Information processing methods, programs, and equipment.

Abstract

DEPCT6830 / 04 / 2568 Methods of information processing include making computers perform actions: seeking to record life. This includes textual information obtained by recording the lives of the test subjects; judgments; Based on biographical records, psychological and / or behavioral symptoms are attributed to brain conditions. Did deterioration occur in the test subjects? Identification, if the judgment indicates that symptoms have occurred. One or more causes of symptoms are selected based on life records; and the user device output is generated. Symptom information, which indicates the outcome of the decision, and cause information, which indicates each one. Or rather, reasons to choose, in response to user requests;

Description

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

[0001] This application is based on Japanese Patent Application No. 2022-126487, filed on August 8, 2022, the contents of which are incorporated herein by reference.

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

[0003] Conventionally, there is a technology for determining the occurrence of behavioral symptoms and psychological symptoms in a subject by using sensor data obtained by sensing the living body of the subject and the subject's surrounding environment. Patent Document 1 listed below discloses a method for determining the subject's sleep state, such as the frequency of awakenings and the frequency of daytime or evening naps, based on sensor data related to the subject, and determining the occurrence of dementia-related symptoms in the subject based on the determined sleep state.

[0004] Japanese Patent Application Laid-Open No. 2019-076689

[0005] The technology described in Patent Document 1, when using sensor data to determine the occurrence of behavioral or psychological symptoms in a subject, is unavoidably a uniform determination based on quantitative data. However, for example, when using a sleep sensor, even if the sensor data indicates similar sleep states for subject A and subject B, the sleep states that subject A and subject B feel comfortable in may be different. Subject A may feel comfortable in their current sleep state, while subject B may feel anxious about their current sleep state. As such, it has been difficult to determine the occurrence of behavioral or psychological symptoms tailored to each subject. Furthermore, when a uniform determination result is obtained, a uniform approach is also required when identifying the contributing factors based on the determination result.

[0006] Therefore, some aspects of the present disclosure aim to provide an information processing method, a program, and an information processing device that can determine the occurrence of behavioral symptoms and psychological symptoms of a subject and identify potential causes of the occurrence, tailored to each subject.

[0007] In an information processing method according to one aspect of the present disclosure, a computer acquires a life log including text information that records the life of a subject, determines whether the subject is experiencing psychological and / or behavioral symptoms related to dementia based on the life log, and, if the determination result indicates that symptoms are occurring, identifies one or more candidate factors for the occurrence of the symptoms based on the life log.

[0008] A program according to one aspect of the present disclosure causes a computer to implement an acquisition function for acquiring a life record including text information recording the life of a subject, and a determination function for determining whether or not psychological symptoms and / or behavioral symptoms related to dementia are occurring in the subject based on the life record, and also causes the computer to implement an identification function for identifying one or more candidate factors for the occurrence of the symptoms based on the life record if the determination result indicates that symptoms are occurring.

[0009] An information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires a life record including text information that records the life of a subject, and a determination unit that determines whether or not psychological symptoms and / or behavioral symptoms related to dementia are occurring in the subject based on the life record, and if the determination result indicates that symptoms are occurring, an identification unit that identifies one or more candidate factors for the occurrence of the symptoms based on the life record.

[0010] According to some aspects of the present disclosure, it is possible to determine the occurrence of behavioral symptoms and psychological symptoms of a subject, and identify possible causes of the occurrence, tailored to each individual subject.

[0011] FIG. 1 is a diagram illustrating an example of the system configuration of a care support system according to an embodiment. FIG. 2 is a diagram illustrating an example of an overview of the care support system according to an embodiment. FIG. 3 is a diagram illustrating an example of the functional configuration of a server device according to an embodiment. FIG. 4 is a diagram illustrating an example of a screen of the care support system according to an embodiment. FIG. 5 is a diagram illustrating an example of a screen of the care support system according to an embodiment. FIG. 6 is a diagram illustrating an example of a screen of the care support system according to an embodiment. FIG. 7 is a diagram illustrating an example of an operation of the care support system according to an embodiment. FIG. 8 is a diagram for explaining an example of the hardware configuration of the care support system according to an embodiment.

[0012] An embodiment of the present invention (hereinafter referred to as "this embodiment") will be described with reference to the accompanying drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0013] <1. System Configuration> An example of the system configuration of a care support system 1 according to this embodiment will be described with reference to Fig. 1. The care support system 1 according to this embodiment is a system for supporting care staff who are caregivers when providing care services to a care recipient (one aspect of a target person). The care recipient is a person who receives care related to daily life (hereinafter simply referred to as "care") from the care staff using the care support system 1.

[0014] In the care support system 1, a life record including text information recorded by a recorder or a computer about the life of the care recipient, and data obtained by sensing the living body of the care recipient and / or the surrounding environment of the care recipient (hereinafter also referred to as "sensor data") are used for providing care to the care recipient. The recorder may be, for example, a care staff member or a family member of the care recipient.

[0015] The care support system supports care staff in responding to psychological and / or behavioral symptoms of dementia in care recipients, known as BPSD (Behavioral and Psychological Symptoms of Dementia). Hereinafter, the psychological and / or behavioral symptoms of dementia in care recipients will also be referred to as "BPSD."

[0016] 1 , the care support system 1 includes a server device 100 and a staff terminal 200 used by care staff. The server device 100 and the staff terminal 200 are connected via a communication network N. Possible users of the care support system 1 include, for example, care staff, care service providers other than care staff, and / or people related to the care recipient (for example, family members of the care recipient).

