JP2022064458A - Alert issuing method, alert issuing program, and alert issuing system - Google Patents

Abstract

To provide a method for issuing a labor management alert using a server having an employee ID holding unit that holds one or more employee IDs in association with one business operator ID.SOLUTION: An alert issuing method implemented using a computer includes: accepting input of attendance information including working hours of a predetermined working period in association with an employee ID; recording the accepted attendance information in association with the employee ID; determining the necessity of alert issuing related to labor management of a business operator specified by one business operator ID based on attendance information associated with a plurality of recorded employee IDs; and issuing an alert depending on determined contents.SELECTED DRAWING: Figure 4

Description

The present invention relates to a system for supporting labor management of small and medium-sized enterprises, sole proprietors and other businesses who do not have sufficient knowledge about labor, methods and programs for operating the system, and the like.

The importance of labor management of the workers employed is increasing day by day for businesses. The reasons for this are the revision of various legal systems that have been promoted in the name of work style reform, and the need for non-uniform labor management for each worker against the backdrop of the widespread use of flexible work styles.

Businesses are required to appropriately adopt and operate labor management methods that are suitable for the changing environment, and at the same time, they must confirm whether such methods are being operated appropriately and change them as necessary. Businesses with inadequate labor management not only bear various labor risks with regulatory agencies and workers, but are also evaluated as "black companies" and "rigid companies", which is negative in the market. It also carries the risk of working.

Therefore, conventionally, various techniques related to a system for efficient and objective labor management using a computer have been disclosed. For example, Patent Document 1 discloses a technique relating to a device for analyzing information on the operation history and operation time of an employee's terminal during working hours and calculating the time when the employee was truly working.

JP 2014-178907

However, the prior art described in Patent Document 1 is a technique that cannot be applied to workers whose business content is only to operate the terminal in an environment where the operation time of the terminal can be grasped. There was a bias in the types of jobs, business types, and working styles that could be done. In addition, because the technique was aimed at monitoring whether or not the worker was engaged in work, the repulsion of workers was expected, and it was hard to say that the technique was widely accepted.

In order to solve the above problems, the present invention is a labor management alert issuing method using a server having an employee ID holding unit that holds one or more employee IDs in association with one business ID. There is an attendance information input acceptance step that accepts input of attendance information including working hours of a predetermined working period in association with one employee ID, and attendance information that records the accepted attendance information in association with the employee ID. Alert judgment to determine whether or not to issue an alert related to labor management of the business operator specified by the one business operator ID based on the recording step and the attendance information associated with the recorded multiple employee IDs. We propose an alert issuing method that realizes the step and the alert issuing step that issues an alert according to the judgment content of the alert judgment step using a computer.

In connection with the above method, the Employee ID Holding Department also retains the employee's employment conditions in association with the employee's employee ID, and the alert determination step also uses the employee's employment conditions. We also propose an alert issuing method that has an employment condition usage judgment sub-step to determine whether or not an alert is issued.

Further, in relation to each of the above methods, an incident recording step for recording labor management incident information, which is incident information related to labor management, is further provided, and an alert determination step requires an alert to be issued using the labor management incident information as well. We also propose an alert issuing method that has an incident usage judgment sub-step to judge whether or not to use it.

Further, in relation to each of the above methods, the alert determination step further includes a trained model utilization sub-step for determining whether or not an alert is issued by using attendance information, a business operator ID, and a trained trained model. And so on.

As a method of generating the trained model used here, an information acquisition step for acquiring training data including a business ID, working hours of one or more employees, labor management incident information, and the training data. Based on the information input acceptance step that accepts the input of the business ID and multiple attendance information, and the content is to output the identification result that identifies the labor management incident information corresponding to the business identified by the business ID. We also propose a model generation step to generate a trained model, and a method characterized by realizing the processing on a computer.

Further, in relation to each of the above methods, the alert issuing step also proposes an alert issuing method for issuing an alert in a different mode according to the determination content of the alert determination step.

It also has an alert performance recording step that records the alert performance information, which is information including the content of the alert issued in the alert issuing step and the fact of the issuing, in association with the business operator ID, and the alert determination step is the recorded alert. We also propose an alert issuing method that has a performance utilization sub-step to determine whether or not an alert is issued using the performance information.

Then, we also propose a program for realizing each method described so far on a computer and a system using the method.

The present invention, which mainly has the above-mentioned structure, not only facilitates labor management according to the type of job, business type, and working style of the worker, but also makes it easier for the worker to carry out labor risks that he / she did not notice. It will be possible for the business operator to detect this as soon as possible.

The figure which shows the outline of the alert issuing system of this invention. The figure which shows an example of the functional block of the alert issuing system of Embodiment 1. The figure which shows another example of the functional block of the alert issuing system of Embodiment 1. The figure which shows still another example of the functional block of the alert issuing system of Embodiment 1. Schematic diagram showing an example of the configuration when the functional configurations of the alert issuing system of the first embodiment are collectively realized as one piece of hardware. The figure which shows an example of the processing flow in the alert issuing system of Embodiment 1. The figure which shows an example of another flow of the process in the alert issuing system of Embodiment 1. The figure which shows an example of still another flow of the processing in the alert issuing system of Embodiment 1. The figure which shows an example of the functional block of the alert issuing system of Embodiment 2. The figure which shows an example of the process flow about the generation of the trained model used in the alert issuing system of Embodiment 2. The figure which shows an example of the processing flow in the alert issuing system of Embodiment 2.

