Information processing method, program, and information processing system

Abstract

To properly arrange a record of care.SOLUTION: The information processing method includes (A) a step of specifying a first time at which any caregiver enters a specific room and a second time at which any caregiver exits the specific room from an image captured by a camera installed in a corridor, and recording the first time and the second time as an entry and exit record, and (B) a registration step of specifying a corresponding entry and exit record among a plurality of entry and exit records for each of a plurality of assistance items in schedule data including the plurality of assistance items to be executed for a resident in the specific room and execution scheduled times of the plurality of assistance items, and registering the specified entry and exit record as a start time and an end time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a technique for recording care activities. [Background technology]

[0002] For example, Patent Document 1 discloses a technology for home care in which a caregiver inserts an identification card into a reader in a terminal device each time they enter and leave the room of a care recipient to provide care, and the entry and exit times are transmitted to a computer via a communication line, thereby monitoring the execution status of the care schedule. It also discloses a configuration in which the computer issues an alarm if the caregiver's entry time is later than the time scheduled in the care schedule by a predetermined time interval or more, or if the time the caregiver spends in the room is shorter than a predetermined shortest target period or longer than a predetermined longest target period.

[0003] Furthermore, for example, Patent Document 2 discloses a business analysis system that includes a synchronized image acquisition means that synchronizes multiple images acquired from multiple video cameras to obtain synchronized images associated with location coordinates on a map, a flow line acquisition means that acquires the flow line of the business analysis target from the synchronized images, and a business content acquisition means that acquires the business content of the business analysis target in chronological order from the acquired flow line and location coordinates on a map, in order to perform business analysis by specifying an analysis target at a lower cost.

[0004] Patent Document 1 assumes home care, and with the widespread use of mobile devices such as smartphones, there is little motivation to install fixed cameras for such purposes. Patent Document 2 synchronizes multiple images from multiple video cameras to obtain information such as the movement paths of caregivers, but this is not necessarily the only task that requires the entire movement path of an individual caregiver to be analyzed. Furthermore, to obtain detailed movement paths, it would be desirable to install cameras not only in hallways but also in rooms, but installing cameras in rooms is not recommended from a privacy standpoint.

[0005] Meanwhile, at some nursing care facilities, caregivers are required to carry mobile devices such as smartphones and input the start and end times of assistance and the details of care (e.g., data describing the specific condition of the resident) when providing assistance to residents. However, this information is often forgotten or postponed. While the details of care can often be handled even if input is postponed, the start and end times often become unclear and cannot be restored later. However, accumulating the assistance time specified by the start and end times can lead to improvements and efficiency in assistance, so it is preferable to collect this information. However, further increasing the burden on caregivers is undesirable. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-259971 [Patent Document 2] Japanese Patent Publication No. 2023-12087 Summary of the Invention [Problem to be solved by the invention]

[0007] SUMMARY OF THE INVENTION It is therefore an object of the present invention, according to one aspect, to provide a novel technique for properly organizing records of care. [Means for solving the problem]

[0008] The information processing method of the present invention includes: (A) a step of identifying a first time when any caregiver enters a specific room and a second time when any caregiver leaves the specific room from video footage captured by a camera installed in a hallway, and recording these as entry / exit records; and (B) a registration step of identifying a corresponding entry / exit record from among multiple entry / exit records for each of multiple assistance items in schedule data that includes multiple assistance items to be performed on residents in the specific room and the scheduled times for performing the multiple assistance items, and registering these as start and end times. [Effects of the Invention]

[0009] In one aspect, it allows for proper documentation of care. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of a functional configuration of an information processing system according to an embodiment of the present invention. [Figure 2A] FIG. 2A is a diagram schematically illustrating an example of a hallway captured by a camera. [Figure 2B] FIG. 2B is a diagram schematically illustrating an example of a scene in which a caregiver enters a specific room in a hallway captured by a camera. [Figure 2C] FIG. 2C is a diagram schematically illustrating an example of a scene in which a caregiver leaves a specific room in a hallway captured by a camera. [Figure 3] FIG. 3 is a diagram illustrating an example of data stored in the entry / exit data storage unit in the first embodiment. [Figure 4] FIG. 4 is a diagram showing an example of schedule data for a caregiver stored in the schedule data storage unit in the first embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of data stored in the care input data storage unit in the first embodiment. [Figure 6] FIG. 6 is a diagram showing a processing flow of video processing in the first embodiment. [Figure 7] FIG. 7 is a diagram showing a processing flow of the recording process of care input data in the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating a processing flow of the analysis processing in the first embodiment. [Figure 9] FIG. 9 is a diagram for explaining the analysis process in the first embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of data stored in the output data storage unit according to the first embodiment. [Figure 11] FIG. 11 is a diagram illustrating an example of data stored in the output data storage unit according to the first embodiment. [Figure 12] FIG. 12 is a diagram illustrating a processing flow of the analysis processing in the first embodiment. [Figure 13] FIG. 13 is a diagram illustrating a processing flow of the care call response analysis processing according to the first embodiment. [Figure 14] FIG. 14 is a diagram showing an example of schedule data for a caregiver stored in the schedule data storage unit in the second embodiment. [Figure 15A] FIG. 15A is a diagram schematically illustrating an example of a scene in which a caregiver and a non-caregiver leave a specific room in a hallway captured by a camera. [Figure 15B] FIG. 15B is a diagram schematically illustrating an example of a scene in which a caregiver and a non-caregiver enter a specific room in a hallway captured by a camera. [Figure 16] FIG. 16 is a diagram showing a processing flow of video processing in the second embodiment. [Figure 17] FIG. 17 is a diagram illustrating a processing flow of the first processing in the second embodiment. [Figure 18] FIG. 18 is a diagram illustrating a processing flow of the second processing in the second embodiment. [Figure 19] FIG. 19 is a diagram illustrating an example of data stored in the entry / exit data storage unit in the second embodiment. [Figure 20] FIG. 20 is a diagram showing a processing flow of the recording process of care input data in the second embodiment. [Figure 21] FIG. 21 is a diagram illustrating an example of data stored in a care input data storage unit in the second embodiment. [Figure 22] FIG. 22 is a diagram illustrating a processing flow of the analysis processing in the second embodiment. [Figure 23] FIG. 23 is a diagram showing a process flow of the process for identifying records of entry and exit with unknown reasons in the second embodiment. [Figure 24] FIG. 24 is a diagram illustrating the analysis process according to the second embodiment. [Figure 25] FIG. 25 is a diagram illustrating a processing flow of the analysis processing in the second embodiment. [Figure 26] FIG. 26 is a diagram illustrating a processing flow of the analysis processing in the second embodiment. [Figure 27] FIG. 27 is a diagram illustrating a processing flow of the association processing in the second embodiment. [Figure 28] FIG. 28 is a diagram illustrating a processing flow of the association processing in the second embodiment. [Figure 29] FIG. 29 is a diagram illustrating an example of data stored in an output data storage unit according to the second embodiment. [Figure 30] FIG. 30 is a diagram illustrating a second example for explaining the analysis process in the second embodiment. [Figure 31] FIG. 31 is a diagram illustrating a second example of data stored in the output data storage unit in the second embodiment. [Figure 32] FIG. 32 is a diagram showing an example of schedule data for a caregiver stored in the schedule data storage unit in the third embodiment. [Figure 33] FIG. 33 is a diagram illustrating an example of data stored in the entry / exit data storage unit in the third embodiment. [Figure 34] FIG. 34 is a diagram illustrating an example of data stored in a care input data storage unit in the third embodiment. [Figure 35] FIG. 35 is a diagram illustrating a processing flow of the analysis processing in the third embodiment. [Figure 36] FIG. 36 is a diagram illustrating the analysis process according to the third embodiment. [Figure 37] FIG. 37 is a diagram illustrating an example of data stored in an output data storage unit according to the third embodiment. [Figure 38] FIG. 38 is a diagram illustrating an example of a functional configuration of a computer. DETAILED DESCRIPTION OF THE INVENTION

[0011] [Embodiment 1] In this embodiment, the system utilizes footage from security cameras installed in the hallways of a nursing home to determine whether any caregivers have entered or left a resident's room, and analyzes the assistance work. Note that the system is not limited to existing security cameras; newly installed cameras can also be used. However, to be able to utilize footage from existing security cameras, the camera resolution does not need to be clear enough to identify individual caregivers. Furthermore, given the premise that there are no cameras in resident rooms for privacy reasons, even if a camera is installed with the resident's permission, analysis can be performed even without the video from the camera in that room.