[0017] The communication network N is composed of a wireless network and a wired network. Examples of the communication network N include a mobile phone network, a PHS (Personal Handy-phone System) network, a wireless LAN (Local Area Network), 3G (3rd Generation), LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation), WiMax (registered trademark), infrared communication, Bluetooth (registered trademark), a wired LAN, a telephone line, a power line communication network, and a network conforming to IEEE 1394.

[0018] [Server Device] The server device 100 is an information processing device capable of communicating with the staff terminal 200. The server device 100 provides functions for supporting care staff when providing care services to care recipients. In this embodiment, an example will be described in which the server device 100 generates a website for providing care services (hereinafter also referred to as a "care support site") and distributes the web page of the generated care support site to the staff terminal 200. The server device 100 allows the care staff to access the authorized page of the care support site by specifying the URL of the care support site via the staff terminal 200 and logging in. This login is performed using an account (user ID and password) that each user has registered in advance in the care support system 1.

[0019] [Staff Terminal] The staff terminal 200 is configured by, for example, a general-purpose or dedicated information processing device such as a smartphone, tablet terminal, PDA, or laptop. The staff terminal 200 is one aspect of a user device. In this embodiment, an example will be described in which a web browser that is standardly provided on the staff terminal 200 is used. The staff terminal 200 receives learning tools from the server device 100 by browsing web pages distributed from the server device 100 using the web browser.

[0020] <2. System Overview> An overview of the care support system 1 according to this embodiment will be described with reference to Fig. 2. As shown in Fig. 2, the care support system 1 allows a staff terminal 200 to output a dashboard (hereinafter also referred to as a "care support dashboard") that summarizes information related to each of (1) to (4) for each care recipient, such as (1) assessment, (2) life records and accidents (falls, wrong entry, etc.) based on DAR (Data Action Response), (3) sensors / physical condition records / medications, and (4) tips for improving care, at the care support site.

[0021] (1) Assessment (basic information of the care recipient) The care support dashboard outputs, for example, a record of the assessment of the care recipient (the most recent record and records from a predetermined period prior to that) as basic information of the care recipient. This assessment includes, for example, evaluations of the care recipient's level of care need, stage of dementia, presence or absence of disorientation, and level of independence in each aspect of daily life (e.g., level of independence in daily life).

[0022] (2) DAR / Accident (Condition of the Care Recipient) The care support dashboard may output, for example, the trend in the number of BPSD incidents per unit period based on the life log as the condition of the care recipient. Furthermore, the care support dashboard may output, for example, text information contained in the life log as detailed information related to this output. Furthermore, the life log may be, for example, a record of the progress of observation of the life of the care recipient using a focus charting (DAR) technique as a recording method.

[0023] The care support dashboard may output the number of each type of face mark based on the results of recording the facial expressions of the care recipient using face marks, for example.

[0024] The care support dashboard outputs, for example, the status of the care recipient, the accident occurrence situation (e.g., the trend in the number of accidents occurring per unit period, etc.), based on an accident record including text information recording accidents of the care recipient. Furthermore, the care support dashboard may output, for example, the text information included in the accident record itself as detailed information related to this output.

[0025] The care support dashboard may output, for example, the number of accidents, BPSDs, and face marks mentioned above by unit period (represented as "time period" in Figure 2) as well as by type of care when these occurred.

[0026] (3) Sensors / health records / medicine (factors that cause the condition of the person being cared for) The care support dashboard outputs, for example, the sensor data of the person being cared for, health records, prescription medications, and details of the care currently being provided as factors that cause the condition described in (2) above.

[0027] (4) Hints for Improving Care (Response to Factors) The care support dashboard outputs hints for improving care, for example, in response to the factors described in (3) above. For example, if sensor data from a sleep sensor indicates that the care recipient's sleep time is shorter than the standard value, the care support dashboard may output a hint such as, "Your sleep time seems short. Is your sleeping position okay?"

[0028] There are many things that care staff must consider when caring for a care recipient, such as what kind of person the care recipient is, whether the care recipient's condition is good or bad, what factors cause the good or bad condition, and what should be done to address them. Based on the above configuration, the care support system 1 can compile information that could be the answer or a hint on the care support dashboard and output it in line with the care staff's train of thought.

[0029] With the above configuration, the care support system 1 can output the trend in the number of BPSD occurrences per unit period based on text information from the subject's life record and accident record. Therefore, it is possible to output the occurrence status of BPSD tailored to the subject based on detailed records that take into account the personality and preferences of each subject, which cannot be fully expressed by quantitative records or records using a selection method.

[0030] 3. Functional Configuration The functional configuration of the server device 100 according to this embodiment will be described with reference to Fig. 3. As shown in Fig. 3, the server device 100 includes a control unit 110, a communication unit 120, and a storage unit 130.

[0031] [Control Unit] The control unit 110 includes an acquisition unit 111, a determination unit 112, an identification unit 113, and an output unit 115. The control unit 110 may also include a classification unit 114, for example.

[0032] [Acquisition Unit] The acquisition unit 111 acquires the life record of the care receiver from the staff terminal 200 or the storage unit 130 .

