Information Processing Apparatus and Information Processing Method

Abstract

To provide an information processor and a method for processing information that can use implicit knowledge properly.SOLUTION: The information processor includes: a processing unit for receiving a request to register know-how information including information in which output information and input information are related to each other, the output information being used for nursing care and being output to a care-giver and the input information being for outputting the output information; and a storage unit for storing the know-how information on the basis of the request of registration. The processing unit determines the importance level of the know-how information on the basis of relation information which relates the change of state information showing the state of a care-taker and the know-how information used to nurse the care-taker to each other.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and the like.

Background Art

[0002] Conventionally, a system used in a scene where an assistant assists a person in need of assistance is known. Patent Document 1 discloses a method of arranging sensors in a living space and generating provision information regarding the state of a resident living in the living space based on the time change of detection information acquired by the sensors.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Provided are an information processing apparatus, an information processing method, and the like that can appropriately utilize tacit knowledge.

Means for Solving the Problems

[0005] One aspect of the present disclosure relates to an information processing apparatus including: a processing unit that receives a registration request for know-how information including information used in assistance, in which output information output to an assistant and input information for outputting the output information are associated with each other; and a storage unit that stores the know-how information based on the registration request. The processing unit determines the importance of the know-how information based on association information associating a change in state information representing the state of a person in need of assistance with the know-how information used for assisting the person in need of assistance.

Brief Description of the Drawings

[0006]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13A

Figure 13B

Figure 14A

Figure 14B

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22A

Figure 22B

Figure 22C

Figure 23A

Figure 23B

Figure 23C

Figure 23D

Figure 23E

Figure 24

Figure 25

Figure 26

Figure 27

Figure 28

Figure 29A

Figure 29B

Figure 30A

Figure 30B

Figure 31

Figure 32A

Figure 32B

Figure 33A

Figure 33B

Figure 34A

Figure 34B

Figure 35

Figure 36

Figure 37A

Figure 37B

Figure 37C

Figure 37D

Mode for Carrying Out the Invention

[0007] Hereinafter, this embodiment will be described with reference to the drawings. For the drawings, the same or equivalent elements are denoted by the same reference numerals, and redundant descriptions are omitted. Note that the embodiment described below does not unduly limit the content described in the claims. Also, not all of the configurations described in this embodiment are essential constituent elements of the present disclosure.

[0008] 1. Example of System Configuration FIG. 1 is a configuration example of an information processing system 10 including an information processing apparatus according to the present embodiment. The information processing system 10 according to the present embodiment provides information to care staff so that appropriate assistance can be provided regardless of the proficiency of the care staff by digitizing the "intuition" and "tacit knowledge" involved in the work performed by the care staff based on their "intuition" and "tacit knowledge" in, for example, a care facility. Hereinafter, for the sake of simplicity, "intuition" and "tacit knowledge" will be simply referred to as tacit knowledge. In the following, a method for accumulating and using tacit knowledge related to assistance in a care facility, a hospital, etc. will be described, but the present embodiment is not limited to this. For example, in home care where care is provided outside the facility, tacit knowledge related to the assistance of helpers may be accumulated and used. Furthermore, the method of the present embodiment provides the tacit knowledge of experts, etc. to other users, and is widely applicable to scenes where tacit knowledge is used, such as schools, factories, and companies.

[0009] The information processing system 10 shown in FIG. 1 includes a server system 100, a terminal device 200, and a headset 300. In FIG. 1, two terminal devices 200-1 and 200-2 are illustrated as the terminal device 200, and headsets 300-1 and 300-2 are illustrated as the headset 300. However, the configuration of the information processing system 10 is not limited to FIG. 1, and various modifications such as omitting a part or adding other configurations are possible. For example, the number of terminal devices 200 and headsets 300 may be three or more. The sound input unit and sound output unit of the terminal device 200 may be used instead of using the headset 300. Also, the same applies to FIGS. 2 and 3 described later in that modifications such as omitting or adding configurations are possible.

[0010] Hereinafter, when there is no need to distinguish between a plurality of terminal devices 200 from each other, they will be simply referred to as the terminal device 200. Similarly, when there is no need to distinguish between a plurality of headsets 300 from each other, they will be simply referred to as the headset 300.

[0011] The information processing apparatus according to the present embodiment corresponds to, for example, the server system 100. However, the method of the present embodiment is not limited to this, and the processing of the information processing apparatus may be executed by distributed processing using the server system 100 and other devices. For example, the information processing apparatus according to the present embodiment may include the server system 100 and the terminal device 200. Hereinafter, an example in which the information processing apparatus is the server system 100 will be described.

[0012] The server system 100 is connected to the terminal device 200 and the headset 300 via a network, for example. The network here is a public communication network such as the Internet, for example, but may also be a LAN (Local Area Network) or the like. For example, the terminal device 200 and the headset 300 are devices used by the staff of a nursing facility or nurses in a hospital during their work. Note that the headset 300 is not limited to a device that can be directly connected to the server system 100, and may be a device connected to the server system 100 via the terminal device 200.

[0013] Also, the terminal device 200 is not limited to a device that directly communicates with the server system 100. For example, a relay device (not shown) may be provided in a nursing facility or the like. The relay device is a device that can communicate with the server system 100 via a network. The terminal device 200 and the headset 300 may be connected to the relay device using a LAN within the nursing facility and connected to the server system 100 via the relay device. For example, in a nursing facility or the like, it is assumed that a plurality of terminal devices 200 and a plurality of headsets 300 are used simultaneously. The relay device may perform a process of selecting the terminal device 200 or the headset 300 that is the transmission target of the information from the server system 100. Alternatively, the relay device may be an administrator terminal used by the administrator of the nursing facility and may operate based on the operation input of the administrator. For example, information from the server system 100 may be displayed on the display unit of the relay device, and the administrator who has viewed the display result may select the terminal device 200 or the headset 300 as the transmission destination. Also, as described above, the information processing apparatus according to the present embodiment can be variously modified, and for example, the above-described relay device may be included in the information processing apparatus.

[0014] The server system 100 may be a single server or may include a plurality of servers. For example, the server system 100 may include a database server and an application server. The database server stores various data to be described later with reference to FIG. 2. The application server performs the processes to be described later with reference to FIGS. 4, 6, 10, 12, etc. Here, the plurality of servers may be physical servers or virtual servers. Further, when virtual servers are used, the virtual servers may be provided on one physical server or may be distributed and arranged on a plurality of physical servers. As described above, the specific configuration of the server system 100 in the present embodiment can be variously modified.

[0015] The terminal device 200 is a device used for presenting information provided by the server system 100 to the user and for inputting information by the user of the terminal device 200. In the present embodiment, the user may be, for example, a caregiver who assists a care recipient (patient, resident) in a care facility or the like. Alternatively, the user of the terminal device 200 may be a home helper who provides visiting care, or may be a nurse, physical therapist, occupational therapist, or speech therapist who assists patients in a hospital or the like. Assistance in the present embodiment refers to assisting those with a low degree of self-care ability in daily life. Assistance includes various cares for the care recipient, such as meal assistance, excretion assistance, transfer / movement assistance, etc. Further, assistance in the present embodiment may be extended to caregiving and nursing.

[0016] Also, the user in the present embodiment is not limited to a user who performs assistance as a job, and may be a family member of the care recipient. Since the family member of the care recipient may not have specialized knowledge regarding assistance, for example, they do not perform the registration of tacit knowledge to be described later with reference to FIGS. 4 and 6, and are users who exclusively utilize the tacit knowledge registered by other users. However, the family member of the care recipient is not prohibited from registering tacit knowledge.

[0017] Considering its use in a scene where assistance is provided, for example, the terminal device 200 may be a smartphone or a tablet terminal that is easy to carry. However, the screens described later with reference to FIG. 16 etc. may be viewed in a scene where the assistant is not providing assistance, and the terminal device 200 may be a PC (Personal Computer) or the like.

[0018] The headset 300 also includes earphones or headphones for outputting sound, and a microphone that converts sound into an electrical signal and outputs it as audio data. The headset 300 is a device that performs a process of outputting the speech of the user as audio data and a process of presenting information from the server system 100 to the user as sound.

[0019] For example, a user such as an assistant is lent one terminal device 200 and one headset 300, and communicates with the server system 100 using the terminal device 200 and the headset 300. However, the method of this embodiment is not limited to this, and the headset 300 may be omitted from the device used by the user, or other wearable devices may be added. The wearable device here may be a glasses-type device, a wristwatch-type device, or a device of other shapes.

[0020] FIG. 2 is a block diagram showing a detailed configuration example of the server system 100. The server system 100 includes, for example, a processing unit 110, a storage unit 120, and a communication unit 130. The processing unit 110 receives a registration request for know-how information 121 that includes information used in assistance, output information output to the assistant, and input information for outputting the output information. The storage unit 120 stores a plurality of know-how information 121 based on a plurality of registration requests.

[0021] The output information here refers to information that enables the user, who is an assistant, to utilize tacit knowledge by receiving the presentation of the output information. The output information may be, for example, information for supporting the specific actions of the assistant. The assistant performs various types of assistance such as meal assistance and toileting assistance. Also, in each type of assistance, the assistant performs specific actions for executing the assistance. For example, in meal assistance, the assistant performs various assistance actions such as making the assisted person sit in a posture suitable for eating and taking food with a spoon and bringing it to the mouth of the assisted person. The output information may be assistance information representing these assistance actions. For example, the output information may be information indicating whether an action should be performed, or information specifying the correct timing, movement, posture, amount, etc. when performing an action.

[0022] Also, an experienced assistant may use their intuition such as "feeling that the person is likely to fall" for a specific assisted person. This is presumably because an experienced assistant has the ability to appropriately grasp the state of the assisted person and the living environment of the assisted person, and naturally estimate the risks of the assisted person. The output information of this embodiment may be information representing the risks of the assisted person. Narrowly speaking, the risk here refers to the risk of an incident occurring, and the incident represents an incident that can be suppressed by appropriate assistance. The output information here does not necessarily need to be something that instructs the assistant to perform specific actions. For example, even if the output information is not information instructing specific actions for preventing a fall, by appropriately grasping the fall risk of the assisted person, the assistant can independently determine actions considering the fall risk.

[0023] Thus, the output information of this embodiment may be assistance information for instructing a caregiver to perform specific actions, or may be information for providing the caregiver with knowledge considered useful in caregiving. When the output information is the latter, the specific action content will be left to the caregiver, but at least compared to the case where there is no output information, it is possible to promote the execution of high-quality caregiving. Note that the knowledge useful in caregiving is not limited to risks. For example, in meal assistance, information presenting the manner of cooking may be used as the output information. The output information may be information representing other knowledge used in meal assistance, or may be information used in caregiving other than meal assistance.

[0024] Also, the input information in this embodiment is information for outputting the output information, and specifically, may be information representing elements considered by experts in tacit knowledge. For example, when the output information is assistance information representing assistance actions to be performed by a caregiver, the input information may be condition information representing the start conditions of the assistance actions. In caregiving, there may be situations where the same assistance action is useful and situations where it is not. For example, an expert adjusts their actions according to the situation (conditions), such as performing the first action when the first condition is met and performing the second action when the second condition is met, to provide high-quality caregiving. Therefore, by using condition information as the input information of the know-how information 121, it becomes possible to cause the caregiver to perform appropriate actions in appropriate situations.

[0025] However, so that the input information is not limited to the condition information representing the start condition, the input information is not limited to the condition information representing the start condition. For example, the input information may be one or more pieces of information that serve as an index when obtaining the output information. In the above example of risks, a skilled person can estimate the risks of the person requiring assistance by intuition or tacit knowledge by comprehensively judging the physical functions, cognitive functions, specific action contents, etc. of the person requiring assistance. In this case, in order to utilize the tacit knowledge of the skilled person as the output information, information representing physical functions, information representing cognitive functions, information representing action contents, etc. may be used as the input information. The same applies when the output information is information other than risks, and the input information can widely include information that can be a judgment index when obtaining the output information.

[0026] In the following description, an example will be described in which the input condition is condition information representing a given start condition. Also, an example will be described in which the output information is assistance information representing the assistance actions to be executed when the above start condition is satisfied. However, as described above, the condition information in this specification can be extended to input information representing other than the start condition. Also, the assistance information in this specification can be extended to output information representing other than the assistance actions.

[0027] The processing unit 110 of the present embodiment is configured by the following hardware. The hardware can include at least one of a circuit that processes digital signals and a circuit that processes analog signals. For example, the hardware can be configured by one or more circuit devices mounted on a circuit board or one or more circuit elements. The one or more circuit devices are, for example, IC (Integrated Circuit), FPGA (field-programmable gate array), etc. The one or more circuit elements are, for example, resistors, capacitors, etc.

[0028] Further, the processing unit 110 may be implemented by the following processors. The server system 100 of the present embodiment includes a memory that stores information, and a processor that operates based on the information stored in the memory. The information is, for example, a program and various types of data. The processor includes hardware. The processor can use various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and a DSP (Digital Signal Processor). The memory may be a semiconductor memory such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), or flash memory, a register, a magnetic storage device such as a hard disk drive (HDD), or an optical storage device such as an optical disk drive. For example, the memory stores instructions readable by a computer, and when the processor executes the instructions, the functions of the processing unit 110 are realized as processing. The instructions here may be instructions in an instruction set that constitutes a program, or instructions that instruct operations to the hardware circuit of the processor.

[0029] The processing unit 110 includes, for example, a registration processing unit 111, a search processing unit 112, a similarity determination unit 113, a state determination unit 114, and an importance determination unit 115.

[0030] The registration processing unit 111 receives information corresponding to the tacit knowledge of the user and performs processing for storing the information in the storage unit 120. For example, as will be described later with reference to FIG. 4, the registration processing unit 111 performs processing for registering tacit knowledge as know-how information 121. Further, as will be described later with reference to FIG. 6, the registration processing unit 111 may perform processing for creating and updating registration information 122 that associates devices, processing algorithms, parameters, etc. with the know-how information 121 in order to make the tacit knowledge in a more easily usable form.

[0031] When there is a user who wishes to use the know-how information 121 registered by the registration processing unit 111, the search processing unit 112 receives the search request of the user and performs a process of presenting search results. Also, when any know-how information 121 among the search results is selected by the user, the search processing unit 112 may create and update list information 123 which is information associating the user with the know-how information 121. Thereby, each user can utilize the know-how information 121 registered by others. More specifically, the list information 123 is a set of one or a plurality of know-how information 121 being used by a given user.

[0032] The similarity determination unit 113 performs a first similarity determination process for determining the similarity between two pieces of know-how information 121. For example, when the search processing unit 112 acquires the above search request, it may acquire the result of the first similarity determination process from the similarity determination unit 113 and determine the know-how information 121 to be presented as search results based on the result.

[0033] The state determination unit 114 performs a process of acquiring state information representing the state of the assisted person. Details of the state information and details of the acquisition process will be described later.

[0034] The importance determination unit 115 performs a process of determining the importance of the know-how information 121 based on association information associating changes in the state information of the assisted person with one or a plurality of know-how information 121 used for assisting the assisted person.

[0035] The storage unit 120 is a work area of the processing unit 110 and stores various information. The storage unit 120 can be realized by various memories, and the memory may be a semiconductor memory such as SRAM, DRAM, ROM, flash memory, a register, a magnetic storage device, or an optical storage device.

[0036] The storage unit 120 may store know-how information 121, registration information 122, and list information 123. The know-how information 121 is information in which condition information representing a start condition and assistance information representing an assistance action to be executed when the start condition is satisfied are associated with each other. The condition information and the assistance information are, for example, text.

[0037] The registration information 122 includes one or more know-how information 121 registered by the user. The registration information 122 is information in which, for example, a device (sensor) for at least automating the determination of the start condition and the specific processing content of the start determination are associated with the know-how information 121. However, it is not prohibited for the registration information 122 to include information that is not associated with a device or the like. The list information 123 is a set of one or more know-how information 121 being used by a given user. Details of each piece of information will be described later. Also, the storage unit 120 may store other information.

[0038] The communication unit 130 is an interface for performing communication via a network, and includes, for example, an antenna, an RF (radio frequency) circuit, and a baseband circuit. The communication unit 130 may operate according to the control by the processing unit 110, or may include a processor for communication control different from the processing unit 110. The communication unit 130 is an interface for performing communication according to, for example, TCP / IP (Transmission Control Protocol / Internet Protocol). However, various modifications of the specific communication method are possible.

[0039] FIG. 3 is a block diagram showing a detailed configuration example of the terminal device 200. The terminal device 200 includes, for example, a processing unit 210, a storage unit 220, a communication unit 230, a display unit 240, and an operation unit 250.

[0040] The processing unit 210 is composed of hardware including at least one of a circuit for processing digital signals and a circuit for processing analog signals. Also, the processing unit 210 may be realized by a processor. The processor can use various processors such as a CPU, a GPU, a DSP, etc. By the processor executing the instructions stored in the memory of the terminal device 200, the functions of the processing unit 210 are realized as processing.

[0041] The storage unit 220 is a work area of the processing unit 210 and is realized by various memories such as SRAM, DRAM, and ROM.

[0042] The communication unit 230 is an interface for performing communication via a network and includes, for example, an antenna, an RF circuit, and a baseband circuit. The communication unit 230 communicates with the server system 100 via, for example, a network.

[0043] The display unit 240 is an interface for displaying various information and may be a liquid crystal display, an organic EL display, or another type of display. The operation unit 250 is an interface for receiving user operations. The operation unit 250 may be buttons or the like provided on the terminal device 200. Also, the display unit 240 and the operation unit 250 may be a touch panel configured integrally.

[0044] Also, the terminal device 200 may include components not shown in FIG. 3, such as a light emitting unit, a vibration unit, a sound input unit, and a sound output unit. The light emitting unit is, for example, an LED (light emitting diode) and performs notification by light emission. The vibration unit is, for example, a motor and performs notification by vibration. The sound input unit is, for example, a microphone, and the sound output unit is, for example, a speaker, and performs notification by sound. Also, the terminal device 200 may include various sensors such as a motion sensor such as an acceleration sensor and a gyro sensor, an imaging sensor, and a GPS (Global Positioning System) sensor.

[0045] 2. Registration of Data Next, with reference to FIGS. 4 to 9, the process of registering know-how information 121 in the storage unit 120 of the server system 100 will be described. The following process is for a user who is an assistant or a nurse to accumulate their tacit knowledge in a manner that can be utilized by others.

[0046] 2.1 Registration Process by Text First, the user inputs text including a start condition such as "when xxx, do yyy" and the assistance action to be executed when the start condition is satisfied. By doing so, it becomes possible to accumulate in the server system 100 the situations and actions that the target user considers important in providing assistance.

[0047] FIG. 4 is a diagram for explaining the flow of the registration process of know-how information 121. When this process starts, first, the user speaks the above-mentioned content "when xxx, do yyy" toward the microphone of the headset 300. In step S101, the headset 300 converts the user's speech into voice data and transmits the voice data to the terminal device 200. Note that, as a pre-step of voice input, recognition processing of a given trigger word may be performed, or an operation on an operation unit provided on the headset 300 may be performed.

[0048] In step S102, the terminal device 200 performs voice recognition processing on the voice data transmitted from the headset 300. In the voice recognition processing, first, acoustic analysis for extracting feature amounts from the voice data is performed. For the result of the acoustic analysis, a process of identifying phonemes with similar features using an acoustic model is performed. Further, using a pronunciation dictionary and a language model, the voice recognition result is obtained by converting phonemes into words and sentences. The voice recognition result is data representing the conversion result of converting voice data into text. Note that in the voice recognition processing of the present embodiment, since well-known methods can be widely applied, further detailed description is omitted.

[0049] In step S103, the terminal device 200 transmits the text that is the result of the speech recognition process to the server system 100. The data transmitted in step S103 is, for example, text such as "if xxx, then do yyy". Alternatively, in the speech recognition process, the terminal device 200 may obtain two texts representing the start condition and the assistance action by detecting words such as "if... then", "in the case of", and "when". In the above example, "xxx did" is the text representing the start condition, and "do yyy" is the text representing the assistance action.