[0012] In this embodiment, care is provided only inside the resident's room. Furthermore, the room is a private room, and there is a one-to-one correspondence between a specific room and a resident.

[0013] First, an overview of the system according to this embodiment is shown in Fig. 1. As described above, cameras 200 installed in the corridors of the nursing care facility are connected to information processing system 100, and the captured images are stored in image storage unit 101. The number of cameras 200 is not limited to one, and multiple cameras may be installed. Information processing system 100 performs processing on each individual room or a room of interest that appears in the images captured by camera 200.

[0014] In addition, each resident is given a predetermined first schedule, which is written in a document such as Table 3 (also called the weekly service plan) of the care plan (also called the service plan), which specifies what assistance items the caregiver will provide and when.In addition, a second schedule is also determined in advance, which specifies what assistance items will be provided to which resident and when, based on the first schedule.

[0015] Each caregiver has a mobile terminal 300 (300a or 300b in FIG. 1) and uses the mobile terminal 300 to input care details (also referred to as assistance details) for each of the assistance items that the caregiver is scheduled to implement according to the second schedule. Note that, outside of the second schedule, there may be cases where assistance is required unexpectedly, and care details are also input in such cases. The mobile terminal 300 transmits the input data of the caregiver to the information processing system 100 as appropriate. The information processing system 100 receives the input data via the data receiving unit 108 and stores it in the care input data storage unit 109. The number of mobile terminals is not limited to two as shown in FIG. 1.

[0016] The information processing system 100 has a video storage unit 101, an entry / exit inference unit 102, an entry / exit data storage unit 103, a schedule data storage unit 104, an analysis unit 105, an output data storage unit 106, an output unit 107, a data receiving unit 108, a care input data storage unit 109, and a care call recording unit 110.

[0017] For example, when a care call is made by a resident from a room, the care call recording unit 110 records at least the time of the care call (received time) and the identifier of the room (or the resident's identifier) ​​that is the call source in the care input data storage unit 109. When a care call is made, typically, one of the caregivers goes to the room to respond. In this case, too, the caregiver uses the mobile terminal 300 to input the care details and stores the input data in the care input data storage unit 109.

[0018] The schedule data storage unit 104 stores, for example, first schedule data for each resident and second schedule data for each caregiver. The second schedule data for each caregiver can be accessed from the mobile terminal 300 and checked by each caregiver.

[0019] The entry / exit inference unit 102 determines whether any caregiver has entered or exited a specific room from the video footage of the hallway captured by the camera 200, and stores the entry and exit times in the entry / exit data storage unit 103 in association with the identifier of the specific room.

[0020] The entry / exit inference unit 102 includes, for example, a trained model that has been machine-learned in advance so that entry and exit can be identified using training data that specifies the entry and exit scenes without distinguishing between caregivers from the video captured by the camera 200. Instead of a trained model using machine learning, an appropriate technology related to artificial intelligence may be adopted for implementation.

[0021] For example, consider a situation where a hallway such as that shown in Fig. 2A is being photographed by camera 200. In this example image, six rooms appear, and the entry and exit times of any caregiver to each room are identified, and the entry and exit times are recorded in association with the room identifier. Here, for example, room 1000 is the focus of attention.

[0022] Then, by detecting a scene in which, for example, caregiver 1100 is walking down a corridor from the front of the page, stops in front of room 1000, opens the door as shown in Fig. 2B, enters room 1000, and then disappears from the corridor, entry into room 1000 can be identified. Note that in this embodiment, it is sufficient to identify any one of the caregivers, and since caregivers typically wear a uniform, entry into the room can be identified by identifying the uniform part in the video and tracking the movement of rectangle 1200 pointing to it.

[0023] Similarly, for example, by detecting a scene in which there is no one in front of room 1000, the door to room 1000 then opens, and caregiver 1100 appears in the hallway as shown schematically in FIG. 2C, and walks down the hallway toward the front of the page, for example, exit from room 1000 can be identified. Here too, exit can be identified by identifying the uniform part in the video and tracking the movement of rectangle 1200b pointing to it.

[0024] The entry / exit inference unit 102 stores data such as that shown in FIG. 3 in the entry / exit data storage unit 103. The example in FIG. 3 shows entry / exit data for a specific room, with the entry time and the exit time recorded in pairs. In this example, the first row contains an entry / exit record for an unknown reason, which is a record of an entry / exit that is not included in the schedule, and the fourth row contains an entry / exit record for non-regular assistance that is not included in the schedule but for which care input data exists. Even when non-regular assistance is provided, there may be cases where care input data has not been entered, so not all cases apply. However, from a security perspective, it is preferable to deal with entry / exits for an unknown reason separately, and therefore, in this embodiment, this is identified. The data in the remarks column is not registered by the entry / exit inference unit 102, but rather indicates notes for the following explanation.

[0025] The analysis unit 105 performs the analysis process described below using the data stored in the entry / exit data storage unit 103, the schedule data storage unit 104, and the care input data storage unit 109, and outputs the processing results to the output data storage unit 106. The output unit 107 outputs the data stored in the output data storage unit 106 to a display unit, a printer, or other output device. It may also output the data to another computer connected via a network. In some cases, the output unit 107 may read out and output a relevant portion from the video storage unit 101.

[0026] The analysis process includes a process for identifying and recording the start and end times of assistance tasks without the caregiver having to enter them into the mobile terminal 300, a process for identifying entries and exits for unknown reasons, and a process for identifying the response time for care calls.

[0027] It is assumed that the schedule data storage unit 104 stores second schedule data such as that shown in Fig. 4 in addition to the entry and exit records shown in Fig. 3. In the example of Fig. 4, the assistance item ID, user information (here, room ID + resident ID), assistance type, assistance category to which the assistance type belongs, scheduled assistance time, and person in charge are registered for each assistance item. In the following explanation, we will explain the processing target as Room 210 where Mr. A resides.

[0028] 3 and 4, care input data such as that shown in FIG. 5 is received from the mobile terminal 300 and stored in the care input data storage unit 109. In the example of FIG. 5, data on care content and the recording time of the data are registered in association with the assistance item ID, user information, assistance type, and person in charge. Note that the third line in the example of FIG. 5 is care input data for non-regular assistance not included in the schedule, i.e., non-regular assistance input data, and this is recorded. Note that the data in the remarks column indicates annotations for the following explanation.