[0033] The acquisition unit 111 may acquire sensor data at the time when the life record was recorded (hereinafter also referred to as the "recording time") from, for example, a sensor device (not shown) or the storage unit 130. The sensor device may be, for example, a body movement sensor, a sleep sensor, a pulse sensor, a respiration sensor, a temperature sensor, an excretion detection sensor, a blood pressure sensor (sphygmomanometer), a weight scale, a hygrometer, a barometer, and / or an image sensor. Furthermore, the recording time may indicate, for example, a time period with a certain range (i.e., a time period). For example, if the date and time when the life record was recorded is "June 30, 2022, 10:15 AM," the recording time of this record may be between 10:00 AM on June 30, 2022, or may be the morning of June 30, 2022.

[0034] The sensor data may include, for example, data obtained by sensing the living body of the care recipient (hereinafter also referred to as "biological data"). The biological data may be, for example, measurements of the care recipient's sleep state, excretion state, pulse state, breathing state, blood pressure state, weight state, and / or body temperature state. The sensor data may also include data obtained by sensing the surrounding environment of the care recipient (hereinafter also referred to as "environmental data"). The environmental data may be, for example, measurements of the temperature state, humidity state, and / or air pressure state of the surrounding environment of the care recipient.

[0035] The acquisition unit 111 may acquire, for example, a healthy life record and healthy sensor data from the storage unit 130. The healthy life record is a life record including text information recording the life of the care recipient when the care recipient was healthy. The healthy sensor data is data obtained by sensing the living body of the care recipient and / or the surrounding environment of the care recipient when the care recipient was healthy.

[0036] The acquiring unit 111 may acquire the assessment information from, for example, the storage unit 130. The assessment information is information indicating the results of an assessment performed on the care receiver.

[0037] [Determination Unit] The determination unit 112 determines the occurrence of psychological symptoms and / or behavioral symptoms related to dementia (in other words, BPSD) for the care recipient based on the life record. Specifically, the determination unit 112 may determine whether or not the care recipient has experienced BPSD (in other words, whether or not the care recipient has experienced BPSD), and what kind of symptoms the BPSD has experienced. The determination unit 112 may store symptom information indicating the result of this determination in the storage unit 130.

[0038] The life log may be, for example, a text recorded in free text by a recorder (e.g., a caregiver) using focus charting as a recording method. Specifically, the life log may include text information recording the progress of the care recipient, focusing on the care recipient's concerns and interests, the care recipient's behavior, or events that occurred to the care recipient. The life log may also be, for example, a free text record by a recorder that observes the progress of the care recipient using the focus charting (DAR) method. With this configuration, observations are made that focus on events that occurred to each care recipient, tailored to the care recipient, and the occurrence of BPSD can be determined based on the caregiver's free-flowing observation records. Therefore, the occurrence of BPSD can be determined for each care recipient, and the determination can be made in a manner that incorporates the caregiver's know-how and knowledge by based on observation records that utilize the caregiver's know-how and knowledge.

[0039] The symptom information is information related to BPSD for each care recipient. The symptom information may include, for example, whether or not BPSD has occurred, and (if BPSD has occurred) for each BPSD that has occurred, the type of BPSD, the date and time of occurrence, and / or the location of occurrence.

[0040] The determination unit 112 may determine the occurrence of BPSD using, for example, natural language processing technology, machine learning technology, or deep learning technology. The determination unit 112 may make a determination using, for example, a determination model for determining which symptom of BPSD has occurred.

[0041] The judgment model may be, for example, a model trained using machine learning and deep learning techniques based on training data. Furthermore, this training data may be, for example, text information to which labels indicating the occurrence or non-occurrence of BPSD, its type, and the presence or non-occurrence of motivation / POS behavior are attached. Furthermore, these labels may be attached in response to a care staff member's specification of the text information displayed on the staff terminal 200 (in other words, an operation input on the screen displaying the text information).

[0042] For example, as a preprocessing step, the determination model performs morphological analysis on the text information included in the life log and divides the sentences included in the text information into word units. The determination model may include, for example, BERT (Bidirectional Encoder Representations from Transformers). The determination model uses BERT to convert the divided word groups into vector sequences, inputs the converted vector sequences, and outputs vector sequences corresponding to answer sentences. Next, the determination model generates feature vectors based on the output vector sequences. Next, the determination model includes a neural network (classifier), inputs the feature vectors into the neural network, and outputs a classification of which type of BPSD symptoms are present or absent, thereby determining whether or not the BPSD is present and further classifying the type of BPSD. Furthermore, the determination model may, for example, determine the presence or absence of motivated behavior and / or positive behavior (hereinafter also referred to as "motivation / POS behavior") using the determination model, in addition to determining the presence or absence of BPSD.

[0043] According to the above configuration, the determination unit 112 can determine the occurrence of BPSD based on text information recorded in consideration of the personality and preferences of each subject, which cannot be fully expressed by quantitative recording or recording using a selection method. Therefore, the occurrence of BPSD can be determined in accordance with each subject.

[0044] [Determination Unit] The determination unit 112 determines the motivation / POS behavior of the care recipient based on the life record. Specifically, the determination unit 112 may determine whether the care recipient is performing motivation / POS behavior (in other words, whether or not the care recipient is performing an activity) and what kind of motivation / POS behavior the care recipient is performing. The determination unit 112 may store behavior information indicating the result of this determination in the storage unit 130.

[0045] [Identification Unit] The identification unit 113 identifies one or more candidate factors for the occurrence of BPSD based on the life record when the result of the determination by the determination unit 112 indicates the occurrence of BPSD. The identification unit 113 may store candidate factor information indicating each of the identified one or more candidate factors in the storage unit 130.

