An automatic care record creation system, and an automatic care time tracking system using this system, a support system for nursing care certification, a support system for calculating nursing care fees, and a system for evaluating the skill level of caregivers.

Abstract

We provide an automatic care record creation system that automatically creates care records, a care fee calculation support system, and a caregiver skill level evaluation system. [Solution] The automatic creation system consists of a wearable terminal equipped with video recording means, audio recording means, and communication means, and a computer equipped with means for receiving video data and audio data and analyzing this data to automatically recognize the care content.The wearable terminal starts recording when the name of the care recipient recognized by the face recognition means matches the name of the care recipient spoken by the caregiver, and is equipped with means for automatically recognizing the care content from the video of the care recipient contained in the video data and means for automatically recognizing the care content from the words uttered by the caregiver contained in the audio data, and further equipped with means for converting the care content automatically recognized from the video data and audio data into text to create a care record.

Description

[Technical Field]

[0001] The present invention relates to a system that automatically recognizes the content of care services (care content) provided by a caregiver to a care recipient and automatically creates a care record, and further relates to an automatic care time grasping system that utilizes this automatic care record creation system, a support system for nursing care certification, a support system for calculating nursing care fees, and a system for evaluating the skill level of a caregiver. [Background technology]

[0002] With Japan now said to be a super-aging society, it is predicted that there will be a shortage of approximately 570,000 care workers by 2040. Based on this prediction, the number of care workers will need to be increased by 32,000 each year, and since achieving such an increase is extremely difficult, there are concerns that the shortage of care workers will become an even more serious problem. Financial issues resulting from the increasing burden of social insurance premiums such as nursing care insurance, and human resource issues resulting from a shortage of caregivers (care workers, helpers, and other care-related personnel) are becoming particularly major social issues. As the elderly population increases, the number of dementia patients will also increase, with some predictions that by 2025, one in five people aged 65 and over will have dementia. An increase in dementia patients means an increase in the number of people requiring care, and it is expected that financial and human resource issues related to nursing care will become increasingly major social issues.

[0003] Although nursing care is a major social issue that affects the entire nation, the adoption of IT (Information Technology) and ICT (Information and Communication Technology) has been progressing very slowly. As a result, the efficiency of nursing care-related tasks has not been improved sufficiently, and an environment has not been created in which costs can be reduced by improving work efficiency or in which nursing care can be provided to a large number of people with limited personnel.

[0004] By promoting IT and ICT, it is possible to make various nursing care-related tasks more efficient, which will hopefully reduce work costs and enable a greater number of tasks to be performed with limited human resources.

[0005] To solve these problems, the Ministry of Health, Labour and Welfare is promoting the introduction and spread of ICT to care providers, etc. This ICT adoption mainly involves the digitization of care records, and the aggregation of this digitized care-related information to accumulate big data, which can then be analyzed to help solve the problems.

[0006] However, these electronic care records are data manually entered by caregivers on-site using computers or tablet PCs, which means there is a risk of input errors or omissions. Furthermore, even if the same care content is provided, there may be differences in how it is expressed, or differences in judgment as to whether or not it should be kept as a care record, and so there can be variations and arbitrary elements in the content recorded.

[0007] Furthermore, for caregivers who have a lot of care work to do, even the task of entering these records can be a heavy burden.In many cases, care records are created after the caregiver has finished their normal care work, taking one to two hours a day, and in a situation where there is a shortage of caregivers, this is a heavy workload. In light of this situation, it is desirable to have a means to automatically and accurately (eliminate variations and arbitrary elements) grasp and recognize the content of care, and to automatically create care records, especially in the field of care.

[0008] The inventors have focused on understanding the specific content of care services provided (also simply referred to as "care content") and the actual time required for these care services (also simply referred to as "care time"), among other things, within care records. This is because, in the field of care, it is important to calculate and bill for care fees, collect information for determining whether a person needs care, and create care records, and these matters are closely related to the content of care and the time spent on care. In other words, if the content of care and the time spent on care could be automatically and accurately understood, the workload associated with these matters would be greatly reduced.

[0009] Regarding the creation of nursing care records, Patent Document 1 is disclosed as prior art aimed at IT / ICT adoption. The technology described in Patent Document 1 is "A voice acquisition means for acquiring voice data related to care work for a care recipient, which is generated by a caregiver; a voice recognition / text conversion means for recognizing the voice data acquired by the voice acquisition means and converting it into text data; a care record creating means for creating a care record based on the text data converted from the voice data by the voice recognition / text conversion means; a display means for displaying the care record created by the care record creation means so that the caregiver can confirm the care record; a correction means for allowing a caregiver to correct the care record displayed on the display means as needed; A confirmation means for finalizing the care record after confirmation by the caregiver and correction as necessary has been completed; and a voice data learning means for learning the text conversion function of the voice recognition / text conversion means based on the voice data, the text data converted from the voice data, and the text data finally adopted in the care record confirmed by the confirmation means.

[0010] This technology has the following effect: "A voice acquisition means can acquire voice data related to the care work of the care recipient spoken by the caregiver, and a care record can be created based on this. This makes it possible to create a care record using only the voice of the caregiver, and eliminates the need for voice communication between the caregiver and the system, thereby reducing the burden on the caregiver during care work."

[0011] However, while the technology described in Patent Document 1 saves caregivers the trouble of manually entering care records, it has the problem that the care records are created by the caregiver using a voice recognition function, and therefore cannot be said to be created automatically. Furthermore, there was also the problem that the means for identifying the care recipient and the means for grasping the start and end of care work were unclear, and the means for grasping these were insufficient. [Prior art documents] [Patent documents]

[0012] [Patent Document 1] Patent Publication No. 2020-140620 Summary of the Invention [Problem to be solved by the invention]

[0013] Therefore, an object of the present invention is to provide an automatic care record creation system that can automatically and accurately grasp the specific content of care services provided at care sites, automatically and accurately grasp the identification of care recipients and the start and end times of care work, and automatically create care records. It is also an object of the present invention to provide an automatic care time capture system, a support system for nursing care certification, a support system for calculating nursing care fees, and a caregiver skill level evaluation system that utilize this automatic care record creation system. [Means for solving the problem]

[0014] The above object of the present invention can be achieved by the following means. 1. A system that automatically recognizes the content of the care services provided and automatically creates care records based on this. a wearable terminal including a means for capturing and recording the care provided by a caregiver, a means for collecting and recording the words spoken by the caregiver, and a communication means for transmitting the recorded video data and the recorded audio data to an external device; The system comprises a computer having means for receiving the video data and the audio data, analyzing the data, and automatically recognizing the care content, The wearable device is configured to start recording when the name of the care recipient recognized by the face recognition means matches the name of the care recipient spoken by the caregiver (such as by calling out the name of the care recipient and confirming it), The computer A means for automatically recognizing the content of care from the image of the care recipient included in the video data (using a face recognition system, etc.); a means for automatically recognizing the content of care from the words uttered by the caregiver contained in the voice data (such as calling out the name of the care recipient and confirming the name); The system further comprises a means for automatically recognizing the content of care from the video data and audio data and converting the content into text to create a care record.