[0029] Next, the processing contents of the information processing system 100 will be described with reference to FIGS. 6 to 13. First, the processing contents of the room entry / exit inference unit 102 will be described with reference to FIG. 6. The room entry / exit inference unit 102 reads a portion (e.g., a predetermined number of frames) of a video of a hallway captured by the camera 200 from the video storage unit 101 (step S1). The room entry / exit inference unit 102 executes a process to identify a caregiver in the read portion of the video (step S3). As described above, the room entry / exit inference unit 102 identifies, for example, a caregiver wearing a uniform of a nursing home. If the room entry / exit inference unit 102 cannot identify a caregiver in the read portion of the video (step S5: No route), the process proceeds to step S15. On the other hand, if the room entry / exit inference unit 102 can identify a caregiver in the read portion of the video (step S5: Yes route), the room entry / exit inference unit 102 tracks the movement of the identified caregiver and determines whether the caregiver has entered a specific room (step S7). If entry into a specific room can be identified, the entry / exit inference unit 102 records the entry time in association with the identifier of the specific room in the entry / exit data storage unit 103 (step S9). The process then proceeds to step S15. On the other hand, if entry into a specific room is not identified, the entry / exit inference unit 102 determines whether the caregiver has left the specific room based on the identified caregiver's movements (step S11). If exit from a specific room can be identified, the entry / exit inference unit 102 records the exit time in association with the identifier of the specific room in the entry / exit data storage unit 103 (step S13). The process then proceeds to step S15. On the other hand, if neither entry nor exit can be identified, for example, if the caregiver is simply walking down a hallway, the entry / exit is not recorded and the process proceeds to step S15.

[0030] Then, the processes of steps S1 to S13 are repeated until all of the video data for a predetermined time period (for example, one day's worth) stored in the video storage unit 101 has been processed (step S15). If multiple cameras 200 are installed, the video data captured by each of the cameras 200 is processed.

[0031] Next, the process of recording care input data from the mobile terminal 300 will be described with reference to FIG. 7. It is assumed that a dedicated application program is installed in the mobile terminal 300. The mobile terminal 300 acquires, for example, second schedule data stored in the schedule data storage unit 104, i.e., schedule data of a specific caregiver who is the user of the mobile terminal 300a, and displays it on the display device (step S21). For example, a list of assistance items to be performed by the caregiver is displayed in chronological order. The caregiver then selects from the list the assistance item for which care content is to be input, or selects whether to input care content for non-regular assistance that is requested to be performed separately from the second schedule.

[0032] When an assistance item included in the second schedule, i.e., a scheduled assistance item, is selected (step S23: Yes route), the mobile terminal 300 accepts input of care content for the assistance item from the caregiver and transmits input data of the care content for the assistance item to the data receiving unit 108 of the information processing system 100 (step S25). The data receiving unit 108 receives the input data of the care content for the assistance item from the mobile terminal 300 and stores it in the care input data storage unit 109 together with the recording date and time (or the data reception time or data transmission time) to be recorded in the care input data storage unit 109. Then, the processing proceeds to step S29.

[0033] On the other hand, when entering care details for non-regular assistance (step S23: No route), the mobile terminal 300 accepts input from the caregiver of the identifier (ID) of the target resident, the assistance items, and the care details, and transmits them as non-regular assistance input data to the data receiving unit 108 of the information processing system 100 (step S27). The data receiving unit 108 receives the non-regular assistance input data and stores it in the care input data storage unit 109 together with the recording date and time.

[0034] Then, the processes of steps S23 to S27 are repeated until input is completed for all scheduled assistance items (step S29).

[0035] In this embodiment, it is preferable to input the care content etc. immediately after the work for the scheduled assistance item is completed, but there are cases where the input is not made immediately after the work is completed. However, when non-scheduled assistance is performed, the input is made immediately after the work is completed for the purpose of analysis processing.

[0036] Next, the details of the analysis process will be described with reference to FIGS.

[0037] First, analysis unit 105 initializes n, which is a room counter, to 1 in order to process each room (i.e., each resident) (FIG. 8: step S31). Then, analysis unit 105 reads the entry and exit record (i.e., a pair of entry and exit records) for the nth room from entry and exit data storage unit 103 (step S33).

[0038] Furthermore, the analysis unit 105 initializes an entry / exit record counter i to 1 in order to process the entry / exit records in order (step S35). Then, the analysis unit 105 searches for an assistance item corresponding to the i-th entry / exit record from among the assistance item group registered for the occupant of the n-th room in the schedule data storage unit 104 (step S37). In this step, the analysis unit 105 determines the similarity between the combination of the entry time, exit time, and stay duration (= exit time - entry time) and the planned assistance time recorded in association with the assistance item.

[0039] Figure 9 shows a diagram illustrating the comparison between the entry and exit data shown in Figure 3 and the schedule data shown in Figure 4. There are four entry and exit records, with the first line being an entry and exit record for an unknown reason and the fourth line being an entry and exit record for non-regular assistance.

[0040] For the entry / exit record on the first line, it is determined that there is no similar scheduled assistance time. On the other hand, for the entry / exit record on the second line, it is determined that it is similar to the scheduled assistance time for assistance item "001". For the entry / exit record on the third line, it is also determined that it is similar to the scheduled assistance time for assistance item "002". For the entry / exit record on the fourth line, it is determined that there is no similar scheduled assistance time.

[0041] If an assistance item corresponding to the i-th entry / exit record is identified in step S37 (step S39: Yes route), the analysis unit 105 extracts input data on the care content entered for the identified assistance item from the care input data storage unit 109 (step S41). Since an assistance item is assigned an assistance item ID, the input data on the care content is read out using the assistance item ID.

[0042] The analysis unit 105 also registers the data of the assistance items stored in the schedule data storage unit 104, the input data on the extracted care content, and the i-th entry / exit record in the output data storage unit 106 (step S43). The process shifts to the process of FIG. 12 via terminal A.

[0043] Fig. 10 shows an example of data stored in the output data storage unit 106. In the example of Fig. 10, the start time (i.e., entry time), end time (i.e., exit time), hours (minutes: end time - start time), and care content are registered in association with the assistance item ID, user information, assistance type, and person in charge. Data for assistance item IDs "001" and "002" are registered in step S43.

[0044] On the other hand, if an assistance item corresponding to the i-th entry / exit record is not identified in step S37 (step S39: No route), the analysis unit 105 searches for an item corresponding to the i-th entry / exit record in the non-regular assistance input data (step S45). The analysis unit 105 identifies the non-regular assistance input data registered for the occupant of the n-th room, whose recorded time is similar to the exit time in the i-th entry / exit record. In the example of FIG. 5, the third line is the non-regular assistance input data for the occupant of the n-th room with user information "No. 210_A," and the recorded time "11:30" is similar to the exit time. Therefore, this non-regular assistance input data is identified.

[0045] If non-regular assistance input data is identified in step S45 (step S47: Yes route), the analysis unit 105 stores the identified non-regular assistance input data and the i-th entry / exit record in the output data storage unit 106 (step S49). Then, the process proceeds to the process of FIG. 12 via terminal A. In the example of FIG. 10, the third line is data regarding non-regular assistance, and the i-th entry / exit record is recorded as the start time and end time. Also, in FIG. 10, the end time - start time is also registered as the required time.

[0046] On the other hand, if non-regular assistance input data is not identified in step S45 (step S47: No route), the analysis unit 105 registers the i-th entry / exit record as an entry / exit record with an unknown reason in the output data storage unit 106 (step S51). Then, the process proceeds to the process of FIG. 12 via terminal A.

[0047] Since this is processing for the nth room, user information identifying the occupant of the nth room is also registered. In this example, as shown in Fig. 11, the entry time, exit time, and time (= exit time - entry time) are registered in association with the user information.