First, FIG. 1 is shown. FIG. 1 is a diagram showing an outline of the present invention, in which terminals A2 to A6 operated by workers working inside the office of company A and a server A1 that manages them are connected by an internal network and work outside the office. It shows how the terminals B1 to B4 operated by the worker are connected by a network. All workers working inside and outside the office record the start of their work by operating the terminals they manage when starting working hours. The server A1 manages the attendance information of each worker, and by acquiring various information such as working hours, it is possible to issue an alert based on a predetermined rule. By adopting such a mechanism, not only the labor management of individual workers but also the labor risk that Company A wants to avoid is grasped and managed in advance, and measures for appropriate countermeasures are considered in advance. Will be easier.

Hereinafter, each embodiment of the present invention will be described with reference to the drawings. First, the mutual relationship between the embodiment and the claims is as follows. First, the first embodiment mainly corresponds to claims 1, 2, 3, 5, 6, 8, 9, and the like. The second embodiment mainly corresponds to claims 4, 7, and the like.

It should be noted that the present invention is not limited to these embodiments, and has various technical ideas as described in each claim in accordance with common general technical knowledge and does not deviate from the gist thereof. It can be carried out in an embodiment.

<< Embodiment 1 >>
<Overview>
FIG. 2A is a diagram showing an example of a functional block when the contract conclusion method of the present embodiment is realized by one system. As shown in the figure, the "alert issuing system" 0200 of the present embodiment includes an "employee ID holding unit" 0201, an "attendance information input reception unit" 0202, and an "attendance information recording unit" 0203. , "Alert determination unit" 0204 and "Alert issuing unit" 0205.

The alert issuing system described in detail below may be configured to realize one or more functions of the functions by a plurality of devices, and the functional blocks thereof are all hardware or software. Can be realized as. Taking a computer as an example, CPU, main memory, GPU, TPU, image memory, bus, secondary storage device (hardware and non-volatile memory), keyboard and operation buttons, touch panel, electronic for touching touch panel Various input devices such as pens, microphones, thermometers, time recorders, speakers, displays and other various output devices, hardware components such as other external peripheral devices, interfaces for the external peripheral devices, communication interfaces, and their hardware. Driver programs and other application programs for controlling the memory can be mentioned.

These devices may be used only within one business establishment, may be used across a plurality of business establishments, or may use a mobile terminal used by an employee. In other words, it is often necessary to grasp the employment status of those who work outside the business, such as employees, sales staff, remote work employees, etc. who work at multiple business establishments managed by one business operator. The invention can also be applied to such situations.

Then, by arithmetic processing according to the program expanded on the main memory of each device, the data input from the input device or other interface and held in the memory or hardware can be processed and accumulated, or the above-mentioned hardware can be processed and stored. Instructions for controlling hardware and software are generated. Here, the above program may be realized as a plurality of modularized programs, or may be realized as one program by combining two or more programs. Of course, distributed processing may be performed in the form of cloud computing, or execution processing may be performed by a plurality of programs provided across a plurality of businesses in the form of API linkage.

<Functional configuration>
The "employee ID holding unit" 0201 is configured to hold one or more employee IDs in association with one business operator ID. The employee ID may be unique information such as the employee's name if it is not specially managed like a subcontractor, but like a full-time employee, the employee is concerned from the viewpoint of labor and other matters in advance. In the case of managing a person, it is conceivable that the ID (employee number, etc.) given at the time of the management is used as the employee ID.

The employee ID is held in association with one business operator ID, and when one business operator has multiple business establishments or does not substantially have a specific business establishment. , A business place ID or the like according to the operating status of the business operator may be separately assigned. One of the benefits of the present invention is to facilitate understanding of labor risks as a business operator through labor management of individual employees linked to one business operator, and the above-mentioned business location ID is used. If you adopt a configuration that also retains, you will be able to receive alerts to understand labor risks at each business location, so by receiving the alerts in a timely manner, you can take effective countermeasures. It will be easier to take.

It should be noted that the employment conditions of the employee may also be configured to be associated with the employee ID of the employee and retained. Specifically, it has a structure that holds different contractual relationships with regular employees, non-regular employees, dispatched workers, part-time workers, business consignments, and other businesses, information such as job titles and job titles, working hours, legal holidays, and paid holidays. Various conditions based on the contractual relationship between the employee and the business operator, such as the number of days of leave granted and the number of days taken and the date, awards and penalties, work evaluation and salary / bonus, years of service (years belonging to the department), and the conditions concerned. It is conceivable to retain the associated information. More specifically, a personnel database managed in the personnel department inside the business operator can be applicable, and by adopting this configuration, comprehensive management of personnel and labor can be facilitated.

The "attendance information input reception unit" 0202 is configured to receive input of attendance information including a predetermined working period in association with one employee ID. Specifically, it is conceivable to receive information from the relevant employee regarding the time stamping of work hours, break times, and leaving hours through the terminal operated by the employee. It is conceivable that the predetermined working hours are acquired through other devices and the input is accepted.