[0046] For example, the identification unit 113 may refer to dictionary information in which character strings representing each of multiple factors that cause the occurrence of BPSD (hereinafter also referred to as "factor character strings") are registered, and if it can extract a character string that at least partially matches the factor character string from the character strings included in the text information that has been determined by the determination unit 112 to be a cause of BPSD, it may identify the factor corresponding to this factor character string as a candidate factor.

[0047] The identification unit 113 may identify one or more candidate factors for the occurrence of BPSD using, for example, natural language processing technology, machine learning technology, or deep learning technology. The identification unit 113 may identify one or more candidate factors for the occurrence of BPSD using, for example, an identification model for identifying one or more candidate factors for the occurrence of BPSD. Note that this identification model and the determination model of the determination unit 112 may be the same model.

[0048] The specific model may be, for example, a model trained using machine learning and deep learning techniques based on training data. Furthermore, this training data may be, for example, text information to which labels indicating the presence or absence of BPSD, its type, and the causes of the occurrence of BPSD are attached. Furthermore, the cause labels may be attached in response to a care staff member's specification of the text information displayed on the staff terminal 200 (in other words, an operational input on the screen displaying the text information).

[0049] The identification unit 113 may identify one or more candidate factors for the occurrence of BPSD based on, for example, sensor data and / or care records at the time of recording the life log. Specifically, if sensor data from a sleep sensor at the time of the occurrence of BPSD indicates insufficient sleep time for the care recipient, the identification unit 113 may identify insufficient sleep time as a candidate factor. With this configuration, it is possible to quantitatively represent changes in the biological state and environmental condition of the care recipient that cannot be fully expressed by recording text information, and to identify candidate factors based on sensor data and care records that contain a large amount of information without placing a burden on the care staff.

[0050] The identification unit 113 may identify one or more factors that contribute to the occurrence of BPSD from one or more candidate factors, for example, based on the contribution of each of the one or more candidate factors (hereinafter simply referred to as "contribution") calculated by the contribution calculation unit 113b described below.

[0051] The identification unit 113 may identify a pattern of the care recipient depending on the care (hereinafter also referred to as a "care recipient pattern") based on, for example, the assessment information and / or the symptom information. The care recipient pattern may be, for example, a pattern representing a type of care the care recipient receives, a pattern representing a type of behavior of the care recipient, a pattern representing a type of physical condition of the care recipient including a state of dementia, and / or a pattern representing a type of preference of the care recipient (including a combination of two or more of these patterns).

[0052] The identification unit 113 may identify the content of care provided at the time of the occurrence of the BPSD, for example, by referring to the storage unit 130 that stores care history information. The care history information is information that indicates the history of care provided to the care recipient over a predetermined period of time.

[0053] The identification unit 113 may, for example, refer to the storage unit 130 that stores improvement plan information indicating each of a plurality of improvement plans for care for the subject, and identify, from the plurality of improvement plans, an improvement plan for care that corresponds to at least one of one or more candidate cause factors (hereinafter also simply referred to as a "corresponding improvement plan") based on the improvement plan information. Furthermore, the identification unit 113 may, for example, identify a corresponding improvement plan further based on the degree of approximation calculated by the approximation calculation unit 113c. For example, the identification unit 113 may identify, from the plurality of improvement plans, the improvement plan with the highest degree of approximation as the corresponding improvement plan.

[0054] The identification unit 113 may include, for example, a comparison unit 113a. For example, when the result of the determination by the determination unit 112 indicates the occurrence of BPSD, the comparison unit 113a compares (hereinafter also referred to as a "first comparison") the life record in which it has been determined that BPSD has occurred (hereinafter also referred to as a "BPSD life record") with the healthy life record. Furthermore, for example, when the result of the determination by the determination unit 112 indicates the occurrence of BPSD, the comparison unit 113a compares (hereinafter also referred to as a "second comparison") the sensor data at the time of recording the BPSD life record (hereinafter also referred to as "BPSD sensor data") with the healthy life sensor data.

[0055] The BPSD life record and the healthy life record may each include data recorded from a first period going back from the start date of the recording to June 30, 2022. For example, if the recording date of the life record is "June 30, 2022" and the first period is "three months," the life record may include data recorded from June 30, 2022, going back three months, up to March 30, 2022. In this case, the comparison unit 113a may extract multiple differences (hereinafter also referred to as "first differences") between the BPSD life record and the healthy life record along a timeline, for example, based on the results of a first comparison performed on the timeline of the first period.

[0056] For example, the comparison unit 113a may weight each of the extracted first differences in accordance with the length of time from the start time to the time at which each of the extracted first differences is extracted. For example, the comparison unit 113a may assign a weight proportional to the length of time, so that the shorter the length, i.e., the closer the extraction time is to the start time, the greater the weight.

[0057] The BPSD sensor data and the healthy state sensor data may include data obtained by sensing data from a second period going back from the corresponding recording time point as a starting point. For example, if the recording time point corresponding to the sensor data is "June 30, 2022" and the second period is "three months," the BPSD sensor data may include data measured three months prior to June 30, 2022, up to March 30, 2022. In this case, the comparison unit 113a may extract multiple differences between the sensor data and the healthy state sensor data (hereinafter also referred to as "second differences") along a time series, for example, based on the results of a second comparison performed on the time series for the second period. Note that the first period and the second period may be the same or different periods.