[0048] Shifting to the explanation of the processing after terminal A, the analysis unit 105 determines whether i has reached its maximum value (FIG. 12: step S53). If i has not reached its maximum value, the analysis unit 105 increments i by 1 (step S55), and the processing returns to step S37 in FIG. 8 via terminal C. On the other hand, if i has reached its maximum value, the analysis unit 105 determines whether a care call has been made from the nth room during the period in which processing should be performed (step S57). As described above, data about care calls is also stored in the care input data storage unit 109, and therefore, it is determined whether data about care calls is stored in association with user information.

[0049] If a care call is not being made from the nth room, the process proceeds to step S61. On the other hand, if a care call is being made from the nth room, the analysis unit 105 executes a care call response analysis process (step S59). This process will be described later with reference to FIG. 13.

[0050] Then, the analysis unit 105 determines whether or not n has reached its maximum value (step S61). If n has not reached its maximum value, the analysis unit 105 increments n by 1 (step S63), and the processing returns to step S33 in FIG. 8 via terminal B.

[0051] On the other hand, if n reaches its maximum value, the analysis unit 105 determines whether or not any entry / exit records for unknown reasons have been identified in the processing up to this point (step S65). If no entry / exit records for unknown reasons have been identified, the processing ends.

[0052] On the other hand, if an entry / exit record for an unknown reason has been identified, the analysis unit 105 causes the output unit 107 to output a warning, such as displaying or notifying the administrator, that an entry / exit record for an unknown reason has been identified (step S67). Note that an entry / exit record for an unknown reason includes the entry time and the exit time, so the output unit 107 may read video data for the time period before and after that from the video storage unit 101 and output it, for example, in response to a request from the administrator. Data other than the entry / exit record for an unknown reason may also be output.

[0053] By executing this process, even if the caregiver has not registered the start and end times of the work for each assistance item, the start and end times can be identified from the image from the camera 200. In other words, the input burden on the caregiver can be reduced. Note that, as a rule, the caregiver inputs the start and end times from the mobile terminal 300, and this process may be executed as a supplementary step in case the caregiver forgets to input the times.

[0054] Furthermore, entering a room when it is not scheduled or explicitly requested by the resident is typically not recommended, as it can pose a security risk. If such unexplained room entry / exits are identified, it will be easier to later confirm the reason. It will also be easier to determine whether or not an unscheduled assistance entry was missed.

[0055] Next, the care call response analysis process will be described with reference to Fig. 13. The process in Fig. 13 is a process for one care call.

[0056] The analysis unit 105 searches for non-regular assistance input data, for example, in the care input data storage unit 109 (or the output data storage unit 106), based on the room from which the care call was sent and the time of receipt (step S71). More specifically, the analysis unit 105 identifies the non-regular assistance input data in which the entry time closest to the time of receipt of the care call is registered.

[0057] The analysis unit 105 then calculates the difference between the time the care call was received and the time the patient entered the room (step S73). The analysis unit 105 then determines whether the care call can be associated with the non-regular assistance input data, for example, depending on whether the difference is equal to or smaller than a threshold value (e.g., the longest possible time for responding to a care call) (step S75).

[0058] If the difference is too long to allow for matching, the analysis unit 105 registers "no dispatch" for the care call (step S79). Processing for the care call then ends, and the process returns to the caller's process. Since "no dispatch" may be appropriate in some cases, this point will also be confirmed later.

[0059] On the other hand, if the care call can be associated with the non-regular assistance input data, the analysis unit 105 associates the difference with the care call and registers it (step S77). The process for the care call then ends, and the process returns to the caller. In this way, the response time for the care call (the difference) can be obtained.

[0060] As described above, response time can be obtained for care calls, and by accumulating this time, it can be used to review operations, etc.

[0061] [Embodiment 2] In the first embodiment, assistance was provided only inside the resident's room, but in this embodiment, assistance is provided not only inside the resident's room, but also when the resident is accompanied on trips or in places outside the room (for example, the dining room). Note that rooms are private, and there is a one-to-one correspondence between a specific room and a resident.

[0062] For example, it is assumed that the second schedule data shown in Fig. 14 is stored in the schedule data storage unit 104. In this schedule, first, assistance with movement from the living room to the dining room, second, assistance with eating in the dining room, third, assistance with movement from the dining room to the living room, fourth, assistance with excretion, and fifth, cleaning are performed. In the example of Fig. 14, there is only one person in charge, "D," and at the discretion of the person in charge, multiple assistance items may be performed consecutively even if time intervals are set for each assistance item.

[0063] In this embodiment, the function of the entry / exit inference unit 102 is added to appropriately grasp the situation from the video captured by the camera 200. Specifically, in addition to the caregiver's entry and exit alone as shown in the first embodiment, it is possible to identify the caregiver leaving or entering a room accompanied by a person other than the caregiver (a non-caregiver; generally, a care recipient, but the care recipient status is not identified). For example, by detecting a scene in which there is no one in front of the living room 1000, the door to the living room 1000 subsequently opens, and a caregiver 1100 and a non-caregiver 1300 appear together in the hallway as schematically shown in FIG. 15A and, for example, walk down the hallway together toward the front of the page, it is possible to identify the caregiver's exit from the living room 1000 accompanied by a person. Here, by identifying, for example, a uniform part in the video and tracking the movement of a rectangle 1200c pointing to the uniform part and a rectangle 1400a pointing to a person moving near the rectangle 1200c, it is possible to identify the caregiver's exit accompanied by a person. If the caregiver 1100 moves around in a wheelchair, the movement of the rectangle pointing to the uniform of the caregiver 1100 and the rectangle pointing to the non-caregiver 1300 in the wheelchair will be tracked.

[0064] Similarly, by detecting a scene in which, for example, caregiver 1100 and non-caregiver 1300 are walking down a corridor from the front of the page, stop in front of room 1000, open the door as shown schematically in Fig. 15B, and then disappear from the corridor, it is possible to identify entry into room 1000 as accompanied. Here too, entry into room 1000 as accompanied can be identified by identifying, for example, the uniform portion of caregiver 1100 in the video and tracking the movement of rectangle 1200d pointing to the uniform portion and rectangle 1400b pointing to the person moving near rectangle 1200d.

[0065] For this reason, the entry / exit inference unit 102 executes the processes shown in Figures 16 to 18 instead of the process in Figure 6. The differences from Figure 6 are that step S81 is executed instead of step S9, and step S83 is executed instead of step S13. In step S81, the first process shown in Figure 17 is executed. In step S83, the second process shown in Figure 18 is executed. The other steps are the same, so their explanations will be omitted.

[0066] In the first process, the entry / exit inference unit 102 determines whether or not a non-caregiver has been detected (FIG. 17: step S91). If a non-caregiver has been detected, the entry / exit inference unit 102 records the entry time with an accompanying flag in association with the identifier of the specific room (step S93). The process then returns to the original process. On the other hand, if a non-caregiver has not been detected, that is, the caregiver has entered the room alone, the entry / exit inference unit 102 records the entry time in association with the identifier of the specific room (step S95). The process then returns to the original process. In this way, whether or not a caregiver is accompanied is distinguished from the other information when it is registered.

[0067] Similarly, in the second process, the entry / exit inference unit 102 determines whether or not a non-caregiver is detected (FIG. 18: step S101). If a non-caregiver is detected, the entry / exit inference unit 102 records the exit time with an accompanying flag in association with the identifier of the specific room (step S103). The process then returns to the original process. On the other hand, if a non-caregiver is not detected, that is, if the caregiver left the room alone, the entry / exit inference unit 102 records the exit time in association with the identifier of the specific room (step S105). The process then returns to the original process. In this way, whether or not a caregiver is accompanied is distinguished from the other information when it is registered.