It is desirable that the attendance information is configured to accept the input of the relevant information as appropriate, and the attendance information can be configured so as to be able to cope with subsequent addition / subtraction correction. However, when making additions and subtractions, it is necessary to store the log of the process so that it can be verified ex post facto whether there is a risk of falsification in the process.

Incidentally, the attendance information for which input is accepted may include information regarding the attendance of the employee other than the information regarding the predetermined working hours. Specifically, whether or not there are hours of working hours in the middle of the night and early in the morning and the number of hours, whether or not they work on holidays and the number of hours, whether or not they have paid leave and the number of days they have acquired or have not been used, and whether they leave early or are absent. Some information is directly related to attendance, such as the presence or absence of work and the number of days, and information that can be obtained in relation to attendance, such as body temperature at the time of going to work or starting work, body temperature during breaks and leaving work, and the presence or absence of illness. Etc. can also be included in the attendance information referred to here. By adopting a configuration in which these pieces of information are also combined and acquired, it becomes possible to comprehensively judge the labor risk as a business operator that cannot be estimated only by the time spent by the employee.

The mode of acquisition of information that can be acquired in relation to attendance is not particularly limited. For example, information may be input from an external device such as a digital thermometer via a network, or may be acquired through in-house paid acquisition or application processing to a workflow system for application for absenteeism.

Regarding the timing of acquisition of work information, it is conceivable that the information on the prescribed working hours is acquired at the time of the end of work, the acquisition of breaks, the time of leaving work, etc., but the information such as paid acquisition and absenteeism is special. Since input at the timing of is not expected, it is desirable to have a configuration that accepts input at a timing other than real time, that is, within a certain range. By adopting the configuration that allows flexible information input instead of the strict configuration, as a result, it becomes possible to issue alerts based on the analysis of attendance information that is more realistic.

The "attendance information recording unit" 0203 is configured to record the received attendance information in association with the employee ID. Here, first, by recording the attendance information in association with a specific employee, the attendance information recording unit can be positioned as a configuration for attendance management.

However, here, it is preferable that the acquired attendance information is associated with the employee ID and is recorded in a searchable manner in association with other information of the attribute of the employee. Specifically, information that can be linked to employee IDs such as "regular employees, 20s, men", "sales departments, outside work, women", "X branch offices, managers" is recorded in association with attendance information. Can be considered. By adopting this configuration, for example, "Attendance information of all male employees in their twenties", "Attendance information of all employees working at the X branch", and "Attendance information of employees who have not yet consumed paid leave for one day". It becomes possible to extract attendance information according to conditions such as.

The "alert judgment unit" 0204 determines whether or not an alert is issued related to the labor management of the business operator specified by the one business operator ID based on the attendance information associated with the recorded multiple employee IDs. It is configured to judge.

"Based on attendance information" may be configured to determine, for example, whether or not the recorded attendance information exceeds a predetermined threshold value when the recorded attendance information is quantified. For example, when "whether or not overtime hours exceed 400 hours per month" is set as a threshold, the overtime hours (number of hours exceeding the prescribed working hours) of all employees associated with the business operator ID are predetermined. Whether or not to exceed 400 hours per month is positioned as a rule for determining whether to issue an alert, and each time attendance information is recorded, it is determined according to the rule, and if it is exceeded or is likely to be exceeded. , A configuration that issues an alert is conceivable.

Here, the business operator may decide appropriately whether to issue an alert when it is exceeded or when it is likely to be exceeded, but from the aspect of issuing an alert for proactive measures, it is likely to be exceeded. It is desirable to issue an alert in such cases. Then, various configurations can be considered as to in what case it is judged that "it is likely to be exceeded", and it is possible to appropriately determine it.

Here, in relation to the above aspect, the threshold value can be arbitrarily set by the business operator, or a specific threshold value may be set in advance. The specific structure will be described in detail in relation to the labor management incident information described later.

Further, "based on attendance information" does not determine whether or not an alert is issued based only on the attendance information of one employee. The alert issued based on the attendance information of one employee functions only as a system for labor management of the employee in the first place. However, by adopting the configuration of the present invention that assumes the use of attendance information of a plurality of employees from the beginning, the labor risk of each business establishment or the business operator as a whole becomes apparent instead of the framework of individual labor management. You will be able to contribute to.

Therefore, it is not necessary to particularly limit the selection or identification of a plurality of employee IDs in the case of "attendance information associated with a plurality of employee IDs". For example, it may be targeted at a plurality of employees in a specific business establishment, or it may be targeted at employees of a specific work style (only outside workers and remote workers). In addition, it is possible to adopt a configuration that determines the necessity of issuing an alert using attendance information whose population is various groups such as years of service, job title, and employees whose absenteeism exceeds a predetermined number of days.

Specifically, prior to determining whether or not an alert is issued, the input of conditions for limiting the employees who are the population is accepted, and the attendance information recorded in association with the employee ID that matches the conditions is extracted. After that, it will be decided whether or not an alert is issued.