[0050] In step S104, the registration processing unit 111 of the server system 100 performs a process of storing the know-how information 121 in the storage unit 120 based on the acquired text. For example, the registration processing unit 111 stores information for identifying the user who is the source of the text. The information for identifying the user may be the identification information assigned to the headset 300, or may be the identification information assigned to the terminal device 200. Alternatively, the information for identifying the user may be a user ID that uniquely identifies the user. For example, the registration processing unit 111 stores information including the user ID, the text representing the start condition, and the text representing the assistance action in the storage unit 120 as the know-how information 121.

[0051] FIG. 5 is an example of the know-how information 121 stored in step S104. The ID in FIG. 5 is information that uniquely identifies the know-how information 121. Note that when the know-how information 121 can be uniquely identified by the combination of the start condition and the assistance action, the ID may be omitted. The registered user is a user ID or the like representing the user who registered the target know-how information 121. Regarding the start condition and the assistance action, as described above, they are texts based on user input. Note that the condition information representing the start condition is not limited to text only, and may include voice data or the result of the speech recognition process. The result of the speech recognition process is, for example, the result of morphological analysis, which is information associating morphemes with parts of speech. The same applies to the assistance information representing the assistance action, which may include voice data or the result of the speech recognition process.

[0052] Also, as shown in FIG. 5, the registration processing unit 111 may perform a process of registering information other than the above as know-how information 121. For example, the know-how information 121 may include information for specifying the situation in which the assistance action is performed. For example, the know-how information 121 may include information indicating in which type of assistance among various types of assistance such as meal assistance, excretion assistance, transfer / movement assistance, etc. the assistance action is executed. Further, the know-how information 121 may include information representing the attributes of the care recipient who is the target of the user's assistance. The attributes here include information such as the age, gender, height, weight, medical history, medication history, etc. of the care recipient. Also, the know-how information 121 may include physical evaluation data representing the physical evaluation of the care recipient. The physical evaluation data includes information such as the evaluation value of ADL (Activities of Daily Living), rehabilitation history, fall risk, pressure ulcer risk, etc. In this way, it becomes possible to store the know-how information 121 representing tacit knowledge regarding in which type of assistance and for which type of care recipient it should be used.

[0053] Note that additional information such as the type of assistance, the attributes of the care recipient, and the physical evaluation data may be input by the user voluntarily. For example, in addition to utterances such as "when xxx, do yyy", the user may make utterances including words such as "meal", "tall height", etc. Also, the user may make a series of utterances including additional information such as "when a tall patient xxx during a meal, do yyy".

[0054] Also, the server system 100 may send questions such as "In what kind of scene is it used?", "For what kind of care recipient is it used?" to the headset 300. When the user answers the question by voice and the text representing the answer result is sent to the server system 100, the above additional information is acquired.

[0055] Thus, in this embodiment, the tacit knowledge is stored in the storage unit 120 of the server system 100 as know-how information 121 including text. Since the user only needs to mutter the start conditions and assistance actions that he / she deems important during the assistance process using the headset 300, complex operation inputs are not required. Therefore, it becomes easy to collect a large amount of tacit knowledge used in the fields of nursing care and medical care.

[0056] When the collection of the know-how information 121 progresses, the server system 100 may perform an analysis process on the know-how information 121. For example, the processing unit 110 may perform a process of mapping each know-how information 121 onto a feature space by obtaining feature amounts based on each know-how information 121. For example, the processing unit 110 can estimate particularly important information among the tacit knowledge by obtaining a dense region in the feature space.

[0057] Although FIG. 4 shows an example in which voice recognition processing is performed in the terminal device 200, it is not limited thereto. For example, the terminal device 200 may transmit the voice data received from the headset 300 to the server system 100. In this case, the processing unit 110 of the server system 100 may perform voice recognition processing. Also, the voice recognition processing may be executed on an external voice recognition server.

[0058] Also, the user's input may be made using text instead of voice. For example, the terminal device 200 may obtain text such as "if xxx occurs, do yyy" by accepting a character input operation by the user. The processing after obtaining the text is the same as the example in FIG. 4.

[0059] 2.2 Association with Devices By performing the processing shown in FIG. 4, for example, assume that know-how information 121 including a start condition of "when the face starts to wobble during a meal" and an assistance action of "stop providing the meal" is registered. Since these texts can be used to draw attention in meal assistance, they are meaningful information.

[0060] However, the method of this embodiment is not limited to accumulating tacit knowledge as text data, and additional information may be associated. For example, the registration processing unit 111 associates information for automatically determining the start condition with the know-how information 121. In this way, whether or not the condition of "the face starts to wobble" is satisfied can be automatically determined in the server system 100. As a result, the variation in judgment for each user can be suppressed, and it becomes possible to make a user with low proficiency perform the same actions as a user with high proficiency.

[0061] Specifically, in this embodiment, information for identifying a device having a sensor for data collection, information for identifying specific processing contents for the sensor information from the sensor, etc. may be associated with the know-how information 121. Hereinafter, it will be described with reference to FIGS. 6 to 8.

[0062] FIG. 6 is a diagram for explaining the flow of processing for collecting information for automation. First, in step S201, the registration processing unit 111 extracts a portion that requires interpretation from the condition information representing the start condition. The portion that requires interpretation is specifically a portion that is the target of automatic determination by the server system 100, and is, for example, text representing the movement of the assisted person, the state of the assisted person, the environment of the assisted person, etc.

[0063] For example, in the case of the start condition of "if the face starts to wobble during a meal", the text "starts to wobble" represents the movement of the assisted person to be detected in the determination of the start condition. Also, the portion "the face" is information for specifying the part to be the detection target of the movement. Therefore, the registration processing unit 111 extracts the portion "the face starts to wobble" from "if the face starts to wobble during a meal" as the portion that requires interpretation.

[0064] Similarly, for the know-how information 121 in which the assistance action of "changing to an easy-to-eat posture" is associated with the start condition of "eating only a little of the rice with a spoon", "not eating" represents the direct movement of the person receiving assistance. Also in this case, "the rice" is used in the determination because it represents the object to be eaten. Also, the part "with a spoon" also specifies the location where the rice is located and can be used in the determination. Also, "only a little" also gives a criterion for the amount and can be used in the determination. Therefore, the registration processing unit 111 extracts, for example, the text "eating only a little of the rice with a spoon" as a part that requires interpretation.

[0065] As described above, the registration processing unit 111 may identify parts that require interpretation, for example, by performing morphological analysis or the like in natural language processing. For example, as described above, the registration processing unit 111 first extracts phrases representing movements and states based on the results of morphological analysis. Further, the registration processing unit 111 may perform a process of sequentially extracting noun phrases that are the target words, adverbial phrases, adjective phrases, etc. that modify the movements and states. For example, when morphological analysis is performed in the speech recognition process shown in step S102 of FIG. 4, the registration processing unit 111 may extract parts that require interpretation based on the results of the speech recognition process.

[0066] Alternatively, the storage unit 120 of the server system 100 may store in advance words representing movements, states, etc. that are highly necessary to detect in assistance. The registration processing unit 111 may extract parts that require interpretation based on a comparison process between those words and the text representing the start condition. In addition, various modifications of the process of extracting parts that require interpretation are possible. For example, machine learning may be performed on a neural network or the like using training data of know-how information and information on parts that require interpretation among that know-how information, and parts that require interpretation may be automatically extracted using the learned model. Hereinafter, the neural network will be denoted as NN. Also, examples of NN will be described later with reference to FIG. 17 and the like.

[0067] In step S202, the registration processing unit 111 identifies a device including sensors necessary for processing based on the extraction result of the part that requires interpretation. For example, when determining the start condition of "the face began to wobble", the registration processing unit 111 determines that it is necessary to detect the movement of the face (head) of the assisted person. For example, the registration processing unit 111 identifies a camera capable of imaging the face of the assisted person, a wearable device that can be worn on the head and includes a motion sensor, etc. as the devices necessary for processing. For example, the storage unit 120 of the server system 100 may store in advance one or more devices capable of detecting the movement of each part of the assisted person for each part of the assisted person. Also, for example, machine learning may be performed on a neural network or the like using the text information of the start condition and the training data of the devices necessary for processing, and the devices necessary for processing may be automatically identified using the learned model.

[0068] Also, as a device for determining that "only a little of the rice with the spoon was eaten", a camera or the like capable of imaging the hand of the caregiver or the mouth of the assisted person is identified as a device including the sensors necessary for processing.

[0069] In step S203, the registration processing unit 111 determines whether the device identified for the target user is available. The user here is, for example, the registered user who registered the know-how information 121 by performing the process of FIG. 4.

[0070] For example, the storage unit 120 stores in advance a device list available for each user. The device list is information identifying specific devices such as smartphones, headsets, glasses-type wearable devices, watch-type wearable devices, devices capable of acquiring the biological information of the assisted person, etc. More specifically, the device list may store not only information such as simply "smartphone", but also the manufacturer of the smartphone, the model number of the product, etc.

[0071] Also, the devices available to the user are not limited to the devices worn or carried by the user, and may be devices placed in a nursing facility or the like. For example, the device list may include a camera placed in the work environment of the target user, or may include other sensor devices. The sensors included in the sensor device can be implemented in various modifications, and various sensors such as a temperature sensor, a humidity sensor, an illuminance sensor, a barometric pressure sensor, an activity meter, and an odor sensor can be used.

[0072] In step S203, the registration processing unit 111 compares the device specified in step S202 with the device list available to the registered user. In the above example, the registration processing unit 111 determines whether each device included in the device list can image the face of the care recipient or includes a motion sensor and can be worn on the head.

[0073] If the registration processing unit 111 determines that the registered user cannot use the specified device, the processing after step S204 is omitted. In this case, no device or the like is associated with the registered know-how information 121. That is, the know-how information 121 is used in the form of text such as "when xxx" "do yyy", and no automatic start condition determination or the like is performed.

[0074] Note that the registration processing unit 111 may instruct the terminal device 200 to display information indicating that the device identified via the communication unit 130 is not available. When the registered user determines that the identified device is available, the registration processing unit 111 determines the information necessary to automatically determine the start condition. For example, the registration processing unit 111 determines a first processing algorithm for the device to collect device data, a second processing algorithm for processing the collected device data, and parameters used in the second processing algorithm. Note that device data is specifically sensor information detected by sensors included in the device. For example, when a device having a camera such as a smartphone is identified, the device data (sensor information) is image data captured by the camera.

[0075] In step S204, the registration processing unit 111 determines the first processing algorithm. In other words, the registration processing unit 111 determines the processing content when acquiring sensor information.

[0076] For example, when automating the determination of a start condition such as "the face is wobbling," the registration processing unit 111 needs to acquire, as sensor information, information that can be distinguished between the case where "the face is wobbling" and the case where "the face is not wobbling." That is, the sensor information in this case is information representing the result of detecting the movement of the face of the care recipient, and may be, for example, a moving image of about one second capturing the range including the head of the care recipient, or time-series data of about one second from a motion sensor attached to the head of the care recipient.

[0077] For example, the storage unit 120 may store a table in which a plurality of first processing algorithms are associated with words representing movements such as "wobbly". In the example of detecting whether the "face is wobbling", the first processing algorithm is an algorithm that causes the camera (imaging sensor) to execute a process of imaging a moving image and outputting it in one-second intervals. Alternatively, the first processing algorithm is an algorithm that causes the motion sensor to execute a process of acquiring acceleration data and angular velocity data in time series and outputting them in one-second intervals. The registration processing unit 111 performs a process of specifying a table based on the word extracted in step S201 and selecting any one of the first processing algorithms included in the table. Although omitted in FIG. 6, the registration processing unit 111 may perform a process of displaying a plurality of first processing algorithms included in the specified table on the terminal device 200 and receiving a selection operation by the user.

[0078] When the first processing algorithm is determined, it becomes possible to collect device data (sensor information). Next, the processing unit 110 (registration processing unit 111) performs a process of collecting a plurality of device data acquired by the device and a process of transmitting a request for adding a correct answer tag for each of the plurality of device data to the terminal device 200 used by the registered user. The correct answer tag here represents the determination result by the registered user as to whether each of the plurality of device data is data when the start condition is satisfied. In this way, it is possible to collect information associating the input data in the start condition determination process with the correct answer data to be output when the input data is input. The registration processing unit 111 can determine the parameters used in the second processing algorithm based on these. The parameters will be described later. According to the method of this embodiment, since the determination criteria of the registered user are reflected in the parameters, it becomes possible to appropriately digitize the tacit knowledge of the registered user. Hereinafter, specific processing will be described.

[0079] In step S205, the registration processing unit 111 instructs the terminal device 200 to collect device data serving as a sample (hereinafter also referred to as sample data) via the communication unit 130. For example, the registration processing unit 111 may transmit a program for executing a process corresponding to the first processing algorithm described above. In step S206, the terminal device 200 instructs the sensor to collect sample data. Here, the sensor may be included in the terminal device 200 or may be included in a sensor device different from the terminal device 200. That is, in step S206, the terminal device 200 may perform a process of controlling an internal sensor or may transmit information for instructing data collection to an external device. The terminal device 200 or the sensor device starts collecting sample data by installing the program transmitted from the registration processing unit 111.

[0080] In step S207, the sensor collects sample data. In step S208, the sensor transmits the collected sample data to the terminal device 200. In step S209, the terminal device 200 transmits the sample data to the server system 100. In step S210, the registration processing unit 111 of the server system 100 stores the received sample data in the storage unit 120.

[0081] Through the processes of steps S207 to S210, one piece of sample data is stored in the storage unit 120 of the server system 100. In the present embodiment, the processes of steps S207 to S210 are repeated until a predetermined number of sample data are accumulated. For example, after the registered user performs the process shown in FIG. 4 and continues normal work, sample data collection gradually proceeds. For example, when a start condition such as "the face started to wobble during a meal" is registered, when the registered user performs meal assistance, the camera of the smartphone is controlled to be turned on, and sample data obtained by imaging the head of the person to be assisted is automatically collected. Then, when the registered user continues work including meal assistance for a certain period, collection of a predetermined number of sample data is completed.

[0082] When it is determined that the collection of a predetermined number of sample data is completed, in step S211, the registration processing unit 111 performs a process of generating screen information for displaying the sample data. In step S212, the registration processing unit 111 transmits the screen information to the terminal device 200. In step S213, the display unit 240 of the terminal device 200 displays the sample data. Here, the screen information may be the display screen itself or information that can identify the display screen.

[0083] FIG. 7 is an example of a screen displayed on the display unit 240 in step S213. For example, when the sample data is a moving image of about 1 second that captures the head of the assisted person, the display unit 240 displays a screen including thumbnails of each moving image. The display unit 240 may also display a screen prompting the user to input whether each sample data satisfies the start condition. In the example of FIG. 7, the display unit 240 displays the text "Please select the data of 'the head starts to wobble'".

[0084] In step S214, the terminal device 200 acquires correct answer data indicating whether each sample data satisfies the start condition. For example, based on the screen of FIG. 7, the user uses the operation unit 250 to perform an operation of selecting the data of "the head starts to wobble". For example, the terminal device 200 acquires a correct answer tag indicating that it is correct as the correct answer data corresponding to the selected sample data. The terminal device 200 also acquires an incorrect answer tag indicating that it is incorrect as the correct answer data corresponding to the sample data not selected when the user operation is completed.

[0085] Also, in step S214, the terminal device 200 may acquire information regarding the perspective of the user's judgment. For example, when determining whether the face is "wobbling", it is conceivable to use the magnitude of the maximum movement amount from the reference position as the judgment criterion. Here, the reference position may be, for example, the position of the face in a state of sitting straight on a chair or a bed, or the center in the captured image may be used. Alternatively, it is also possible to use the magnitude of the movement amount of the head in one instance as the judgment criterion regardless of the reference position. That is, even if the same word "wobbling" is extracted, the judgment may vary depending on the user.

[0086] The storage unit 120 may store a table in which information representing a plurality of perspectives is associated with words representing movements such as "wobbling". For example, the table stores two perspectives: "the maximum movement angle of the head with respect to the reference position of the image is greater than the threshold α" and "the movement angle of the head in one instance is greater than the threshold β". The registration processing unit 111 may transmit, for example, in step S212, a display screen that prompts the selection of any of the plurality of perspectives included in the table. Then, in step S214, the terminal device 200 receives information regarding the perspective of judgment together with the reception of the correct answer data.

[0087] In step S215, the terminal device 200 transmits the correct answer data to the server system 100. Also, when the perspective of judgment is input as described above, the terminal device 200 transmits the information regarding the perspective to the server system 100.

[0088] In step S216, first, the registration processing unit 111 performs a process of determining a second processing algorithm for taking device data as input and outputting output data indicating whether the start condition is satisfied. For example, the registration processing unit 111 determines the second processing algorithm based on the user input regarding the perspective of judgment obtained in step S215. For example, when the perspective of "the maximum movement angle of the head with respect to the reference position of the image is greater than the threshold α" is selected, the second processing algorithm is an algorithm including a process of obtaining "the maximum movement angle of the head with respect to the reference position of the image" and a process of comparing the obtained movement angle with the threshold α. When the perspective of "the movement angle of the head in one time is greater than the threshold β" is selected, the second processing algorithm is an algorithm including a process of obtaining "the movement angle of the head in one time" and a process of comparing the obtained movement angle with the threshold β. Also, it is assumed that the specific processing contents are different between the case of targeting a moving image and the case of targeting time-series acceleration data or the like. Therefore, the second processing algorithm may be determined according to the type of device (type of sensor) and the content of the first processing algorithm.

[0089] However, α and β, which are parameters in the above second processing algorithm, are unknown. Therefore, in step S216, the registration processing unit 111 performs a process of calculating parameters based on the sample data and the correct answer data. For example, the registration processing unit 111 obtains "the maximum movement angle of the head with respect to the reference position of the image" for the sample data according to the second processing algorithm. Then, the registration processing unit 111 performs a process of obtaining the most probable α such that the movement angle becomes greater than α for the sample data with the correct answer tag attached, and the movement angle becomes less than or equal to α for the sample data with the incorrect answer tag attached.

[0090] For example, the registration processing unit 111 may classify the sample data with correct tags and the sample data with incorrect tags using an SVM (support vector machine). For example, the registration processing unit 111 obtains a hyperplane that separates the sample data with correct tags and the sample data with incorrect tags, and determines parameters such as α and β based on the hyperplane.

[0091] Note that the second processing algorithm is not limited to the above example, and an NN may be used. For example, the storage unit 120 may store a plurality of NNs with different structures as a plurality of second processing algorithms. For example, the storage unit 120 stores an NN1 that is suitable for processing with image data as input, and an NN2 that is suitable for processing with acceleration data or angular velocity data from a motion sensor as input. In step S216, the registration processing unit 111 performs a process of automatically or based on user input to select any one of a plurality of NNs including NN1 and NN2. Note that NN1 is, for example, a CNN (Convolutional Neural Network). NN2 is, for example, a DNN (Deep Neural Network).

[0092] And in step S216, the registration processing unit 111 may perform a learning process using an NN. For example, the registration processing unit 111 inputs sample data into the NN, and obtains output data by performing a forward operation using the weights at that time. The registration processing unit 111 also obtains an objective function (for example, an error function such as a mean squared error function) based on the output data and the correct data, and updates the weights so as to reduce the error using the error backpropagation method or the like. The registration processing unit 111 may store the NN including the weights at the end of learning in the storage unit 120 as a learned model. That is, when using an NN, the structure of the NN corresponds to the second processing algorithm, and the weights correspond to the parameters.

[0093] In step S217, the registration processing unit 111 stores, in the storage unit 120 in association with the know-how information 121, the device used to acquire the sample data, the processing details for the device data (sensor information) of the device, and the identified parameters.

[0094] FIG. 8 is an example of the registration information 122 stored in step S217. As shown in FIG. 8, the registration information 122 includes a user ID representing the user associated with the device, an ID representing the know-how information 121, the device, and the processing program. Here, the user is, for example, the registered user who registered the know-how information 121 using FIG. 4. The device included in the registration information 122 is, for example, information such as the manufacturer and model number of the device as described above. The processing program is, for example, a combination of the second processing algorithm and parameters, and may be an NN including weights. In the following, an example will be described in which the processing program included in the registration information 122 is the second processing algorithm and parameters, but the processing program here may include the first processing algorithm described above. In this way, it becomes possible to manage the first processing algorithm for acquiring the device data to be processed by the second processing algorithm using the registration information 122.