[0015] 2. The automatic care record creation system described in claim 1, characterized in that the wearable device is configured to end recording when it detects the name of the person being cared for and a keyword indicating the end of care services from words spoken by the caregiver.

[0016] 3. Regarding the means to automatically recognize the care content from the words spoken by the caregiver contained in the voice data, The computer includes a means for storing in advance specific terms that represent specific care content, 2. The system for automatically creating nursing care records according to claim 1, characterized in that it detects specific terms uttered by the caregiver and automatically recognizes the content of the care based on these specific terms.

[0017] 4. The system for automatically creating nursing care records according to claim 1, characterized in that video data and audio data are recorded together with text indicating the content of nursing care.

[0018] 5. The automatic care record creation system described in claim 1, characterized in that it is equipped with a means for comparing the care content automatically recognized from video data with the care content automatically recognized from audio data, and confirming that there are no differences in the care content provided at the same time.

[0019] 6. A system using the automatic care record creation system according to claims 1 to 5, a means for automatically determining whether or not the care content is content that should be added to the care time; An automatic care time grasping system characterized by comprising means for accumulating the care time provided to each care recipient.

[0020] 7. A system using the automatic care time grasping system according to claim 6, Regarding the means for automatically determining whether the care content should be accumulated in care time, The criteria for determining whether the care content falls into one of the five categories: direct assistance with daily living, joint assistance with daily living, behavioral problems, functional training, or medical care. For care content that falls under any of the above five categories, the time required for this care is calculated as care time. This support system for nursing care certification is characterized in that the accumulated nursing care time is used as the nursing care certification reference time in nursing care certification.

[0021] 8. A system using the automatic care time determination system according to claim 6, Regarding the means for automatically determining whether the care content should be accumulated in care time, The criteria for determining whether the care is eligible for nursing care fees is whether or not the care is eligible for nursing care fees. For each care content that corresponds to the billable item, the time required for each care content is accumulated as care time, This is a nursing care fee calculation support system characterized in that the obtained nursing care content and the nursing care time required for it are used to calculate nursing care fees.

[0022] 9. A system using the automatic care time grasping system according to claim 6, This is a system for evaluating the skill level of a caregiver, which evaluates the skill level of a caregiver based on the skill score obtained by analyzing video data and the care time required for each care content. [Effects of the Invention]

[0023] The invention shown in 1 above is a system that automatically recognizes the content of the care services actually provided from both audio and video, and automatically creates a care record based on this. According to the invention shown in 1 above, the content of the care services actually and specifically provided (hereinafter simply referred to as "care content") can be automatically and accurately grasped, and care records can be automatically created based on that content without the caregiver having to consciously record it.

[0024] The specific effects are as follows: First, if the system has a means for recording the words spoken by the caregiver (for example, "Mr. / Ms. XX, I'll help you with meals now," "Mr. / Ms. XX, I'm going to take a bath now," "Thank you for the meal," "Now that you've gotten out of the bath, let's dry your hair," etc.), and a means for automatically analyzing the care content from this recorded voice data, it can automatically recognize from the results of this analysis what kind of care service was provided to which care recipient at a certain time.

[0025] Technologies with such effects are known as voice recognition and speech analysis, and are widely used in smartphones, smart speakers, etc. By analyzing the voice data of a caregiver using known voice recognition and speech analysis technologies, it is possible to specifically and automatically grasp the content of care.

[0026] Next, if the system has a means for filming and recording the care provided by the caregiver and a means for automatically analyzing the care content from this recorded video data, the results of this analysis can automatically recognize information about which care recipient was provided with what type of care service at a certain time.

[0027] The technology with such an effect is known as video analysis, and is widely used in security cameras, medical diagnosis, etc. By analyzing the video data of the care recipient using known image analysis technology, it is possible to grasp the details of care in a concrete and automatic manner.

[0028] In the invention described above in 1, the analysis means based on audio data or video data is configured to be entirely automated, i.e., the analysis is performed automatically by a computer or the like. It has been pointed out that means that humans check and analyze audio and video carry the risk and disadvantage of violating the privacy of the care recipient. The configuration according to the present invention has the effect of eliminating these risks and disadvantages. Therefore, the present invention can be said to be effective from the perspective of privacy protection as well.

[0029] As mentioned above, this system automatically recognizes the care content from both audio and video of the actual care services provided. When automatically recognizing care content from either audio or video, there is a possibility of errors in voice recognition or image / video analysis. However, because this system automatically recognizes care content from both audio and video, it is possible to improve the accuracy of automatic recognition of care content. Then, by transcribing this accurately recognized care content into text, accurate care records can be automatically created.

[0030] Furthermore, according to the invention described above in 1, by using a wearable device to implement the present invention, it is not necessary to install microphones or cameras in each location where care is provided, such as the living room, dining room, bathroom, etc., thereby reducing initial costs. Furthermore, since the care service can be filmed from the caregiver's perspective, the care recipient and the care they are receiving can be clearly captured, and the problem of being unable to film due to camera blind spots can be resolved.

[0031] The invention described in 1 above is ideal for the purpose of understanding the content and duration of care in a one-on-one care environment where one caregiver cares for one care recipient. In particular, in the field of home care, where it is difficult to install microphones and cameras in the homes being visited, it is effective for the caregiver to wear a wearable device to record and record audio and video.

[0032] Furthermore, according to the invention described above in 1, the wearable device is configured to start recording (which may include audio recording; the same applies below) when the name of the care recipient recognized by the face recognition means matches the name of the care recipient spoken by the caregiver (the name spoken when confirming the care recipient's name), so recording can be started automatically without bothering the caregiver, and the caregiver can remain hands-free. The start time of care work for a specific care recipient can also be automatically and accurately determined and recorded. Furthermore, the identification of the care recipient can be double-checked using both the facial recognition function and the caregiver's comments, allowing for automatic and accurate identification of the care recipient, preventing mistakes such as misidentifying the care recipient or incorrectly recording the care record of the wrong care recipient.

[0033] According to the invention described in 2 above, recording can be automatically stopped by detecting the name of the care recipient and a keyword indicating the end of care services. This allows the recording to be automatically stopped without bothering the caregiver, and also allows the end time of care to be automatically and accurately grasped and recorded.

[0034] The invention described in 3 above is a configuration for further improving the reliability of automatic speech recognition. If each caregiver uses different terms for the content of a particular care service, the content of the care may not be recognized correctly. Therefore, if an agreement is made that caregivers use specific terms (specific terms) for the content of the care service, and if these specific terms are also stored in the computer, the content of the care service can be automatically recognized correctly.

