Work recording method, information processing device, and program

Abstract

This work recording method is executed by an information processing device 10 and includes: a step for acquiring environment information related to details of work for a staff member; a step for estimating a plurality of candidates for details of work on the basis of the environment information; a step for presenting the plurality of candidates for details of work; and a step for determining, as details of work for the staff member, details of work selected from the plurality of candidates for details of work.

Description

Work recording method, information processing device, and program CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to Japanese Patent Application No. 2023-187185, filed on October 31, 2023, the entire disclosure of which is incorporated herein by reference.

[0002] The present disclosure relates to a work recording method, an information processing device, and a program.

[0003] Techniques for compiling the work details of staff members have been known for some time. For example, Patent Document 1 discloses a method for dividing a work area where staff members move into small work sections, and recording and compiling the work details by combining the work name with the name of the small work section.

[0004] Japanese Patent Application Laid-Open No. 2003-280726

[0005] Conventional technology records the name of each task combined with the name of each small task area, making it easy to compile the details of tasks and the time spent on them when staff move around a large work area and perform multiple tasks. However, the task of recording the location and details of each task along with the time for each staff member is assumed to be manually entered by the user, and there has been insufficient consideration given to improving the efficiency of the recording process. As such, there is room for improvement in the technology for recording staff work.

[0006] In view of the above circumstances, the purpose of the present disclosure is to improve the technology for recording staff work.

[0007] (1) A work recording method according to one embodiment of the present disclosure is a work recording method executed by an information processing device, and includes the steps of: acquiring environmental information related to the work content of a staff member; estimating a plurality of candidate work content based on the environmental information; presenting the plurality of candidate work content; and determining a work content selected from the plurality of candidate work content as the work content of the staff member.

[0008] (2) A work recording method according to one embodiment of the present disclosure is the work recording method described in (1), wherein the environmental information includes a group of data relating to position information on a facility floor plan, posture information of the staff member, and time information.

[0009] (3) A work recording method according to one embodiment of the present disclosure is the work recording method described in (2), wherein the staff member's posture information includes sensing data acquired from a terminal worn or carried by the staff member.

[0010] (4) A work recording method according to an embodiment of the present disclosure is the work recording method described in (3), further comprising the step of: the sensing data including acceleration information, angular velocity information, and magnetic information.

[0011] (5) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (2) to (4), further comprising the step of: the position information on the facility floor plan includes position information of the staff observed by a beacon placed in the facility.

[0012] (6) A work recording method according to an embodiment of the present disclosure is the work recording method described in any one of (1) to (5), wherein the environmental information includes at least one of staff attendance information and work schedule information.

[0013] (7) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (1) to (6), wherein in the estimating step, the plurality of work content candidates are estimated by inputting the environmental information into a trained learning model that has undergone machine learning to estimate the plurality of work content candidates.

[0014] (8) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (1) to (7), wherein the learning model further outputs an estimated likelihood of each work content candidate, and the order of presentation of the multiple work content candidates is based on the estimated likelihood.

[0015] (9) A work recording method according to an embodiment of the present disclosure is the work recording method described in any one of (1) to (8), in which the number of presented work content candidates is seven or less.

[0016] (10) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (1) to (9), wherein the number of presented work content candidates is determined based on the total value of estimated likelihoods for the plurality of work content candidates.

[0017] (11) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (7) to (10), in which the work content of the staff member determined in the step of determining the work content of the staff member is used as training data to re-train the learning model.

[0018] (12) A work recording method according to one embodiment of the present disclosure is a work recording method described in any one of (1) to (11), in which, when a work content candidate with a predetermined estimated likelihood or higher is changed, an alert is issued by sound or vibration.

[0019] (13) A work recording method according to one embodiment of the present disclosure is a work recording method according to any one of (1) to (12), in which, when a special task or a candidate task content not included in the work schedule information is estimated, an alert is issued by sound and vibration.

[0020] (14) An information processing device according to an embodiment of the present disclosure is an information processing device including a processor, wherein the processor executes the work recording method according to any one of (1) to (13).

[0021] (15) A program according to an embodiment of the present disclosure is a program executed by an information processing device, causing a computer to execute the work recording method according to any one of (1) to (13).