[0095] By using the know-how information 121 in FIG. 5 and the registration information 122 in FIG. 8, it becomes possible to automatically determine the start condition. For example, for the know-how information 121 corresponding to ID1 in FIG. 5, by performing processing according to PG1 on the device data of Device1, it is possible to automatically determine whether the start condition if1 is satisfied.

[0096] As described above, the processing unit 110 (registration processing unit 111) performs a process of identifying a device used for determining the start condition represented by the condition information by performing text analysis processing on the condition information (for example, steps S202 and S203), and information representing the identified device may be associated with the know-how information 121 (for example, step S217). In this way, since the condition information is associated with a specific device, it becomes possible to determine whether the start condition is satisfied using the device.

[0097] Note that the know-how information 121 in the present embodiment can be considered in three categories from the perspective of association with a device. First, it is the know-how information 121 for which it is determined in step S203 that the device is available and the process of step S217 has been completed. This is know-how information 121 for which, in addition to the association of the device, the second processing algorithm and parameters have also been identified, so that automatic determination of the start condition is possible.

[0098] Second, it is the know-how information 121 for which it is determined in step S203 that the device is unavailable and the processes after step S204 have not been performed. Since the know-how information 121 is used in text form, for example, the user himself / herself determines whether the start condition is satisfied.

[0099] Third, it is the know-how information 121 for which it is determined in step S203 that the device is available but the process of step S217 has not been completed. This is know-how information 121 for which sample data sufficient to determine the parameters has not been collected. For example, the registration processing unit 111 may not generate the registration information 122 for this know-how information 121 and may handle it in the same way as the know-how information 121 for which it is determined in step S203 that the device is unavailable. In the future, when sufficient sample data has been accumulated, the process of step S217 will be completed and the registration information 122 will be generated, so that automatic determination of the start condition will be possible. Also, there may be a case where the generation of the registration information 122 is not performed because the collection of sample data is not completed even after a certain period of time.

[0100] In addition, FIG. 6 shows an example in which the parameter obtained in step S216 is directly stored in step S217. However, the processing of this embodiment is not limited to this. For example, the registration processing unit 111 may use a part of the combination of the sample data and the correct answer data as validation data, and obtain the correct answer rate of the determination processing using the second processing algorithm and the parameter by using the validation data. The registration processing unit 111 transmits the correct answer rate to the terminal device 200. The terminal device 200 presents the correct answer rate and accepts user input on whether to adopt the parameter. Then, when the user inputs to adopt the parameter, the registration processing unit 111 may perform the processing of step S217. Further, when the user inputs not to adopt the parameter, the registration processing unit 111 may, for example, reset the parameter and resume the collection of sample data.

[0101] 2.3 Determine the correct operation As described above, among the start conditions and assistance actions included in the know-how information 121, a method for automating the determination of the start conditions has been described. However, the method of this embodiment is not limited to this, and the processing related to the assistance action may be automated. For example, when there is know-how information 121 such as "only ate a little rice with a spoon", "change the posture of the person to be assisted to a posture that is easy to eat", the process of obtaining the correct answer of "a posture that is easy to eat" may be performed, or a process of warning when the posture taken by the user deviates from the correct posture may be performed. By obtaining the correct answer of the assistance action, it becomes possible to cause the user to perform the assistance action according to the registered know-how information 121 regardless of the user's proficiency.

[0102] The specific processing flow is the same as that in FIG. 6. That is, the registration processing unit 111 extracts the part that requires interpretation from the text representing the assistance action in the same manner as in step S201. In the above example, the registration processing unit 111 extracts "a posture that is easy to eat".

[0103] Next, in the same manner as in steps S202 and S203, the registration processing unit 111 identifies a device including a camera that images the user, a motion sensor that detects the posture, etc., as a device for detecting an easy-to-eat posture, and determines whether the device is available.

[0104] If it is available, in the same manner as in steps S207 to S215, the registration processing unit 111 collects sample data representing the posture of the care recipient and instructs the user to tag the collection result. For example, the sample data is a still image that images the entire body of the user during a meal, and the registration processing unit 111 performs a process of accepting a selection operation of a still image having an easy-to-eat posture among a plurality of still images.

[0105] The registration processing unit 111 determines parameters based on the assigned tags in the same manner as in step S216. The second processing algorithm representing the processing content for the device data may be a comparison process between the bending angle of a joint or the like and a threshold value, or may be another process. Further, an NN that takes the still image itself as an input may be used. The parameter may be the above threshold value or the weight of the NN.

[0106] The registration processing unit 111 associates the registration information 122 including the device, the second processing algorithm, and the parameters for determining the assistance action with the know-how information 121 in the same manner as in step S217.

[0107] Figure 9 shows another example of the registration information 122. As shown in Figure 9, the registration information 122 includes a user ID representing the user who associated the device, an ID representing the know-how information 121, a device In which is the device used for start determination, a processing program In which is the processing program used for start determination, a device Out which is the device used for determination of assistance action, and a processing program Out which is the processing program used for determination of assistance action. The device Out is information such as the manufacturer and model number of the device, similar to the device In. The processing program Out is, similar to the processing program In, for example, a combination of a second processing algorithm and parameters, and may be an NN including weights.

[0108] In addition, for example, in the case of the know-how information 121 of "stop providing meals" when "the face starts to wobble during a meal", it is easy to perform the assistance action of "stop providing meals", and there is little need to obtain the correct action in the server system 100. Therefore, in this case, the above-described processing for the assistance action may be omitted. For example, the device Out and the processing program Out may have no data, like the know-how information 121 of ID1 in Figure 9.

[0109] Also, regarding the determination of the assistance action, there may be a case where the device is determined to be usable, but the second processing algorithm and parameters are not determined due to factors such as insufficient sample data being collected. In this case as well, the device Out and the processing program Out have no data.

[0110] 3. Use of Data Through the above processing, the user's tacit knowledge is accumulated as the know-how information 121. Also, for the know-how information 121 that meets the conditions, the registration information 122 that identifies devices and the like for automating the determination of the start condition and the determination of the assistance action is associated. Hereinafter, a method for using the obtained know-how information 121 will be described.

[0111] 3.1 Search Processing If a user with a low level of proficiency can utilize the tacit knowledge of an expert, appropriate assistance can be executed regardless of the user's proficiency level. For example, each of a plurality of users who use the information processing system 10 selects any one of the know-how information 121 stored in the storage unit 120 of the server system 100 and uses the selected know-how information 121.

[0112] FIG. 10 is a diagram for explaining the flow of processing in which each user selects and uses the know-how information 121. First, in step S301, the user performs a process of inputting a word for search using the headset 300. For example, the user speaks the start condition or the assistance action toward the microphone of the headset 300.

[0113] In step S302, the terminal device 200 performs speech recognition processing and acquires text representing the start condition or text representing the assistance action. In step S303, the terminal device 200 transmits the acquired text to the server system 100 as a search key.

[0114] In step S304, the server system 100 executes a search process using the acquired search key. That is, the processing unit 110 (search processing unit 112) of the server system 100 outputs, as a search result, any one of the know-how information 121 among the plurality of know-how information 121 based on a search request including search information (search key) that is either text corresponding to the start condition or text corresponding to the assistance action. For example, the search processing unit 112 may output, as a search result, know-how information 121 that satisfies conditions such as the degree of coincidence with the search key. Also, as will be described later with reference to FIGS. 13A, 13B, etc., the search processing unit 112 may output, as a search result, know-how information 121 for which the result of the first similarity determination process satisfies a given condition.

[0115] The scenarios where the start condition is used as a search key are, for example, scenarios where the user cannot determine appropriate assistance actions. For example, assume that the user has recognized a situation such as the assisted person making a certain movement or the environment in which the assisted person lives changing in this way, but does not know the assistance actions to be executed in that situation. In this case, by performing a search process using the situation as the start condition, know-how information 121 representing an appropriate response in that situation is provided.

[0116] Also, the assistance actions represent specific actions by the assistant such as feeding with a spoon, speaking, and changing the posture. For example, assume that the user recognizes the actions necessary to assist the assisted person with eating, excretion, etc., but lacks the judgment of in what scenarios and at what timings to execute them. In this case, by performing a search process based on the assistance actions, know-how information 121 representing the start conditions for executing the assistance actions is provided.

[0117] Thus, according to the method of this embodiment, by performing a search process using the start condition or the assistance action as the search key, it is possible to determine and present the know-how information 121 suitable for the user among the plurality of know-how information 121 representing tacit knowledge.

[0118] Note that the specific process of step S304 can be variously modified. For example, when a text representing the start condition is input as the search key, the search processing unit 112 may determine that the know-how information 121 satisfies the condition when at least a part of the text representing the start condition included in the know-how information 121 matches the search key. Also, when a text representing the assistance action is input as the search key, the search processing unit 112 may determine that the know-how information 121 satisfies the condition when at least a part of the text representing the assistance action included in the know-how information 121 matches the search key. Alternatively, the search processing unit 112 may determine the similarity between texts and determine that the condition is satisfied when the similarity is equal to or greater than a threshold value.

[0119] In step S305, the server system 100 transmits one or more pieces of know-how information 121 determined to satisfy the conditions to the terminal device 200. In step S306, the display unit 240 of the terminal device 200 displays the acquired one or more pieces of know-how information 121. In step S307, the terminal device 200 receives a selection operation by the user using, for example, the operation unit 250. That is, the user selects the know-how information 121 that the user wants to use from the know-how information 121 presented as the search result.

[0120] In addition, when the registration information 122 shown in FIG. 5 is associated with the know-how information 121, in order to fully utilize the know-how information 121, it is necessary to select a specific device. For example, assume that the registered user who registered the target know-how information 121 used a smartphone of model number BBB of manufacturer AAA for the determination of the start condition, and the registration information 122 indicating that is stored. However, the user who uses the know-how information 121 does not necessarily own a smartphone of model number BBB of the same manufacturer AAA. Also, if only the camera of the smartphone is used, products of different model numbers of the same manufacturer may be used, or products of other manufacturers may be used. Furthermore, for example, if the registered user's smartphone was used for the purpose of imaging the face of the care recipient, as a device used for automatic determination, for example, a camera installed in a care bed, a camera installed in a living room, a camera mounted on a movable device, etc. may be used. Therefore, when the know-how information 121 registered by the registered user is used by a user other than the registered user, the device may be selected for each user.

[0121] In step S308, the terminal device 200 receives a device selection operation by the user. For example, the storage unit 120 of the server system 100 holds a device list representing the devices owned by the user who performed the search process, and from among them, a process of selecting and presenting a device close to the device included in the registration information 122 may be performed. For example, as described above, when the device of the registered user is a smartphone, the search processing unit 112 may perform a process of displaying a list of smartphones or similar devices owned by the user who performed the search process on the display unit 240 of the terminal device 200. Note that when the registration information 122 is not associated with the know-how information 121, the process of step S308 is omitted.

[0122] Next, in step S309, the terminal device 200 transmits the know-how information 121 selected by the user to the server system 100. In step S310, the server system 100 updates the list information 123 representing the know-how information 121 being used by the target user. When the process of step S308 is performed, the information of the selected device is also transmitted and added to the list information 123.

[0123] As shown in FIG. 10, the processing unit 110 can acquire a usage request for any one of the plurality of know-how information 121 stored in the storage unit 120 from a plurality of users. And the storage unit 120 may store, in association with each of the plurality of users, list information 123 including one or more pieces of know-how information 121 being used. In this way, among the large number of know-how information 121 accumulated in the storage unit 120, it becomes possible to appropriately manage the know-how information 121 used by each user.

[0124] For example, a user with low proficiency may increase the scenarios where they can utilize the tacit knowledge of experts by actively using know-how information 121. Also, when there is an overabundance of information and it cannot all be grasped, adjustments such as limiting the know-how information 121 to be used to important ones are also possible. Additionally, for users with a certain degree of experience, since there are many scenarios where they can appropriately execute assistance without using know-how information 121, the number of know-how information 121 they use may be reduced compared to beginners.

[0125] FIG. 11 is an example of list information 123. The list information 123 includes information for identifying a user, information for identifying the know-how information 121 that the user is using, and information for identifying the device for using the know-how information 121. In the example of FIG. 11, the user a corresponding to UserIDa is using the know-how information 121 of ID1 registered by the registered user corresponding to UserID1. As shown in FIG. 8, the registered user had registered Device1 to automate the know-how information 121 of ID1. In contrast, as shown in FIG. 11, the user a has selected Device1a as the device for automating the know-how information 121 of ID1. That is, even for the same know-how information 121, the devices used may vary according to the user, and the storage unit 120 can store a plurality of devices associated with one know-how information 121.

[0126] Also, in the example of FIG. 11, the user a is using the know-how information 121 of ID2 registered by the registered user corresponding to UserID2. Since the registered user of the know-how information 121 of ID2 has not registered a device, no device is associated when the user a uses it. Note that know-how information 121 without an associated device, such as ID2 in FIG. 11, is utilized, for example, in text form. For example, when information such as "meal" is included as additional information in the know-how information 121, the text corresponding to the know-how information 121 may be notified to the user at the timing of starting meal assistance.

[0127] On the one hand, as in the know-how information 121 associated with the device as shown in ID1 of FIG. 11, automation such as determination of start conditions is possible.

[0128] FIG. 12 is a diagram for explaining the processing flow using the know-how information 121 associated with the device. First, when the know-how information 121 is added to the list information 123, in step S401, the corresponding device starts collecting sensor information. Note that the collection of sensor information may be performed constantly, or may be used in a specific situation related to the know-how information 121. For example, when information such as "excretion" is included as additional information in the know-how information 121, the device may start collecting sensor information at the timing of starting excretion assistance.

[0129] In step S402, the sensor transmits the sensor information to the terminal device 200. Note that when the device here is the terminal device 200, the processing in step S402 corresponds to the transfer of data from the sensor to the processor within the terminal device 200. In step S403, the terminal device 200 transmits the sensor information to the server system 100.

[0130] In step S404, the processing unit 110 automatically determines the start condition based on the sensor information. For example, the processing unit 110 determines the second processing algorithm and parameters based on the registration information 122 in FIG. 8. The processing unit 110 uses the sensor information as input data and performs processing according to the second processing algorithm and parameters to obtain output data indicating whether the start condition is satisfied.

[0131] When it is determined that the start condition is satisfied, in step S405, the processing unit 110 identifies an assistance action based on the know-how information 121. In step S406, the processing unit 110 transmits information representing the identified assistance action to the terminal device 200. In step S407, the terminal device 200 transmits the information representing the assistance action to the headset 300. In step S408, the headset 300 announces the assistance action using a speaker. Note that the information representing the assistance action here is text, and the processing in step S408 may be a voice reading process. However, as described above with reference to FIG. 9, the processing unit 110 may obtain the correct answer of the assistance action and perform notification based on the correct answer.

[0132] As described above, according to the method of the present embodiment, it is possible to digitize the tacit knowledge of a skilled user and provide appropriate assistance to a user with low proficiency. For example, even a user with low proficiency can receive assistance equivalent to that of a skilled person, so the reproducibility of assistance is improved. In addition, variations in care skills are suppressed, and organizational management becomes easier, so incidents such as falls of the care recipient are suppressed. As a result, for example, in a nursing facility or the like, the occurrence of empty beds due to hospitalization and the occurrence of overtime due to the creation of accident reports can be suppressed. In addition, if incidents are suppressed, the user's excessive sensitivity to risks is also suppressed, so stress can be reduced, and as a result, the turnover rate can also be suppressed. In addition, by enabling the improvement of the user's skills and the improvement of the working environment, it is also possible to improve the satisfaction of the care recipient and their family and the quality of life (QOL).

[0133] Note that the information processing system 10, server system 100, terminal device 200, etc. of this embodiment may implement part or most of their processing by a program. In this case, the information processing system 10, etc. of this embodiment is realized by a processor such as a CPU executing the program. Specifically, the program stored in a non-temporary information storage medium is read out, and the read program is executed by a processor such as a CPU. Here, the information storage medium (a medium readable by a computer) stores programs, data, etc., and its function can be realized by an optical disk, HDD, or memory (card-type memory, ROM, etc.). And a processor such as a CPU performs various processes of this embodiment based on the program stored in the information storage medium. That is, the information storage medium stores a program for causing a computer to function as each part of this embodiment.

[0134] Also, the method of this embodiment can be applied to an information processing method including the processing executed in the information processing apparatus 10. The information processing method of this embodiment receives a registration request for know-how information 121 including information in which condition information representing a given start condition and assistance information representing an assistance action to be executed when the start condition is satisfied are associated, and based on a search request including search information for specifying either the start condition or the assistance action, outputs, as a search result, any one of the plurality of know-how information 121 stored based on the plurality of registration requests.

[0135] 3.2 Similarity determination between know-how information Also, the server system 100 (similarity determination unit 113) of this embodiment may perform a process of determining the similarity between a given know-how information 121 and other know-how information 121. For example, in step S304 of FIG. 10, the search processing unit 112 may determine that not only the know-how information 121 extracted using the search key but also similar know-how information, which is know-how information similar to the know-how information 121, satisfies the condition.

[0136] For example, the similarity determination unit 113 may determine the similarity between two pieces of know-how information 121 based on the additional information included in the know-how information 121. For example, as shown in FIG. 5, the additional information includes the type of assistance and words representing the attributes of the person receiving assistance. The similarity determination unit 113 determines that the similarity is high when the same word is included in the two pieces of know-how information 121. Alternatively, synonyms are defined for each word, and the similarity determination unit 113 may determine that the similarity between the two pieces of know-how information 121 is high when a synonym of a word included in one piece of know-how information 121 is included in the other piece of know-how information 121.

[0137] Alternatively, the similarity determination unit 113 may determine the similarity based on text mining. For example, the similarity determination unit 113 performs text mining on at least one of the text representing the start condition and the text representing the assistance action. For each word extracted by text mining, the similarity determination unit 113 obtains the tf-idf representing the importance of the word. Tf is the frequency of occurrence of a word, and idf represents the inverse document frequency. Tf-idf is an index in which the importance of a word with a high frequency of occurrence becomes high, and the importance of a word that appears in many documents becomes low. For example, the similarity determination unit 113 obtains a vector in which tf-idf is associated with each word that appears in the know-how information 121 as a value. The similarity determination unit 113 obtains vectors for two pieces of know-how information 121 respectively, and obtains the similarity between the two pieces of know-how information 121 based on the angle θ formed by the two obtained vectors. For example, the similarity is cos θ. However, various methods for obtaining the similarity between two documents are known, and they can be widely applied in this embodiment. Also, the part to be subjected to text mining is not limited to at least one of the start condition and the assistance action, and may include additional information.

[0138] Also, the similarity determination unit 113 may obtain similar know-how information of the given know-how information 121 from the viewpoint of whether it is frequently used together with the given know-how information 121.

[0139] For example, the plurality of know-how information 121 includes first know-how information, second know-how information, and third know-how information, and the processing unit 110 (similarity determination unit 113) performs a similarity determination process for determining the similarity between any two of the plurality of know-how information 121 stored in the storage unit 120. At this time, the similarity determination unit 113 determines the similarity based on the number of users in which the first know-how information and the second know-how information are included in the list information 123 and the number of users in which the first know-how information and the third know-how information are included in the list information 123.

[0140] FIGS. 13A and 13B are diagrams for explaining the similarity determination process. FIG. 13A is an example of the list information 123 regarding users who are using both the first know-how information corresponding to IDa and the second know-how information corresponding to IDb. In the example of FIG. 13A, 100 users corresponding to UserIDx1 to UserIDx100 are using both the first know-how information and the second know-how information.

[0141] FIG. 13B is an example of the list information 123 regarding users who are using both the first know-how information corresponding to IDa and the third know-how information corresponding to IDc. In the example of FIG. 13B, only one user corresponding to UserIDy1 is using both the first know-how information and the third know-how information.

[0142] In this case, the second know-how information is likely to be used together with the first know-how information, and the third know-how information is less likely to be used together with the first know-how information. The similarity determination unit 113 determines that the similarity between the first know-how information and the second know-how information is higher than the similarity between the first know-how information and the third know-how information.