It is also possible to adopt a configuration in which an incident recording unit is provided as a configuration for recording labor management incident information, which is incident information related to labor management. The "incident information related to labor management" here is, for example, the inter-working interval system (a system that provides a certain rest time between the end of work time and the next start time) and interview guidance by doctors (accumulation of fatigue). Employees who meet the requirements such as being approved are offered to receive interview guidance from a doctor), mandatory paid leave, childcare leave for male employees, etc. It may be set.

Many labor-related figures have upper limits and other thresholds set by laws and guidelines. It is convenient for the business operator to record the threshold value based on such information in advance. In addition, it is preferable to have a configuration in which the information is changed from an external server to the revised information via the network according to the circumstances such as revision of laws and regulations. Not only can the information be updated smoothly without being forced to input, but also the threshold can be set in accordance with the latest laws and regulations, which can contribute to the reduction of labor risk of the business operator.

Here, an example of setting or updating the threshold value will be described. For example, if the average overtime hours of employees at a business establishment exceeds 45 hours per month, the possibility that the penalties stipulated in the Labor Standards Act will be applied to the business will increase. Therefore, when a value such that the average value does not exceed 45 hours (for example, 38 hours, 40 hours, 42 hours, etc.) is set as a threshold value, and it is determined that the threshold value has been exceeded as a result of acquiring attendance information. It is conceivable to set up a rule to determine that an alert should be issued.

In addition, for example, there is information on other businesses such as a business operator operating a similar business in the neighborhood, which was investigated by the Labor Standards Inspection Office in the case where one employee had 46 hours of overtime per month. It seems that the business operator obtains information on judicial precedents such as a court ruling that was ordered to pay damages for neglecting to manage the health of employees who chronically worked overtime for 44 hours per month. There may be cases. By acquiring this information from an external terminal via the network or through input by an expert, it is possible to change the threshold value in the rules that have already been set, or to issue a new alert. A child that sets a threshold is also possible.

For incident information, a uniform threshold value may be applied mechanically to all businesses, or one of a plurality of threshold values may be applied depending on the type of business and business scale. In addition, different thresholds may be set for each business establishment, such as the number of overtime hours specified in the 36 Agreement, or the business operator may set a threshold as its own index without any special legal basis. be. The threshold value can be appropriately changed so that any of these cases can be dealt with.

Up to this point, the configuration in which the necessity of issuing an alert is determined using the attendance information associated with the employee ID working under the business operator specified by one business operator ID has been described. In addition to such a configuration, it is conceivable to adopt a configuration in which the necessity of issuing an alert is determined by using attendance information that is not directly linked to the business ID that can be the destination of the alert. Specifically, it is necessary to issue an alert using the attendance information of employees associated with other businesses identified by a business ID that has the same business type, business type, region, or business scale as the business. A configuration to judge whether or not is conceivable. For example, if the business operator you use runs a small or medium-sized supermarket, in addition to the attendance information of the employees who work for the business, other businesses that also run small and medium-sized supermarkets in the neighboring area Whether or not an alert is issued is determined using attendance information as well. By adopting this configuration, it is issued in a form that confirms that it does not perform labor management that is divergent from other businesses, and that it can confirm that the labor risk is not relatively high. You will be able to catch alerts.

In addition, it is conceivable to use attendance information recorded not by the business operator but by a supervisory authority, an expert, or another third-party organization to determine whether or not an alert is issued. For example, from terminals managed by labor administration consultation counters such as the Labor Standards Inspection Office, Hello Work, and the Industrial Labor Bureau, to reduce labor risks in various forms regardless of guidelines, notifications, or other compulsory measures. In many cases, information such as attendance information, which serves as a model, is output. In addition, specialists such as social insurance labor consultants and lawyers may also output attendance information, etc., which serves as a model for reducing the labor risk of business operators based on their respective knowledge. It is also possible to acquire this information and determine whether or not an alert is issued. By adopting this configuration, it becomes easier to grasp labor risks based on orthodox standards, and it is possible to issue more effective alerts.

Then, in the alert judgment unit, it is conceivable to adopt a configuration in which the necessity of issuing an alert is judged by using the labor management incident information explained so far. Specifically, prior to determining whether or not an alert is issued, it is predicted whether the threshold value set in relation to the predetermined labor management incident information has been exceeded or is likely to be exceeded, and the threshold value has already been exceeded or is likely to be exceeded. Can be configured to issue an alert. By adopting this configuration, it becomes easier to take measures to avoid the risk before being forced into a situation where there is a relatively high labor risk of violating the law.

The "alert issuing unit" 0205 is configured to issue an alert according to the determination content of the alert determination unit. Various specific modes of alert issuance can be considered here, and the management department (executives, representatives, personnel department managers) of the business operator, etc., along with the facts that are the basis for issuing the alert, are sent by e-mail or in-house. It can be realized by a message or other information output mode on the network system. It is conceivable that the alert is issued to the terminal managed by one or more persons in the management department mentioned above, but in addition, it is managed by the social insurance labor consultant who is the adviser of the business operator. A configuration may be adopted in which an alert is issued to a terminal that is used or a terminal managed by an industrial physician. It is desirable that these destinations can be appropriately set and changed according to the content of the alert to be issued. By adopting this configuration, it becomes possible to issue alerts promptly and effectively.