[0058] For example, the comparison unit 113a may weight each of the extracted second differences in accordance with the length of time from the start point to the point in time at which each of the extracted second differences is extracted. As with the first differences, the comparison unit 113a may weight each of the extracted second differences in proportion to the length of time, so that the shorter the length of time, the greater the weight.

[0059] The identification unit 113 may include, for example, a contribution calculation unit 113b. The contribution calculation unit 113b may calculate the contribution of each of one or more candidate factors to the BPSD based on, for example, the results of the first comparison and / or the second comparison.

[0060] The contribution calculation unit 113b may calculate the contribution of each of one or more candidate factors using, for example, a variable importance analysis method. For example, the contribution calculation unit 113b may evaluate, as the contribution, the importance of the feature of one or more candidate factors (so-called Feature Importance) based on the date and time of occurrence of the BPSD and the sensor data and / or the nursing care record. Furthermore, the contribution calculation unit 113b may use, for example, an Individual Conditional Expectation (ICE) method to evaluate the importance of the feature.

[0061] The contribution degree calculation unit 113b may calculate the contribution degree further based on, for example, weighting each of the multiple first differences. With this configuration, it is possible to change the degree to which the difference from the healthy state contributes to the occurrence of BPSD depending on the temporal distance from the time of the BPSD occurrence. Therefore, for example, by increasing the weight for a difference closer to the time of the occurrence, the contribution degree value can be increased, thereby making it possible to identify candidate factors that have a stronger correlation with BPSD.

[0062] The contribution degree calculation unit 113b may calculate the contribution degree further based on, for example, weighting each of the plurality of second differences. With this configuration, it is possible to change the degree to which the difference from the healthy state contributes to the occurrence of BPSD depending on the temporal distance from the time of the BPSD occurrence. Therefore, for example, by increasing the weight for a difference closer to the time of the occurrence, the contribution degree value can be increased, thereby making it possible to identify candidate factors that have a stronger correlation with BPSD.

[0063] The identification unit 113 may include, for example, an approximation calculation unit 113c. The approximation calculation unit 113c calculates the approximation of each of a plurality of improvement plan candidates for the care recipient to the care recipient pattern identified by the identification unit 113. The approximation calculation unit 113c may, for example, calculate a degree of agreement indicating the degree to which improvement plan information representing each of the plurality of improvement plans matches pattern information representing the care recipient pattern, and calculate the approximation based on the calculated degree of agreement.

[0064] [Classification Unit] When the result of the determination by the determination unit 112 indicates the occurrence of a BPSD, the classification unit 114 classifies the occurred BPSD into a plurality of types (hereinafter also referred to as "BPSD types").

[0065] The classification unit 114 includes an evaluation unit 114a. The evaluation unit 114a evaluates the condition of symptoms for each of a plurality of BPSD types (for example, the occurrence rate of symptoms for each type).

[0066] [Output Unit] The output unit 115 causes the staff terminal 200 to output various information via the screen or audio of the care support system 1. The output unit 115 may generate display information (e.g., a web page) for displaying each screen of the care support dashboard A1 shown in FIGS. 4 to 7 (described later) based on, for example, the life record, sensor data, symptom information, behavioral information, assessment information, improvement plan information, and / or care history information. The output unit 115 may transmit the generated display information to the staff terminal 200. The staff terminal 200 displays each screen based on the received display information.

[0067] The output unit 115 outputs the symptom information to the staff terminal 200 in response to a request from the user. The symptom information is information indicating the result of the determination of the occurrence of BPSD by the determination unit 112. With this configuration, the output unit 115 can present the occurrence of BPSD determined based on the life record to the care staff, thereby supporting the care of the care recipient by the care staff.

[0068] For example, the output unit 115 may output candidate cause information indicating each of the one or more candidate cause identified by the identification unit 113 to the staff terminal 200 in response to a request from the care staff. With this configuration, candidate causes of the occurrence of BPSD can be presented to the care staff. Therefore, the care staff can identify the cause of the occurrence of BPSD by referring to the presented candidate causes, thereby supporting the care of the care recipient by the care staff.

[0069] For example, the output unit 115 may output cause information indicating each of the one or more causes identified by the identification unit 113 to the staff terminal 200 in response to a request from the care staff. With this configuration, causes of the occurrence of BPSD can be presented to the care staff.

[0070] The output unit 115 may output, for example, the occurrence status of symptoms evaluated by the evaluation unit 114a for each of a plurality of BPSD types to the staff terminal 200 in response to a request from the care staff. With this configuration, it is possible to confirm which of the BPSD types is most pronounced. Therefore, the care staff can prioritize the type in which the symptom is most pronounced over the other types.

[0071] For example, the output unit 115 may output improvement plan information indicating the improvement plan identified by the identification unit 113 to the staff terminal 200 in response to a request from the care staff. With this configuration, it is possible to suggest to the care staff hints on how to improve care for the output cause candidates or causes. This allows the care staff to make improvements so that care is more appropriate for each care recipient in order to address BPSD, without having to think about how to improve care from scratch, and even if the care staff has little skill or experience.

[0072] For example, when the determination result by the determination unit 112 indicates the occurrence of BPSD, the output unit 115 may, in response to a request from a care staff member, output to the staff terminal 200 the symptom information, the care content identified by the identification unit 113, and improvement plan information indicating the improvement plan identified by the identification unit 113 in association with each other. With this configuration, the care staff member can check the associated occurrence of BPSD, the care content at the time of the occurrence, and the improvement plan all at once. This makes it possible to provide a care support system that is easy for care staff to use.