[0143] In this way, it becomes possible to present the know-how information 121 that is useful for use together to the user as similar know-how information. For example, it is possible to present a combination of useful know-how information 121 to the user who has performed the search process described above using FIG. 10. Here, the first know-how information and the second know-how information may have different types of assistance. For example, when the first know-how information is related to meal assistance, the second know-how information is related to excretion assistance or transfer assistance. In this way, it becomes possible to include the know-how information 121 that is determined to have a low similarity from the viewpoint of additional information or the like in the similar know-how information.

[0144] 3.3 Importance determination of know-how information As described above, in this embodiment, it is possible for the user to easily register the know-how information 121. Also, by the search process, it is possible for users other than the registered user to use the know-how information 121. However, when the registration of the know-how information 121 is easy, there is a high probability that a large number of know-how information 121 will be accumulated in the storage unit 120. In this case, in order to efficiently use a large number of know-how information 121, the importance of each know-how information 121 may be determined. Hereinafter, the first importance from the viewpoint of the care recipient who receives assistance using the know-how information 121 and the second importance from the viewpoint of the caregiver who performs the assistance will be described. Also, in the following description, the first importance is also simply referred to as the importance.

[0145] 3.3.1 Importance considering the care recipient <Status information> The processing unit 110 of this embodiment may determine the importance of the know-how information 121 based on the association information that associates the change in the status information indicating the status of the care recipient with the know-how information 121 used for the care of the care recipient. In this way, it is possible to determine the importance from the viewpoint of how the assistance performed using the know-how information 121 has affected the status of the care recipient. That is, the importance of the know-how information 121 is determined according to the degree of contribution to improving or maintaining (suppressing deterioration) of the status of the care recipient.

[0146] The state information here may be the degree of care needed, which represents the degree of care required by the person receiving assistance. Since various methods are known for obtaining the degree of care needed as numerical data, it becomes possible to use an easily evaluable indicator as the state information.

[0147] The degree of care needed is an indicator for determining whether the target person is in a state of needing care or support, and the degree within that. The state of needing care is, for example, a state where constant care is required. The state of needing support is a state where support is needed in daily life such as housework and personal grooming, and in particular, a state where preventive care services are effective.

[0148] For example, the degree of care needed may be information representing the evaluation results at seven levels of support needed 1 - 2 and care needed 1 - 5 specified by the method described at https: / / www.mhlw.go.jp / stf / seisakunitsuite / bunya / hukushi_kaigo / kaigo_koureisha / nintei / gaiyo2.html. For example, the degree of care needed is determined based on the results of investigations conducted by certifying investigators for various survey items such as physical function and daily living activities, living function, cognitive function, mental and behavioral disorders, and adaptation to social life. Hereinafter, the survey items are also simply referred to as items.

[0149] Figures 14A and 14B are examples of items used for determining the degree of care needed. Each item is determined using one of the evaluation axes of ability, assistance, and presence / absence. Ability represents the degree to which the subject has the ability to perform the target item. For example, for "turning over" shown in 1 - 3 of physical function and daily living movements, the evaluation result will be one of the levels such as "can be done without grasping anything", "can be done by grasping something", "cannot be done". Assistance represents the degree of assistance when performing the target item. For example, for "body washing" shown in 1 - 10 of physical function and daily living movements, the evaluation result will be one of the levels such as "independent", "partial assistance", "full assistance". Presence / absence represents the evaluation of the presence or absence of an event corresponding to the target item. Each item is also classified into one of five categories: ADL / daily living movements, cognitive function, behavior, social life, and medical care, regarding the impact on the life of the target patient or elderly person.

[0150] These items are disclosed, for example, at https: / / www.mhlw.go.jp / file / 06 - Seisakujouhou - 12300000 - Roukenkyoku / 0000077237.pdf and may be used for determining the degree of care needed in this embodiment. Also, the items for determining the degree of care needed may include items not shown in Figures 14A and 14B, such as whether to start hospice care, whether to use a lift, wheelchair, or walker, and whether to guide to the toilet.

[0151] The status information of the person receiving assistance may also be the evaluation result of the ADL (Activities of Daily Living) of the person receiving assistance. The evaluation of ADL may be obtained, for example, using FIM (Functional Independence Measure). In FIM, for each of the 13 items related to motor ADL and 5 items related to cognitive ADL, a 7 - level evaluation from 1 to 7 points is performed, and ADL is evaluated with a numerical value of 18 - 126 points. Note that the evaluation method of ADL is not limited to FIM, and various methods can be applied.

[0152] However, the state information in the present embodiment is not limited to the above example and can be extended to an index representing the state of assistance for the assisted person. Specifically, the state related to assistance is information that identifies the presence or absence of the need for assistance, the type and degree of necessary assistance, and the like.

[0153] Hereinafter, an example where the state information is the degree of care need will be described. Also, hereinafter, it is assumed that the state information is any numerical value from 1 to 7. The numerical value represents that 1 represents Support Needed Level 1, 2 represents Support Needed Level 2, 3 represents Care Needed Level 1, 4 represents Care Needed Level 2, 5 represents Care Needed Level 3, 6 represents Care Needed Level 4, and 7 represents Care Needed Level 5. That is, in the following example, the smaller the numerical value representing the state information, the better the state of the assisted person.

[0154] <Flow of Importance Judgment Process> FIG. 15 is a diagram for explaining the method in the present embodiment. The horizontal axis of FIG. 15 represents time, and t1 and t2 represent given timings. Also, state represents the value of the state information at each timing. The state determination unit 114 of the present embodiment sets a period of a given length and acquires the state information of the assisted person for each such period. The given length here is, for example, one month, but a period of a different length may also be used. In the example of FIG. 15, the state determination unit 114 performs a process of acquiring the state information of the assisted person at each of the timings t1 and t2.

[0155] For example, the determination of the status information may be performed by an expert such as a doctor based on the investigation results obtained by an accredited investigator. The server system 100 receives the input of the status information determined by a doctor or the like. The status determination unit 114 acquires the transmitted status information. Alternatively, when the investigation results obtained by the investigator are acquired, the status determination unit 114 may calculate the status information. For example, in the above-mentioned https: / / www.mhlw.go.jp / stf / seisakunitsuite / bunya / hukushi_kaigo / kaigo_koureisha / nintei / gaiyo2.html, a method for estimating the standard time for long-term care certification or the like using a tree model and the association between the standard time for long-term care certification or the like and the degree of long-term care are described. The status determination unit 114 may calculate the status information from the investigation results by performing the same processing. Alternatively, the status determination unit 114 may perform a process of estimating the evaluation results regarding each item as described later using FIG. 18 or the like. In this case, it is also possible to omit the investigation by the investigator.

[0156] Also, in the present embodiment, the processing unit 110 acquires know-how information 121 (tacit knowledge) used for assisting each care recipient. For example, the user who is the caregiver may be a family member of the care recipient. Since the family member does not provide care as a job, it is highly probable that the family member provides care only for the care recipient. Therefore, it is possible to consider that the know-how information 121 included in the list information 123 of the user who is a family member has been used for assisting the target care recipient.

[0157] Also, the user here is not precluded from being a caregiver or a nurse working in a nursing facility or a hospital. However, when the user is in charge of care recipients A and B, not all of the know-how information 121 included in the user's list information 123 is necessarily used in common by care recipients A and B. For example, it is conceivable that the user uses some of the know-how information 121 included in the list information 123 for the assistance of care recipient A and some other part for the assistance of care recipient B. For example, in addition to the list information 123 shown in FIG. 11, the storage unit 120 may store information that can identify the care recipients to whom each know-how information 121 applies. In this case, even when the user is in charge of a plurality of care recipients, the know-how information 121 used for each care recipient can be identified.

[0158] FIG. 15 is an example of three pieces of association information obtained for three care recipients during a period from t1 to t2, for example. For example, the care recipient whose state information value was 4 at t1 received assistance using four pieces of know-how information 121 with IDs 1, 2, 34, and 56, respectively, during the period from t1 to t2, and the state information value at t2 became 5. Hereinafter, for simplicity of explanation, the know-how information 121 with ID i is also denoted as ai. i is an integer of 1 or more.

[0159] In the example of FIG. 15, similarly, for example, the care recipient whose state information value was 2 at t1 received assistance using three pieces of know-how information 121 with IDs 1, 2, and 31, respectively, during the period from t1 to t2, and the state information value at t2 became 1. Similarly, the care recipient whose state information value was 2 at t1 received assistance using the know-how information 121 with ID 1 during the period from t1 to t2, and the state information value at t2 did not change and remained 2.

[0160] In this way, by specifying the change in state information when one unit of time has elapsed for one care recipient, and the know-how information 121 used during that one unit of time, one piece of association information is obtained. Although three pieces of association information were exemplified in FIG. 15, more association information can be obtained by increasing the number of care recipients targeted and by lengthening the targeted period.

[0161] The importance determination unit 115 determines the importance of the know-how information 121 based on the association information. For example, if there is a tendency for the state of the care recipient for whom the know-how information 121 of a1 was used to improve, the importance determination unit 115 determines that the importance of a1 is high. In the above example, since the greater the value of the state information, the more care is required, an improvement in the state corresponds to a decrease in the numerical value. However, as can be seen from the example in FIG. 15, when assistance is provided using the know-how information 121 of a1, the state may improve, may deteriorate, or may be maintained. Also, when a plurality of pieces of know-how information 121 are combined, it is necessary to identify which piece of know-how information 121 has contributed to the change or maintenance of the state information. Also, it is conceivable that using a given piece of know-how information 121 in combination with other know-how information 121 contributes to the improvement or maintenance of the state information rather than using it alone. That is, it is difficult to understand to what extent the know-how information 121 affects the change in the state information by only focusing on individual know-how information 121.

[0162] Therefore, the processing unit 110 (importance determination unit 115) may perform processing to identify important know-how information based on a regression analysis that uses the value related to the state information as the objective variable and the information indicating the use / non-use of the know-how information 121 as the explanatory variable. The regression analysis here may specifically be a multiple regression analysis that uses the information indicating the use / non-use of each of the plurality of pieces of know-how information 121 as the explanatory variable. The important know-how information here represents the know-how information 121 for which the importance is determined to be a predetermined level or higher.

[0163] The value related to the state information is, for example, a value based on the difference between the value Initial of the state information at the start point of the target period and the value Output of the state information at the end point. Here, as described above, considering the example where the better the state, the smaller the value, the reward shown in the following formula (1) may be used as the value related to the state information. Reward is numerical data where the value increases as the degree of state improvement increases, and it becomes a positive value when the state improves, 0 when the state remains unchanged, and a negative value when the state deteriorates. reward = Initial - Output …(1)

[0164] Also, let the variable representing the use / non - use of the know - how information 121 corresponding to ai be Ai. For example, Ai is a variable that becomes 1 when ai is used for assisting the target assisted person and 0 when it is not used. In this case, multiple regression analysis is performed based on the regression formula of the following formula (2). α1~αn in the following formula (2) are partial regression coefficients, and β is a constant term. n is a positive integer representing the number of pieces of know - how information 121. Narrowly speaking, n represents the number of pieces of know - how information 121 that appear at least once among the plurality of association information to be processed among the know - how information 121 stored in the storage unit 120. In other words, the importance determination unit 115 may exclude the know - how information 121 that does not appear even once in the association information from the target of importance determination. reward = β + α1×A1 + α2×A2 + … + αn×An …(2)

[0165] For example, the importance determination unit 115 performs a process of obtaining the most probable α1~αn and β using the least - squares method based on a plurality of association information. Since multiple regression analysis is a well - known method, a detailed explanation is omitted.

[0166] Further, the importance determination unit 115 tests the significance of each partial regression coefficient. The significance test is, for example, a t-test. The importance determination unit 115 obtains a t-value by performing a t-test on each partial regression coefficient, and further obtains a p-value from the t-value. When the p-value is smaller than a given threshold, the importance determination unit 115 determines that the target partial regression coefficient is significant, that is, the use / non-use of the know-how information 121, which is the explanatory variable corresponding to the partial regression coefficient, affects the change in the state information that is the target variable. The given threshold here is, for example, 0.05, but other values may be used.

[0167] Also, in the above formula (2), the better the state of the assisted person, the larger the value of the reward, which is the target variable. Therefore, when the partial regression coefficient is positive, the target know-how information 121 may contribute to the improvement of the state, and when the partial regression coefficient is negative, the target know-how information 121 may contribute to the deterioration of the state. Therefore, when the p-value is smaller than 0.05 and the partial regression coefficient is positive, the importance determination unit 115 determines that the importance of the corresponding know-how information 121 is high.

[0168] The importance determination unit 115 may determine the importance in two levels: high / low. In the above example, the know-how information 121 with a p-value smaller than the threshold and a positive partial regression coefficient has a high importance, and the other know-how information 121 has a low importance. However, the importance determination unit 115 may determine the importance in three or more levels according to the value of the p-value and the value of the partial regression coefficient.

[0169] In this embodiment, as described above, it is easy to register the know-how information 121 representing tacit knowledge. For example, when a large number of users each register their own tacit knowledge as the know-how information 121, the storage unit 120 can accumulate a huge number of know-how information 121. For example, the number of know-how information 121 may be in the range of tens of thousands to hundreds of thousands. In this regard, by performing the above processing by the importance determination unit 115, the importance of the know-how information 121 can be determined.

[0170] In addition, the explanatory variables that significantly affect the above-described objective variable and have a positive partial regression coefficient are not limited to one, and there may be multiple cases. That is, the importance determination unit 115 may specify a plurality of know-how information 121 as high-importance know-how information 121. For example, assume that the importance determination unit 115 determines that two of the know-how information 121 corresponding to a1 to an, namely as and at, have high importance. s and t are each an integer of 1 or more and n or less, and s ≠ t.

[0171] In this case, as and at can each be used alone, but it is considered that the quality of assistance can be further improved by using these two in combination. Therefore, when the importance determination unit 115 determines that a plurality of know-how information 121 has high importance in a single multiple regression analysis, the information storage unit 120 may store information specifying the combination.

[0172] <Attributes of the assisted person> Through the above processing, among the plurality of know-how information 121, the know-how information 121 considered important for improving and maintaining the state of the assisted person can be specified. However, if the attributes of the assisted person are significantly different, the important assistance for the target assisted person may also be different. The attribute here is, for example, the state information at the starting point of the target period. For example, an assisted person in need of support level 1 with a relatively good current state can often perform tasks by themselves, and assistance for suppressing the transition to long-term care and assistance for promoting self-reliance are effective. On the other hand, for assisted persons requiring long-term care level 3 or higher, intensive assistance at a facility is considered effective for suppressing the deterioration of the state. That is, there may be differences in the important know-how information 121 between assisted persons with relatively good states and assisted persons with relatively poor states.

[0173] Therefore, the storage unit 120 may store attribute information representing the attributes of the care recipient. The processing unit 110 identifies important know-how information in the care for a care recipient having a given attribute based on the association information corresponding to the care recipient determined to have the given attribute based on the attribute information. Note that the important know-how information is information obtained based on, for example, regression analysis. Specifically, a plurality of association information corresponding to a plurality of care recipients determined to have a given attribute may be used in the processing.

[0174] For example, the attribute information is state information, and the importance determination unit 115 performs a process of identifying know-how information 121 that is important for a care recipient requiring support level 1 based on the association information obtained for the care recipient whose state information is 1 (requiring support level 1). Also, the importance determination unit 115 performs a process of identifying know-how information that is important for a care recipient requiring support level 2 based on the association information obtained for the care recipient whose state information is 2 (requiring support level 2). The same applies to other states, and the importance determination unit 115 determines the importance of the know-how information 121 for each of the levels of care required from level 1 to level 5. Here, an example is shown where the state information is 7-level information and there are also 7 types of attributes represented by the attribute information. In this case, the importance determination unit 115 performs importance determination for each of the 7 types of attributes. However, various modifications are possible for the relationship between the state information and the attribute information, such as treating support level 1 and support level 2 together as one attribute.

[0175] By considering the attributes of the care recipient in this way, it becomes possible to improve the processing accuracy in the importance determination unit 115. That is, it becomes possible to appropriately identify know-how information 121 suitable for improving and maintaining the state for each attribute.

[0176] Note that the attributes in this embodiment are not limited to the state information at the start point of the period. For example, as described above for the attributes of the care recipient in the know-how information 121 of FIG. 5, the attributes here may include information such as the age, gender, height, weight, medical history, and medication history of the care recipient. The attributes may also include physical assessment data representing the physical assessment of the care recipient, and the physical assessment data may include information such as rehabilitation history, fall risk, and pressure ulcer risk.

[0177] <Examples of Processing Using Importance> Further, the processing unit 110 may perform processing to present recommended know-how information recommended for assisting the given care recipient based on the know-how information 121 used for assisting the given care recipient and the know-how information 121 determined to have a high importance by the importance determination unit 115. In this way, it becomes possible to prompt the caregiver who assists the care recipient to use the know-how information 121 with a high importance, that is, the know-how information 121 considered useful for improving and maintaining the state of the care recipient.

[0178] More specifically, the processing unit 110 may determine the recommended know-how information based on the attribute information of the care recipient as described above. For example, if the first attribute to the m-th attribute are defined as attributes, the importance determination unit 115 performs processing to obtain the know-how information 121 with a high importance for each of the first attribute to the m-th attribute. m is an integer of 2 or more. When it is determined that the target care recipient has the k-th attribute, the processing unit 110 specifies the recommended know-how information based on the know-how information 121 with a high importance corresponding to the k-th attribute. k is an integer from 1 to m. In this way, it becomes possible to recommend the know-how information 121 according to the attributes of the care recipient.

[0179] The recommended know-how information is, for example, know-how information 121 that is similar to the know-how information 121 in use and has a high importance. The recommended know-how information is also, for example, know-how information 121 that is effective when used in combination with the know-how information 121 in use. Hereinafter, each example will be described using an example of a display screen.

[0180] FIG. 16 is an example of a service usage screen of the information processing system 10 according to the present embodiment, which is a user page on which information about a given user is displayed. The user here may be a caregiver who executes assistance, a family member of the care recipient, or a nurse or the like working at a nursing facility or the like. The user page is displayed on the display unit 240 of the terminal device 200, for example, based on the control of the processing unit 110 of the server system 100. The processing unit 110 may generate and transmit the image shown in FIG. 16. Further, the processing unit 110 may transmit information for image generation to the terminal device 200, and the processing unit 210 of the terminal device 200 may generate an image.

[0181] As shown in FIG. 16, the user page includes a region RE1 for displaying know-how information 121 that the target user is using and a region RE2 for displaying registered know-how information 121. In RE1, for example, the know-how information 121 included in the list information 123 described above with reference to FIG. 11 is displayed. In RE2, for example, the know-how information 121 registered by the target user is displayed. By performing such display, the user can easily grasp the registration and usage status of the know-how information 121.

[0182] The user page may also include a display for proposing replacement of the know-how information 121 in use. For example, the processing unit 110 identifies know-how information 121 similar to the know-how information 121 determined to have a high importance. The determination of importance is performed by the importance determination unit 115 as described above. Also, the determination of similar know-how information 121 is performed by the similarity determination unit 113 as described above. For convenience of explanation, the know-how information 121 determined to have a high importance by the importance determination unit 115 is referred to as important know-how information. Also, the know-how information determined to be similar to the important know-how information by the similarity determination unit 113 is referred to as replacement target know-how information.

[0183] When the processing unit 110 determines that the replacement target know-how information is included in the know-how information 121 being used by the target user, it proposes to replace the replacement target know-how information with important know-how information. For example, the importance determination unit 115 determines that the importance of the know-how information 121 corresponding to a34 is high by multiple regression analysis. Also, the similarity determination unit 113 determines that the similarity between a34 and a5 is high. In this case, a34 is the important know-how information, and a5 is the replacement target know-how information.

[0184] As shown in FIG. 16, the target user is using the know-how information 121 corresponding to a5. In FIG. 16, a5 is expressed as "if5 - then5" using start conditions and assistance actions. The same applies to other know-how information 121. Since a5 and a34 are similar, for example, they can be used in the same type of assistance and in the same kind of scene. For example, both a5 and a34 are know-how information for appropriately determining the pace of a meal in meal assistance. Therefore, even if the currently used know-how information 121 is replaced with similar know-how information 121, it is considered that the user can use the know-how information 121 in the same scene as before.