[0068] By performing this processing, entry and exit data such as that shown in FIG. 19 is stored in the entry and exit data storage unit 103. In the example of FIG. 19, the W in "8:18W" and "9:02W" represents the accompanying flag, indicating that the caregiver and non-caregiver left the room at 8:18 and that the caregiver and non-caregiver entered the room at 9:02. Note that even in this embodiment, entries and exits for unknown reasons and entries and exits due to non-regular assistance are recorded. Furthermore, it is difficult to determine whether the assistance items were performed consecutively just by looking at this. Note that the data in the remarks column is merely an annotation for the following explanation.

[0069] Therefore, in this embodiment, when the same caregiver performs multiple consecutive assistance items that are scheduled for the same resident, the caregiver inputs the information using the mobile terminal 300. Specifically, instead of the processing shown in Fig. 7, the processing shown in Fig. 20 is executed by the mobile terminal 300. Note that the difference from Fig. 7 is that step S111 is additionally executed after step S25.

[0070] In step S111, if there are any assistance items that have been performed consecutively from the caregiver, the mobile terminal 300 accepts the designation of those items and transmits data on the designation to the data receiving unit 108 of the information processing system 100. The data receiving unit 108 receives data on the assistance items that have been performed consecutively from the mobile terminal 300 and stores the data in the care input data storage unit 109.

[0071] For example, in this embodiment, data as shown in Fig. 21 is stored in the care input data storage unit 109. Compared to the example of the first embodiment shown in Fig. 5, information on successive implementation is additionally recorded, and in this example, it is indicated that the first to fourth assistance items marked with circles, namely, mobility assistance, meal assistance, mobility assistance, and toilet assistance, have been implemented successively.

[0072] Next, the processing executed by the analysis unit 105 will be described with reference to FIGS.

[0073] To perform processing for each room, analysis unit 105 first initializes n, which is a counter for the room, to 1 (FIG. 22: step S121). Then, analysis unit 105 reads the entry and exit record for the nth room from entry and exit data storage unit 103 (step S123).

[0074] The analysis unit 105 then executes a process for identifying records of entry and exit for unknown reasons for the read entry and exit records (step S125). This process is performed to extract records of entry and exit for unknown reasons in advance if a resident has entered or left the room while the resident has left, in order to check the records separately from a security perspective and to facilitate subsequent processing. This process will be described with reference to FIG. 23.

[0075] The analysis unit 105 determines whether or not there is an entry / exit record between the exit time with an accompanying flag and the entry time with an accompanying flag (FIG. 23: step S131). In the example of FIG. 19, there is an entry / exit record with an entry time of "8:55" and an exit record of "9:00" between the exit time with an accompanying flag of "8:18W" and the entry time with an accompanying flag of "9:02W". If no such entry / exit record exists, the process returns to the original process.

[0076] On the other hand, if such an entry / exit record is included, the analysis unit 105 identifies the identified entry / exit record as an entry / exit record with an unknown reason, associates it with the room identifier, and registers it in the output data storage unit 106 (step S133). The analysis unit 105 also excludes the entry / exit record with an unknown reason from the entry / exit record for the room (step S135). This process is performed to ensure smooth execution of subsequent processes. The process then returns to the process that called it.

[0077] Returning to the explanation of the process in Fig. 22, the analysis unit 105 references the implementation records of the caregiver appearing in the care input data and generates an assumed entry and exit record in accordance with the first schedule data (step S127). In this embodiment, when consecutive assistance items for the same resident are assigned to the same caregiver, the items may or may not be implemented consecutively depending on the circumstances at the time. Therefore, simply comparing the first schedule data with the entry and exit record may not result in a correspondence, and therefore this step is executed.

[0078] This step will be explained by summarizing the above-mentioned example in Figure 24. In this example, person in charge D is assigned to all assistance items "001" to "0005," but person in charge D has registered that assistance items "001" to "004" have been performed consecutively. From this record of consecutive execution and the first schedule data stored in the schedule data storage unit 104, the analysis unit 105 predicts the times when entry and exit will occur and sets them as the expected entry time and expected exit time.

[0079] In the example of Figure 24, assistance item "001" is mobility assistance, and since it is the first assistance item in a series, entry and exit will occur, so an expected entry time and an expected exit time are set. The expected entry time and expected exit time may be the start and end times of the scheduled assistance time, and the expected exit time may be set based on past performance (for example, the average interval between entry and exit).

[0080] Furthermore, since assistance item "002" is meal assistance, no entry or exit occurs, so no expected entry record or expected exit record is set. Assistance item "003" is mobility assistance, so in principle entry and exit occurs, but since assistance items "001" to "004" were performed consecutively, only entry occurs. Since assistance items "001" to "004" were performed consecutively, the expected entry time is set taking into consideration the fact that the interval between each assistance item is omitted. In this example, there is a 10-minute interval between assistance items "001" and "002," so the expected entry and exit record is set to reflect this, excluding all or part of this 10 minutes. In this example, for example, based on past performance, the time is set to 9:00, half the time, or 5 minutes, earlier.

[0081] Furthermore, assistance item "004" is toilet assistance, and although there is a 5-minute interval between it and assistance item "003," because they were performed consecutively, the end time of the scheduled assistance time is brought forward by 5 minutes to set the expected departure time. Assistance item "005" is an assistance item performed independently, so the start and end times of the scheduled assistance time are set as the expected entry and departure times.

[0082] Such expected entry and exit times are set in accordance with various rules that are determined in advance, for example.

[0083] Returning to the explanation of the processing in FIG. 22, the analysis unit initializes the entry / exit record counter i and the assumed entry / exit record counter j to 1 (step S129). Then, the processing shifts to the processing in FIG. 25 via terminal D.

[0084] 25, the analysis unit 105 determines whether the i-th entry / exit record corresponds to the j-th estimated entry / exit record (step S141). For example, the analysis unit 105 determines whether there is a correspondence based on the similarity of the start time and the required time. In the example of FIG. 24, the actual entry time and estimated entry time for assistance item "001" are similar, and furthermore, (actual exit time - actual entry time) and (estimated exit time - estimated entry time) are similar, so it is determined that there is a correspondence. Furthermore, the actual entry time and estimated entry time for assistance items "003" and "004" are similar, and furthermore, (actual exit time - actual entry time) and (estimated exit time - estimated entry time) are similar, so it is determined that there is a correspondence. Regarding similarity, when consecutive events are performed, the estimated time and the scheduled time are likely to differ, so it is preferable to use a method that sets looser criteria for the determination when consecutive events are performed. Furthermore, the actual entry time and the estimated entry time for assistance item "005" are similar, and furthermore, (actual exit time - actual entry time) and (estimated exit time - estimated entry time) are also similar, so it is determined that they correspond.

[0085] If it is determined that the i-th entry / exit record corresponds to the j-th assumed entry / exit record, the analysis unit 105 executes a correlation process (step S143). Then, the process proceeds to the process of Fig. 26 via terminal E. Details of this step will be described with reference to Figs. 27 and 28.