[0022] According to the work recording method, information processing device, and program according to an embodiment of the present disclosure, it is possible to improve the technology for recording staff work.

[0023] Fig. 1 is a block diagram showing a schematic configuration of an information processing device that executes a work recording technology according to an embodiment of the present disclosure. Fig. 2 is a flowchart showing a work recording method according to an embodiment of the present disclosure. Fig. 3 is a flowchart showing an example of a procedure for generating a learning model that estimates work content in the work recording method according to an embodiment of the present disclosure. Fig. 4 is a diagram showing an example of a hierarchical structure of work content. Fig. 5 is a diagram showing an example of a user interface screen output by an information processing device.

[0024] Hereinafter, a work recording technology according to an embodiment of the present disclosure will be described with reference to the drawings.

[0025] In each drawing, the same or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0026] First, an overview of the present embodiment will be described. The work recording technology according to an embodiment of the present disclosure is executed by an information processing device 10. The work recording technology according to an embodiment of the present disclosure can be used, for example, in nursing care, medical care, and other settings. The work in these settings is more diverse than the work in factories, as described in Patent Literature 1, and flexible responses to situations are expected, making the effects of the present invention even more pronounced. Specifically, in the work recording technology according to an embodiment of the present disclosure, the information processing device 10 acquires environmental information related to the work content of staff members and can infer multiple candidate work content from the environmental information. The multiple inferred candidate work content is presented to the user. The user can select an appropriate candidate work content from the presented multiple candidate work content. If the user selects one of the multiple candidate work content, the selected candidate work content is determined as the work content of the staff member. This not only ensures accurate recording of staff members' work content, but also reduces the burden of recording itself, contributing to more efficient recording work.

[0027] Here, "staff" refers to a person who provides care, etc., directly or indirectly to a subject in a caregiving, nursing, medical, or other field. For example, the staff may be a worker, a care manager, or other administrator. Furthermore, "environmental information related to the work content of the staff" refers to any information that can be used to estimate the work content of the staff. Furthermore, the "user" refers to a person who selects an appropriate work content from multiple candidate work content presented in the work recording technology according to an embodiment of the present disclosure. The user may be the staff member themselves or another staff member.

[0028] In this way, according to the work recording technology of this embodiment, when a user records the work content of staff members, the frequency with which the user has to manually input the work content of staff members can be reduced, thereby improving the technology for recording staff members' work.

[0029] A configuration according to an embodiment of the present disclosure will be described below.

[0030] (Configuration of Information Processing Device) Next, each component of the information processing device 10 will be described in detail. The information processing device 10 is any device used by a user. For example, a personal computer, a server computer, a general-purpose electronic device, or a dedicated electronic device can be adopted as the information processing device 10.

[0031] As shown in FIG. 1, the information processing device 10 includes a control unit 11 , a storage unit 12 , an input unit 13 , an output unit 14 , and a communication unit 15 .

[0032] The control unit 11 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a central processing unit (CPU) or a graphics processing unit (GPU), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC). The control unit 11 controls each unit of the information processing device 10 and executes processes related to the operation of the information processing device 10.

[0033] The storage unit 12 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The semiconductor memory is, for example, a random access memory (RAM) or a read-only memory (ROM). The RAM is, for example, a static random access memory (SRAM) or a dynamic random access memory (DRAM). The ROM is, for example, an electrically erasable programmable read-only memory (EEPROM). The storage unit 12 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 12 stores data used in the operation of the information processing device 10 and data obtained by the operation of the information processing device 10.

[0034] The input unit 13 includes at least one input interface. The input interface may be, for example, a physical key, a capacitance key, a pointing device, or a touch screen integrated with a display. The input interface may also be, for example, a sound sensor that accepts voice input, or a camera that accepts gesture input. The input unit 13 accepts an operation to input data used in the operation of the information processing device 10. The input unit 13 may be connected to the information processing device 10 as an external input device instead of being provided in the information processing device 10. Any connection method may be used, for example, a Universal Serial Bus (USB), a High-Definition Multimedia Interface (HDMI) (registered trademark), or Bluetooth (registered trademark).