[0185] And a34 is determined to have a higher importance than a5. That is, by replacing a5 with a34, the user can execute assistance that is more useful for improving and maintaining the state of the person being assisted while using the know-how information 121 in a similar scene.

[0186] In the example of FIG. 16, while displaying "if5 - then5" corresponding to the know-how information 121 being used in the RE1 area, "if34 - then34", which is the important know-how information recommended for replacement, is displayed as Replaced tacit knowledge. By proposing to replace the know-how information 121 that is similar to the currently used know-how information 121 and has a high importance, it becomes possible to change the assistance by the user to a higher-quality one that contributes more to the state of the person being assisted.

[0187] Also, the user page may include a display for proposing know-how information 121 that is recommended to be used in combination with the know-how information 121 in use.

[0188] As described above, when there are multiple pieces of know-how information 121 determined to have a high importance level, the importance determination unit 115 stores information for specifying the combination in the storage unit 120. When the know-how information 121 being used by the user is included in the combination, the processing unit 110 performs processing to propose to the user the addition of other know-how information 121 included in the combination.

[0189] For example, assume that the importance determination unit 115 determines that the importance levels of four pieces of know-how information 121, namely a6, a7, a10, and a34, are high, and stores information regarding this combination in the storage unit 120. In the example of FIG. 16, the user is using the know-how information 121 of a6. Therefore, the processing unit 110 proposes not to use a6 alone but to add a7, a10, and a34 and combine them. In the example of FIG. 16, since a34 is displayed as a replacement destination in RE1, the know-how information 121 to be the subject of the additional proposal may be the two pieces, a7 and a10.

[0190] For example, as shown in FIG. 16, the user page may include RE3 that displays know-how information 121 recommended for use. In RE3, for example, know-how information 121 whose combination with the know-how information 121 in use is recommended is displayed as "Recommend tacit knowledge". In the above-described example, "if7 - then7" and "if10 - then10" corresponding to a7 and a10 are displayed in RE3. In this way, it is possible to propose using a combination of multiple pieces of know-how information 121 considered useful for improving and maintaining the state of the assisted person, and thus it is possible to further improve the quality of assistance.

[0191] As shown in FIG. 16, in the area shown by RE1, in addition to the know-how information 121 in use, the device associated with the know-how information 121 may be displayed. The device displayed here is the device included in the list information 123 as shown in FIG. 8 or FIG. 9. In this way, the information of the device used in the know-how information 121 in use can be presented to the user in an easy-to-understand manner.

[0192] Also, as shown in FIG. 16, in the area shown by RE2, information indicating the registration status of the device related to the know-how information 121 registered by the target user may be displayed. For example, for the know-how information 121 where the device in FIG. 6 is not associated (No in step S203), an object including the text "No device" indicating that is displayed.

[0193] Also, although the device is associated (Yes in step S203), since sufficient sample data has not been collected (during the loop continuation of steps S207 - S210), for the know-how information 121 where the preparation for adding correct answer data by the user is not available, an object including the text "Not ready" indicating that is displayed.

[0194] Also, since sufficient sample data has been collected (end of the loop of steps S207 - S210), for the know-how information 121 where the preparation for adding correct answer data by the user is available, an object including the text "ready" indicating that is displayed. For example, by performing a selection operation on the object where "ready" is displayed by the user, the processing after step S211 in FIG. 6 is started.

[0195] Although not shown in FIG. 16, an object including text "completed" indicating that addition of correct answer data by the user, determination of the second processing algorithm and parameters (step S216), and creation of registration information 122 (step S217) have been completed may be displayed in the know-how information 121. As described above, by displaying not only information for specifying the know-how information 121 but also information associated with the know-how information 121, it is possible to clearly present the usage status and registration status of the know-how information 121 of the target user.

[0196] Although not shown in FIG. 16, the above-described importance may be used for priority determination of association with the device. By preferentially associating the know-how information 121 with a high importance with the device, it becomes possible to facilitate the use of the know-how information 121 considered useful for improving and maintaining the state of the assisted person.

[0197] For example, the processing unit 110 may promote the collection of sample data by displaying a screen that prompts the execution of active assistance for the know-how information 121 that has a high importance but is "Not ready". Also, the processing unit 110 may promote the association with the device by displaying a screen that prompts the user to execute the processing after step S211 for the know-how information 121 that has a high importance and is "ready".

[0198] <Variation Examples in Importance Judgment and Presentation of Its Results> In the above, an example mainly using binary data indicating whether the determination result of the importance determination unit 115 is important has been described. Also, in the above description, the know-how information 121 determined to be important in one regression analysis becomes important know-how information, and when a plurality of important know-how information is detected in the one regression analysis, it is determined that it is useful to use all of them in combination. However, whether it is important know-how information or not, and whether it is useful when combined may be determined using different conditions.

[0199] For example, the importance determination unit 115 may determine the importance in multiple levels of three levels or more as described above. The importance determination unit 115 determines, for example, know-how information 121 with an importance equal to or higher than a given first threshold value th1 as important know-how information. Further, when there are a plurality of pieces of know-how information 121 with an importance higher than the first threshold value th1 and equal to or higher than a second threshold value th, the importance determination unit 115 may determine that it is useful to use them in combination. In other words, the importance determination unit 115 may determine that it is useful to combine some pieces of know-how information 121 with particularly high importance among the important know-how information.

[0200] For example, consider a case where the importance determination unit 115 determines that the importance of four pieces of know-how information 121, namely a6, a7, a10, and a34, is high, and further determines that the combination of a6 and a7 among them is useful. In this case, a6, a7, a10, and a34 become candidates for the replacement destination. For example, as shown in FIG. 16, when a5 used by the user is similar to a34, the information representing a34 is displayed in the item of Replaced tacit knowledge.

[0201] Also, in the above example, a6 and a7 become candidates for know-how information 121 recommended for combined use. For example, as shown in FIG. 16, when the user is using a6, a7 is presented as know-how information 121 recommended. In this way, it becomes possible to flexibly determine the information displayed in RE1 and the information displayed in RE3 based on different conditions.

[0202] Further, the importance determination unit 115 may repeatedly perform regression analysis in a time series. For example, at the timing of tx, the importance determination unit 115 performs regression analysis based on the association information acquired during the period from t1 to tx, and at the timing of ty, performs regression analysis based on the association information acquired during the period from tx to ty. For example, x and y are integers that satisfy x < y, and ty represents a timing later than tx. However, specific methods such as performing regression analysis based on the association information acquired during the period from t1 to ty at the timing of ty can be variously modified and implemented.

[0203] When the results of repeated regression analysis are obtained in this way, the importance determination unit 115 may make a determination by integrating the results of multiple regression analyses.

[0204] For example, the importance determination unit 115 determines the know-how information 121 determined to have a high importance in a predetermined ratio or more of the multiple regression analyses as important know-how information. For example, when the number of times the importance of a1 is determined to be high in multiple regression analyses is equal to or greater than a given threshold th3, the importance determination unit 115 determines a1 as important know-how information.

[0205] Further, the importance determination unit 115 determines that know-how information 121 for which it is useful to use a plurality of pieces of know-how information 121 for which the importance has been determined to be high at the same time and the number of times is equal to or greater than a given threshold th4. For example, in a given regression analysis, if a1 is determined to be important and, in the same regression analysis, a2 is determined to be important, the importance determination unit 115 increments the count value for the combination (a1, a2). The importance determination unit 115 performs the increment process for all combinations based on the results of multiple regression analyses. For example, if it is determined that the importance of (a1, a2, a3) is high in a given regression analysis, the importance determination unit 115 may increment the count values for the combinations (a1, a2), (a1, a3), (a2, a3), and (a1, a2, a3). The importance determination unit 115 identifies a combination for which the final count value is equal to or greater than th4 and presents RE3 as described above based on the identified combination. Therefore, for example, in the determination using the above th3, even if a1 is equal to or greater than th3 and a2 is equal to or greater than th3, if the number of times they appear simultaneously is small, the combination (a1, a2) is not determined to be useful.

[0206] Even in this way, it becomes possible to flexibly determine the determination of important know-how information and the know-how information 121 that is useful to use in combination, respectively.

[0207] Further, the importance determination unit 115 may preliminarily limit the know-how information 121 that is often used in combination. For example, the importance determination unit 115 identifies a combination of know-how information 121 with a high usage frequency based on a plurality of association information. For example, among a plurality of association information, it is assumed that the number of association information including all four pieces of know-how information 121 of (a1, a2, a3, a4) is equal to or greater than a given threshold value th5. In this case, the importance determination unit 115 may determine the importance of the four pieces of know-how information 121 of (a1, a2, a3, a4) based on a plurality of association information including the four pieces of know-how information 121 of (a1, a2, a3, a4). And when a plurality of pieces of know-how information 121 with an importance equal to or greater than a given threshold value th6 are detected among (a1, a2, a3, a4), the importance determination unit 115 determines that the plurality of pieces of know-how information 121 are know-how information 121 that is useful to use in combination. For example, when the importance of a1 and a3 is equal to or greater than th6, and the importance of a2 and a4 is less than th6, the importance determination unit 115 determines that the combination of (a1, a3) is useful.

[0208] In this way, by determining the importance for a plurality of pieces of know-how information 121 that are frequently used in combination, it becomes possible to identify the know-how information 121 that is considered particularly important among the combinations. Here, a combination of (a1, a2, a3, a4) is exemplified, but the same processing is possible for other combinations.

[0209] In addition, the method of this embodiment widely includes those that determine the importance of know-how information 121 based on changes in state information and the know-how information 121 used, and the specific method is not limited to the above example.

[0210] 3.3.2 Importance Based on Selection of Assistant Further, the importance determination unit 115 may determine a second importance based on the degree of utilization or popularity of each piece of know-how information 121 by the user. While the above-described importance is information considering the state of the assisted person, the second importance is information based on the judgment of the assistant who provides assistance.

[0211] For example, the importance determination unit 115 may count the number of times each piece of know-how information 121 has been downloaded for use. The number of downloads indicates how useful the target know-how information 121 has been determined to be for how many users. Therefore, the importance determination unit 115 determines that the higher the number of downloads, the higher the second importance of the target know-how information 121.

[0212] Also, the importance determination unit 115 may count the number of users currently using each piece of know-how information 121. The number of users using it also indicates how useful the target know-how information 121 has been determined to be for how many users. Therefore, the importance determination unit 115 determines that the higher the number of users using it, the higher the second importance of the target know-how information 121.

[0213] Also, in this embodiment, it may be possible to evaluate the know-how information 121 used by each user. Although various modes of evaluation can be considered, for example, each user assigns a score to the know-how information 121. The importance determination unit 115 may obtain a statistical quantity (such as an average value) of the scores given to the target know-how information 121 and determine the second importance based on the statistical quantity.

[0214] Also, the number of downloads, the number of users using it, and the scores representing the evaluation are not limited to being used alone, and two or more of them may be combined. For example, the importance determination unit 115 may perform a process of obtaining the second importance based on a given function that takes as input two or more of the number of downloads, the number of users using it, and the scores representing the evaluation.

[0215] Further, the processing unit 110 may perform a process of presenting second recommended know-how information recommended for assisting the given care recipient based on one or more pieces of know-how information 121 used for assisting the given care recipient and the know-how information 121 determined by the importance determination unit 115 to have a high second importance. In this way, it becomes possible to encourage the use of the know-how information 121 with a high second importance, that is, the know-how information 121 considered useful by the caregiver. The second recommended know-how information is, for example, know-how information 121 that is similar to the know-how information 121 in use and has a high second importance.

[0216] 3.4 Determination of the Condition of the Care Recipient As described above, in the method of the present embodiment, the condition information of the care recipient may be used for determining the importance of the know-how information 121. The condition information is obtained, for example, based on the survey results by the investigator. However, in the present embodiment, part or all of the survey by the investigator may be automated.

[0217] The information processing apparatus of the present embodiment may perform a process of estimating the evaluation result of each item in the survey. Hereinafter, machine learning will be described as a specific example of the method for estimating the evaluation result. However, the method of the present embodiment is not limited to using machine learning, and various modifications can be made. Further, although an example using NN as machine learning will be described below, other methods such as SVM may be used for machine learning, or methods developed from NN or SVM may be used.

[0218] FIG. 17 is a basic structural example of an NN. One circle in FIG. 17 is called a node or a neuron. In the example of FIG. 17, the NN has an input layer, two or more intermediate layers, and an output layer. The input layer is I, the intermediate layers are H1 and Hn, and the output layer is O. Also, in the example of FIG. 17, the number of nodes in the input layer is 2, the number of nodes in each intermediate layer is 5, and the number of nodes in the output layer is 1. However, the number of intermediate layers and the number of nodes included in each layer can be variously modified. Also, FIG. 17 shows an example in which each node included in a given layer is connected to all the nodes included in the next layer, but this configuration can also be variously modified.

[0219] The input layer receives input values and outputs them to the intermediate layer H1. In the example of FIG. 17, the input layer I receives two types of input values. Each node in the input layer may perform some processing on the input value and output the value after the processing.

[0220] In the NN, weights are set between two connected nodes. W1 in FIG. 17 is the weight between the input layer I and the first intermediate layer H1. W1 represents a set of weights between a given node in the input layer and a given node in the first intermediate layer. For example, W1 in FIG. 17 is information containing ten weights.

[0221] At each node in the first intermediate layer H1, an operation is performed in which the outputs of the nodes in the input layer I connected to the node are weighted and added using the weight W1, and a bias is further added. Further, at each node, the output of the node is obtained by applying an activation function, which is a non-linear function, to the addition result. The activation function may be a ReLU function, a sigmoid function, or another function.

[0222] Also, the same applies to the subsequent layers. That is, in a given layer, the output to the next layer is obtained by weighted addition of the output of the previous layer using the weight W, adding a bias, and then applying an activation function. The NN uses the output of the output layer as the output of the NN.

[0223] As can be seen from the above description, in order to obtain desired output data from input data using an NN, it is necessary to set appropriate weights and biases. In learning, training data is prepared by associating given input data with correct answer data representing the correct output data for the input data. The learning process of the NN is a process of obtaining the most probable weights based on the training data. Note that in the learning process of the NN, various learning methods such as the backpropagation method are known. In the present embodiment, since these learning methods can be widely applied, detailed description thereof is omitted. Also, the NN is not limited to the configuration shown in FIG. 17, and a CNN, an RNN (Recurrent Neural Network), or the like may be used.

[0224] FIG. 18 is a diagram illustrating input data and output data of an NN for determining the presence or absence of paralysis or the like, which is used for estimating an evaluation result regarding an example of an investigation item, "presence or absence of paralysis or the like". The input data here may include output data of sensors arranged in the living environment of the care recipient. The output data of the sensors is referred to as sensing data. Also, the input data may include information regarding one or more know-how information 121 used for assisting the care recipient.

[0225] For example, when estimating an evaluation result regarding the presence or absence of paralysis or the like, the sensing data includes at least one of data detecting the muscle mass of the care recipient, data detecting myoelectricity, and data imaging the target site. The muscle mass may be detected using, for example, a weighing scale (body composition analyzer). Also, in recent years, portable and small-sized body composition analyzers are also known, and various modifications of the specific sensor shape are possible. Also, myoelectricity is detected by fixing a sensor having a plurality of electrodes to the body surface of the care recipient. Also, data imaging the target site is acquired by a camera (imaging sensor) capable of imaging the care recipient. The camera here may be fixed to the living room or bed of the care recipient, or may be mounted on a terminal device 200 or a headset 300 used by the caregiver.

[0226] The input data also includes information indicating the use or non-use of know-how information 121 regarding "how to change diapers when there is contracture or paralysis". This know-how information 121 is information used when changing diapers for a care recipient with contracture or paralysis in the limbs. For example, the assisting actions include the correct actions in diaper changing. When there is contracture or paralysis, since the movement of the care recipient's limbs is restricted, different correct actions are used compared to the case without contracture or paralysis. When the know-how information 121 regarding "how to change diapers when there is contracture or paralysis" is used, the probability that the target care recipient has contracture or paralysis is high. Therefore, the use or non-use of this know-how information 121 is useful input data for estimating the evaluation result of the presence or absence of paralysis or the like. Here, the value of the input data is, for example, binary data that becomes a first value when the target know-how information 121 is used and a second value when it is not used.

[0227] The input data also includes information indicating the use or non-use of know-how information 121 regarding "how to change body positions when there is contracture or paralysis". This know-how information 121 is information used when changing the body position of a care recipient with contracture or paralysis in the limbs. For example, the assisting actions include the correct actions in body position change. Also in this case, it is considered that the correct actions are different from those in the case without contracture or paralysis. When the know-how information 121 regarding "how to change body positions when there is contracture or paralysis" is used, the probability that the target care recipient has contracture or paralysis is high. Therefore, the use or non-use of this know-how information 121 is useful input data for estimating the evaluation result of the presence or absence of paralysis or the like.

[0228] The input data also includes information indicating the use or non-use of know-how information 121 regarding "ways of gymnastics for preventing contracture and paralysis, and ways of moving the body". In this case, the assisting action may be the correct movement of gymnastics or body movement performed by the person receiving assistance, or the correct movement regarding the movement of the assistant when causing the person to perform such gymnastics. When the know-how information 121 regarding "ways of gymnastics for preventing contracture and paralysis, and ways of moving the body" is used, the probability that the target person receiving assistance is a potential candidate for paralysis or the like is high. Therefore, the use or non-use of this know-how information 121 is useful input data when estimating the evaluation result of the presence or absence of paralysis or the like.

[0229] The evaluation result of the presence or absence of paralysis or the like is, for example, the result of selecting all applicable numbers for "1. None", "2. Left upper limb", "3. Right upper limb", "4. Left lower limb", "5. Right lower limb", "6. Others". Note that "6. Others" represents limb deficiencies or the like.

[0230] Therefore, the output data is six data respectively representing the probabilities of "1. None" being selected, the probability of "2. Left upper limb" being selected, the probability of "3. Right upper limb" being selected, the probability of "4. Left lower limb" being selected, the probability of "5. Right lower limb" being selected, and the probability of "6. Others" being selected. For example, the six data are each numerical data between 0 and 1, and the closer the value is to 1, the more it indicates that the corresponding number should be selected.

[0231] Note that the configuration of the NN for determining the presence or absence of paralysis or the like is not limited to FIG. 18, and the input data and output data can be variously modified and implemented. For example, some of the sensing data in the input data may be omitted, or other sensing data may be added to the input data. Also, regarding the know-how information 121, some input data regarding the know-how information 121 may be omitted, or other input data regarding the know-how information 121 may be added.

[0232] In the learning stage, for a plurality of assisted persons, training data for creating an NN for determining the presence or absence of paralysis or the like is obtained by associating correct answer data with the above input data. For example, the input data is obtained based on the sensing data of sensors arranged in the living environment of the assisted person and the know-how information 121 used for the assisted person. The know-how information 121 is specified from, for example, the list information 123 of assistants who assist the target assisted person.

[0233] Also, the correct answer data may be given by an expert having specialized knowledge such as an investigator. The expert conducts an investigation according to, for example, the certified investigator text shown in the above URL and selects all the applicable numbers among the above six. For example, when the expert selects only "1. None" and does not select the other five, the correct answer data is data in which the value corresponding to "1. None" is 1 and the values corresponding to the other five are 0.

[0234] For example, the processing unit 110 of the server system 100 obtains training data and creates an NN for determining the presence or absence of paralysis or the like by performing machine learning based on the training data. Note that the machine learning may be performed by a device different from the server system 100.

[0235] FIG. 19 is a flowchart for explaining the learning process of generating an NN for determining the presence or absence of paralysis or the like. When this process is started, first, in step S501, the processing unit 110 obtains input data for learning. The input data here is as described above and includes, for example, sensing data and information indicating the use or non-use of the know-how information 121. Note that the input data may include information representing the result of communication by the assisted person. For example, the input data may include the output of a communication robot. Details of the communication robot will be described later.

[0236] Also in step S502, the processing unit 110 acquires correct answer data associated with the input data. For example, the processing unit 110 executes the processes of steps S501 and S502 by reading out any one data set among the training data acquired in the learning stage.