[0035] Furthermore, when this specific term is used, it triggers the need to record the care content in the care record, ensuring that the necessary information is recorded in the care record. Therefore, according to the invention shown in 2 above, terms (specific terms) related to the content of the care services used by the caregiver are determined in advance, and the computer can detect these specific terms, thereby accurately understanding the content of the care services provided.

[0036] According to the invention described in 4 above, by recording video data and audio data along with text indicating the content of the care, the state of care can be recorded in three ways: video, audio, and text. The care record is created automatically by a computer without human intervention, but if, for example, doubts arise about the content of the care record or if some kind of trouble occurs during the care service, it can be verified after the fact using human hearing and vision rather than a computer.

[0037] According to the invention described in 5 above, by collating the care content automatically recognized from the video data with the care content automatically recognized from the audio data and by providing a means for checking whether there are any discrepancies between the care content provided at the same time, if any discrepancies occur in the automatically recognized care content, the scene can be checked after the fact using video and audio. This allows for the creation of a more accurate care record, and also increases the reliability of this care record.

[0038] The invention shown in 6 above is a system that utilizes the automatic care record creation system described in 1 to 5 above, and is a system for automatically understanding the time (care time) required for the actual care services provided. By accurately understanding the care time, which is the actual time required for care services, it is possible to "quantitatively" understand the degree of need for care services for each care recipient. In other words, it is possible to "quantify" and understand the need for care services for each care recipient.

[0039] More specifically, the invention described in 6 above is configured to automatically determine whether a care content should be included in care time based on analysis data obtained from audio data and video data. In other words, it is possible to automatically determine whether or not the care content should be included in care time and calculate the amount accordingly, depending on the purpose of understanding the care content. For example, if a contract for a nursing care service includes meal assistance in the monthly fee, but bathing assistance is not included in the monthly fee and requires an optional fee, meal assistance and bathing assistance should not be included in the same care time range; instead, the care time included in the monthly fee and the care time not included should be calculated separately. The configuration of the present invention makes it possible to meet such categorization and classification requirements.

[0040] As described above, according to the invention shown in 6 above, it is possible to automatically and accurately grasp the specific content of the care services provided and the actual time required for those care services, making it possible to "quantify" the care services actually provided, and also to "quantitatively" grasp the degree of need for care services for each care recipient. All of the components of the system can be operated automatically without the caregiver's operation, and the caregiver can remain hands-free, so they can concentrate on their work without interfering with the care provided to the care recipient. Furthermore, they are freed from indirect tasks such as recording the content of care and the time spent on care, reducing the overall workload.

[0041] According to the invention shown in 7 above, by automatically and accurately determining the care time (standard time for nursing care certification, etc.), which is one of the criteria for determining the level of nursing care required, from the content of the care actually provided, it is possible to provide support for determining the level of nursing care required with high accuracy. It also reduces the burden on care sites, visiting investigators, and care certification review boards involved in nursing care certification. Furthermore, because the actual care time provided can be automatically and accurately "quantified" as the basis for determining whether a person needs nursing care, it is expected that some or all of the procedures and assessment work involved in nursing care certification will be automated, and fairness can be enhanced by eliminating subjective and arbitrary judgments made by humans. Because it is a means of determining the amount of care time provided based on the actual content of care, it is particularly effective when reassessing the level of care required for care recipients who are already receiving care.

[0042] The details are as follows: According to the certification standards for nursing care certification set forth by the Ministry of Health, Labor and Welfare, the level of nursing care required is determined as level 1 or 2 for support or level 1 to 5 for care required, based on the amount of care time (standard time for nursing care certification, etc.) for the five nursing care classifications defined as direct assistance for daily living, joint assistance for daily living, problem behavior-related activities, functional training-related activities, or medical-related activities. For example, if the amount of care time for the above five classifications is between 32 and 50 minutes, the person is assessed as "level 1 for nursing care."

[0043] The standard time for nursing care certification used here is a measure of the effort required for care, and is an estimated time based on statistical data on the "ability," "method of assistance," and "presence (of disabilities or conditions)" of the person receiving care, and is not a figure that accumulates the actual amount of time required for care. The "ability," "method of assistance," and "presence (of disabilities or conditions)" of the person receiving care are based on interviews conducted by visiting investigators, and there is a possibility that the answers given by the person receiving care or their family, etc., and the visiting investigators may interpret the answers differently, which raises the issue of the possibility that the answers may contain subjective or arbitrary elements.

[0044] Furthermore, in a situation where the number of people requiring care is on the rise, the greater the number of people requiring care, the greater the burden of these home visits will be on investigators, care providers, and municipalities, etc., and at a time when there are already concerns about a shortage of personnel in the care field, there is a high possibility that this will increase the burden on the care field.

[0045] While the certification of need for nursing care currently faces the problems described above, the invention described in item 6 above makes it possible to use "nursing care time," which is the actual time required for nursing care services, as a basis for the certification of need for nursing care. In other words, nursing care certification, which was previously determined "qualitatively," can now be determined based on "quantitative" information, eliminating subjective and arbitrary human factors and enabling a more fair judgment. Moreover, because this "nursing care time" can be calculated automatically and accurately, it reduces the burden on visiting investigators and others involved in the certification of need for nursing care.

[0046] According to the invention shown in 8 above, the content of the nursing care services actually provided and the time required for the care can be automatically and accurately grasped by utilizing the invention shown in 6 above, and the calculation and billing process for nursing care fees (the sum of nursing care benefit fees and user charges) can be automated or assisted.

[0047] Calculating and billing nursing care fees is a heavy burden for caregivers and care providers, so if the present invention could automatically and accurately grasp the care content and care time and apply them to nursing care fee point items, it would significantly reduce that burden. It would also prevent oversights, such as not claiming nursing care fees for care services that were actually provided. Furthermore, because calculations are automated and audio and video data can be checked later, it is expected that care recipients and insurers (such as municipalities) will be able to prevent and curb fraudulent claims.

[0048] According to the invention shown in 9 above, the actual care content and care time can be automatically and accurately grasped by utilizing the invention shown in 6 above, and the skill level of the caregiver can be automatically evaluated by analyzing the video data of the care situation and grasping the care time required for each care task.

[0049] This skill level evaluation is based on automatic analysis of video data and automatic understanding of care time, providing a fair and objective evaluation system that eliminates arbitrary elements. In addition, by accurately understanding the skill level of caregivers, it is possible to fairly evaluate their treatment, which is expected to improve caregivers' job satisfaction and motivation, and is also beneficial for care providers in securing talented personnel.