[0035] The output unit 14 includes at least one output interface. The output interface is, for example, a display that outputs information as a video. The display is, for example, a liquid crystal display (LCD) or an organic electroluminescence (EL) display. The output unit 14 displays and outputs data obtained by the operation of the information processing device 10. The output unit 14 may be connected to the information processing device 10 as an external output device instead of being provided in the information processing device 10. Any connection method, such as USB, HDMI (registered trademark), or Bluetooth (registered trademark), can be used.

[0036] The communication unit 15 includes at least one external communication interface. The communication interface may be either a wired or wireless communication interface. In the case of wired communication, the communication interface is, for example, a LAN (Local Area Network) interface or a USB (Universal Serial Bus). In the case of wireless communication, the communication interface is, for example, an interface compatible with mobile communication standards such as LTE (Long Term Evolution), 4G (4th generation), or 5G (5th generation), or an interface compatible with short-range wireless communication such as Bluetooth (registered trademark). The communication unit 15 receives data used in the operation of the information processing device 10 and transmits data obtained by the operation of the information processing device 10.

[0037] The functions of the information processing device 10 are realized by executing a program according to this embodiment on a processor corresponding to the information processing device 10. That is, the functions of the information processing device 10 are realized by software. The program causes a computer to execute the operations of the information processing device 10, thereby causing the computer to function as the information processing device 10. That is, the computer functions as the information processing device 10 by executing the operations of the information processing device 10 in accordance with the program.

[0038] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-transitory computer-readable media, such as a magnetic recording device, an optical disc, a magneto-optical recording medium, or a semiconductor memory. The program can be distributed, for example, by selling, transferring, or lending a portable recording medium, such as a DVD (digital versatile disc) or a CD-ROM (compact disc read only memory), on which the program is recorded. The program can also be distributed by storing the program in the storage of an external server and transmitting the program from the external server to another computer. The program can also be provided as a program product.

[0039] Some or all of the functions of the information processing device 10 may be realized by a dedicated circuit corresponding to the control unit 11. In other words, some or all of the functions of the information processing device 10 may be realized by the hardware of the information processing device 10 itself.

[0040] Referring to the flowchart of FIG. 2, a work recording method according to one embodiment of the present disclosure is illustrated.

[0041] Step S101: The control unit 11 of the information processing device 10 acquires environmental information related to the work content of the staff member. For example, the control unit 11 acquires position information on a facility floor plan, staff member posture information, and time information. The position information on the facility floor plan can be determined over time, for example, by observing the staff member's position using a beacon placed in the facility, understanding changes in the staff member's walking speed and direction of travel using a device worn or carried by the staff member, and comparing this with the information on the facility floor plan. The information on the facility floor plan requires information on structurally unwalkable areas, such as the layout of the facility's walls. The facility floor plan may be, for example, a wall map. The information on the facility floor plan may also include semantic information on places where staff members perform specific tasks, such as baths and dining rooms.

[0042] Staff posture information can be obtained from sensing data acquired from a device worn or carried by the staff. The sensing data includes acceleration information, angular velocity information, and magnetic information. The staff posture can be obtained from acceleration information and angular velocity information. Angular velocity information may contain drift error, but by using magnetic information in addition, the drift error can be corrected. In addition, environmental information may include information obtainable from nurse call systems, excretion sensors, voice information from nursing record support, IoT vital sign measuring devices, or existing task content estimation software. Including more information in the environmental information makes it possible to understand the subject's situation, the type of support currently required, etc., and the accuracy of task content estimation can be further improved.

[0043] Any method can be used to acquire environmental information. For example, the control unit 11 may use the input unit 13 to acquire sensing data such as acceleration information, angular velocity information, and magnetic information from a device worn or carried by the staff member. The device worn or carried by the staff member may be a smartphone, which can be hung from the neck. To improve accuracy, it is preferable to place the device in close contact with the torso, for example, by placing the device in a chest pocket or by securing it in a smartphone holder around the waist. In addition, the control unit 11 may acquire location information of the device worn or carried by the staff member using a beacon installed in the facility. In addition, the control unit 11 may acquire observation data from sensors installed in the facility as environmental information.