It is conceivable that the alert issuing unit issues an alert in a different mode depending on the judgment content of the alert determination unit. For example, when it is determined that one or more of the threshold values used for determining the alert issuance are to be exceeded, the mode of alert issuance is changed according to the number of the thresholds to be determined to be exceeded (the configuration in which the alert issuance mode is changed. For example, the larger the number of thresholds that are likely to be exceeded, the more alerts will be issued including those with higher positions in the company).

Further, when the judgment result in the alert judgment unit is that the alert is unnecessary, it is desirable that not only the alert is not issued but also the special processing is not performed. While the cost of labor management can be reduced through the present invention, if a configuration is adopted in which some information is output to the business operator indefinitely, the amount of information received by the business operator becomes unnecessarily large, and the time of labor management is rather long. This is because it may lead to an overwhelming situation such as an increase in work volume costs (note that even if information such as a regular labor management report is output at intervals of a predetermined period or longer, such as once a month). Is not intended to exclude).

It should be noted that a configuration in which alerts of different modes are issued depending on the degree of judgment that "it is likely to be exceeded" can be considered. In this case, it is conceivable that an alert will be issued to include persons with higher positions in the company as the risk of exceeding the threshold increases. Configurations can also be combined, and by adopting this configuration, operators can timely share information with experts on labor risks that are often overlooked due to lack of specialized knowledge, and as a result, operators. It will be easier to take measures to reduce overall labor risk.

Here, it is conceivable to further have an alert performance recording unit that records the alert performance information, which is information including the content of the alert issued by the alert issuing unit and the fact of the issuance, in association with the business operator ID. In that case, in the alert judgment, it is conceivable to adopt a configuration in which a performance utilization means for determining whether or not an alert is issued is provided by using the recorded alert performance information as well.

That is, as described above, there are cases where an alert is issued in stages when the threshold is likely to be exceeded, and alerts are issued multiple times in relation to the same or different thresholds. A case can be assumed. In such a case, it is desirable to record the fact of the alert issuance and its contents in advance, and to issue the alert based on the actual results when the alert is issued again. This is because the fact that alerts are issued many times can be judged as evidence that labor risks are becoming apparent, and it is necessary for the business operator to understand and understand that it is in such a situation. This is because it is ready to take more comprehensive measures.

Here, the description of the mode of the alert to be issued is supplemented. First, take the case of acquiring the body temperature of an employee as attendance information as an example. If it is determined that the body temperature of an employee in a certain business establishment is higher than the normal average value by a predetermined percentage or more, there is a possibility that there is a certain percentage or more of employees who have a fever in the business establishment. Concerns, and thus the possibility of transmitting colds, flu, and other infectious diseases, may be a concern. Therefore, it is conceivable to issue an alert to the manager of the business establishment.

And even if it is configured to issue a similar alert even if the change in body temperature of one employee in the same office is higher than the change in body temperature of other employees by a predetermined percentage or more. good. In these cases, depending on the degree of excess from the above-mentioned predetermined ratio, an alert should be issued to the effect that a message urging employees to work from home should be sent, or the content to ventilate the office. It is conceivable to issue an alert. By providing such a mechanism for issuing alerts, it becomes possible to properly manage hygiene in business establishments and avoid labor risks in advance, which may lead to liability for breach of safety consideration obligations.

As another example, it is conceivable to issue an alert when the total overtime hours of all employees in the business establishment is likely to exceed a predetermined threshold. If it is the conventional technique, it seems that the structure was such that an alert for improving the working environment was issued by individually analyzing the overtime working hours of the employees of the business establishment. However, in the present invention, an alert is issued using the attendance information of a plurality of employees. Therefore, in the case of the above example, there may be a problem in the method of business execution or the management of the person in charge at the business establishment. The hypothesis that there is no such thing can be established. The alerts issued there may be not only those related to mental health, but also alerts for considering business improvement for the person in charge, or alerts for reporting the status of business performance.

As described above, in the present invention, it is possible to issue an alert not only by simply acquiring and analyzing quantitative information, but also for an administrator or a manager to perform a qualitative evaluation. It is characterized by being able to do it.

Regarding the judgment of whether or not to issue an alert, which has been explained in various ways up to this point, in addition to the case where a rule is held in advance and the judgment is made using the rule, an alert is made using a feature amount obtained through predetermined machine learning. It is conceivable that the issue will be issued, and it is not excluded to adopt either means. The case of using machine learning will be described in detail in the second embodiment.

<Concrete configuration>
Here, FIG. 3 is shown. The figure is a schematic diagram showing an example of the configuration when each functional configuration of the alert issuing system of the present embodiment is collectively realized as one hardware. Each device has a "CPU" 0301, a "storage device (storage medium)" 0302, a "main memory" 0303, an "input interface" 0304, and an "output interface" 0305 for executing various arithmetic processes. , A "network interface" 0306, and transmits / receives information to / from an external peripheral device such as a "touch panel" 0307 or a "display" 0308 via an input / output interface. It also sends and receives information to and from external devices such as the "employee management terminal" 0309 and other "electronic thermometers" 0310 via the network interface. The specific aspect of this network interface may be wired or wireless, and the communication method may be direct or indirect. Therefore, it is also possible to adopt a so-called cloud computing format in which information is transmitted / received between a specific external device or a user of the device and a server managed by a third party associated with the device.