[0050] Furthermore, by linking with the nursing care certification support system shown in 7 above, it is possible to make a judgment that takes into account the skill level of the caregiver in charge, which can be useful for making an appropriate judgment in nursing care certification. Specifically, when using the actual care time obtained with the nursing care certification support system shown in 7 above as the standard time for nursing care certification, for example, when the same nursing care service is provided, a caregiver with a high level of nursing care skill tends to require shorter care time, while a caregiver with a low level of nursing care skill tends to require longer care time, it is possible to make an evaluation that adjusts and corrects for the difference in the level of nursing care skill that varies depending on the caregiver. [Brief explanation of the drawings]

[0051] [Figure 1] System diagram showing an example of an automatic nursing care record creation system [Figure 2] FIG. 1 is a schematic diagram illustrating an embodiment of a wearable terminal. [Figure 3] System diagram showing an example of an automatic care time tracking system [Figure 4] System diagram showing an example of a support system for nursing care certification [Figure 5] System diagram showing an example of a nursing care fee calculation support system [Figure 6] System diagram showing an embodiment of a caregiver skill level evaluation system DETAILED DESCRIPTION OF THE INVENTION

[0052] An automatic care record creation system 1 according to the present invention (hereinafter also referred to as "automatic care record creation system 1" for short) will be described with reference to the drawings. In this specification, the care recipient Y refers to an elderly person or a person with a disability who requires care or assistance and receives such services, and the caregiver Z refers to a person who provides care or assistance services to the care recipient Y, such as a care worker or helper, who is engaged in the practice of care or assistance.

[0053] FIG. 1 is a system diagram showing the basic configuration of an automatic care record creation system 1. As shown in Figure 1, the automatic care record creation system 1 is (1) A means of identifying the care recipient who is the target of care (means of identifying the care recipient), (2) A means for collecting and recording the care content spoken by the caregiver (recording means), (3) A means for photographing and recording the care provided by the caregiver to the care recipient (recording means); (4) Means for transmitting recorded audio data and video data to a computer (communication means); (5) A means for automatically recognizing the content of the care service actually provided from the recorded audio data and video data (recognition means); (6) A means for transcribing the automatically recognized care content and creating a care record (creation means) The configuration has the following.

[0054] The above means (1) to (6) will be explained in order. The target person identification means (1) above is a means for identifying a care recipient who is the target of care. Since the care content and care time must be understood for each care recipient, it is essential to specifically and accurately identify the target of care services. This function is particularly essential when using the present invention for the automatic creation of care records, as well as for understanding the care time required, supporting the certification of need for care, and supporting the calculation of care fees, as described below.

[0055] A specific example of such a method is for caregiver Z to verbally utter the name of care recipient Y or the identification mark assigned to each care recipient Y, and then automatically analyze the resulting voice data to identify the care recipient. By utilizing conventionally known technologies such as voice recognition, it is possible to automatically and accurately identify care recipient Y, who is the person receiving care. The identification mark assigned to each care recipient Y is composed of numbers, symbols, etc., and is a unique identification mark assigned to an individual, such as a medical card number or patient number in a hospital, or a student number or student number in a school.

[0056] Other means may also be employed as specific means for identifying the target person. For example, a two-dimensional code or the like may be displayed on a band attached to the wrist or the like of the care recipient Y, and caregiver Z may identify care recipient Y by reading this code when providing care. Furthermore, for example, a means for automatically identifying the care recipient Y can be adopted using short-range wireless communication such as RFID (radio frequency identifier) ​​or Bluetooth.

[0057] A facial recognition system can also be used as a means of identifying the subject. A facial recognition system is a system that detects human faces from images captured by a camera or other device, digitizes the information obtained from the faces, converts it into facial data, and compares that facial data with facial data registered in a database to identify the target person. In the present invention, facial data of the care recipient is registered in a database in advance, and the facial data of the care recipient is obtained from video captured by a wearable terminal, and the care recipient (target person) can be identified by comparing this data. In the present invention, the target person identification means that utilizes this face recognition system is called face recognition means.

[0058] There is no limitation on the specific configuration of the face recognition system used in the present invention, and publicly known and publicly used technologies such as a visual method (2D authentication) or an IR method (3D authentication) can be used without any particular restrictions.

[0059] Furthermore, a means can be adopted to confirm the target person when the name of the target person, who is the care recipient, obtained by the face recognition means described above matches the name of the care recipient spoken by the caregiver (the name spoken when confirming the name of the care recipient by speaking to them). With this means, the name of the target person, who is the care recipient, can be double-checked, and mix-ups and recording errors can be reliably prevented.

[0060] The recording means in (2) above is a means for collecting the voices (terms indicating the content of care, etc.) spoken by caregiver Z and recording and saving them on a recording medium. There are no restrictions on the specific method of collecting and recording the voices, and any publicly known and publicly used recording means may be adopted without any particular restrictions.

[0061] The content to be recorded is the voice spoken by caregiver Z, but it is especially important to record the voice that speaks the care content. As will be explained later, this voice that speaks the care content can be analyzed to automatically understand the care content.

[0062] Caregiver Z's verbal instructions include, for example, "I will now assist with eating," "I will now assist with bathing," "I will now finish assisting with eating," and "I will finish assisting with bathing." By verbally announcing the details of the care tasks to be performed or completed, the care details can be automatically understood using technology such as voice recognition. Furthermore, by verbally confirming the care tasks, caregiver Z can reduce mistakes, such as by pointing and calling out, and communicate with care recipient Y. Furthermore, by reading out the necessary steps for treatment, such as administering medication or intravenous drips, care recipient Y can confirm whether medication has been administered and whether the medication is the correct one. Furthermore, caregiver Z can confirm these steps after the fact by playing back or viewing the analyzed care record.

[0063] The recording means in (3) above is a means for recording the video footage of the caregiving situation on a recording medium. There are no restrictions on the specific method of the video and video recording means, and any publicly known and publicly used recording means may be used without any particular restrictions.

[0064] The recorded content is the care service provided by caregiver Z to care recipient Y. The purpose is to automatically understand the content of the care by analyzing the video footage of this care. By analyzing the care using video analysis or other means, the content of the care can be understood specifically and automatically, and the time required for it can also be easily understood.

[0065] Next, the on / off (ON / OFF) of the (2) sound recording means and the (3) video recording means will be described. Regarding the above (2) sound recording means and the above (3) video recording means, in addition to means for continuous sound recording and video recording, means for starting and ending sound recording and video recording only when providing care services can be adopted. First, regarding the start of audio and video recording, the wearable device W starts audio and video recording when the name of the person being cared for, as recognized by the face recognition means described above, matches the name of the person being cared for spoken verbally by caregiver Z (the name spoken when confirming the name of the person being cared for). The face recognition means is configured to constantly detect a human face (the face of care recipient Y) shown in the video captured by the wearable device W, compare it with a database, and identify care recipient Y. Furthermore, when caregiver Z provides care services to care recipient Y, it is normal for the caregiver Z to speak his / her name at the start of the service. That is, because these configurations allow the recording to start when caregiver X speaks (reads out, etc.) the name of care recipient Y, which is a normal action for caregiver X, caregiver X does not need to do anything to start the recording and can maintain a hands-free state. In this way, the recording function can be started automatically without bothering caregiver X, and caregiver X can maintain a hands-free state.