[0073] [Communication Unit] The communication unit 120 transmits and receives various information such as web pages of the care support site to and from the staff terminal 200 via the communication network N.

[0074] [Storage Unit] The storage unit 130 stores various types of information related to care, including life records, sensor data, symptom information, behavioral information, assessment information, improvement plan information, and care history information. The storage unit 130 may store these pieces of information in association with each other, for example. The storage unit 130 may store various types of information using a database management system (DBMS) or a file system. When using a DBMS, a table may be provided for each piece of information, and the various pieces of information may be managed by associating these tables.

[0075] 4 to 7, examples of screens of the care support dashboard of the care support system 1 will be described. Note that each of the screens described in Figures 4 to 7 may include elements other than the components of the screens described using Figures 4 to 7, or some of the components of the screens described using Figures 4 to 7 may be omitted as appropriate.

[0076] 4 to 7 illustrate examples of the BPSD status / cause candidate screen A2, BPSD occurrence cause details A3, and life record (DAR) screen A4 displayed by the care support dashboard A1. The care support dashboard A1 can be switched to display the screen corresponding to the specified tab by specifying a tab corresponding to each screen in the switching tab area a11.

[0077] 4 and 5 are schematic diagrams showing an example of a BPSD situation / cause candidate screen A2 for displaying the situation of the occurrence of BPSD and its cause candidate. In this example, it is assumed that FIG. 5 is displayed after FIG. 4 by scrolling the BPSD situation / cause candidate screen A2.

[0078] 4, the BPSD situation / cause candidate screen A2 includes a BPSD number display area a22, a positive record display area a23, a face mark display area a24, and an accident occurrence number display area a25. The BPSD situation / cause candidate screen A2 is displayed by specifying the tab displayed as "BPSD situation / cause candidate" in the switching tab area all.

[0079] The BPSD number display area a22 displays the number of BPSD occurrences per unit period in a vertical bar graph. The number of BPSD occurrences is, for example, the number of BPSD occurrences counted for each BPSD symptom that has occurred when the determination unit 112 determines that a BPSD has occurred. Note that in each graph displayed on the BPSD status / cause candidate screen A2, the unit period can be switched between days, weeks, quarters, and years, and when the unit period is switched, the display of each graph also changes to match the switched unit.

[0080] The positive record display area a23 displays the number of occurrences of motivation / POS behaviors per unit period in a bar graph. The number of occurrences of motivation / POS behaviors is, for example, the number of occurrences counted for each motivation / POS behavior when the determination unit 112 determines that motivation / POS behaviors exist.

[0081] The face mark display area a24 displays, in a vertical bar graph, the number and size of each type of face mark that records the facial expression of the care recipient for each unit period.

[0082] The accident count display area a25 displays the number of accidents per unit period in a vertical bar graph. For example, the accident count display area a25 may not be displayed if the number of accidents is zero. The number of accidents is counted based on care records or daily life records. Care records may be, for example, quantitative and / or selective records of the condition of a care recipient. Specifically, care records are quantitative and / or selective records of sleep, excretion, diet, water intake, weight, blood pressure, respiratory status, arterial oxygen saturation (hereinafter also referred to as "SpO2"), etc., of a care recipient.

[0083] 5 , the BPSD situation / cause candidate screen A2 may include a BPSD classification display area a26, a care-based BPSD number display area a27, a time-based BPSD display area a28, and a BPSD cause candidate display area a29 when the determination unit 112 determines that a BPSD has occurred. In other words, when the determination unit 112 determines that a BPSD has occurred, the BPSD situation / cause candidate screen A2 does not need to display these areas.

[0084] The upper part of the BPSD classification display area a26 classifies the BPSDs that have occurred into multiple types (nine types in this example), calculates the occurrence rate for each type (in this example, the number of BPSDs is calculated by tallying the number of BPSDs for each type), i.e., evaluates the occurrence status of symptoms, and displays it in a radar chart. The lower part of the BPSD classification display area a26 displays links (hereinafter also referred to as "care hint links") for displaying the care hint screen A2-1 for each of the multiple BPSD types. The types displayed in the upper part and the lower part may be the same or different. In the latter case, the types displayed in the upper part may be, for example, a superordinate conceptualization of the types displayed in the lower part, in other words, a more general classification of the types displayed in the lower part.

[0085] When a care hint link is specified, the care support dashboard A1 displays a care hint screen A2-1. In this example, it is assumed that a care hint link corresponding to the "No. 3 Violence Refusal to Care" type among multiple BPSD types is specified. The care hint screen A2-1 displays care improvement suggestions corresponding to this specified BPSD type as care hints for the care staff.

[0086] The BPSD number by type of care display area a27 displays the number of BPSD occurrences in a horizontal bar graph for each type of care being provided when the BPSD occurred.

[0087] The time-slot-specific BPSD display area a28 displays the number of BPSD occurrences in a bar graph for each time slot in which the BPSD occurred.

[0088] The BPSD factor candidate display area a29 displays the magnitude of the contribution of each of one or more factor candidates to the occurrence of BPSD in a horizontal bar graph. In this horizontal bar graph, the one or more factor candidates are sorted and displayed in descending order of the magnitude of the contribution (in FIG. 5, this is expressed as "horizontal lines with the strongest relationship are arranged from top to bottom").