Various programs as described below are stored in the storage device, and the CPU reads these various programs into the work area of the main memory, expands and executes them. It should be noted that these configurations are interconnected by a data communication path such as "system bus" 0399 to transmit / receive and process information (the basic configuration of the above configuration is any of the other devices described below. The same applies to.

(Specific configuration of employee ID holding unit)
The employee ID holding unit is composed of a computer program and computer hardware. Specifically, the CPU reads the "employee ID recording program" 0301 from the storage device into the main memory and executes it, via a network, via a storage medium, or via a keyboard or other input interface. By various methods, the input of the information of one or more employee IDs is received in association with one business ID and recorded in the storage area of the computer.

The employee ID holding unit may also accept addition / subtraction / correction of the employee ID that has been input once, and the employee ID is stored in a predetermined address in the main memory together with those logs.

(Specific structure of attendance information input reception department)
The attendance information input reception unit is composed of a computer program, computer hardware, and more specifically, various input interfaces. Specifically, the CPU reads the "attendance information input reception program" 0302 from the storage device into the main memory and executes it, and accepts the input of attendance information including the working hours of the predetermined working period in association with one employee ID. It is configured as follows.

(Specific structure of attendance information recording department)
The attendance information recording unit is composed of a computer program and computer hardware. Specifically, the CPU reads the "attendance information recording program" 0303 from the storage device into the main memory and executes it, and the attendance information obtained by executing the attendance information input reception program is associated with the attendance information. The employee ID is read from the employee ID holding unit, and both are stored at a predetermined address in the main memory.

(Specific configuration of alert judgment unit)
Specifically, the alert determination unit is composed of a computer program and computer hardware. Specifically, the CPU reads the "alert determination program" 0304 from the storage device into the main memory and executes it, and reads out the attendance information associated with the plurality of employee IDs obtained by executing the attendance information recording program. A process for determining whether or not an alert is issued related to labor management of the operator specified by the one operator ID is performed, and the determination result is stored in a predetermined address in the main memory.

(Specific configuration of alert issuing section)
Specifically, the alert issuing unit is composed of a computer program and computer hardware. Specifically, the CPU reads the "alert issuing program" 0305 from the storage device into the main memory and executes it, reads the determination result obtained by executing the alert determination program, and issues an alert according to the determination result. Specifically, a method of issuing an alert in the form of an email to a predetermined administrator using an e-mail program, or a short message or other format to a predetermined administrator by executing a predetermined in-house SNS program. A method of issuing an alert can be considered.

<Processing flow>
FIG. 4 is a diagram showing an example of a processing flow in the alert issuing system of the present embodiment. The processing flow in the figure consists of the following steps. First, in step S0401, the input of attendance information including the working hours of the predetermined working period is accepted from the employee in association with one employee ID (attendance information input acceptance step). After that, the attendance information received in step S0402 is associated with the employee ID and recorded (attendance information recording step). Then, in step S0403, it is determined whether or not it is necessary to issue an alert related to the labor management of the business operator specified by the one business operator ID based on the attendance information associated with the plurality of recorded employee IDs (alert). Judgment step), and if the judgment result here is that it is not necessary to issue an alert, no further processing is performed. On the other hand, if it is necessary to issue an alert, the process proceeds to step S0404. That is, in step S0404, an alert is issued according to the determination content of the alert determination step (alert issue step).

FIG. 5 is a diagram showing an example of another flow of processing in the alert issuing system of the present embodiment. The processing flow in the figure consists of the following steps. First, in step S0501, input of attendance information including working hours of a predetermined working period is accepted from an employee in association with one employee ID (attendance information input acceptance step). After that, the attendance information received in step S0502 is associated with the employee ID and recorded (attendance information recording step). Then, in step S0503, it is determined whether or not it is necessary to issue an alert related to the labor management of the business operator specified by the one business operator ID based on the attendance information associated with the plurality of recorded employee IDs (alert). Judgment step). Here, it may be configured to determine whether or not an alert is issued by using the employment conditions of the employee (condition use substep), or it is determined whether or not an alert is issued by using the labor management incident information as well. May be good (incident utilization substep). If the judgment result here is that it is not necessary to issue an alert, the subsequent processing is not performed. On the other hand, if it is necessary to issue an alert, the process of step S0504, that is, an alert is issued according to the determination content of the alert determination step (alert issue step).

FIG. 6 is a diagram showing an example of still another flow of processing in the alert issuing system of the present embodiment. The processing flow in the figure consists of the following steps. First, in step S0601, the input of attendance information including the working hours of the predetermined working period is accepted from the employee in association with one employee ID (attendance information input acceptance step). After that, the attendance information received in step S0602 is associated with the employee ID and recorded (attendance information recording step). Then, in step S0603, the business operator specified by the one business operator ID is based on the attendance information associated with the recorded plurality of employee IDs and the previously recorded alert performance information. It is judged whether or not it is necessary to issue an alert related to labor management (results utilization substep), and if the judgment result here is that it is not necessary to issue an alert, no further processing is performed. On the other hand, if it is necessary to issue an alert, the process of step S0604, that is, an alert is issued according to the determination content of the alert determination step (alert issue step). After that, in step S0605, the alert record information, which is information including the content of the issued alert and the fact of the issue (including the presence or absence of the issue), is recorded in association with the business operator ID (alert record record step).