[0066] In other words, the above-mentioned start of audio and video recording is configured to start audio and video recording by the wearable device W when the following (a) and (b) are met: (a) The name of the care recipient obtained through facial recognition (b) The name of the care recipient as verbally stated by the caregiver

[0067] Next, regarding the end of the recording, the wearable device W stops the recording when it detects the name of the care recipient Y and a keyword indicating the end of care services from the words spoken by the caregiver X. Examples of keywords that indicate the end of nursing care services include "Thank you for your hard work," "I'll come again," etc. Regarding these keywords, a means can be adopted in which a computer learns the voice data obtained by the wearable device W and determines when a certain keyword is uttered to indicate the end of a specified nursing care service. As mentioned above, the timing for recording to end is when the name of care recipient Y spoken by caregiver X and a keyword indicating the end of care services are detected. For example, if voice such as "Thank you for your hard work, Mr. / Ms. XX," or "I'll come again, Mr. / Ms. XX," is recognized, the recording will end.

[0068] In other words, the above-mentioned audio / video recording termination is configured to terminate audio / video recording by the wearable device W when the following (c) and (d) are issued consecutively. (c) Keywords indicating the end of nursing care services (d) The name of the care recipient as verbally stated by the caregiver There is no limitation on the order in which the above (c) and (d) are issued, and they may be issued in the order from (c) to (d), or from (d) to (c). There may be an interval of a few seconds between (d), and other statements may occur during this interval. This interval of a few seconds is preferably within 10 seconds, and more preferably within 5 seconds.

[0069] The communication function (4) above is a means for transmitting recorded audio data and video data to an external computer. The external computer may be, for example, a cloud-based computer or server. To transmit audio data or video data to the cloud-based computer, it is sufficient to be able to transmit and receive data using a wireless or wired network. There are no restrictions on the specific method of communication, and any publicly known or publicly used communication method may be used without any particular restrictions.

[0070] For example, it is preferable to use a wireless communication system used in mobile phones, and in particular, the fifth generation mobile communication system (commonly known as "5G"), which can send and receive large amounts of data at high speed. Furthermore, 5G communication methods can be used even in environments where care is provided that do not have communication facilities such as wireless or wired LAN. If the location is remote or a radio-blocked area where it is difficult to use mobile phone communications, the audio and video data recorded and stored on the wearable device W may be transferred to a computer C using a recording medium M such as a USB flash drive.

[0071] As a device equipped with the above-mentioned (2) sound recording means, (3) video recording means, and (4) communication means, it is preferable to use a wearable terminal W worn by the caregiver Z, as shown in Fig. 2. The same applies when the above-mentioned (1) target person identification means employs a means in which the caregiver Z orally utters the name of the care recipient Y or an identification mark assigned to each care recipient Y, and the voice data is automatically analyzed to identify the person.

[0072] A wearable device W is an information terminal worn by a person. Commonly used types include wristbands and watches worn on the wrist, armbands worn on the arm, and eyeglasses, headbands, or headsets worn on the head or face. There are no limitations on the specific configuration of the wearable device W used in the present invention, but it is required to have at least a microphone function W1, a camera function W2, and a communication function (not shown), and to be configured to be able to record audio and video and communicate (transmit and receive data).

[0073] The wearable terminal W employed in the present invention is preferably a glasses-type, headband-type, or headset-type device worn on the head or face, since it is necessary to record the voice of the caregiver and capture images of the care being provided (particularly to capture images of the care recipient Y from the line of sight of the caregiver Z). It is particularly preferable to use smart glasses, which are widely used as devices equipped with the above-mentioned (2) sound recording means, (3) video recording means, and (4) communication means.

[0074] Currently, as a measure against infectious diseases such as COVID-19, caregivers Z may wear face shields in nursing care settings. Therefore, it is particularly preferable that a face shield W3 be attached or attachable to a wearable device W in the form of glasses, a headband, or a headset that is worn on the head or face (see FIG. 2(b)). Previously, caregivers Z tended to find it bothersome to have some kind of device attached to their body. However, with the spread of COVID-19, wearing a face shield has become mandatory in some nursing care settings, and caregivers Z are now less resistant to wearing a wearable device along with a face shield. Taking this opportunity, it would be convenient for caregivers Z to wear a wearable device W and adopt the system according to the present invention.

[0075] FIG. 2 shows an example of a wearable device W. FIG. 2(a) shows a configuration in which a microphone function W1 and a camera function W2 are attached to the side of the caregiver Z's face. This configuration is generally referred to as smart glasses. FIG. 2(b) shows a configuration in which the microphone function W1 is attached to the side of the face and the camera function W2 is attached to the forehead. In either configuration, the microphone function W1 is preferably located near the caregiver Z's mouth, and the camera function W2 is preferably located near the caregiver's eyes. The example shown in FIG. 2(b) also shows a configuration in which a face shield W3 is provided to cover the caregiver Z's face.

[0076] The recognition means (5) above is a means for automatically analyzing the audio data recorded by the recording means (2) above and the video data recorded by the video recording means (3) above, and automatically recognizing the content of the care provided. This recognition means is executed by a computer C.

[0077] Analysis from voice data is a means of analyzing the content of care tasks verbally uttered by caregiver Z using technology such as voice recognition. Technology known as voice recognition is already in use as a function of smartphones and smart speakers, and by adapting these technologies for caregiving, they can be used as this analytical method. For example, if caregiver Z says, "I will now assist with mealtimes," this voice data can be analyzed using technology such as voice recognition to recognize that the care task being performed is "assistance with mealtimes."

[0078] If each caregiver uses different terms for the content of a particular care service, the content of the care may not be recognized correctly. Therefore, if an agreement is made that caregivers use specific terms (specific terms) for the content of the care service, and if these specific terms are also stored in computer C, the content of the care service can be automatically recognized correctly. Therefore, by determining in advance the terms (specific terms) used by the caregiver regarding the content of the care service, and by having the computer C detect these specific terms, the content of the care service provided can be accurately understood.

[0079] Each nursing care facility determines terms to describe specific care contents and instructs caregivers to use these terms. If the terms used at each nursing care facility are stored in advance in computer C as specific terms, it will be possible to recognize the specific terms uttered by caregiver Z and accurately identify the care contents.

[0080] Analysis of video data is a method of analyzing the care service provided by caregiver Z to care recipient Y using technologies such as video recognition and video analysis. Video recognition and video analysis technologies are widely used in security cameras, medical diagnostics, and other fields, and these technologies can be adapted for use in this analysis by adapting them for caregiving. For example, a computer can be trained on a large amount of video data capturing the care service, and the video data capturing the care work can be used to analyze the content of the care based on the accumulated data. It is preferable to use technologies such as deep learning and artificial intelligence (AI) for such learning and analysis.