[0086] If it is not determined that the i-th entry / exit record corresponds to the j-th assumed entry / exit record, the analysis unit 105 searches for an item corresponding to the i-th entry / exit record in the non-regular assistance input data (step S145). This is the same as step S45 in FIG. 8. That is, the analysis unit 105 identifies the non-regular assistance input data registered for the occupant of the n-th room, whose recorded time is similar to the exit time in the i-th entry / exit record. In the example of FIG. 21, the sixth line is the non-regular assistance input data for the occupant of the n-th room with user information "No. 210_A," and the recorded time "11:30" is similar to the exit time. Therefore, this non-regular assistance input data is identified.

[0087] If non-regular assistance input data is identified in step S145 (step S147: Yes route), the analysis unit 105 stores the identified non-regular assistance input data and the i-th entry / exit record in the output data storage unit 106 (step S149). This step is the same as step S47 in FIG. 8. That is, for the non-regular assistance input data, the i-th entry / exit record is recorded as the start time and end time. Then, the analysis unit 105 decrements j by 1 (step S151). This is to cancel the increment of j that is performed uniformly in later processing, because the i-th entry / exit record and the j-th assumed entry / exit time were not associated. Then, the processing proceeds to the processing of FIG. 26 via terminal E.

[0088] On the other hand, if no non-regular assistance input data is identified in step S145 (step S147: No route), the analysis unit 105 registers the i-th entry / exit record as an entry / exit record with an unknown reason in the output data storage unit 106 (step S153). This step is the same as step S51 in FIG. 8. Since this is processing for the n-th room, user information identifying the occupant of the n-th room is also registered. That is, the entry time, exit time, and duration (= exit time - start time) are registered in association with the user information. Then, the analysis unit 105 decrements j by 1 (step S155). This step is the same as step S151. Then, the processing proceeds to the processing of FIG. 26 via terminal E.

[0089] The processing from terminal E onwards (FIG. 26) is similar to the processing in FIG. 12. That is, step S53 and steps S57 to S67 are the same as the processing in FIG. 12, and therefore description thereof will be omitted. The difference between the processing in FIG. 12 and that in FIG. 26 is that step S157 is executed instead of step S55. Specifically, the analysis unit 105 increments i by 1 and increments j by 1, and the processing returns to the top of FIG. 25 via terminal D (step S157). Note that the processing after step S63 returns to step S123 in FIG. 22 via terminal F.

[0090] In this way, even in cases such as those described at the beginning of the second embodiment, it is possible to properly estimate the start and end times of assistance items, record and output entries and exits for unknown reasons, record non-regular assistance, and analyze care call responses.

[0091] Next, the association process will be described with reference to FIGS.

[0092] First, the analysis unit 105 determines whether the j-th estimated entry and exit record corresponds to multiple assistance items (step S161). In the example of FIG. 24, assistance items "003" and "004," which were performed consecutively, are associated with one estimated entry and exit record including an estimated entry time and an estimated exit time. On the other hand, assistance item "001," which was performed consecutively, is associated with one estimated entry and exit record including an estimated entry time and an estimated exit time. Similarly, assistance item "005" is associated with one estimated entry and exit record including an estimated entry time and an estimated exit time.

[0093] If the j-th assumed entry / exit record does not correspond to multiple assistance items (step S161: No route), the analysis unit 105 calculates the time difference from the i-th entry time to the i-th exit time (step S171). The analysis unit 105 also extracts, from the care input data storage unit 109, the care content input for the assistance item corresponding to the j-th assumed entry / exit record for the n-th room (step S173). The analysis unit 105 then stores the i-th entry time and exit time, the input care content, and the calculated time difference in the output data storage unit 106, in association with the assistance item corresponding to the j-th assumed entry / exit record (step S175). The i-th entry / exit record is also registered as the start time and end time. The process then proceeds to the process of FIG. 28 via a terminal G.

[0094] In the above example, for assistance items "001" and "005" in Figure 24, the entry time as the start time, the exit time as the end time, the care input data, and the calculated time difference are registered in association with the data for the assistance item. This is shown in Figure 29.

[0095] On the other hand, if the jth assumed entry / exit record corresponds to multiple assistance items (step S161: Yes route in FIG. 27), the analysis unit 105 calculates the time difference from the i-th entry time to the i-th exit time (step S163). The analysis unit 105 also apportions the time difference calculated in step S163 based on the ratio of each planned assistance time to the total planned assistance time (here, planned end time - planned start time) for the multiple assistance items (step S165). In the example described above, for assistance items "003" and "004" in FIG. 24, the actual entry time (start time) is 9:02 and the actual exit time (end time) is 9:08. The planned assistance time for assistance item "003" is 5 minutes and the planned assistance time for assistance item "004" is 5 minutes, so the ratio of the planned assistance times for each is 1 / 2. When the time difference of 6 minutes is apportioned based on this ratio, each is 3 minutes. Such apportioned time (minutes) is registered as shown in Fig. 29. Since the time is apportioned, the start time and end time of each of these assistance items are not registered, but the corresponding times may be registered as shown in Fig. 29. Then, the analysis unit 105 extracts input data of the care content entered for each assistance item from the care input data storage unit 109 (step S167).

[0096] Then, the analysis unit 105 registers the input care content and apportioned time in association with each assistance item in the output data storage unit 106 (step S169). Then, the processing shifts to the processing of FIG. 28 via a terminal G.

[0097] 28, the analysis unit 105 determines whether or not an accompanying flag is attached to the exit time in the i-th entry / exit record (step S177). If an accompanying flag is not attached to the exit time in the i-th entry / exit record, the process returns to the process that called the call.

[0098] On the other hand, if an accompanying flag is attached to the exit time in the i-th entry / exit record, the analysis unit 105 extracts the corresponding entry time with the accompanying flag from the entry / exit record for the n-th room (step S179). Here, the analysis unit 105 extracts the entry time with the accompanying flag immediately after the exit time with the accompanying flag. Then, the analysis unit 105 calculates the time difference from the exit time with the accompanying flag to the entry time with the accompanying flag (step S181). In the example of FIG. 24, the actual exit time of assistance item "001" is "8:18" with an accompanying flag, and the corresponding actual entry time with the accompanying flag is "9:02". Therefore, the time difference is 44 minutes.

[0099] Thereafter, the analysis unit 105 extracts, for the nth room, the care content input for the assistance item next to the assistance item corresponding to the jth assumed entry / exit record from the care input data storage unit 109 (step S183). Furthermore, the analysis unit 105 registers the input care content and the calculated time difference in the output data storage unit 106 in association with the data for the next assistance item (step S185). The process then returns to the calling process. In the example of FIG. 29, a time difference of 44 minutes is registered as the actual required time for meal assistance, which is assistance item "002" next to assistance item "001."

[0100] By performing the above-described processing, it is possible to obtain a rough estimate of the required time for assistance such as meal assistance, which is performed in a location other than the patient's room.

[0101] Note that the example described above shows an example in which multiple assistance items are carried out consecutively, but we will briefly explain an example in which no consecutive implementation is carried out at all in a similar schedule using Figures 30 and 31.

[0102] In the example of Figure 24, assistance items "001" to "004" are performed consecutively, so for assistance items "003" and "004," the actual exit time for assistance item "003" and the actual entry time for assistance item "004" are not recorded. On the other hand, in the example of Figure 30, assistance items are not performed consecutively, so these times are also recorded. Since this is anticipated, the corresponding estimated entry and exit times are also set. As a result, for assistance items "001," "003," "004," and "005," the estimated entry and exit records are associated with the actual entry and exit records, respectively.

[0103] 27 and 28, data such as that shown in Fig. 31 is stored in the output data storage unit 106. In the example of Fig. 29, there were assistance items "003" and "004" whose required time was apportioned by being performed consecutively, but in the example of Fig. 31, all are performed independently, so there are no assistance items for which apportioned time is calculated, and the required time is calculated from the end time (time to leave the room) - the start time (time to enter the room).