[0044] The control unit 11 uses such environmental information as explanatory variables. For example, the control unit 11 extracts, as explanatory variables, a data group from the past few minutes that is highly relevant to a certain work content. The data group includes at least position information on the facility floor plan and staff posture information at a certain time. In other words, the environmental information used by the control unit 11 may include a data group related to position information on the facility floor plan, staff posture information, and time information. The amount of data in the data group need only be sufficient to estimate the work content that has been performed up to a certain point in time, and is not limited to data from the past few minutes, and may be data from a longer or shorter period of time.

[0045] Step S102: The control unit 11 estimates multiple candidate work content related to the work performed by the staff member up to that point based on the environmental information. For example, the control unit 11 may generate a learning model as shown in the flowchart of FIG. 3 and estimate multiple candidate work content by inputting the environmental information acquired in step S101 into this trained learning model. In the example of FIG. 3, the control unit 11 acquires previously acquired environmental information related to the staff member's work content (step S201) and the work content performed by the staff member at that time (step S202). The control unit 11 generates a work content estimation model using the acquired environmental information and work content as training data (step S203). The learning model may be, for example, a machine learning model based on a decision tree. Examples of machine learning models based on decision trees include, but are not limited to, Light GBM and XGBoost. Alternatively, the learning model may be a model generated based on a machine learning algorithm such as a convolutional neural network (CNN), a recurrent neural network (RNN), or other deep learning algorithms.

[0046] In terms of ease of selection for the user, the number of estimated task content candidates (posting number) can be set to 7 or less, preferably 5 or less. The number of postings of task content candidates estimated using such a learning model can be set to a preferable number in terms of ease of selection for the user.

[0047] The estimated work content candidates may be selected from a work classification table that classifies the work content into large, medium, and small, for example, according to the granularity of the work content. The work content may be classified into multiple hierarchical categories as illustrated in FIG.

[0048] In the example of Figure 4, the work content performed by staff members is divided into three hierarchies: major, medium, and minor. A major category may include at least one medium category. A medium category may include at least one minor category. In other words, the number of categories belonging to the minor category is the largest, and the number of categories belonging to the medium category is smaller than the number of categories belonging to the minor. The number of categories belonging to the major category is even smaller than the number of categories belonging to the medium category.

[0049] The major categories may be categories that classify the work performed by staff members by type of service. The major categories may include, for example, caregiving, nursing, rehabilitation, nursing support, food and nutrition, indirect work, common work, other work, or non-work. The major categories may include measurement error as a category to classify work performed by staff members that cannot be classified into any other category. The major categories are not limited to these examples and may include various categories.

[0050] The intermediate categories may be divisions that classify the work performed by staff members according to the purpose or situation of the work. The intermediate categories may include, for example, getting up or going to bed, changing positions, dressing and grooming, moving users, excretion, eating, cleanliness, environmental maintenance, laundry, going out, recreation, transportation, medical treatment, drug management, vital sign measurement, examination, and direct intervention on physical functions. They may also include physical therapy, occupational therapy, speech-language-hearing therapy, care plans, nutritional management, meals, hygiene management, staff movement, meetings, office cleaning, understanding users or patients, information sharing, record-keeping, confirmation, dealing with visitors, other services, other tasks, and breaks.

[0051] The intermediate categories may include, for example, categories belonging to the major category of caregiving, such as waking up or going to bed, changing positions, dressing and grooming, moving the user, toileting, eating, cleaning, environmental maintenance, laundry, going out, recreation, or transportation. Furthermore, categories belonging to the major category of nursing may include medical treatment, drug management, vital sign measurement, examination, or direct intervention on physical functions. Categories belonging to the major category of rehabilitation may include physical therapy, occupational therapy, or speech-language-hearing therapy. Categories belonging to the major category of care support may include care plans. Categories belonging to the major category of meals and nutrition may include nutritional management, meals, and hygiene management. Categories belonging to the major category of indirect tasks may include staff transportation, meetings, or office cleaning. Categories belonging to the major category of common tasks may include understanding the user or patient, sharing information, record-keeping, confirmation, dealing with visitors, or other services. Categories belonging to the major category of non-work may include breaks.

[0052] A subcategory may be a division that more specifically classifies the work performed by staff.

