies to the information in the environmental information storage unit 33d, and although it is not the direct measurement information of the worker, if any abnormality occurs in the worker, the environment at the work site has an influence. There is. For example, the noise of construction work being done in the neighborhood may make it difficult to concentrate on the work, or the light incident from the window may be too strong to cause a panic. In such cases, it is difficult for even an administrator or expert to identify the cause of the abnormality, but by gaining experience in machine learning, it is possible to take measures that even the administrator or expert will not notice. It will be possible.

In this way, in the employment support device according to the present embodiment, by acquiring the information about the manager who manages the disabled person from the sensor and learning the information about the manager together with the result information, the mentality of the disabled person who is working Machine learning is performed in consideration of the information of the manager who has a great influence on the target and / or physically, and it becomes possible to acquire the coping information more appropriately.

In addition, by acquiring information on the working environment of persons with disabilities from sensors and learning information on the working environment together with the result information, the working environment that can have a significant psychological and / or physical impact on persons with disabilities during work. Machine learning that takes into account information (for example, sound, light, people coming and going, presence or absence of people, etc.) is performed, and it becomes possible to acquire coping information more appropriately.

(Third Embodiment of the present invention)
Hereinafter, other embodiments will be described. In the second embodiment described above, the configuration in which the measurement information of the administrator when an abnormality occurs in the worker is incorporated into the coping model 332 has been described, but in the present embodiment, based on the measurement information of the administrator. It is determined whether or not an abnormality has occurred in the administrator, and if an abnormality has occurred in the administrator, the countermeasure information for the administrator is output. In the field of managing the employment of people with disabilities, the manager himself is liable to get sick and many people quit. Since workers are people with disabilities, they tend to pay attention to the care of people with disabilities, but the care of managers is also extremely important because they work in a unique environment. In this embodiment, the description of overlapping each of the above embodiments will be omitted.

FIG. 9 is a diagram showing the configuration of the management database 33 in the employment support device according to the present embodiment. In terms of configuration, the configuration of FIG. 8 in the second embodiment is different in that the management database 33 is provided with the administrator coping model 333, and the abnormality determination unit 64 performs abnormality determination processing based on the measurement information of the administrator. If it is determined that an abnormality has occurred in the administrator, the handling information for the administrator corresponding to the abnormality is acquired from the administrator handling model 333 of the management database 33 by the acquisition processing unit 63. .. The coping information for the administrator may be presented to the administrator who is experiencing the abnormality, or as described above, it may be presented to the doctor, public institution, the manager's boss, etc. You may.

The learning model construction of the manager coping model 333 is performed by the learning model construction unit 32 as in the case of each of the above-described embodiments. The information used for learning is anomaly information about an abnormality that occurred in the monitor, coping information acquired from the coping model 333 for the administrator, and coping result information, and if necessary, measurement of the worker at the time of the abnormality. Information (information of the individual data storage unit 33a) or environmental information at the working place may be used.

In this way, by constantly monitoring the abnormalities of the manager and taking care of the working condition of the manager, it is possible to bring the environment closer to a comfortable working environment for both the worker and the manager.

In each of the above embodiments, the employment support device may take measures based on the measures information. For example, depending on the type of coping, it is possible to perform it with a employment support device instead of an administrator. Specifically, for example, the output of alerting by voice signal, the output of relaxing music and video, the output of video corresponding to a unique commitment, the output of video, voice, text communication with family, the output of advice for work, etc. Is possible.

1 Employment support system 10 Employment support device 11 Sensor unit 12 Display 13 Employment record information 14 Result information 21 CPU
22 RAM
23 ROM
24 HD
25 Communication I / F
26 I / O I / F
31 Individual information acquisition unit 32 Registration processing unit 32a Input unit 32b Writing unit 33 Management database 33a Individual data storage unit 33b Corresponding information storage unit 33c Administrator information storage unit 33d Environmental information storage unit 34 Corresponding information extraction unit 61 Input unit 62 Abnormality Judgment unit 63 Analysis processing unit 64 Output control unit

Claims (8)

Individual information acquisition means to acquire information about each individual with a disability during work from the sensor,
Based on the information acquired by the individual information acquisition means, it is determined whether the working condition of the person with a disability is normal or abnormal, and if it is determined to be abnormal, the coping information for the abnormality is acquired from the learning model and output. Information extraction means and
Working characterized in that when it is determined that the information extraction means is abnormal, the learning model construction means for constructing the learning model with the result information indicating the result of the coping according to the coping information together with the coping information is provided. Support device. In the employment support device according to claim 1,
The learning model building means is a employment support device that builds a learning model that outputs appropriate work information based on information on the previous working conditions of the person with a disability and / or other persons with a disability before the person with a disability starts working. .. In the employment support device according to claim 1 or 2.
The individual information acquisition means acquires information about the manager who manages the person with a disability from the sensor, and the learning model building means works to build the learning model based on the information about the manager together with the result information. Support device. In the employment support device according to any one of claims 1 to 3,
It is equipped with an environmental information acquisition means for acquiring information on the working environment of the disabled person from a sensor.
A employment support device in which the learning model building means builds the learning model based on the result information and information on the working environment. In the employment support device according to any one of claims 1 to 4,
A employment support device that includes information acquired by the individual information acquisition means when the result information is dealt with according to the coping information. In the employment support device according to claim 3,
The information extraction means determines whether or not an abnormality has occurred in the administrator based on the information about the administrator acquired by the individual information acquisition means, and if it is determined that an abnormality has occurred, the abnormality is dealt with. The coping information for the administrator is acquired from the learning model and output, and when the learning model construction means determines that an abnormality has occurred in the information extraction means, the coping information for the administrator is also included. A employment support device that builds the learning model with result information indicating the result of coping according to coping information. The computer
Individual information acquisition step to acquire information about each individual with a disability at work from the sensor,
Based on the information acquired by the individual information acquisition means, it is determined whether the working condition of the person with a disability is normal or abnormal, and if it is determined to be abnormal, the coping information for the abnormality is acquired from the learning model and output. Information extraction steps and
When it is determined that the coping information extraction means is abnormal, the learning model construction step of constructing the learning model with the result information indicating the result of coping according to the coping information is executed together with the coping information. How to support employment. Individual information acquisition means to acquire information about each individual with a disability during work from the sensor,
Based on the information acquired by the individual information acquisition means, it is determined whether the working condition of the person with a disability is normal or abnormal, and if it is determined to be abnormal, the coping information for the abnormality is acquired from the learning model and output. Information extraction means,
A employment support program that causes a computer to function as a learning model construction means for constructing the learning model with result information indicating the result of coping according to the coping information together with the coping information when it is determined that the coping information extraction means is abnormal. ..

Images