[0081] Furthermore, with regard to the recognition means (5) above, a configuration can be adopted in which the image of the person (mainly the care recipient Y or both the care recipient Y and the caregiver Z) included in the video data capturing the care situation is converted into a stick figure, and the care content is automatically recognized from the movements of this converted stick figure. A stick figure is a representation of a human body that has been extremely deformed, with a circular head and stick-like limbs. It is used in a variety of fields, for example, in the field of computer graphics (CG), where the movements of a real person are converted into stick figures and new images are generated using computer graphics based on these, or in the field of sports science, where the movements of athletes are converted into stick figures and used to scientifically analyze their movements.

[0082] By converting the people included in the video data into stick figures, the computer C can accurately grasp the movements of the people, and it also helps to protect the privacy of the people being photographed.

[0083] Furthermore, for the recognition means (5) above, a configuration can be adopted in which musculoskeletal analysis technology is used to analyze the images of people (particularly the care recipient) included in the video data capturing the care situation, and the content of the care is automatically recognized. Musculoskeletal analysis is a technology that reproduces human movements in a human body model (musculoskeletal model) made up of muscles and bones, and calculates muscle activity during movement and the forces generated in each part of the model.By using this technology, it is possible to estimate the load on a person's muscles and joints from video and perform movement analysis, so by accurately understanding the condition and movements of the person receiving care, it is possible to accurately understand what kind of care is being provided.

[0084] The recognition means (5) above can also be configured to analyze either the audio data recorded by the audio recording means (2) above or the video data recorded by the video recording means (3) above. For example, only the audio data can be analyzed, and the analysis data can be output and processed by the determination means and accumulation means (described later). In this case, the video data can be used as verification material in the event of any trouble or doubts about the results of understanding the care content or care time.

[0085] On the other hand, in order to improve the accuracy of automatic recognition of care content, it is preferable to automatically recognize the state of the actual care service provided from both audio and video. If care content is automatically recognized from either audio or video, errors in voice recognition or image / video analysis are possible, but because care content is automatically recognized from both audio and video, the accuracy of automatic recognition of care content can be improved. Then, by transcribing this accurately recognized care content, accurate care records can be automatically created.

[0086] It is also preferable to have a means for comparing the care content automatically recognized from the video data with the care content automatically recognized from the audio data to check whether there are any discrepancies between the care content provided at the same time. If a discrepancy occurs in the automatically recognized care content, the scene can be checked after the fact using video and audio, thereby making it possible to create a more accurate care record.

[0087] The creation means (6) above is a means for transcribing the care content automatically recognized from the audio data and video data and creating a care record.

[0088] Nursing care records are created for each individual care recipient and are daily records that include the details of the care services provided, and are saved as paper or electronic data. Specifically, they include the details of the care services provided by the caregiver to the care recipient, the location and date of the care, vital data such as blood pressure and temperature, and the condition of the care recipient.

[0089] The above (1) to (5) allow the care recipient and the care provided to be identified, and this information is then transcribed and recorded as text. Video data and images extracted from this video data may also be recorded and posted. The location where care was provided can be automatically recognized from the caregiver's spoken voice data, or a location-identifying system such as GPS built into the wearable device W worn by the caregiver can be used. The date and time of care provided is typically included in the voice and video data, and can be identified using these. Vital data such as blood pressure and body temperature can be automatically recognized from the recorded audio data when the caregiver reads out the results of the measurement or temperature check, or can be automatically recognized and recorded from the recorded video data by capturing the screen displaying the results of the measurement or temperature check.

[0090] The creating means (6) above is preferably configured to be linked with the scientific nursing care information system (LIFE). The Scientific Information System for Long-Term Care (LIFE) is a system created by the Ministry of Health, Labour and Welfare with the aim of promoting the provision of high-quality services that contribute to supporting independence and preventing the condition from worsening, with scientifically proven effectiveness, and promoting the PDCA cycle using LIFE and efforts to improve the quality of services.

[0091] To summarize the contents of LIFE, it is an initiative to centrally collect nursing care data from all over Japan. In other words, each caregiver and care provider will periodically provide the data they collect as the basis for nursing care to LIFE, a centralized national management system. LIFE will then analyze this information (big data) and provide analytical information to care sites, and is also expected to play a role in showing the direction in which welfare in Japan should move forward. Therefore, each caregiver and care provider must enter daily care records into LIFE and provide them, and this input work places a burden on those in the field.

[0092] The creation of nursing care records and the input of data into the Scientific Nursing Care Information System (LIFE) are generally performed by caregivers after they have completed providing nursing care services to the care recipient, which places a considerable burden on the caregiver. If the creation of nursing care records and the input of data into the Scientific Nursing Care Information System (LIFE) could be automated in the creation method described above (6), it would be possible to reduce the workload of caregivers.

[0093] Each of the means (5) to (6) above is processed by a computer C (including any type of electronic computer such as a personal computer, a general-purpose server, a mobile information terminal, a tablet terminal, or a smartphone).

[0094] On the other hand, as mentioned above, it is preferable to use a wearable terminal W for each of the means (1) to (4) above. The subject data, audio data, and / or video data obtained by each of the means (1) to (3) above is transferred to a computer C, a mobile information terminal S, or the like used in each of the means (5) to (6) above by the communication means (4) above.

[0095] There is no limitation on the means of data transfer, but examples include means for transferring data via a wired connection such as USB (Universal Serial Bus) or wired LAN (Ethernet), means for transferring data via a wireless connection such as wireless LAN or a mobile phone network W, and means for transferring data via a storage medium such as a USB flash drive. For example, it is preferable to use a wireless communication system used in mobile phones, particularly the fifth generation mobile communication system (commonly known as "5G"), which can transmit and receive large volumes of data at high speeds. Furthermore, 5G communication methods can be used even in environments where care is provided that do not have communication facilities such as wireless or wired LANs.

[0096] The automatic care record creation system 1 is comprised of the above means (1) to (6), and is characterized in that all the means are performed automatically without requiring any operation by a caregiver, etc. The above means (1) to (6) may be processed in any order.

[0097] <Automatic care time tracking system> As an application example of the automatic care record creation system 1, an automatic care time tracking system 2 will be described. Care time is the actual time required for care services. Specifically, it is the time calculated from the start and end times of each care service.

[0098] The specific configuration of the care time automatic determination system 2 is as follows. FIG. 3 is a system diagram showing the basic configuration of the system 2 for automatically determining care time. Among these, the means (1) to (6) are common to the automatic care record creation system 1 shown in FIG.