[0104] [Embodiment 3] In the second embodiment, the mobility assistance before and after meal assistance is set separately. This allows different caregivers to be assigned to meal assistance and mobility assistance before and after meal assistance, which allows for flexibility in scheduling caregivers. However, in some cases, when assistance is provided in a location other than the living room, such as bathing assistance or meal assistance, mobility assistance is almost always provided before and after meal assistance, so there are cases where mobility assistance + meal assistance + mobility assistance is considered to be meal assistance and scheduled.

[0105] For example, assume that second schedule data as shown in Fig. 32 is stored in the schedule data storage unit 104 instead of the second schedule data as shown in Fig. 14. The example in Fig. 32 shows a schedule for providing assistance that is substantially the same as the second schedule as shown in Fig. 14.

[0106] This embodiment deals with such a case. In this case, the basic processing content is the same as in the second embodiment. The differences will be explained below with reference to Figs. 33 to 37.

[0107] First, the recording of the entry time and the exit time is the same, and the recording of the entry time and the exit time with the accompanying flag is also performed in the same way. The same applies to the registration of care input data, including the recording of consecutive care.

[0108] FIG. 33 shows an example of entry / exit records stored in the entry / exit data storage unit 103 according to this embodiment. While this is essentially the same as in the second embodiment, since mobility assistance + meal assistance + mobility assistance constitutes meal assistance, it cannot be processed well using the same analysis process as in the second embodiment. Again, the data in the remarks column in this figure is merely a note for the following explanation. Note that FIG. 34 shows an example of care input data according to this embodiment. In this example, as with the first specific example in the second embodiment, it is recorded that meal assistance and toilet assistance were performed consecutively.

[0109] In order to process such data appropriately, the process of Fig. 22 according to the second embodiment is modified as shown in Fig. 35. Specifically, a new step S201 is added between step S127 and step S129 also shown in Fig. 22.

[0110] Specifically, the analysis unit 105 deletes entry and exit records with accompanying flags (step S201). In the example of Fig. 33, "8:18W", which is the exit time for moving from the living room to the dining room, and "9:02W", which is the entry time for moving from the dining room to the living room, are deleted. This is because an assistance item for mobility assistance alone is not provided.

[0111] In such a case, the correspondence is made as shown in Fig. 36. In the example of Fig. 36, assistance items "101" and "102" are performed consecutively, so the estimated entry and exit records including their estimated entry times and estimated exit times are corresponded to the entry and exit records including the first entry and exit times. Furthermore, assistance item "103" is performed alone, so the second estimated entry and exit record is corresponded to the second entry and exit record. Note that non-regular assistance and entry and exit records for unknown reasons are extracted in the same way as in the second embodiment, so a description thereof will be omitted here.

[0112] When an analysis process is performed on such data, data such as that shown in FIG. 37 is stored in the output data storage unit 106. In this embodiment, assistance items "101" and "102" are performed consecutively, so the time difference between the first entry time and the first exit time is apportioned based on the ratio of the planned assistance times for the two assistance items, resulting in 51.82 minutes for meal assistance and 5.18 minutes for toilet assistance. The rest is the same as in the second embodiment. Note that the meal assistance in this embodiment is mobility assistance + meal assistance + mobility assistance in the second embodiment, so further breakdowns may be calculated and registered according to predetermined rules, such as 5 minutes for the return trip, 5 minutes for the outbound trip, and a remaining 41.82 minutes.

[0113] Although the embodiments of the present invention have been described above, the present invention is not limited to these. For example, the functional configuration of the information processing system shown in Figure 2 is an example, and may differ from the program configuration. Furthermore, the processing flow is also an example, and the processing order may be changed or multiple steps may be executed simultaneously as long as the same processing results can be obtained.

[0114] Furthermore, while the example above shows the installation of a camera in a hallway, a hallway is not limited to simply functioning as a passageway, but may also face the residents' rooms and include spaces used by multiple residents (for example, conversation spaces and dining spaces).

[0115] The information processing system described above is, for example, a computer device as shown in FIG. 38 , in which a memory 2501, a CPU 2503, a hard disk drive (HDD) 2505, a display control unit 2507 connected to a display device 2509, a drive device 2513 for a removable disk 2511, an input device 2515, and a communication control unit 2517 for connecting to a network are connected via a bus 2519. An operating system (OS) and an application program for carrying out the processing of this embodiment are stored in the HDD 2505, and when executed by the CPU 2503, they are read from the HDD 2505 to the memory 2501. The CPU 2503 controls the display control unit 2507, the communication control unit 2517, and the drive device 2513 in accordance with the processing content of the application program to perform predetermined operations. Data during processing is mainly stored in the memory 2501, but may also be stored in the HDD 2505. In an embodiment of the present invention, an application program for performing the above-described processing is distributed by being stored on a computer-readable removable disk 2511, and is installed from the drive device 2513 onto the HDD 2505. It may also be installed onto the HDD 2505 via a network such as the Internet and the communication control unit 2517. Such a computer device realizes the above-described various functions through organic cooperation between hardware such as the CPU 2503 and memory 2501 described above and programs such as the OS and application programs.

[0116] Furthermore, the entry / exit inference unit 102 and the like may be implemented using not only the CPU 2503 but also a plurality of GPUs (Graphics Processing Units).

[0117] Furthermore, instead of implementing all of the functions of the information processing system in a single computer device, the functions may be shared among multiple computer devices. For example, multiple functions may be implemented in different computers connected to a network. Also, some or all of the functions may be implemented on a cloud. Note that whether the system is implemented in a single computer device or multiple computer devices, the system as a whole is referred to as an information processing system.

[0118] The above-described embodiment can be summarized as follows.

[0119] The information processing method of this embodiment includes: (A) a step of identifying a first time when any caregiver enters a specific room and a second time when any caregiver leaves the specific room from video footage captured by a camera installed in a hallway, and recording these as entry / exit records; and (B) a registration step of identifying a corresponding entry / exit record from among multiple entry / exit records for each of multiple assistance items in schedule data that includes multiple assistance items to be performed on residents in the specific room and the scheduled times for performing the multiple assistance items, and registering these as the start time and end time.

[0120] In this way, even if the caregiver does not explicitly register the start and end times, the start and end times for each of the multiple assistance items in the schedule data are automatically registered from the entry and exit records captured on video from a camera installed in the hallway, so that care records can be properly organized. This also reduces the caregiver's workload and allows them to focus on implementing the assistance items. Note that the entry and exit times, as well as the time intervals between them, can be used to associate the assistance items with the entry and exit records.

[0121] The information processing method described above may further include the steps of (C) receiving and recording input data, which includes the details of the assistance items actually performed by each caregiver and the recording time, and which is entered using each caregiver's mobile terminal, (D) if there is an entry / exit record that does not correspond to any of the plurality of assistance items in the schedule data, searching for input data corresponding to the entry / exit record, and (E) if input data corresponding to an entry / exit record that does not correspond to any of the plurality of assistance items in the schedule data is found, correlating the entry / exit record with the input data and recording it. Because non-regular assistance is not scheduled, by performing this processing, the input data and the entry / exit record are correlated, and the care record is organized.

[0122] Furthermore, the information processing method described above may further include a step (F) of registering an entry / exit record that cannot be associated with any input data as an entry / exit record with an unknown reason if there is an entry / exit that needs to be confirmed due to a data entry omission or security reasons. For example, if there is an entry / exit omission or delay in the entry of non-regular assistance data, the entry / exit record may be linked to the input data for the non-regular assistance. Note that if such an entry / exit record with an unknown reason is detected, a warning may be output to the administrator.