[0237] In step S503, the processing unit 110 performs a process of updating the weights of the NN. Specifically, the processing unit 110 inputs the input data acquired in step S501 to the NN for determining the presence or absence of paralysis or the like, and acquires output data by performing a forward operation using the weights at that stage. The processing unit 110 obtains an objective function based on the output data and the correct answer data. The objective function here is, for example, an error function based on the difference between the output data and the correct answer data, or a cross entropy function based on the distribution of the output data and the distribution of the correct answer data.

[0238] The processing unit 110 updates the weights so that, for example, the error function decreases. As a method for updating the weights, the error backpropagation method and the like described above are known, and those methods can also be widely applied in this embodiment.

[0239] In step S504, the processing unit 110 determines whether to end the learning process. For example, the plurality of data sets included in the training data may be divided into learning data and validation data. The processing unit 110 may end the learning process when the process of updating the weights is performed using all the learning data, or may end the learning process when the correct answer rate based on the validation data exceeds a given threshold.

[0240] When the learning process is not ended, the processing unit 110 returns to step S501 and continues the process. That is, the processing unit 110 reads out a new data set from the training data and performs a process of updating the weights based on the data set.

[0241] When the learning process ends, the processing unit 110 stores the NN for determining the presence or absence of paralysis or the like at that stage in the storage unit 120 as a learned model. The learned model includes an algorithm for performing forward calculations and weighting coefficients. Note that FIG. 19 is an example of the learning process, and the method of this embodiment is not limited thereto. For example, in machine learning, methods such as batch learning are widely known, and these methods can be widely applied in this embodiment.

[0242] FIG. 20 is a flowchart for explaining the processing of the state determination unit 114 at the inference stage. When this process starts, first, in step S601, the state determination unit 114 determines whether the current timing is the timing for obtaining the state information of the assisted person. For example, as described above with reference to FIG. 15, when the state information is obtained at a predetermined interval such as one month, the state determination unit 114 determines whether the predetermined interval has elapsed since the previous process.

[0243] If it is determined that the timing is not for obtaining the state information, the state determination unit 114 ends the process without performing steps S602 and subsequent steps.

[0244] If it is determined that the timing is for obtaining the state information, in step S602, the state determination unit 114 acquires input data regarding the assisted person who is the processing target. For example, the storage unit 120 acquires and stores sensor information collected by a group of sensors arranged in the living environment of the assisted person. The state determination unit 114 performs a process of reading out, from the collected data, data regarding the target assisted person and used as input data. For example, the state determination unit 114 reads out the output of a body composition analyzer, the output of a sensor for detecting myoelectricity, the output of a camera that images the target site, and the like.

[0245] Further, the state determination unit 114 identifies know-how information 121 used for the care recipient based on list information 123 of caregivers who assist the care recipient, etc. Specifically, the state determination unit 114 determines for each of the target care recipients whether or not three pieces of know-how information 121, namely, "how to change diapers when there is contracture or paralysis", "how to change body positions when there is contracture or paralysis", and "how to perform gymnastics and move the body to prevent contracture and paralysis", have been used.

[0246] In step S603, the state determination unit 114 reads the NN for determining the presence or absence of paralysis, etc. from the storage unit 120. Then, the input data acquired in step S602 is input to the NN for determining the presence or absence of paralysis, etc., and output data is obtained by performing forward calculation. The output data of the NN for determining the presence or absence of paralysis, etc. is, for example, six numerical data representing the probability that each of the six numbers is selected as described above. The state determination unit 114 determines that the target number is selected when, for example, the numerical value satisfies a threshold th where 0 < th < 1. For example, when the numerical data corresponding to "1. None" is equal to or greater than th and the other five numerical data are less than th, the state determination unit 114 selects "1. None" as the evaluation result regarding the presence or absence of paralysis, etc., and outputs an estimation result of not selecting the other five.

[0247] Thus, according to the method of this embodiment, it becomes possible to automatically estimate the evaluation result in the investigation item of the presence or absence of paralysis, etc. In the above, the specific item of the presence or absence of paralysis, etc. has been described as an example, but the point that the evaluation result can be estimated based on the presence or absence of use of sensing data and know-how information 121 is the same for other items.

[0248] FIG. 21 is a configuration example of the NN when estimating the evaluation results in p investigation items. FIG. 21 shows an example in which one NN is created for each item. Each NN acquires, as input data, sensing data, information indicating the presence or absence of use of know-how information 121, and information representing the communication result using the communication robot. However, each NN does not necessarily need to receive all three types of these inputs, and some of them may be omitted.

[0249] In particular, as shown in FIG. 21, with respect to whether or not the know-how information 121 is used, filtering processing for extracting a part may be performed according to the target item. As described above, the know-how information 121 may be extremely large in number. If the filtering processing is not performed, the use or non-use of the know-how information 121 will occupy most of the input data, and the influence of the sensing data and the interview results by the communication robot on the output may be extremely reduced. In that regard, since the number of know-how information 121 serving as input data is limited by performing the filtering processing, it is possible to accurately estimate the evaluation results.

[0250] Also, the sensors that output sensing data are not limited to the above-described body composition meter, electromyography sensor, and imaging sensor (camera), and various sensors such as motion sensors such as acceleration sensors and angular velocity sensors, pressure sensors, excretion detection sensors such as odor sensors, position sensors such as GPS (Global Positioning System), sleep detection sensors that detect pulse and heart rate, temperature sensors, humidity sensors, illuminance sensors, and barometric pressure sensors can be used. And each NN does not need to receive all of these as inputs, and for example, as will be described later with reference to FIGS. 23A to 23E, some sensing data may be acquired.

[0251] As described above, know-how information 121 has various information registered by a plurality of users. FIGS. 22A to 22C are examples of the know-how information 121. FIG. 22A is an example of the know-how information 121 used in meal assistance for assisting the meal of the assisted person. For example, in meal assistance, an assistance action is performed to smooth the execution of the meal by having the assistant grasp the characteristics of the assisted person and explain them clearly to the assisted person himself / herself. For example, in the case of an assisted person with a characteristic of low chewing ability, if the assistant grasps this, it is possible to take measures to prevent aspiration, and it is also useful to give guidance to the assisted person such as "The rice is softened, so chew well." Number 2 in FIG. 22A is the know-how information 121 for "conveying (making understood) the characteristics of the user" to the assistant. For example, when a predetermined start condition is satisfied, it causes the assistant to execute assistance actions such as acquiring and viewing data representing the characteristics of the assisted person. Also, as described above, as an assistance action, it may include an operation in which the assistant conveys the characteristics of the assisted person to the assisted person. The same applies to other know-how information 121, and the know-how information 121 shown in FIG. 22A includes information for supporting various actions of the assistant in meal assistance.

[0252] FIG. 22B is an example of the know-how information 121 used in excretion assistance for assisting the excretion of the assisted person. Note that the excretion assistance may be performed in the toilet or using a diaper. Numbers 66 - 72 represent the know-how information 121 when performing excretion assistance in the toilet, and Numbers 73 - 75 represent the know-how information 121 when performing excretion assistance using a diaper.

[0253] Figure 22C is an example of know-how information 121 used in transfer assistance and movement assistance for assisting the transfer or movement of the assisted person. Note that the transfer and movement assistance differ in the presence or absence of equipment or the type of equipment depending on the state of the assisted person and the availability of equipment such as a lift. In the example of Figure 22C, Number 92-103 represents the know-how information 121 when assistance is provided using a wheelchair, Number 104-107 represents the know-how information 121 when assistance is provided using a cane, and Number 108-112 represents the know-how information 121 when assistance is provided using a lift.

[0254] Also, the know-how information 121 is not limited to this, and the know-how information 121 used in scenes other than eating, excretion, transfer, and movement may be used for processing. Also, the "way to change diapers in the case of contracture or paralysis" described above with reference to Figure 18 is the know-how information 121 used in excretion assistance and is information for corresponding to a more specific situation than the example described in Figure 22B. Thus, the know-how information 121 used in eating, excretion, transfer, and movement is not limited to Figures 22A to 22C, and various modifications can be made.

[0255] A communication robot is a robot for communicating with a care recipient. The communication robot may be, for example, a humanoid robot having two arms and capable of voice recognition and voice synthesis. When using such a communication robot, while having a conversation with the care recipient, it is possible to ask whether the care recipient can make the same movement, for example, by bending an arm to show. However, the communication robot is not limited to a humanoid form and may be one that conducts conversations by performing voice recognition and voice synthesis. In this case, the communication robot may be realized by a device such as a PC and may be in a mode capable of having a conversation with an avatar displayed on a display. Also, the communication with the care recipient is not limited to a conversation using voice and may be one using text. For example, at least one of the utterance by the communication robot and the response by the care recipient may be made using text. The result of the communication using the communication robot is mainly useful as input data when evaluating the cognitive function.

[0256] Figures 23A to 23E are examples of the evaluation content indicating what kind of evaluation each item performs and the specific input data when estimating the evaluation result of the item. The input data is described separately for each of the sensing target, tacit knowledge (know-how information 121), and the communication robot. In the column regarding the communication robot, a circle is described when it is used, and it is left blank when it is not used. Figure 23A represents the items related to physical functions and daily living activities. Figure 23B represents the items related to living functions. Figure 23C represents the items related to cognitive functions. Figure 23D represents the items related to mental and behavioral disorders. Figure 23E represents the items related to adaptation to social life. Numbers such as 1-1 correspond to the numbers described in Figure 14A or Figure 14B.

[0257] As shown in FIG. 23A, there are many items for evaluating whether the care recipient can perform a predetermined action in physical functions and daily living activities, and sensing data such as the movement of a predetermined part, contact with a predetermined location, and load distribution in the action is used as input data. For some items, whether the know-how information 121 is used becomes the input data. On the other hand, the output of the communication robot is used only for some items such as hearing ability.

[0258] As shown in FIG. 23B, since the living functions relate to eating, excretion, transfer / movement, cleaning, etc., there are many items for which sensing data such as whether the care recipient is receiving assistance is used. The sensing data is, for example, an imaging image or the like. Also, regarding whether the know-how information 121 is used, the information shown in FIGS. 22A to 22C can be utilized. Number in FIG. 23B represents Number in FIGS. 22A to 22C. The output of the communication robot is not used in the example of FIG. 23B.

[0259] As shown in FIG. 23C, regarding the cognitive function, the words and actions of the care recipient are important in estimating the evaluation result. Therefore, the output of the communication robot becomes input data for many items. Also, the state determination unit 114 may acquire and utilize the answer to the query as sensing data using an imaging sensor, a microphone, or the like. Regarding whether the know-how information 121 is used, it is not used in the example of FIG. 23C.

[0260] As shown in FIG. 23D, regarding the items related to mental / behavioral disorders, the words and actions of the care recipient are also important in estimating the evaluation result. Therefore, the output of the communication robot becomes input data for many items. Also, the state determination unit 114 may acquire and utilize the answer to the query as sensing data using an imaging sensor, a microphone, or the like. Also, as sensing data, the detection result of how many times and with what frequency a predetermined action is performed within a certain period may be used. Regarding whether the know-how information 121 is used, it is not used in the example of FIG. 23D.

[0261] As shown in FIG. 23E, for items related to adaptation to social life, sensing data representing the detection results of how many times and with what frequency a predetermined action was performed over a certain period is often used. Also, regarding medication, whether the know-how information 121 is used is employed. There may also be items for which the output of the communication robot, such as maladaptation to a group, is used.

[0262] As shown in FIGS. 21 and 23A to 23E, according to the method of this embodiment, it is possible to estimate the evaluation result for each item used when obtaining the state information of the care recipient from the sensing data and whether the know-how information 121 is used. In particular, by using whether the know-how information 121 is used, it becomes possible to consider the care being provided to the care recipient, thus enabling an improvement in the estimation accuracy.

[0263] For example, the processing unit 110 (state determination unit 114) may perform processing to calculate the state information based on the know-how information used for the care of the care recipient and the output data of the sensors arranged in the living environment of the care recipient. That is, in addition to the processing of estimating the evaluation result in the survey item, the state determination unit 114 may calculate the state information based on the estimation result. For example, when the state information is the degree of care required, the state determination unit 114 obtains information representing any one of Support Required Level 1 to Care Required Level 5 as the state information. In this way, it becomes possible to automatically calculate the state information. Therefore, for example, it becomes possible to easily realize the processing of determining the importance of the know-how information 121 based on the change in the state information.

[0264] However, the method of this embodiment is not limited to automatically calculating the state information. For example, the estimation results for each item obtained by the method of this embodiment may be provided to the investigator. In this case, the point that the investigator visits the care recipient is the same as in the conventional method. However, since the investigator only needs to confirm whether the estimation result is appropriate, the burden can be reduced compared to the case of conducting the survey of each item from scratch, and the survey time can be shortened.

[0265] Further, the processing unit 110 may perform a primary determination on the state information based on the estimation results for each item, and the result of the primary determination may be provided to an expert such as a doctor. In this case, the doctor or the like determines the final result of the state information based on the primary determination result. Since the investigation by the investigator is omitted, it becomes easier to obtain the state information.

[0266] <Proposal for Action> Also, as described above, it has been explained that sensing data, which is the output data of the sensor, may be used as input data when estimating the evaluation result in the investigation item. However, in order to perform a determination using the sensing data, a certain number may be required.

[0267] For example, as shown in FIG. 23A, when the state determination unit 114 determines the evaluation result of "turning over" from 1 to 3, it may use sensing data representing fluctuations in body pressure and load. At this time, for example, when the load on the bed significantly decreases, it is considered that the care recipient has grasped something or received assistance from the caregiver, so the state determination unit 114 estimates that there is a possibility that the ability is low.

[0268] However, being able to turn over independently is not limited to something that indicates that the load does not decrease in all of the sensing data. For example, if the load does not significantly decrease in the sensing data representing a threshold value or more of a predetermined ratio among the sensing data corresponding to multiple turnings over, a determination that the person can turn over independently may be made. In this case, since the ratio of the sensing data that satisfies a given condition among the sensing data acquired during the period from the previous state determination to the current state determination is important, it is desirable that the number of sensing data is somewhat large. For example, if only one sensing data at the time of turning over is acquired, an extreme result such as the load decreasing in all of the sensing data or the load not decreasing in all of the sensing data will be obtained, so the estimation accuracy of the evaluation result regarding turning over may decrease.

[0269] The fact that the number of sensing data is important also applies to other sensing data, and if a small number of sensing data are used as input data, the estimation accuracy of the evaluation result may decrease.

[0270] Therefore, when it is determined that the number of output data of the sensor is insufficient during a given determination period, the processing unit 110 may output an instruction to a specific action to the assisted person or the caregiver who assists the assisted person. By doing so, since the opportunity to acquire sensing data increases, it becomes possible to increase the input data in the state determination unit 114, thereby improving the estimation accuracy.

[0271] FIG. 24 is a diagram for explaining a process of determining whether the number of sensing data is insufficient. The horizontal axis in FIG. 24 represents time, and the vertical axis represents the number of sensing data. Also, t1 and t2 represent the timings for acquiring state information, similar to FIG. 15.

[0272] For example, in order to acquire state information at t2 in FIG. 24, the state determination unit 114 estimates an evaluation result based on the sensing data during the period from t1 to t2. The state determination unit 114, for example, determines in advance the required number of data for each sensing data that becomes input data for each item. The state determination unit 114 estimates the number of sensing data to be acquired at time t2 based on the number of sensing data acquired so far at a given timing between t1 and t2. For example, the state determination unit 114 may assume that the number of sensing data increases linearly as shown in FIG. 24, or obtain an approximation function representing the transition of the number of sensing data from t1 and estimate the number of sensing data at time t2 based on the approximation function. When the estimated value of the number of sensing data at time t2 is less than the required number of data, the state determination unit 114 determines that the sensing data is insufficient.

[0273] For example, when the state determination unit 114 determines that the sensing data regarding turning over is insufficient, it may output a proposal to the care recipient to execute turning over. Alternatively, the state determination unit 114 may output a proposal to the caregiver to have the care recipient turn over. By doing so, since the sensing data can be acquired before the actual timing of t2, the estimation accuracy of the evaluation result at t2 can be increased.

[0274] Note that the instruction output performed by the state determination unit 114 is not limited to directly proposing turning over, getting up, etc. For example, the state determination unit 114 may output a proposal to execute a series of operations related to a plurality of evaluation items.

[0275] FIG. 25 is a diagram associating the proposed content by the state determination unit 114 with the survey items for which sensing data can be acquired by the proposal. For example, the state determination unit 114 may make a proposal such as "Let's go shopping until XX on XX day". In order for the care recipient to go shopping to a predetermined place, brushing teeth, washing face, grooming hair, trimming nails, changing clothes, etc. are required as preparations. Also, during the preparation stage and after going out, operations such as maintaining a standing position on both feet or one foot, walking, getting up, etc. are performed. That is, by making a proposal to go shopping, it becomes possible to collectively acquire sensing data regarding a plurality of items shown in FIG. 25. That is, it becomes possible to efficiently collect a lot of sensing data without making individual proposals.

[0276] In addition, as shown in FIG. 25, the state determination unit 114 may make a proposal for cleaning or a proposal for going out preparation. Also, when it is difficult to perform going out preparation, proposals for oral cavity cleaning, grooming hair, and clothing putting on and taking off may be made. Also in this case, since operations such as getting up and walking are involved in order to execute each proposal, it is possible to efficiently collect sensing data.

[0277] 3.5 GPO (Group Purchasing Organization) When a medical facility purchases medical equipment, a GPO (Group Purchasing Organization) may be utilized. A GPO is an industry that specializes in price negotiations with sellers such as manufacturers, and provides services to its members by promising to purchase large lots to reduce unit prices. Even when the minimum purchase lot desired by the manufacturer is large, by using a GPO, a medical facility that is a member can purchase the required amount of high-unit-price products while keeping costs down. For example, in the United States, many medical facilities are members of GPOs and purchase various medical equipment through GPOs.

[0278] A GPO provides purchase conditions (contracts), and when a member uses the contract, a part of the purchase amount is paid to the GPO as a fee. The content of the contract varies, such as setting prices for each manufacturer or setting discounts according to the purchase volume.

[0279] A computer system and method suitable for a GPO are described in U.S. Patent Application No. 15 / 783,992, filed on October 13, 2017, entitled "COMPTER-BASED SYSTEMS SPECIFICALLY CONFIGURED TO MANAGE SOFTWARE OBJECTS THAT ARE INTERRELATED VIA TRIGGER CONDITIONS AND METHODS OF USE THEREOF", and U.S. Patent Application No. 16 / 985,609, filed on August 5, 2020, entitled "METHODS AND SYSTEMS FOR PROVIDING IMPROVED MECHANISM FOR UPDATING HEALTHCARE INFORMATION SYSTEMS". These patent applications are hereby incorporated by reference in their entirety into this specification.

[0280] FIG. 6 of U.S. Patent Application No. 15 / 783,992 discloses an example of a screen for creating a Request For Proposal (RFP) by a buyer entering contract parameters, discount conditions, and the like. In this example, an RFP is created based on the specification of a product category using a product classification code such as the United Nations Standard Products and Services Code (UNSPSC), and the created RFP is sent to one or more suppliers.

[0281] When a reply including specific products is received from a supplier based on the RFP, a screen corresponding to, for example, FIG. 22 is presented to the buyer. FIG. 22 is a screen that serves as an interface for selecting products. In FIG. 22, multiple products can be selected according to the buyer's needs while referring to each other.

[0282] Also, FIG. 10 of U.S. Patent Application No. 16 / 985,609 discloses a screen for evaluating the effects when a given product is replaced with another product.

[0283] As can be seen from these descriptions, it is important for the GPO to propose appropriate products according to the buyer's requirements. The method of this embodiment may be used for consulting with the GPO, specifically, for supporting product proposals by the GPO.

[0284] For example, when a plurality of devices are associated with given know-how information 121 as devices, the processing unit 110 may perform processing of presenting, as an alternative device for the first device among the plurality of devices, a device other than the first device among the plurality of devices.