[0053] The minor categories may include, for example, the categories belonging to the medium category of getting up or going to bed include assistance with getting up or assistance with going to bed. The categories belonging to the medium category of changing positions may include changing positions or adjusting recline. The categories belonging to the medium category of changing clothes and grooming may include assistance with changing clothes or assistance with grooming. The categories belonging to the medium category of user mobility may include wheelchair guidance, walking assistance, transfer assistance, or standing assistance. The categories belonging to the medium category of excretion may include excretion assistance, diaper changing, or hand washing assistance. The categories belonging to the medium category of eating may include eating assistance, drinking assistance, serving food, clearing the table, or cooking assistance. The categories belonging to the medium category of cleanliness may include bathing assistance, foot bathing assistance, washing assistance, wiping, genital cleaning, oral care, earwax removal, nail clipping, shaving, hair washing, hand washing assistance, or gargling assistance. Categories belonging to the environmental maintenance major category may include changing sheets, collecting trash, cleaning rooms, checking users' belongings, adjusting room temperature, controlling humidity, adjusting lighting, or ventilation. Categories belonging to the laundry major category may include doing laundry or collecting laundry. Categories belonging to the going out major category may include shopping for the user or accompanying the user on the shopping trip. Categories belonging to the recreation major category may include exercises, oral exercises, music, picture-story shows, or cooking. Categories belonging to the transportation major category may include transportation or assistance with boarding and disembarking.

[0054] For example, the minor categories may include, for example, categories belonging to the major category of medical treatment, tracheal suction, wound care, ointment application, disinfection, medication application, intravascular pressure monitoring, intravenous drip injection, gastrostomy management, urinary management, enema, or oxygen therapy. Categories belonging to the major category of drug management may include oral medication, tube medication, medication distribution, instillation, injection, suppository administration, or inventory check. Categories belonging to the major category of vital sign measurement may include temperature measurement, SpO2 measurement, pulse measurement, blood pressure measurement, weight measurement, or vital sign measurement. Categories belonging to the major category of medical examination may include attending medical examinations or accompanying patients to hospitals. Categories belonging to the major category of direct interventions on bodily functions may include massage or functional restoration. Categories belonging to the major category of physical therapy may include range of motion training, heat therapy, walking training, standing training, stair climbing, exercise training, or physical therapy assistance. Categories belonging to the occupational therapy major category may include occupational tasks, calculation tasks, cognitive tasks, memory tasks, artistic tasks, play tasks, or occupational therapy assistance. Categories belonging to the speech-language-hearing therapy major category may include expression training, auditory comprehension training, swallowing function assessment, indirect swallowing training, or direct swallowing training. Categories belonging to the care plan major category may include care plan creation, conference, monitoring, or assessment. Categories belonging to the nutritional management major category may include nutritional care plan creation, conference, monitoring, nutritional assessment, nutritional screening, or nutrition and dietary consultation. Categories belonging to the school lunch major category may include menu creation, cooking, meal count management, or ingredient procurement. Categories belonging to the hygiene management major category may include physical condition management, ingredient management, or facility management.

[0055] The minor categories may include, for example, moving, waiting, or transporting as categories belonging to the medium category of staff movement. The categories belonging to the medium category of meetings may include morning meetings, evening meetings, or meetings. The categories belonging to the medium category of office cleaning may include cleaning common areas or tidying up.

[0056] The minor categories may include, for example, categories belonging to the medium category of understanding users or patients, such as calling out, listening, watching over, checking on user status, or responding to nurse calls. Categories belonging to the medium category of information sharing may include contacting, handing over, and telephone or fax transmission. Categories belonging to the medium category of record creation may include record creation, calculation, or printing and copying. Categories belonging to the medium category of confirmation may include record confirmation, work confirmation, or equipment confirmation. Categories belonging to the medium category of visiting guest support may include family support or visiting guest support.

[0057] Subcategories may include setup, cleanup, or hand washing as common tasks.

[0058] Step S103: The control unit 11 displays and outputs a user interface screen including the multiple task content candidates estimated in step S102 on the output unit 14, and presents it to the user. For example, the control unit 11 may output the multiple task content candidates along with their respective estimated likelihoods, and present them to the user in order of highest estimated likelihood, associated with time information. In other words, the control unit 11 may output the estimated likelihood of each task content candidate, and the order in which the multiple task content candidates are presented may be based on the estimated likelihoods. If the user is a staff member, the presentation destination may be a terminal worn or carried by the staff member. Alternatively, if the user is a person other than a staff member, the presentation destination may be a terminal used by the person.