<Effect>
By using the alert issuing system that adopts the above configuration, not only is it easier to manage labor according to the type of job, business type, and working style of the worker, but also the entire business establishment that the business operator did not notice, It will be possible to quickly detect macro-level labor risks such as the entire business.

<< Embodiment 2 >>
<Overview>
The alert issuing system of the present embodiment is basically the same as the technical features of the alert issuing system described in the first embodiment, but alerts are made using attendance information, a business ID, and a learned model. As a further technical feature, it is provided to judge whether or not it is necessary to issue. In the following, the above-mentioned features different from the points mentioned in the first embodiment will be described in detail.

<Functional configuration>
FIG. 7 is a diagram showing an example of a functional block when the alert issuing method of the present embodiment is realized by one system. As shown in the figure, the "alert issuing system" 0700 of the present embodiment includes an "employee ID holding unit" 0701, an "attendance information input reception unit" 0702, and an "attendance information recording unit" 0703. , The "alert determination unit" 0704 and the "alert issuing unit" 0705, and the alert determination unit further includes the "learned model utilization means" 0714. Since the basic configuration is common to the alert issuing system described with reference to FIG. 2 of the first embodiment, the function of the "learned model utilization means" 0714, which is a difference, will be described below.

The "learned model utilization means" 0714 is configured so that the alert determination unit determines whether or not an alert is issued by using the attendance information, the business operator ID, and the learned model. Specifically, by inputting the attendance information associated with the business operator ID into the learned model, it is configured to determine whether or not it is necessary to issue an alert corresponding to the predetermined labor management incident information.

Here, the method of generating the trained model described so far will also be described.

<How to generate a trained model>
The learned model described in the present embodiment includes, for example, an information acquisition step for acquiring training data including a business operator ID, attendance information of one or more employees, and labor management incident information, and the training data. Based on the information input acceptance step that accepts the input of the business ID and multiple attendance information, and the content is to output the identification result that identifies the labor management incident information corresponding to the business identified by the business ID. It is conceivable to generate by processing the model generation step of generating the trained model and the computer.

Here, FIG. 8 is shown. The figure is a diagram showing an example of the flow of the generation method of the trained model used in this embodiment. The processing flow in the figure consists of the following steps. First, in step S0801, training data including a business operator ID, attendance information of one or more employees, and labor management incident information is acquired (information acquisition step). Here, attendance information and labor management incident information can be obtained by separate input receiving means. For example, attendance information is acquired from a server that stores information for labor management managed by the business operator, and labor management incident information is acquired from a server managed by a labor expert.

Training data is used to determine the necessity of issuing an alert in response to a predetermined labor management incident. Therefore, it is necessary that the attendance information constituting the training data also includes the information corresponding to the labor management incident. Specifically, it corresponds to information such as the number of prescribed hours worked hours, the number of absentee days, and the number of holiday attendances of employees in the Ichi office, and these information will be used as learning data.

More specifically, various information constituting the attendance information is subjected to a process of assigning a label corresponding to the labor management incident, and is acquired and held as training data as a whole.

The "information input receiving step" S0802 accepts the input of the business operator ID and a plurality of attendance information based on the training data. By adopting a configuration in which a business ID is acquired so as to be associated with a specific business, the learning model generated in the present invention can be used to determine whether or not an alert is issued according to the business situation of one business. Can contribute to.

The "model generation step" S0803 generates a learned model whose content is to output an identification result that identifies the labor management incident information corresponding to the business operator identified by the business operator ID. As a specific example, in relation to a predetermined labor management incident information, inputting attendance information input in association with a business ID for a given pre-learned convolutional neural network such as GoogleLeNet. Then, a trained model corresponding to the labor management incident information can be generated.

More specifically, it is assumed that the output layer of the convolutional neural network outputs the output values related to the information corresponding to the various attendance information, and is tuned through a predetermined cross entropy error function or the like.

It should be noted that this trained model may be appropriately updated by input from an external management terminal, for example. Specifically, it is the alert performance information that has already been explained, or the content is revised by acquiring appropriate information from a terminal managed by an external expert and performing processing for updating such as tuning. Is possible. By adopting this configuration, it becomes possible to provide a trained model that can be used for determining the necessity of issuing an effective alert that more reflects the internal and external circumstances at that time.

By the way, up to this point, in relation to the means of using the trained model, the configuration for determining the necessity of issuing an alert using the trained model generated in association with one business operator ID has been described. In addition to this, it is also possible to determine the necessity of issuing an alert by using a learned model that is associated with another business ID or associated with a specific industry / business category. Specifically, the judgment result obtained by using the trained model associated with the own business operator ID is compared with the judgment result obtained by using other trained models. For example, it is conceivable to determine whether or not to issue an alert according to the determination result that is determined to have a higher risk in the determination result. As another example, it is conceivable to take the average value of both judgment results and judge the necessity of issuing an alert based on the result. In any case, by adopting a configuration in which a plurality of judgment results are used in combination, it becomes possible to judge whether or not to issue an alert more in line with the actual social situation while paying attention to the characteristics of the business operator.