[0285] FIG. 26 shows examples of the know-how information 121, registration information 122, and list information 123 described above. As described above, when the registered user performs the process shown in FIG. 6, a device for determining either the start condition of the know-how information 121 or the assisting action is associated with the know-how information 121. Also, when each user performs the process shown in FIG. 10 (particularly step S308), a device for determining either the start condition of the know-how information 121 or the assisting action is associated with the know-how information 121. As a result, as shown in FIG. 26, one or more devices associated with a given know-how information 121 can be specified. As shown in FIG. 26, it is also possible to associate more detailed information, such as specific start conditions and assisting actions, with the device by further using the know-how information 121 itself.

[0286] As described above, Device1 included in the registration information 122 is a device specified by the registered user for determining start conditions and the like. Device1a included in the list information 123 is a device specified by another user for using the tacit knowledge of the registered user. That is, since the plurality of devices associated with a given know-how information 121 are all devices for determining the same start conditions and the like, there is a high probability that they are similar. The same applies to Device1b.

[0287] Therefore, when, for example, a buyer is considering replacing Device1, the processing unit 110 performs a process of proposing Device1a and Device1b as alternative devices. In this way, it becomes possible to identify and present a product that meets the user's requirements from a perspective different from product classification codes such as UNSPSC.

[0288] Furthermore, for example, when a buyer is considering replacing a device used in given know-how information 121, the processing unit 110 may propose one or more devices associated with similar know-how information similar to the know-how information 121 as alternative devices. As described above, the similar know-how information is determined based on the first similarity determination process. The know-how information 121 and the similar know-how information have a high similarity, for example, in the similarity between texts representing start conditions or in the type of assistance used. Therefore, the know-how information 121 and the similar know-how information are highly likely to be used in similar situations, and the devices associated with the similar know-how information are also considered to be similar to the device to be replaced. By using such similar know-how information in this way, it is possible to increase the number of devices that can be presented and support a wide range of proposals.

[0289] Note that the method of this embodiment does not need to be fixed to a method of proposing a device using the know-how information 121. For example, the processing unit 110 may be able to switch between a determination process of an alternative device using a code such as UNSPSC and a determination process of an alternative device using the know-how information 121. For example, the processing unit 110 determines which of the code and the know-how information 121 to use based on user input.

[0290] Also, the processing unit 110 of this embodiment may perform a process of specifying fifth know-how information with which a device is associated and having a high similarity to fourth know-how information with which no device is associated from a plurality of know-how information 121. The processing unit 110 performs a process of determining the supplier of the device associated with the fifth know-how information as the supplier of the device that determines the start condition of the fourth know-how information.

[0291] 27 is a diagram for explaining a process of identifying a supplier based on the fourth know-how information and the fifth know-how information. For example, the know-how information 121 of ID43 corresponds to the fourth know-how information. The know-how information 121 of ID43 does not have corresponding registration information 122, and is not associated with a device. The similarity determination unit 113 searches for similar know-how information similar to the know-how information 121 of ID43 based on the first similarity determination process. For example, the know-how information 121 of ID10 is similar know-how information and corresponds to the fifth know-how information.

[0292] Here, the know-how information 121 of ID10 has corresponding registration information 122 as shown in Fig. 27, and is associated with Device10 as a device. The storage unit 120 also stores information that associates a device with a supplier that supplies the device. For example, Supplier10 is associated with Device10.

[0293] In this case, the processing unit 110 performs a process of proposing Supplier 10 as a supplier of a device to be used in the know-how information 121 of ID 43. As described above, the know-how information 121 of ID 43 and the know-how information 121 of ID 10 are similar, so there is a high probability that a device similar to Device 10 can be used for automatic determination of the know-how information 121 of ID 43. In other words, the device used for automatic determination of the know-how information 121 of ID 43 has a high affinity with Supplier 10 and may be developed and provided by Supplier 10.

[0294] As described above, since no device is associated with the know-how information 121 of ID43, there is a possibility that devices suitable for automatically determining the starting conditions and the assistance actions are not widely available on the market. However, since it is registered as the know-how information 121, it represents the tacit knowledge of some user, and therefore may be useful in the situation of assistance. In this respect, the method of this embodiment makes it possible to present information for automating the processing of the know-how information 121, which could not be handled by existing devices. As a result, it becomes possible to develop a new sensing device market, etc.

[0295] Figure 28 is an example of a screen presenting recommended suppliers. In the example of Figure 28, the ID number of know-how information 121 not associated with a device and the recommended suppliers associated with the know-how information are displayed. Note that Category in Figure 28 represents a category determined based on a product classification code such as UNSPSC. For example, in the example of Figure 28, Supplier1 and Supplier2 are presented as the suppliers of the device corresponding to the know-how information 121 with ID11. Note that when there are multiple devices associated with the fifth know-how information as shown in Figure 26, or when multiple fifth know-how information similar to one fourth know-how information are selected, etc., there can be multiple recommended suppliers. Similarly, Supplier10 is presented as the supplier of the device corresponding to the know-how information 121 with ID43. The same applies to other know-how information 121. In this way, it becomes possible to clearly present the recommended suppliers for each know-how information 121.

[0296] At this time, the processing unit 110 may present the ranking (second importance) of each know-how information 121. The index for determining the ranking may be, as described above, the number of downloads, the number of users, the evaluation value, or information obtained by combining these. For example, the know-how information 121 with ID11 has a high ranking, and when a device for automating this determination is supplied, it is considered that there are many users who desire to use it. Thus, the ranking is useful for processing as it serves as a material to encourage the supply of new devices by suppliers. For example, Figure 28 is a screen that displays know-how information 121 that satisfies a given condition among a plurality of know-how information 121 not associated with a device in order of ranking.

[0297] In addition, the processing unit 110 may present the importance of each piece of know-how information 121 in consideration of the state of the care recipient. The importance here corresponds to "Care to improve quality" in FIG. 28, and in FIG. 28, the importance is displayed in three levels: A to C. The importance considering the state of the care recipient is obtained by, for example, multiple regression analysis based on the change in state information and the use or non-use of know-how information as described above. For example, the know-how information 121 of ID11 has a high ranking and also a high degree of contribution to the improvement and maintenance of the state of the care recipient. That is, since it can be seen that the importance is high from both the perspectives of the caregiver and the care recipient, it becomes a material to encourage the supplier to supply new devices.

[0298] On the other hand, there may be know-how information 121 such as the know-how information 121 of ID43, which has a high evaluation by the caregiver but is determined to have a low importance when considering the state information of the care recipient. Conversely, there may also be know-how information 121 such as the know-how information 121 of ID44, which has a relatively low evaluation by the caregiver but is determined to have a high importance when considering the state information of the care recipient. By displaying the importance from the two perspectives as shown in FIG. 28, the amount of information regarding the degree of importance of the know-how information 121 increases, enabling the viewer (e.g., GPO) to make an appropriate judgment.

[0299] Also, here, an example of displaying the two importances is shown on the screen presenting the recommended supplier to the GPO. However, the scenes where the importance and the secondary importance are used are not limited to this. For example, in the search process described above using FIG. 10, the two importances may be displayed when displaying the search results. In this way, it is possible to present the two importances to various targets such as caregivers working in care facilities and hospitals, administrators who supervise and direct such caregivers, home helpers, and care recipients. Alternatively, in the search processing unit 112, a search process based on the importance may be performed. Also, the two importances may be used when determining the priority when associating a device or the like with the know-how information 121.

[0300] Also, the screens that present two importance levels are not limited to FIG. 28. For example, in a plane where the number of downloads, the number of users, etc. are on the first axis and the importance level based on the state information of the care recipient is on the second axis, the importance level of a given know-how information 121 may be illustrated. Alternatively, the processing unit 110 may perform processing to obtain a comprehensive importance level based on the two importance levels and present the comprehensive importance level. In addition, various modifications are possible for the specific presentation content.

[0301] 4. Modification Example In the above-described embodiment, a plurality of specific examples of the know-how information 121 are shown, but many other examples can be considered, and some of them are listed below. For example, the know-how information 121 may include (1) information for selecting an appropriate eating form for each care recipient such as a patient, (2) information suggesting whether end-of-life care should be started after a predetermined period for each care recipient such as a patient, and information suggesting the timing for changing the content of care after the start of end-of-life care, (3) information regarding the timing for an assistant to stop providing meals, (4) information regarding the assistant's response when the care recipient chokes during a meal, (5) information for detecting scenes with a high risk of falling, and the like.

[0302] In the know-how information 121 for selecting an appropriate eating form for each care recipient such as a patient, as input information, five types of information are input, namely, the diagnosis results of a doctor or the like regarding chewing ability and swallowing ability, the requests of the care recipient or their family, the presence or absence of the care recipient not being able to chew the provided meal, the presence or absence of the care recipient choking (coughing, etc.) during the meal, and whether negative emotional information (indexed from discomfort, disgust, sadness, surprise, fear, etc.) of the care recipient is expressed during the meal. Also, in the know-how information 121 for selecting an appropriate eating form for each care recipient such as a patient, as output information, an eating form (for example, any one of regular food, divided meals, extremely divided meals, soft food, mixer food, pureed food, jelly food) is output.

[0303] Here, for the diagnosis results of doctors or the like, for example, in the repeated saliva swallowing test (a test of continuously drinking saliva for 30 seconds and counting how many times one can gulp it down continuously), the number of times can be input as information, or the judgment results of doctors or the like can be classified and tagged for each classification and input as information. The requests of the care recipient or their family can be classified, tagged for each classification, and input as information. For example, different tags can be used for requests such as "want to be fed regular meals if possible" and "want to be fed with safety prioritized". Regarding the presence or absence of the state where the care recipient has not chewed the provided food well, the presence or absence of aspiration (such as choking or coughing) of the care recipient during meals, and the presence or absence of expression of negative emotional information, from the video of the care recipient during meals captured by a camera, the state of not chewing well and the state of aspiration are extracted and input as information.

[0304] (2) In the know-how information 121 suggesting whether end-of-life care should be started after a predetermined period for each care recipient such as a patient, as input information, five types of information are input: the intake amount or intake ratio for each type in each meal (for example, it may be the main dish and side dish, or for each ingredient such as meat and fish), the intake amount of water, the timing of intake, information on diseases, and weight (or BMI). In the know-how information 121 suggesting whether end-of-life care should be started after a predetermined period for each care recipient such as a patient and whether the timing of changing the content of care after the start of end-of-life care, as output information, information indicating whether end-of-life care should be started after a predetermined period and whether the timing of changing the content of care after the start of end-of-life care is output. End-of-life care represents assistance for care recipients who are considered likely to die in the near future. End-of-life care differs from normal assistance in that it emphasizes the alleviation of physical and mental pain and the support of a dignified life for the care recipient in question. Also, during the provision of end-of-life care, as the condition of the care recipient changes over time, the assistance suitable for the patient in question may change. That is, by presenting the start timing of end-of-life care and the timing of changing the content of assistance during end-of-life care, it becomes possible to provide appropriate assistance to the care recipient until the end. For example, skilled caregivers have tacit knowledge to estimate the timing and content of care that requires end-of-life care from various perspectives such as the amount of food intake, and by digitizing this tacit knowledge, other caregivers can also provide appropriate end-of-life care.

[0305] A system that provides assistance information regarding the above (1) and (2) to an assistant includes, for example, a terminal device 200 and a server system 100 as shown in FIG. 1. Here, the terminal device 200 is, for example, a PC. As described above, the information processing system 10 of the present embodiment can be realized in various modes, and the server system 100 may be omitted. The terminal device 200 acquires input information including the above five types of information. The terminal device 200 may automatically acquire the input information using a sensor, or may acquire the input information based on an input operation of the assistant. Also, in a nursing facility or the like, nursing software may be used separately from the information processing system 10 according to the present embodiment. Nursing software is software for storing attributes of the care recipient, care history, and the like. Conventionally, various nursing softwares have been used, and the nursing software here can be widely applied to them. The information processing system 10 may acquire input information including the above five types of information from the nursing software.

[0306] When the terminal device 100 receives an instruction to start analysis based on the input information, it sends each input information to the server system 200, and the server system 200 outputs the analysis result to the terminal device 100. FIG. 29A is an example of the my page in this case. The my page in FIG. 29A is a screen that presents information about a given user, similar to the user page shown in FIG. 16, and displays know-how information 121 that the target user is using and the registered know-how information 121.

[0307] In the example of FIG. 29A, the target user is using know-how information 121 for estimating whether it is the start timing of watching care corresponding to the above (2). The my page shown in FIG. 29A includes an object for uploading in the area corresponding to the know-how information 121. When a selection operation of the object is performed, the terminal device 200 uploads the input information regarding the target care recipient to the server system 100.

[0308] The server system 100 obtains an analysis result by inputting the uploaded input information into, for example, a pre-created learned model related to video care. The server system 100 transmits the analysis result to the terminal device 200. The terminal device 200 presents information representing the analysis result to the user.

[0309] FIG. 29B is an example of a screen for displaying an analysis result, and is, for example, a screen displayed on the display unit of the terminal device 200. The analysis result is, for example, as described above, a determination result as to whether video care should be started after a predetermined period, or a determination result as to whether it is time to change the content of care after the start of video care. For example, as shown in FIG. 29B, the analysis result may include the time-series change of the feature amount obtained based on the input information and the determination result as to whether video care should be started after a predetermined period. The feature amount here may be information determined to be important among the input information, such as the moving average of the food intake amount, or information calculated based on the above five pieces of input information. For example, when an NN is used, the feature amount may be the output of a given intermediate layer or output layer. In FIG. 29B, the actual value of the feature amount up to a predetermined timing (for example, October) and the estimated value of the feature amount after that (for example, after November) are presented, and the start timing of the video care determined using the estimated value is displayed. In this way, it becomes possible to appropriately present information related to video care to the user.

[0310] Note that the frequency at which determination such as the start timing of video care is required is sufficiently lower than the frequency of determination related to daily assistance such as meals, excretion, and transfer. Therefore, as described above, by using the user operation on the terminal device 200 as a trigger for upload and analysis processing, it is possible to reduce the communication load and processing load. However, the processing of the know-how information 121 related to video care is not limited to being triggered by a user operation, and may be automatically executed when the target input information is collected.

[0311] Regarding the information in (1) and (2) above, in some cases, the information corresponding to the input information may be managed using care software. Therefore, as described above, part or all of the input information may be obtained via the care software. In this case, the information processing system 10 according to the present embodiment and the care software may be in an interlocking form. For example, the analysis result by the server system 100 may be displayed on the display screen of the care software.

[0312] Figure 30A is an example of the display screen of the care software. For example, the care software displays a screen in which the care contents executed for a given care recipient are arranged in chronological order. However, the display screen of the care software is not limited to this, and various modifications can be made. For example, every time any input information is input to the care software, such input information may be transmitted to the server system 100 and automatically analyzed. The care software may, for example, display a mark indicating the analysis result in a predetermined column of the display screen. In the example of Figure 30A, a mark including an exclamation mark is displayed in the display column for the intake amount or intake ratio for each type in the meal used as one of the input information. Figure 30B is an example of the display screen when an operation of selecting the mark in Figure 30A, for example, is executed. In the example shown in Figure 30B, an analysis result similar to that in Figure 29B is pop-up displayed on the display screen of the care software. Thus, by interlocking the information processing system 10 according to the present embodiment and the care software, for example, the care record and the analysis result can be displayed together, so that it becomes possible to present appropriate information to the user. Note that the display method of the analysis result on the care software is not limited to Figure 30B, and various modifications can be made.

[0313] (3) In the know-how information 121 regarding the timing when the caregiver stops providing meals, as input information, three types of information are input: "if the care recipient continues to show signs of not being able to chew the provided meal", "if frequent choking (such as gagging or coughing) occurs in the care recipient during the meal", and "if the care recipient seems sleepy during the meal". When any one of the three types of information satisfies the condition, as output information, "Stop providing meals" is output.

[0314] (4) In the know-how information 121 regarding the caregiver's response when the care recipient chokes during the meal, as input information, "if the care recipient chokes and their posture is unstable" is input. When this condition is satisfied, as output information, "Please check the posture" is output. As input information, "if the care recipient chokes and seems sleepy" is input. When this condition is satisfied, as output information, "The care recipient seems sleepy. Please call out to them" is output. As input information, "if the care recipient chokes and neither seems sleepy nor has an unstable posture" or "if the care recipient chokes and their eating form is incorrect" is input. When this condition is satisfied, as output information, "Please check the meal (such as the eating form)" is output. As input information, "if the choking (such as gagging or coughing) of the care recipient during the meal increases" is input. When this condition is satisfied, as output information, "Stop providing meals" is output.

[0315] Here, each input information related to the know-how information 121 in the above (3) and (4) is extracted from output data such as waveforms of videos captured by a camera and / or wearable devices for measuring swallowing (for example, described in US Patent Application No. 16 / 276768 filed on February 15, 2019, titled "Swallowing action measurement device and swallowing action support system". This patent application is hereby incorporated by reference in its entirety into this specification).

[0316] A system that provides assistance information regarding the above (3) and (4) to an assistant includes a wearable device 400 that measures swallowing, a first terminal device 200A, a second terminal device 200B, and a server system 100, as shown in FIG. 31. The person to be assisted wears the wearable device 400 around the neck. The first terminal device 200A is placed, for example, on the table where the person to be assisted eats and has a function of imaging the state of the person to be assisted's meal. The first terminal device 200A is, for example, a smartphone installed with a camera device or an app. The second terminal device 200B is a terminal carried by the assistant and has a function of receiving notifications via an app. The first terminal device 200A communicates with the wearable device 400 to exchange data. In FIG. 31, an example is shown in which the server system 100, the first terminal device 200A, and the second terminal device 200B are connected via a network NW such as a LAN or the Internet, and the second terminal device 200B and the wearable device 400 are directly connected using short-range wireless communication or the like. However, the specific connection mode of each device can be variously modified. In the following embodiment, the first terminal device 200A is described by taking an example of imaging one person to be assisted, but it is not limited thereto, and the first terminal device 200A may image a plurality of persons to be assisted and output the output information of each person to be assisted.

[0317] The first terminal device 200A transmits the image of the person to be assisted and the output data of the wearable device 400 to the server system 100. The server system 100 executes the processing regarding the above (3) or (4) based on the image and the output data, and requests output information such as "stop providing meals".

[0318] On the application of the first terminal device 200A, not only the data of the wearable device 400 and the captured image are displayed, but also the output information is displayed. FIG. 32A is an example of a screen displayed on the display unit of the first terminal device 200A. The display unit here corresponds to, for example, the display unit 240 in FIG. 3. In the screen shown in FIG. 32B, an object OB1 indicating the data measured by the wearable device 400 is superimposed and displayed on a partial area of the captured image IM. The information included in the object OB1 is, for example, a graph representing the time-series change of the measurement value by the wearable device 400.

[0319] Also, an object OB2 indicating the output information acquired from the server system 100 is superimposed and displayed on another partial area of the captured image IM. The output information includes, for example, outputs such as "Please confirm your posture", "You seem sleepy. Please talk to me", "Please confirm your meal", "Please stop eating", etc. as shown in the above (4). Further, the output information may be able to output information indicating that no cue is detected, which means that no output is required for any of the above. For example, in the object OB2 shown in FIG. 32A, together with a first mark including a check mark indicating a normal state, the text "No cue is detected" is displayed. FIG. 32B is an example of other information displayed as the object OB2. For example, the object OB2 may be an object that displays texts such as "Please confirm your posture", "You seem sleepy. Please talk to me", "Please confirm your meal", etc. together with a second mark including an exclamation mark. Also, the object OB2 may be an object that displays the text "Please stop eating" together with a third mark including an exclamation mark. In the example of FIG. 32B, the second mark is a mark with an exclamation mark surrounded by a circle, and the third mark is a mark with an exclamation mark surrounded by a triangle.

[0320] "No abnormality detected" is information presented when no abnormality of the care recipient is detected, and its urgency is low. For the other four, since some abnormality is detected, their relative urgency is high. For example, the three, "Please confirm the posture", "Looks sleepy. Please talk to them", and "Please confirm the meal", correspond to situations where attention is required when providing meals. Also, the information "Please stop the meal" is particularly urgent as it corresponds to a situation where aspiration frequently occurs. As described above with reference to FIGS. 32A and 32B, by using the first mark to the third mark together with the corresponding text, it becomes possible to appropriately convey the state of the care recipient to the caregiver. Also, the presentation method according to urgency is not limited to varying the marks and text, and the color of the object OB2 may be changed. For example, the object OB2 including the first mark may be displayed in green, the object OB2 including the second mark may be displayed in yellow, and the object OB2 including the third mark may be displayed in red.