[0099] As shown in Figure 3, the automatic care time tracking system 2 (1) A means of identifying the care recipient who is the target of care (means of identifying the care recipient), (2) A means for collecting and recording the care content spoken by the caregiver (recording means), (3) A means for photographing and recording the care provided by the caregiver to the care recipient (recording means); (4) Means for transmitting recorded audio data and video data to a computer (communication means); (5) A means for automatically recognizing the content of the care service actually provided from the recorded audio data and video data (recognition means); (6) A means for transcribing the automatically recognized care content and creating a care record (creation means) (7) A means for automatically determining, from the analysis data, whether the care content is an item or content that should be added to the care time (determination means); (8) A means for accumulating the care time provided to a specific care recipient (accumulation means); The configuration has the following.

[0100] The judgment means (7) above is a means for automatically judging whether the content of the care work (care content) analyzed from the analysis data obtained by the recognition means (5) above, i.e., the audio data and video data, is content that should be accumulated as care time. For example, if the care content analyzed as "meal assistance" should be counted as care time, the answer is "YES." On the other hand, if the care content analyzed as "transfer (moving from bed to wheelchair, and from wheelchair to dining chair, etc.)" should not be counted as care time, the answer is "NO."

[0101] It is preferable that the criteria for determining whether or not care time should be counted can be set arbitrarily. For example, if the content of care and the amount of care time needed are required to determine whether or not care is needed, the criteria should be set to match the requirements for care time certification. If the content of care and the amount of care time needed are required to calculate and claim care fees, the criteria should be set to match the conditions for claiming care fees (details will be provided later).

[0102] The calculation means (8) above is a means for automatically calculating the time based on the result of the determination made by the determination means (7) above as to whether or not the content should be calculated as care time. The time required for each care content may be calculated for each care content, or may be calculated as the total care time for the care service for one day.

[0103] <Support system for nursing care certification> As an application example of the automatic care record creation system 1, a support system 3 for nursing care certification will be described. According to the Ministry of Health, Labor and Welfare, "Under the long-term care insurance system, a person can receive nursing care services when they become bedridden or suffer from dementia, etc., and require constant care (a state requiring long-term care), or when they require assistance with daily life such as housework and getting ready, and when they are in a state where preventive nursing care services would be particularly effective (a state requiring support). Whether or not a person is in a state requiring long-term care or support, and the extent of that state, is determined by a nursing care certification review board established by the city, town or village that acts as the insurer. As the nursing care certification is linked to the amount of nursing care service benefits, the standards are set uniformly and objectively nationwide."

[0104] The process for nursing care certification is explained as follows: "A municipal certification investigator (which can be outsourced to a designated home nursing care support business, etc.) will conduct a physical and mental condition survey (certification survey) and a computerized assessment (primary assessment) based on the attending physician's opinion. Next, a nursing care certification review board, made up of academic experts in health, medicine, and welfare, will conduct a review and assessment (secondary assessment) based on the results of the primary assessment and the attending physician's opinion, etc."

[0105] In the primary assessment, the level of care required is determined as level 1 or 2 for support or level 1 to 5 for care required, based on the care time (reference time for care certification, etc.) for the five care classifications: direct assistance, joint assistance, problem behavior-related activities, functional training-related activities, or medical care-related activities. For example, if the care time for the above five classifications is between 32 and 50 minutes, the person is assessed as "care required level 1." The reference time for care certification, etc. used here is a measure of the amount of care effort required, estimated based on statistical data from the "ability," "care method," and "presence (of disabilities or conditions)" of the person receiving care, and does not reflect the actual time required for care.

[0106] If this estimated standard time for nursing care certification, etc. can be replaced with the actual time required for nursing care (nursing care hours), it will be possible to determine nursing care certification, which was previously determined "qualitatively," based on "quantitative" information. By operating a system that allows for this "quantitative" determination, it will be possible to eliminate subjective and arbitrary judgment factors on the part of certification investigators, etc., and make highly fair judgments. Moreover, because this "nursing care hours" can be calculated automatically and accurately, it will reduce the burden on certification investigators, etc. when determining nursing care needs.

[0107] The specific configuration of the nursing care certification support system 3 is as follows. FIG. 4 is a system diagram showing the basic configuration of the nursing care certification support system 3. Among these, the means (1) to (6) are common to the automatic care record creation system 1 shown in FIG.

[0108] The nursing care certification support system 3 is a system that uses the above-mentioned automatic nursing care record creation system 1 and automatic nursing care time grasping system 2. In other words, it is a system that uses the information on the care content and nursing care time grasped by these systems to support nursing care certification.

[0109] In the support system 3 for nursing care certification, the above-mentioned (7) determination means in the automatic nursing care time determination system 2 is specifically defined as follows. First, whether or not a particular care item should be calculated into care hours is determined based on whether or not it falls under one of the five care categories used in the initial assessment of nursing care certification: direct assistance with daily living, joint assistance with daily living, behavior-related behavior, functional training-related behavior, or medical-related behavior. Next, the calculation means (8) calculates the care time for each of the five care categories. The calculated care time is used as the reference time for the first determination of care need certification.

[0110] <Nursing care fee calculation support system> As an application example of the automatic care record creation system 1, a care fee calculation support system 4 will be described. FIG. 5 is a system diagram showing the basic configuration of the nursing care fee calculation support system 4. Among these, the means (1) to (6) are common to the automatic care record creation system 1 shown in FIG.

[0111] Nursing care fees are the fees paid to nursing care providers in exchange for providing nursing care services to users (those requiring nursing care or assistance). Nursing care fees are determined for each type of nursing care service, taking into account the average costs according to the service content or level of care required, the location of the business or facility, etc. The calculation and billing of nursing care fees requires fitting the content of nursing care services provided to each care recipient (care content) into pre-defined nursing care fee point items (units), which places a considerable burden on caregivers and care providers.The nursing care fee calculation support system 4 is a system that can automatically grasp the content of care actually provided and automatically fit it into point items (units).

[0112] The units for nursing care fees are determined based on the content of the nursing care service (nursing care content) and the time the nursing care service was provided (nursing care time). Therefore, it is necessary to accurately grasp the actual content of the nursing care provided and the time spent on nursing care. The care content and care time can be grasped by the above-mentioned automatic care content and care time grasping system 1. In the (7) judgment means in this automatic care time grasping system 2, the judgment criterion is whether or not the care service can be claimed as care remuneration. Furthermore, if the care service can be claimed as care remuneration, it is configured to fit into the applicable unit.

[0113] Once the units are known, the unit price can be determined based on the area classification, labor cost ratio, etc., making it possible to determine nursing care fees. The nursing care fee calculation support system 4 is configured to automatically grasp these units, calculate the unit price, and calculate nursing care fees.

[0114] <Care skill evaluation system> As an application example of the automatic care record creation system 1, a caregiver skill level evaluation system 5 will be described. FIG. 6 is a system diagram showing the basic configuration of the caregiver skill level evaluation system 5. As shown in FIG. Among these, the means (1) to (6) are common to the automatic care record creation system 1 shown in FIG.