[0059] Step S104: If the user selects one of the multiple task content candidates presented in step S103, the control unit 11 determines the selected task content as the staff member's task content. If there is no correct option among the multiple presented task content candidates, the control unit 11 may accept input of the correct task content from the user. In this way, the task content information of the staff member determined based on feedback (correct task content) from the user may be used as training data to retrain the task content estimation model (machine learning model). The more this technology is used in nursing, caregiving, medical care, and other settings, the more the accuracy of task content estimation will improve, and the task estimation technology will be further improved.

[0060] Specific examples of user interface screens are shown below. For example, the control unit 11 may cause the output unit 14 to display the user interface screen 300 shown in FIG. 5. The user interface screen 300 shown in FIG. 5 is a screen for selecting a task content. The user interface screen 300 may include all or part of the multiple task content candidates estimated in step S102. The user interface screen 300 may display the task content candidates one by one alongside radio buttons 301-303, allowing the user to select one. In this case, the task content candidates may be displayed from top to bottom in descending order of estimated likelihood. If the optimal task content candidate is not displayed, the user may be allowed to select a radio button 304 and enter the desired information into a text field 305. When the control unit 11 receives input, such as a click on the OK button 306 on the user interface screen 300 shown in FIG. 5, the control unit 11 determines the task content corresponding to the selected radio button 301-303 as the staff member's task content. Furthermore, when the control unit 11 receives an input such as a click on the end button 307 on the user interface screen 300 in FIG. 5, the control unit 11 ends the work recording.

[0061] In this way, the work recording technology according to this embodiment estimates multiple candidate work contents that the staff member has performed up to that point based on environmental information related to the work content of the staff member, and presents the multiple estimated candidate work contents in association with time information. The user simply selects the appropriate candidate work content from the presented candidate work content. In particular, in caregiving, nursing, medical, and other settings, the needs of many users and patients must be met in a timely manner, making the tasks complex and estimating a single correct task content difficult. Furthermore, because many similar tasks, such as toilet assistance and toilet cleaning, or laundry and laundry collection, are common, it is difficult to correctly distinguish between them and estimate a single correct task content. Therefore, presenting several candidate work contents rather than narrowing down the candidate work contents estimated from environmental information to one increases the usability of this technology. In this way, the work recording technology according to this embodiment presents multiple candidate work contents, thereby streamlining staff work recording and improving the work recording technology.

[0062] In particular, when multiple work content candidates are presented to the user in descending order of estimated likelihood, the user only needs to look at the displayed multiple work content candidates in order from top to bottom, which can further improve the efficiency of work recording work.

[0063] In addition, in terms of estimation accuracy, if the environmental information includes not only position information and time information on the facility floor plan but also posture information, estimation accuracy can be improved. Furthermore, the higher the total estimated likelihood value for the multiple presented task content candidates, the higher the probability that the correct answer will be included in the options.

[0064] On the other hand, the more task candidates are presented, the more complicated the user's operation to select the correct answer becomes. Therefore, it is preferable to present three or more, preferably five or more, and at most seven or so. Furthermore, for example, the number of presented task candidates may be determined based on the sum of the estimated likelihoods of the multiple task candidates. For example, the number of presented task candidates may be set so that the sum of the estimated likelihoods is equal to or greater than a predetermined percentage. For example, the predetermined percentage is preferably 99% or greater, but may also be 95% or greater, 90% or greater, 80% or greater, or a lower percentage, or may be changed as appropriate. The predetermined percentage of the sum of the estimated likelihoods may also be optimized so that a more correct task candidate is selected.

[0065] In addition, when a task content candidate with a predetermined estimated likelihood or higher is changed, the control unit 11 may issue an alert by sound or vibration. In the work recording technology according to this embodiment, the information processing device sequentially estimates candidate tasks performed by the staff member up to a certain point in time. When the control unit 11 extracts appropriate data groups and performs estimation, it is considered that the estimated candidate tasks will not change while one task is being performed. On the other hand, when a task content candidate with a predetermined estimated likelihood or higher is changed, it is highly likely that the staff member has just completed a certain task. In this case, to prompt the user for input, the control unit 11 may temporarily suspend the switching of the presented task content candidate, continue to display the task content candidate immediately before the switch on the output unit 14, and issue an alert by sound or vibration. The predetermined estimated likelihood may be, for example, 20% or higher. However, the predetermined estimated likelihood may be less than 20% or more than 20%.