[0089] 6 , the BPSD Occurrence Cause Details Screen A3 displays, in bar graphs or time charts, the magnitude of sleep time and activity time per unit time for the care recipient, which are related to candidate factors for the occurrence of BPSD, based on sensor data. The BPSD Occurrence Cause Details Screen A3 also displays, in bar graphs or other charts, the stool volume, stool characteristics, urine volume, food intake, water volume, weight, body temperature, blood pressure (high and low), pulse rate, and / or respiratory rate for the care recipient, which are related to candidate factors for the occurrence of BPSD, based on care records. The BPSD Occurrence Cause Details Screen A3 is displayed by specifying the tab labeled "BPSD Occurrence Details (Sensor / Record)" in the switching tab area a11.

[0090] As shown in FIG. 7 , the DAR screen A4 displays a table that compiles multiple life records. For each record, the table displays free text recorded for a focused event, including data related to the event (Data), the care or treatment provided in response to the event (Action), and the care recipient's response to the care or treatment. The table also allows multiple life records to be sorted and displayed by their corresponding emoticons. The table also allows multiple life records to be sorted and displayed by the presence or absence of BPSD in each record. The table also allows multiple life records to be sorted and displayed by the presence or absence of motivation and POS behavior in each record.

[0091] 5. Operational Example An operational example of the server device 100 will be described with reference to Fig. 8. Note that the order of the processes shown below is an example and may be changed as appropriate.

[0092] 8 , the acquisition unit 111 of the server device 100 acquires a life log in which a recorder records the life of a subject (S10). The acquisition unit 111 acquires sensor data at the time of recording the life log (S11). The determination unit 112 of the server device 100 determines whether or not the subject is experiencing psychological symptoms and / or behavioral symptoms related to dementia based on the life log (S12).

[0093] If the result of the determination indicates that the symptom is occurring (Yes in S13), the identification unit 113 of the server device 100 identifies one or more candidate factors for the occurrence of the symptom based on the sensor data and the life record (S14). The contribution calculation unit 113b of the server device 100 calculates the contribution of each of the one or more candidate factors to the symptom (S15). The identification unit 113 identifies one or more causes of the occurrence of the symptom from the one or more candidate factors based on the contribution of each of the one or more candidate factors (S16). In response to a user request, the output unit 115 of the server device 100 causes the user device to output symptom information indicating the occurrence of the symptom and cause information indicating each of the one or more causes (S17).

[0094] If the result of the above judgment indicates that the above symptom has not occurred (No in S13), the output unit 115 of the server device 100 outputs symptom information indicating that the above symptom has not occurred to the user device in response to a user request (S18).

[0095] 9, an example of a hardware configuration in which the above-described server device 100 is realized by a computer 800 will be described. Note that the functions of each device can also be realized by dividing them into multiple devices.

[0096] As shown in FIG. 9, the computer 800 includes a processor 801, a memory 803, a storage device 805, an input I / F unit 807, a data I / F unit 809, a communication I / F unit 811, and a display device 813.

[0097] The processor 801 controls various processes in the computer 800 by executing programs stored in the memory 803. For example, each functional unit included in the control unit 110 of the server device 100 can be realized by the processor 801 executing a program temporarily stored in the memory 803.

[0098] The memory 803 is a storage medium such as a RAM (Random Access Memory), etc. The memory 803 temporarily stores the program code of the program executed by the processor 801 and data required when the program is executed.

[0099] The storage device 805 is a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 805 stores an operating system and various programs for implementing the above-mentioned components. In addition, the storage device 805 can also store tables for registering various types of information such as life records, sensor data, symptom information, assessment information, improvement plan information, and care history information, as well as a database for managing these tables. Such programs and data are loaded into the memory 803 as needed and referenced by the processor 801.

[0100] The input I / F unit 807 is a device for receiving input from a user. Specific examples of the input I / F unit 807 include a keyboard, a mouse, a touch panel, various sensors, and a wearable device. The input I / F unit 807 may be connected to the computer 800 via an interface such as a USB (Universal Serial Bus).

[0101] The data I / F unit 809 is a device for inputting data from outside the computer 800. A specific example of the data I / F unit 809 is a drive device for reading data stored in various storage media. The data I / F unit 809 may be provided outside the computer 800. In this case, the data I / F unit 809 is connected to the computer 800 via an interface such as a USB.

[0102] The communication I / F unit 811 is a device for performing data communication via the Internet N, either wired or wirelessly, with devices external to the computer 800. The communication I / F unit 811 may be provided external to the computer 800. In this case, the communication I / F unit 811 is connected to the computer 800 via an interface such as a USB.

[0103] The display device 813 is a device for displaying various types of information. Specific examples of the display device 813 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a display of a wearable device. The display device 813 may be provided outside the computer 800. In this case, the display device 813 is connected to the computer 800 via, for example, a display cable. Furthermore, when a touch panel is used as the input I / F unit 807, the display device 813 can be configured as an integral part of the input I / F unit 807.

[0104] It should be noted that the present embodiment is an example for explaining the present invention, and is not intended to limit the present invention to only this embodiment. Furthermore, the present invention can be modified in various ways without departing from the gist of the present invention. Furthermore, those skilled in the art can adopt embodiments in which the elements described below are replaced with equivalents, and such embodiments are also within the scope of the present invention.

[0105] [Modifications] Although the present invention has been described based on the above embodiment, the following cases are also included in the present invention.