[0115] The skill level of a caregiver is a numerical value or rank that evaluates the professional ability of a caregiver. In other words, it is a numerical value or rank that evaluates the ability required to perform care work such as care services and care tasks. The caregiver skill level evaluation system 5 is a system that automatically evaluates the skill level of a caregiver or a system that supports the evaluation. By properly assessing the skill level of caregivers, it is possible to develop and retain personnel in the care field.

[0116] Specifically, the skill level is evaluated in the following manner: First, the recording means in the automatic care record creation system 1 is used to obtain video data of a caregiver performing a care task.

[0117] Next, the captured video data is compared with a database of nursing skills. This database of nursing skills is a collection of information obtained by using deep learning on a large number of videos of nursing tasks. It is preferable to organize good and bad examples for each type of nursing task.

[0118] The collation method uses a computer equipped with artificial intelligence to collate video data of care work against a database of care skills to determine the skill of the care worker. For example, in the case of meal assistance, it is preferable to judge from multiple perspectives, such as whether the movement and speed of bringing food to the care recipient's mouth are appropriate, whether the care recipient is chewing correctly, and whether the care recipient is eating with the correct posture. In the case of walking assistance, it is also preferable to judge from multiple perspectives, such as whether the assistance is tailored to the care recipient's condition, whether there is a risk of injury to the care recipient, and whether the care recipient is paying attention to their surroundings.

[0119] After the nursing care work skills are judged using the method described above, the skill level is determined based on the judgment results and conforms to a pre-set level / rank. The skill level determined here can be set arbitrarily by each nursing care provider, etc.

[0120] The present invention can be used in applications in the field of nursing, that is, to provide an automatic system for creating nursing records. The problem to be solved by this invention is to provide an automatic nursing record creation system that can automatically and accurately grasp the specific content of nursing provided in the nursing field, automatically and accurately grasp the identification of the care recipient (patient) and the start and end times of nursing work, and automatically create nursing records. Furthermore, by utilizing this automatic nursing record creation system, it is possible to provide an automatic nursing time capture system, a nursing fee calculation support system, and a nurse (nurse) skill level evaluation system.

[0121] In this case, the "caregiver" in the explanation of the automatic care record creation system is the "caregiver (nurse)" and the "care recipient" is the "care recipient (patient)."

[0122] The configuration of the automatic nursing record creation system is the same as that of the automatic care record creation system, and the caregiver (nurse) will provide care while wearing a wearable device. Because there are differences in the format and the items to be recorded between care records and nursing records, appropriate adjustments will be necessary, but it is possible to adapt to the format and items to be recorded of publicly known nursing records.

[0123] The automatic nursing record creation system is also configured to start recording when the wearable device detects a match between the patient's name recognized by the face recognition means and the patient's name spoken by the nurse, and to stop recording when the wearable device detects the patient's name and a keyword indicating the end of nursing care services from the words spoken by the nurse.

[0124] With these configurations, the recording can be started or stopped automatically without bothering the nurse, and the nurse can maintain a hands-free state. Furthermore, patient identification can be double-checked using both facial recognition and the nurse's comments, allowing for automatic and accurate patient identification, preventing mistakes such as misidentifying patients or incorrectly recording the wrong patient's nursing record.

[0125] As an application example of the above configuration, the following configuration can be given. In cases where a nurse administers medication or intravenous drip to a patient, the wearable device uses image and video recognition to identify the name of the medication or intravenous drip, and is configured to confirm whether it matches the name of the medication or intravenous drip read out by the nurse. If there is a discrepancy, a warning can be issued, such as by issuing an alert. In addition, the wearable device may use image and video recognition functions to identify the names of medications and infusions, and compare them with the patient's nursing records, medical chart, or prescription to confirm that the medications and infusions prepared are correct.

[0126] This configuration allows the contents of the medicine or infusion to be double-checked, thereby preventing errors such as administering the wrong medicine or infusion to the patient. [Explanation of symbols]

[0127] 1. Automatic nursing care record creation system 2. Automatic care time tracking system 3. Support system for nursing care certification 4. Nursing care fee calculation support system 5. Caregiver Skill Level Assessment System W Wearable Device W1 Microphone Function W2 Camera Function W3 Face Shield C Computer S Mobile Information Terminal M storage medium N Network (wired / wireless) Y Care recipient Z. Caregiver

Claims

1. A system that automatically recognizes the content of the care services provided and automatically creates care records based on this, a wearable terminal including a means for capturing and recording the care provided by a caregiver, a means for collecting and recording the words spoken by the caregiver, and a communication means for transmitting the recorded video data and the recorded audio data to an external device; The system comprises a computer having means for receiving the video data and the audio data, analyzing the data, and automatically recognizing the care content, the wearable device is configured to start recording when the name of the care recipient recognized by the face recognition means matches the name of the care recipient verbally spoken by the caregiver; The computer means for automatically recognizing care content from the image of the care recipient included in the video data; a means for automatically recognizing the content of care from the words uttered by the caregiver contained in the voice data; The system further comprises a means for automatically recognizing the content of care from the video data and audio data and converting the content into text to create a care record.

2. The automatic care record creation system described in claim 1 is characterized in that the wearable terminal is configured to stop recording when it detects the name of the person being cared for and a keyword indicating the end of care services from words spoken by the caregiver.

3. Regarding a method for automatically recognizing the content of care from the words spoken by the caregiver contained in the voice data, The computer includes a means for storing in advance specific terms that represent specific care content, 2. The system for automatically creating a care record according to claim 1, wherein a specific term uttered by a caregiver is detected and the content of care is automatically recognized based on the specific term.

4. 2. The system for automatically creating a care record according to claim 1, wherein video data and audio data are recorded together with text indicating the content of care.

5. The automatic care record creation system described in claim 1 is characterized in that it is equipped with a means for comparing the care content automatically recognized from video data with the care content automatically recognized from audio data to confirm whether there are any differences in the care content provided at the same time.

6. A system using the automatic care record creation system according to claims 1 to 5, a means for automatically determining whether or not the care content is content that should be added to the care time; An automatic care time grasping system characterized by comprising means for accumulating the care time provided to each care recipient.

7. A system utilizing the automatic care time determination system according to claim 6, Regarding the means for automatically determining whether the care content should be accumulated in care time, The criteria for determining whether the care content falls into one of the five categories: direct assistance with daily living, joint assistance with daily living, behavioral problems, functional training, or medical care. For care content that falls under any of the five categories, the time required for this care is accumulated as care time, This support system for nursing care certification is characterized in that the accumulated nursing care time is used as the nursing care certification reference time in nursing care certification.

8. A system utilizing the automatic care time determination system according to claim 6, This is a system for evaluating the skill level of a caregiver, which evaluates the skill level of a caregiver based on the skill score obtained by analyzing video data and the care time required for each care content.

Images