[0066] If no operation is performed within a predetermined time after the presentation, an alert may be issued by sound and vibration. The predetermined time may be, for example, five minutes. However, it may be less than five minutes or more than five minutes. In this way, by having the user check the estimation result and send feedback each time a task reaches a certain point, it is possible to accurately record what tasks have been performed up to that point.

[0067] The environmental information may also include at least one of staff attendance information and work schedule information. Using this information allows for more accurate estimation of potential work content. When a unique work content or a work content not included in the work schedule information is estimated, an alert may be issued, for example, by sound or vibration, to attract more attention.

[0068] Furthermore, the work recording technology according to this embodiment may retrain the machine learning model using information about the work content of staff members determined based on user feedback as training data. This will improve the accuracy of work content estimation as this technology is used in caregiving, nursing, medical care, and other settings, and will further improve the work recording technology.

[0069] In the work recording technology according to the present embodiment, a method using machine learning has been exemplified as a method for estimating multiple candidate work contents. When estimating multiple candidate work contents using machine learning, preprocessing may be performed on the acquired environmental information. However, the estimation method is not limited to machine learning. For example, multiple candidate work contents may be estimated using statistical methods such as a multiple regression model or a Kalman filter.

[0070] In addition, the control unit 11 may analyze or statisticize the records of the work content of the staff and output the results in a visualized form such as a graph.

[0071] Although the present disclosure has been described based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each means or step can be rearranged so as not to be logically inconsistent, and multiple means or steps can be combined or divided into one.

[0072] 10 Information processing device 11 Control unit 12 Storage unit 13 Input unit 14 Output unit 15 Communication unit 300 User interface screen 301-304 Radio buttons 305 Text field 306 OK button 307 End button

Claims

1. A work recording method executed by an information processing device, comprising the steps of: acquiring environmental information related to the work content of a staff member; estimating a plurality of work content candidates based on the environmental information; presenting the plurality of work content candidates; and determining a work content selected from the plurality of work content candidates as the work content of the staff member.

2. A work recording method as claimed in claim 1, wherein the environmental information includes a group of data relating to position information on a facility floor plan, posture information of the staff member and time information.

3. A work recording method as described in claim 2, wherein the staff member's posture information includes sensing data acquired from a terminal worn or carried by the staff member.

4. A work recording method according to claim 3, further comprising the step of: the sensing data including acceleration information, angular velocity information, and magnetic information.

5. A work recording method as claimed in claim 2, wherein the position information on the facility floor plan includes position information of the staff observed by a beacon arranged in the facility.

6. A work recording method according to claim 1, wherein the environmental information includes at least one of staff attendance information and work schedule information.

7. A work recording method as described in claim 1, wherein in the estimating step, the plurality of work content candidates are estimated by inputting the environmental information into a trained learning model that has undergone machine learning to estimate the plurality of work content candidates.

8. A work recording method as described in claim 7, wherein the learning model further outputs an estimated likelihood of each work content candidate, and the order of presentation of the multiple work content candidates is based on the estimated likelihood.

9. The work recording method according to claim 8, further comprising the step of presenting the plurality of work content candidates in a number of seven or less.

10. A work recording method as described in claim 9, wherein the number of the plurality of work content candidates to be presented is determined based on a total value of estimated likelihoods relating to the plurality of work content candidates.

11. A work recording method as claimed in claim 7, further comprising the step of re-learning the learning model using the work content of the staff member determined in the step of determining the work content of the staff member as training data.

12. A work recording method according to claim 1, further comprising the step of issuing an alert by sound or vibration when a change in a work content candidate occurs that has a predetermined estimated likelihood or higher.

13. A work recording method as claimed in claim 1, wherein when a special work content or a candidate work content not included in the work schedule information is estimated, an alert is issued by sound and vibration.

14. An information processing device comprising a processor that executes the work recording method according to any one of claims 1 to 13.

15. A program for causing an information processing device to execute the work recording method according to any one of claims 1 to 13.

Images