<Concrete configuration>
The hardware configuration of each device constituting the alert issuing system of the present embodiment is basically the same as the hardware configuration of the alert issuing system of the first embodiment described with reference to FIG. Therefore, the specific processing of the "learned model utilization means" that has not been explained so far will be described below.

(Specific configuration of learned model utilization means)
The trained model utilization means consists of a computer program and computer hardware. Specifically, when the CPU reads and executes the alert judgment program from the storage device to the main memory, the trained model utilization subprogram is read and executed, and the attendance information and business are stored in the trained model stored in the storage device. A process of determining whether or not an alert is issued is performed according to an output result obtained by inputting a person ID, and the determination result is stored in a predetermined address in the main memory.

<Processing flow>
FIG. 9 is a diagram showing an example of another flow of processing in the alert issuing system of the present embodiment. The processing flow in the figure consists of the following steps. First, in step S0901, the input of attendance information including the working hours of the predetermined working period is accepted from the employee in association with one employee ID (attendance information input acceptance step). After that, the attendance information received in step S0902 is associated with the employee ID and recorded (attendance information recording step). Then, in step S0903, it is determined whether or not it is necessary to issue an alert related to the labor management of the business operator specified by the one business operator ID based on the attendance information associated with the plurality of recorded employee IDs (alert). Judgment step). Here, the necessity of issuing an alert may be determined using the attendance information, the business ID, and the learned model (learned model use substep). If the judgment result here is that it is not necessary to issue an alert, the subsequent processing is not performed. On the other hand, if it is necessary to issue an alert, the process of step S0904, that is, an alert is issued according to the determination content of the alert determination step (alert issue step).

0200 ... Alert issuing system, 0201 ... Employee ID holding unit, 0202 ... Attendance information input reception unit, 0203 ... Attendance information recording unit, 0204 ... Alert judgment unit, 0205 ... Alert Origin

Claims (9)

It is a labor management alert issuing method using a server having an employee ID holding unit that holds one or more employee IDs in association with one business ID.
Attendance information input acceptance step that accepts input of attendance information including working hours of a predetermined working period in association with one employee ID,
Attendance information recording step to record the received attendance information in association with the employee ID,
An alert judgment step for determining whether or not an alert is issued related to labor management of a business operator specified by the above-mentioned one business operator ID based on attendance information associated with a plurality of recorded employee IDs, and an alert judgment step.
An alert issuance step that issues an alert according to the judgment content of the alert judgment step,
How to issue an alert using a computer. The employee ID holding department also holds the employment conditions of the employee in association with the employee ID of the employee.
The alert issuing method according to claim 1, wherein the alert determination step further includes a condition utilization substep for determining whether or not an alert is issued by using the employment conditions of the employee. It also has an incident recording step to record labor management incident information, which is incident information related to labor management.
The alert issuing method according to claim 1 or 2, wherein the alert determination step further includes an incident utilization substep for determining whether or not an alert is issued by using labor management incident information. The alert determination step is described in any one of claims 1 to 3, further comprising a trained model utilization sub-step for determining whether or not an alert is issued using attendance information, a business ID, and a trained trained model. How to issue an alert. The alert issuing step is the alert issuing method according to any one of claims 1 to 4, wherein an alert having a different mode is issued according to the determination content of the alert determination step. It also has an alert performance recording step that records the alert performance information, which is information including the content of the alert issued in the alert issuance step and the fact of the issuance, in association with the business operator ID.
The alert issuing method according to any one of claims 1 to 5, further comprising a performance utilization sub-step for determining whether or not an alert is issued by using the recorded alert performance information. An information acquisition step to acquire training data including a business ID, attendance information of one or more employees, and labor management incident information.
Based on the training data, an information input acceptance step that accepts input of a business ID and a plurality of attendance information, and
A model generation step to generate a trained model whose content is to output an identification result that identifies the labor management incident information corresponding to the business operator identified by the business operator ID, and
A method of generating a trained model, which is characterized in that the processing is realized by a computer. A labor management alert issuing program that can be executed on a computer that sends and receives information to and from a server that includes an employee ID holding unit that holds one or more employee IDs in association with one business ID.
Attendance information input acceptance step that accepts input of attendance information including working hours of a predetermined working period in association with one employee ID,
Attendance information recording step to record the received attendance information in association with the employee ID,
An alert judgment step for determining whether or not an alert is issued related to labor management of a business operator specified by the above-mentioned one business operator ID based on attendance information associated with a plurality of recorded employee IDs, and an alert judgment step.
An alert issuance step that issues an alert according to the judgment content of the alert judgment step,
Alert issuing program with. An employee ID holding unit that holds one or more employee IDs in association with one business ID,
Attendance information input reception unit that accepts input of attendance information including working hours of a predetermined working period in association with one employee ID,
The attendance information recording department that records the received attendance information in association with the employee ID,
An alert judgment unit that determines whether or not an alert is issued related to labor management of a business operator specified by the above-mentioned one business operator ID based on attendance information associated with a plurality of recorded employee IDs, and an alert judgment unit.
An alert issuing unit that issues an alert according to the judgment content of the alert judgment step,
Alert issuing system with.

Images