[0123] The information processing method described above may further include the step of (G) identifying input data corresponding to a reception record recorded when a care call is received from any room, identifying an entry / exit record associated with the input data, and calculating the difference between the reception time included in the reception record and the first time of the entry / exit record. This allows the response time for the care call to be identified. Storing and analyzing this response time can improve the efficiency of care call response operations.

[0124] Furthermore, the information processing method described above may further include the steps of: (H) identifying, from the video captured by the camera, a first time when a caregiver entered a specific room together with a non-caregiver and a second time when a caregiver left the specific room together with information indicating that the caregiver was accompanied, and recording these together with information indicating that the caregiver was accompanied; and (I) checking whether or not there is a record of entry or exit to the specific room between the second time when the information indicating that the caregiver was accompanied and the first time when the information indicating that the caregiver was accompanied is accompanied, and if there is, identifying this record as an entry or exit record for an unknown reason. This is to enable later confirmation, since entry or exit during times when the resident is presumed to be absent may pose a security risk.

[0125] The schedule data may further include a first assistance item for moving to a location other than the specific living room, a second assistance item to be performed at the location, and a third assistance item for moving from the location to the specific living room, as well as the planned implementation times for each of the first, second, and third assistance items. In this case, the information processing method may further include (J) a step of identifying, from video footage captured by a camera, a first time when a caregiver enters the specific living room with a non-caregiver and a second time when a caregiver leaves the specific living room with a non-caregiver, and recording these times together with information indicating the caregiver is accompanied by a non-caregiver. In the registration step, the second time marked with the information indicating the caregiver is accompanied may be associated with the second assistance item as a start time, and the first time marked with the information indicating the caregiver is accompanied as an end time. This allows the approximate required time for the second assistance item to be identified, and the approximate required times for the first and third assistance items to be obtained from other entry and exit records.

[0126] Furthermore, the above-described information processing method may further include the step of (K) when data indicating that multiple assistance items to be performed on a resident in a specific room have been performed consecutively is received from the caregiver's mobile terminal, identifying one entry / exit record corresponding to the multiple assistance items performed consecutively, and calculating the required time for each of the multiple assistance items performed consecutively by prorating the time difference between the second time and the first time in the single entry / exit record based on the ratio of the planned implementation times of the multiple assistance items performed consecutively.When multiple assistance items for the same resident are assigned to the same caregiver, they may or may not be performed consecutively, so this method deals with the case where they are performed consecutively.

[0127] In addition, there are cases where the schedule data described above includes a fourth assistance item involving movement to a location other than the specific living room and movement from that location to the specific living room, as well as the planned time for carrying out the fourth assistance item. For example, mobility assistance + meal assistance + mobility assistance may be combined into meal assistance. Even in such cases, the same processing can basically be used. However, it is preferable to ignore the first and second times that include information indicating the caregiver is accompanied, or to use only the entry and exit records of the caregiver alone.

[0128] In addition, the information processing method described above may further include (L) a step of allocating the time difference between the second time and the first time included in the entry / exit record identified for the fourth assistance item to multiple tasks included in the fourth assistance item according to a predetermined rule.

[0129] A program for causing a processor to perform the above-described processing can be created, and the program is stored in a computer-readable storage medium or storage device, such as a flexible disk, an optical disk such as a CD-ROM (Read Only Memory), a magneto-optical disk, a semiconductor memory (e.g., a ROM), a hard disk, etc. Data during processing is temporarily stored in a storage device such as RAM (Random Access Memory). [Explanation of symbols]

[0130] 100 Information Processing Systems 101 video storage unit 102 entry / exit inference unit 103 entry / exit data storage unit 104 Schedule data storage unit 105 Analysis unit 106 Output data storage unit 107 Output unit 108 Data receiving unit 109 Care input data storage unit 110 Care Call Recording Department 200 cameras 300, 300a, 300b Mobile terminal

Claims

1. a step of identifying a first time when any caregiver entered a specific room and a second time when any caregiver left the specific room from an image taken by a camera installed in a hallway, and recording the first time and the second time as an entry / exit record; a registration step of identifying a corresponding entry / exit record from a plurality of entry / exit records for each of the plurality of assistance items in the schedule data including a plurality of assistance items to be performed for the resident in the specific room and a scheduled time for performing the plurality of assistance items, and registering the entry / exit record as a start time and an end time; and a computer-implemented information processing method.

2. receiving and recording input data including the content of the assistance items actually performed by each caregiver and the recording time, which is input using the mobile terminal of each caregiver; When there is an entry / exit record that does not correspond to any of the plurality of assistance items in the schedule data, searching for input data corresponding to the entry / exit record; a step of recording the entry / exit record and the input data in association with each other when input data corresponding to the entry / exit record that is not associated with any of the plurality of assistance items in the schedule data is found; The information processing method according to claim 1 , further comprising:

3. If there is an entry / exit record that cannot be associated with any of the input data, registering the entry / exit record as an entry / exit record with an unknown reason. The information processing method according to claim 2, further comprising:

4. Identifying input data corresponding to a reception record recorded when a care call is received from any of the rooms, identifying an entry / exit record associated with the input data, and calculating a difference between a reception time included in the reception record and a first time of the entry / exit record. The information processing method according to claim 2, further comprising:

5. a step of identifying a first time when any caregiver entered the specific room together with a non-caregiver and a second time when any caregiver left the specific room together with a non-caregiver from the video captured by the camera, and recording the identified first time and the second time together with information indicating the non-caregiver's accompaniment; a step of checking whether or not there is a record of entry and exit to the specific room between the second time when the information indicating the accompanying person is attached and the first time when the information indicating the accompanying person is attached, and if there is, identifying the record of entry and exit as a record of entry and exit for an unknown reason; The information processing method according to claim 1 , further comprising:

6. the schedule data further includes a first assistance item relating to movement to a location other than the specific living room, a second assistance item to be performed at the location, a third assistance item relating to movement from the location to the specific living room, and a scheduled implementation time for each of the first to third assistance items; a step of identifying a first time when any caregiver entered the specific room together with a non-caregiver and a second time when any caregiver left the specific room together with a non-caregiver from the video captured by the camera, and recording the identified first time and the second time together with information indicating the non-caregiver being accompanied by the caregiver; further comprising In the registration step, The second assistance item is associated with a second time to which information indicating accompaniment is attached as a start time, and associated with a first time to which information indicating accompaniment is attached as an end time. The information processing method according to claim 1.

7. When receiving data from the mobile terminal of the caregiver indicating that a plurality of assistance items to be performed on the resident in the specific room have been performed consecutively, identifying one entry / exit record corresponding to the plurality of assistance items that have been performed consecutively, and calculating a required time for each of the plurality of assistance items that have been performed consecutively by proportionally dividing the time difference between the second time and the first time in the one entry / exit record by the ratio of the planned implementation times of the plurality of assistance items that have been performed consecutively. The information processing method according to claim 1 , further comprising:

8. The schedule data includes a fourth assistance item that involves movement to a place other than the specific room and movement from the place to the specific room, and a planned implementation time of the fourth assistance item. The information processing method according to claim 1.

9. a step of allocating a time difference between the second time and the first time included in the entry / exit record identified for the fourth assistance item to a plurality of tasks included in the fourth assistance item according to a predetermined rule; The information processing method according to claim 8, further comprising:

Images