[0106] [Variation 1] At least some of the components of the server device 100 according to the above embodiment may be provided in the staff terminal 200. The staff terminal 200 may implement these components by, for example, installing an application program (native application) dedicated to the care support system 1 (hereinafter also referred to as a "care support app") and executing the care support app. In other words, the care support system 1 may use a care support site or a care support app distributed by the server device 100. When using the care support app in the care support system, the care staff can use at least some of the functions even if the staff terminal 200 is offline.

[0107] 1...care support system, 100...server device, 110...control unit, 111...acquisition unit, 112...determination unit, 113...identification unit, 114...classification unit, 115...output unit, 200...staff terminal, 800...computer, 801...processor, 803...memory, 805...storage device, 807...input I / F unit, 809...data I / F unit, 811...communication I / F unit, 813...display device.

Claims

DEPCT6830 / 04 / 25681. Computerized information processing methods, which include: retrieval of life records, including textual information obtained by recording the life of the subject; determination, based on life records, whether psychological and / or behavioral symptoms associated with dementia have occurred in the subject; and identification, if the determination indicates that symptoms have occurred, one or more select causes of symptoms based on life records.

2. Information processing methods based on claim 1, which additionally include: retrieval of sensory information at the recording point of life records and / or care records obtained by quantitatively and / or selectively recording the subject's condition at the recording point; sensory information obtained by perceiving the subject's physical condition and / or surrounding environment; and identification, if the determination indicates that symptoms have occurred, one or more select causes of symptoms based on sensory information and / or care records.3.The information processing method under claim 2, performed by computer, includes the following: retrieval of the subject's healthy life records, including textual information obtained from the subject's healthy life records, and sensory information about the subject in a healthy state obtained from sensory perceptions of the subject's body and / or surrounding environment when the subject is in a healthy state; action, if the determination indicates that a symptom has occurred, a first comparison between the life records and the subject's healthy life records, and / or a second comparison between sensory information and sensory information about the subject in a healthy state; calculation of the participation rate of each one or more symptom-causing options based on the results of the first and / or second comparisons; and identification, based on the participation rate of each one or more symptom-causing options, of one or more symptom-causing options from among the one or more possible options.The information processing method according to claim 3, where each participant's life record at the occurrence of BPSD, which is a judged life record, includes symptoms, and the participant's life record in a healthy state, includes data recorded for the first period tracing back to the starting time point which is the recording time point of each life record, and the method performed by computer includes the following additional steps: extraction, based on the result of the first comparison performed by time series alignment for the first period, of more than one of the first differences between the participant's life record at the occurrence of BPSD and the participant's life record in a healthy state throughout the time series; and the assignment of weights to each more than one of the first differences extracted according to the length of time from the starting time point to the extraction time point of each more than one of the first differences; and the calculation of the participation rate based on additional weights 5.The information processing method under claim 3, where each sensory data point regarding the subject at the occurrence of BPSD is sensory data at the time point of the recorded life log, including symptoms, and sensory data point regarding the subject in a healthy state, including sensory data for the second period harks back from the starting time point, which is the recording time point for each sensory data point, and the method performed by the computer includes: extraction, based on the result of the second comparison performed by time series alignment for the second period, more than one of the second differences between sensory data point regarding the subject at the occurrence of BPSD and sensory data point regarding the subject in a healthy state throughout the time series; and the assignment of weights to each more than one of the second differences extracted according to the length of time from the starting time point to the extraction time point of each more than one of the second differences; and the calculation of the participation rate based on additional weights.

7. Methods of information processing according to claim 1 or 2, where text information is recorded as independent text by a recorder using specific nursing documentation as the recording method.

8. Methods of information processing according to claim 1 or 2, performed by a computer, which include additional methods: classification, if the result of the determination indicates that a symptom has occurred, the symptom is classified into more than one category; and evaluation of the condition of symptom occurrence for each more than one category.

9. Methods of information processing according to claim 1 or 2, performed by a computer, which include additional methods: identification, from among more than one proposed improvement for care to be provided to the patient, the proposed improvement corresponds to at least one or more of any chosen cause.The information processing methods under Claim 8, which are performed by computer, include: retrieval of assessment information indicating the outcome of the assessment performed on the subject; identification of the subject's pattern based on assessment information and / or symptom information indicating the outcome of the decision; calculation of the estimation level of each improvement proposal relative to the pattern; and identification, from among more than one improvement proposal, of the improvement proposal that corresponds to at least one or more of any choice reasons based on the estimation level.

10. The information processing methods under Claim 1 or 2, where if the outcome of the decision indicates that symptoms have occurred, symptom information indicating the outcome of the decision includes the date and time of symptom onset, and the methods performed by computer include: reference to the storage unit that holds care history information indicating the history of care provided to the subject during a specific period; and identification of the content of care provided at the date and time of symptom onset.11.The program for computer implementation consists of: a retrieval function that retrieves life records, including text information obtained from the subject's life records; a decision-making function that determines, based on the life records, whether psychological and / or behavioral symptoms associated with dementia have occurred in the subject; and an identification function that, if the decision indicates that symptoms have occurred, identifies one or more cause-and-effect choices based on the life records.

12. The information processing device consists of: a retrieval unit that retrieves life records, including text information obtained from the subject's life records; a decision-making unit that determines, based on the life records, whether psychological and / or behavioral symptoms associated with dementia have occurred in the subject; and an identification unit that, if the decision indicates that symptoms have occurred, identifies one or more cause-and-effect choices based on the life records.

Images