[0321] When these pieces of information are displayed on the first terminal device 200A, the caregiver (caregiver A in FIG. 31) who performs meal assistance in the vicinity of the care recipient can appropriately grasp the state of the care recipient. Specifically, the caregiver can not only visually confirm the care recipient but also view the output of the sensor (object OB1) and the output information from the server system 100 (object OB2), and thus can perform appropriate assistance.

[0322] Further, the terminal device 200 may include illumination (light emitting unit) such as an LED. The terminal device 200 may control the illumination according to the output information. Specifically, when it is possible to continue providing meals to the assisted person (normal case), the illumination indicates green; when caution is required when providing meals to the assisted person, the illumination indicates yellow; and when the provision of meals is stopped, the illumination indicates red. As a result, the caregiver (caregiver A in FIG. 31) assisting the assisted person with meals can recognize the notification based on the output information presented using the illumination of the first terminal device 200A. Although an example in which the server system 100 calculates the output information has been shown above, the present invention is not limited to this, and the first terminal device 200A may calculate the output information. In this case, the first terminal device 200A performs display processing of the output information calculated by itself.

[0323] Also, the output information is not limited to that presented on the first terminal device 200A. For example, the output information may be presented on the second terminal device 200B used by a caregiver (caregiver B in FIG. 31) located at a position where the first terminal device 200A cannot be directly visually recognized. For example, caregiver B is a person in charge of assisting the assisted person with meals, and it is assumed that the target assisted person is in a relatively good condition and has a high probability of being able to eat independently. In this case, after setting the first terminal device 200A at a predetermined position and starting the meal for the assisted person, caregiver B may perform other assistance with higher priority. In this case, by presenting the output information on the second terminal device 200B carried by caregiver B, caregiver B can return to assisting the assisted person with meals as needed. Alternatively, caregiver B may not originally be the person in charge of meal assistance. For example, when the person in charge, caregiver A, is dealing with another assisted person, etc., by presenting the output information on the second terminal device 200B carried by caregiver B, caregiver B can appropriately intervene to help.

[0324] Figs. 33A and 33B are examples of screens displayed on the second terminal device 200B. Fig. 33A is an example of the lock screen (notification screen) of the second terminal device 200B. For example, as shown in Fig. 33A, the second terminal device 200B may display objects OB21 - OB24 corresponding to the output information. The objects OB21 - OB24 all correspond to the object OB2 in Figs. 32A and 32B. The object OB21 corresponds to "Please stop eating" among the above-mentioned output information. The object OB22 corresponds to "Please check your meal". The object OB23 corresponds to "You seem sleepy. Please talk to me". The object OB24 corresponds to "Please check your posture".

[0325] The notifications corresponding to the objects OB21 - OB24 are not all limited to those to be notified. For example, the output information to be notified may be selected according to the user's proficiency level. For example, for a user with a low proficiency level, in order to prompt the caregiver's attention as much as possible, all output information is set to be notified, and for a user with a high proficiency level, notifications may be limited to the output information with a high urgency. In the above example, since "Please stop eating" has a higher urgency than the other three, for example, when targeting a user with a high proficiency level, the object OB21 may be the display target, and the objects OB22 - OB24 may not be the display targets.

[0326] Also, the second terminal device 200B may display a status screen showing detailed information about the output information. Fig. 33B is an example of the status screen. For example, the status screen includes items such as monitor type, user or device, status, and response.

[0327] The monitor type is information that identifies the scene (assistance) to be monitored. In the above example, it is "meal". The user or device is information that identifies the target care recipient. This may be the name of the care recipient, or it may be the ID of the device used for assisting the target care recipient, etc. The device here may be the wearable device 400, the first terminal device 200A, or other devices. The status represents the output information. For example, "No choking detected" corresponds normally. "Please confirm your posture", "You seem sleepy. Please call out", "Please confirm your meal" correspond to attention. "Please stop eating" corresponds to suspension.

[0328] The response is information that represents the response status by the caregiver. When the status is normal, no action by the caregiver is required. When the status is attention, it is not always necessary for the caregiver to take action. For example, only the notification of the output information may be performed. In this case, as the response, information such as the presence or absence of the notification and information identifying the user to whom the notification was made may be displayed. When the status is suspension, there is a high probability that action by the caregiver is required. Therefore, as the response, information identifying the response / non-response is displayed. Also, when it is non-response, an object indicating that oneself will respond may be displayed as shown in FIG. 33B. For example, when a user with the user name "Sato" performs this operation, the information representing the response is updated to the information representing "Responded by Sato". This can suppress the omission of response in an emergency and suppress the duplication of responses by multiple caregivers to the assistance of a specific care recipient.

[0329] By displaying the status screen shown in FIG. 33B, it becomes possible to appropriately grasp the meal situation of the care recipient and immediately determine whether the caregiver's response is necessary. Although the form of notification using the display unit of the second terminal device 200B has been described above, the form of notification is not limited to this. For example, it may be notified to the caregiver by voice via the headset 300.

[0330] Next, taking the know-how information 121 in (3) and (4) above as an example, an example of a screen displayed when using a given piece of know-how information 121 will be described. As shown in step S203 of FIG. 6, when registering the know-how information 121, a device may be associated with the know-how information 121. Also, as shown in step S216 of FIG. 6, processing details for device data may be associated with the know-how information 121. For the know-how information 121 in (3) and (4) above, the device may be a camera (terminal device 200) or a wearable device 400. The processing details may be processing for detecting the posture of the assisted person from a captured image, or may be processing for detecting the amplitude, frequency, etc. of a waveform output from the wearable device 400.

[0331] However, even for similar know-how information 121, the necessary device data may vary depending on the know-how information 121. For example, for the know-how information 121 shown in (3) and (4) above and similar know-how information 121, based on an image captured by a camera, the posture of the assisted person, etc. is detected. The device data at this time may be any image data capable of detecting the posture of the assisted person, and may be data of the assisted person captured from the front, data of the side profile captured from the side, or data captured from an intermediate direction (diagonal direction). For example, the content of the device data varies depending on which direction a skilled user registering the know-how information 121 considers it necessary to observe the assisted person from. Alternatively, it is also conceivable that the device data differs due to differences in the positions where a camera can be installed according to the facilities such as the nursing facility to which the registering user belongs.

[0332] That is, the know-how information 121 shown in (3) and (4) above is not limited to one, and may include a plurality of pieces of know-how information 121 with different device data registered by a plurality of registered users. Also, there is no hindrance to a single registered user registering a plurality of pieces of know-how information 121 with different device data for performing the same or similar assistance.

[0333] When using such know-how information 121, it is important to align the device data. For example, when using the know-how information 121 for determining the interruption of a meal or the like by performing image processing on device data obtained by imaging the care recipient from the front, if device data obtained by imaging the care recipient from the side or obliquely is used as input information, the accuracy of the processing may decrease. This is because in the know-how information 121, the processing content for the device data is assumed to target data obtained by imaging the care recipient from the front. Therefore, the know-how information 121 may include information for acquiring appropriate device data. For example, when the device is a camera, the information for acquiring appropriate device data is information for specifying the imaging direction when imaging the subject. Also, the information for acquiring appropriate device data may be information for specifying the imaging range, such as whether the entire body of the care recipient is included, whether it is a bust-up, or whether the face is included, or may be other information for determining the characteristics of the captured image. Further, when the device used is other than a camera, there is no hindrance to the know-how information 121 including information for acquiring appropriate device data.

[0334] Figure 34A shows another example of the my page. Similar to Figure 29A, the my page includes the know-how information 121 in use and the registered know-how information 121. In the example of Figure 34A, the user is using the know-how information 121 corresponding to the above (3) or (4). And the my page includes a camera activation object for instructing the activation of the camera as an object for starting the use of the know-how information 121.

[0335] FIG. 34B is an example of a display screen when an operation is performed on the camera activation object shown in FIG. 34A. The screen shown in FIG. 34B includes information for acquiring appropriate device data. The information for acquiring appropriate device data is, for example, a guiding object for indicating the direction of the face of the assisted person in the image. The guiding object in FIG. 34B includes an object OB5 representing a contour and an object OB6 which is an illustration depicting a face. However, either one of the objects OB5 and OB6 may be omitted. Also, information different from both of the objects OB5 and OB6 may be used as information representing an appropriate direction of the face. For example, text such as "Please image the assisted person from the front" may be displayed, or the text may be output as voice using the terminal device 200 or the headset 300. In addition, various modifications can be made to the method of presenting the information for acquiring appropriate device data.

[0336] For example, know-how information 121 is associated with information for acquiring appropriate device data based on the sample data accumulated by the processing of steps S207 - S210 in FIG. 6. For example, when the server system 100 acquires a plurality of images as sample data, the server system 100 obtains the average face direction based on the plurality of images. The server system 100 may obtain objects OB5 and OB6 as information for acquiring appropriate device data based on the obtained average face direction, and associate the obtained objects OB5 and OB6, etc. with the know-how information 121. When using the know-how information 121, the terminal device 200 presents information including the objects OB5 and OB6 as illustrated in FIG. 34B based on the information associated with the know-how information 121.

[0337] In this way, for example, a user who uses the know-how information 121 can appropriately adjust the arrangement of the camera according to the know-how information 121 to be used. Therefore, it becomes possible to acquire input information suitable for the know-how information 121 to be used.

[0338] Alternatively, in the search process of the know-how information 121 shown in FIG. 10, information regarding device data may be presented. For example, in step S309 of FIG. 10, the know-how information 121 using data captured from the front, the know-how information 121 using data captured from the side, and the know-how information 121 using data captured obliquely are presented as different know-how information 121, respectively. At this time, for example, the sample data obtained in step S210 of FIG. 6, information for obtaining appropriate device data, etc. may be displayed in association with the know-how information 121. When determining the know-how information 121 to be used, such as selecting the know-how information 121 using data suitable for the user's own environment, the user can consider the method of obtaining device data. For example, when a camera capable of imaging the care recipient from the front is already arranged in the user's environment, it is possible to adopt the know-how information 121 using data captured from the front in order to divert the use of the camera, or it is also possible to adopt the know-how information 121 using data captured obliquely in order to utilize the know-how information 121 with high evaluation. In the latter case, for example, the user can make a judgment such as "Since the existing camera cannot handle it, use the camera of the terminal device 200 that is easy to adjust the position."

[0339] Here, as an example of the know-how information 121 in (3) and (4), the method of associating information for obtaining appropriate device data with the know-how information 121, and the method of presenting information for obtaining appropriate device data when using the know-how information 121 have been described. However, these methods are widely applicable to the know-how information 121 according to the present embodiment and are not limited to the know-how information 121 in (3) and (4).

[0340] (5) In the know-how information 121 for detecting a scene with a high risk of falling, as input information, three types of information, namely, "if unable to walk independently but starts walking without assistance", "if it is difficult to understand one's own situation, one's physical functions and spatial recognition decline, and one cannot recognize steps", and "if one does not know the location of the toilet", are input. When any one of the three types of information satisfies the condition, as output information, it outputs that "it is a scene with a high risk of falling".

[0341] Here, the above three types of information are extracted from, for example, the information of the foot pressure sensor (for example, pressure sensors are provided at multiple locations on the insole, and the time-series changes of each pressure sensor and the time-series changes of the center of gravity position), and the video captured by the camera. The output information is notified to the caregiver via the headset 300 together with information regarding the care recipient who is determined to be in a scene with a high risk of falling only when it is determined that, for example, "it is a scene with a high risk of falling". The caregiver to be notified may be only the caregiver near or around the care recipient who is determined to be at high risk of falling.

[0342] As shown in FIG. 35, the system for providing the caregiving information (output information) related to the above (5) to the caregiver includes a camera 500, a third terminal device 200C, a fourth terminal device 200D, a server system 100, and a foot pressure sensor 600. The camera 500 is, for example, a wide-area camera and is provided on the ceiling of the room or on the wall near the ceiling. There may be a plurality of such cameras 500. In FIG. 35, two cameras 500-1 provided on the ceiling and 500-2 provided on the wall surface are illustrated as examples. The third terminal device 200C is, for example, placed at a station and has a function of displaying the state of the care recipient imaged by the camera 500. The fourth terminal device 200D is a terminal device used by a given caregiver. In FIG. 35, an example is shown in which the server system 100, the third terminal device 200C, the fourth terminal device 200D, the camera 500, and the foot pressure sensor 600 are connected via a network NW such as a LAN or the Internet. However, various modifications are possible for the specific connection modes of each device.

[0343] The camera 500 transmits the image of the care recipient to the server system 100. Also, the foot pressure sensor 600 transmits the sensing result to the server system 100. The server system 100 executes the processing related to the above (5) based on the acquired information and obtains output information indicating the risk of falling.

[0344] FIG. 36 is an example of a screen displayed on the display unit of the third terminal device 200C. The third terminal device 200C displays the information of the foot pressure sensor 600 of the care recipient and the information indicating the degree of risk in association with the imaged care recipient. In the example of FIG. 36, two care recipients are imaged in the screen, and objects OB31 and OB32 indicating the information of the foot pressure sensor 600 and objects OB41 and OB42 indicating the degree of risk are displayed near each care recipient. The information indicating the degree of risk corresponds to the output information of the above (5). Note that the number of care recipients imaged on the image may be one or three or more. Also, the information indicating the information of the foot pressure sensor 600 and the information indicating the degree of risk may be displayed for all the imaged care recipients or for some of the care recipients. As a means for identifying the care recipient, for example, a known face recognition technology may be used.

[0345] For example, the camera 500 is arranged at various locations such as a nursing facility, and the foot pressure sensor 600 is attached to the care recipient to be monitored for falling. The third terminal device 200C is arranged at a station such as a nursing facility and is used by an administrator or the like. Therefore, by displaying the image shown in FIG. 36 on the third terminal device 200C, it becomes possible to appropriately grasp the risk of falling in the facility.

[0346] Also, the presentation of the output information is not limited to being performed on the third terminal device 200C. For example, the output information may be presented on the fourth terminal device 200D. FIGS. 37A-37D are examples of the screens displayed on the fourth terminal device 200D. FIGS. 37A and 37B are examples of the lock screen (notification screen) of the fourth terminal device 200D. For example, as shown in FIG. 37A, the fourth terminal device 200D may display information indicating that a specific care recipient is likely to fall or that a specific care recipient should be monitored for fall prevention based on the output information in (5) above.

[0347] Also, while it is important to determine the level of the fall risk at a given timing, from the perspective of suppressing the injury of a given care recipient due to a fall, it is also important to observe the state in which the care recipient is walking in a time series. In other words, in the assistance for fall prevention, time series information including the history of the past fall risks is important. Therefore, as shown in FIG. 37B, the fourth terminal device 200D may notify the time series output information of the target care recipient. For example, in the screen shown in FIG. 37A, when an operation of selecting "corresponding" included in a given notification is performed, a display as shown in FIG. 37B may be enabled. For example, in FIG. 37B, a notification to monitor is executed at 17:27, and the output information calculated for the target care recipient after the notification is also notified together within the same object. For example, it is determined that the care recipient to be monitored is also likely to fall at 17:28 and 17:29, and the output information indicating that is displayed together with the output information notified at 17:27.

[0348] Also, the fourth terminal device 200D may display a status screen showing detailed information on the processing of the output information. For example, the status screen shown in FIG. 33B described above includes information related to falls. The status screen related to falls includes items such as location, time, detector, status, response, details, etc.

[0349] "Location" represents the location where the care recipient who is likely to fall is present. For example, the server system 100 stores in advance information associating the ID of the camera 500 with its installation location, and identifies the location based on this information. "Time" is information representing the timing when it is determined that the possibility of falling is high. "Detector" is information representing the care recipient for whom it is determined that the possibility of falling is high, and is, for example, the name of the care recipient. However, the "Detector" may be other information that can be used to identify the care recipient, such as the ID of the foot pressure sensor 600. "Status" is information indicating whether or not the caregiver has taken action, and includes information such as "responded / not responded". "Response" is an area where an object indicating that one will assist the target care recipient is displayed. For example, an object including the text "Respond" is displayed in the response column. "Details" is detailed information representing the state of the care recipient for whom it is determined that the possibility of falling is high, and may be, for example, link information for transitioning to a screen described later using FIG. 37D. By displaying such a status screen, it becomes possible to appropriately present to the user when, where, who is likely to fall, and what actions have been taken in response thereto.

[0350] FIG. 37C is another example of a status screen. As shown in FIG. 37C, the status screen may include time-series information regarding the fall of a given care recipient. In this way, it becomes possible to clearly present the transition of the fall risk of the target care recipient and the actions of the caregiver at each timing. In the example of FIG. 37C, regarding the fall risk at 17:23, no action has been taken by the caregiver due to factors such as, for example, being determined to be okay visually. Also, regarding the fall risks at 17:27, 17:28, and 17:29 that occurred to the same care recipient, for example, a caregiver with the user name Sato has responded.

[0351] In consideration of the risk of fractures or the like for the care recipient, it is important to prevent falls. Therefore, when performing safety - considered control, even in a scenario where the care recipient did not actually fall, a notification indicating that a fall was likely to occur may be issued. In other words, among the scenarios determined by the server system 100 to have a high risk of falling, there may be cases where corresponding measures such as actually supporting the care recipient are necessary, and there may also be cases where just observing is sufficient.

[0352] Therefore, the user of the fourth terminal device 200D may view the detailed information when it is determined that the risk of falling is high. For example, when a selection operation of an object including the text "View" displayed in the details column of FIG. 37C is performed on the fourth terminal device 200D, the detailed information may be displayed, and feedback based on the detailed information may be received.

[0353] FIG. 37D is an example of a screen for displaying detailed information. As shown in FIG. 37D, the detailed information may be a moving image of the target care recipient. Here, the moving image may be the captured moving image itself, or may be information including an object (corresponding to OB31 etc.) indicating the information of the foot pressure sensor 600 as shown in FIG. 36, or an object (corresponding to OB41 etc.) indicating the degree of risk. For example, when the server system 100 obtains output information representing the fall risk based on a 10 - second moving image, the moving image here is a 10 - second moving image when it is determined that the fall risk is high.

[0354] The user of the fourth terminal device 200D views the moving image and then inputs in FIG. 37D whether the care recipient was actually in a situation where a fall was likely, especially whether it was a situation where there was no problem and no intervention by the caregiver was required. The input information may be stored in the nursing facility or may be fed back to the server system 100 and used for the update process of the learned model for determining the fall risk.

[0355] Note that the above has described the form of notification using the display unit of the fourth terminal device 200D, but the form of notification is not limited to this. For example, it may be notified to the caregiver by voice via the headset 300.

[0356] In addition, in the above, regarding the information related to (3) to (5), an example was shown in which each terminal device 200 displays, for example, a status screen to check the status of each assisted person. However, a status screen may also be displayed for the information related to (1) and (2) above. Further, the know-how information 121 to be displayed on the status screen is not limited to (1) to (5), and devices such as the terminal device 200 may display a status screen for other information.

[0357] Although the present embodiment has been described in detail as above, those skilled in the art will easily understand that many modifications can be made without substantially departing from the novel matters and effects of the present embodiment. Therefore, all such modified examples are intended to be included within the scope of the present disclosure. For example, in the specification or drawings, a term described at least once together with a broader or synonymous different term can be replaced with that different term at any place in the specification or drawings. Also, all combinations of the present embodiment and the modified examples are included within the scope of the present disclosure. Further, the configurations and operations of the information processing system, information processing device, server system, and terminal device are not limited to those described in the present embodiment, and various modifications can be implemented.

Explanation of Reference Numerals

[0358] 10... Information processing system, 100... Server system, 110... Processing unit, 111... Registration processing unit, 112... Search processing unit, 113... Similarity determination unit, 114... State determination unit, 115... Importance determination unit, 120... Memory unit, 121... Know-how information, 122... Registration information, 123... List information, 130... Communication unit, 200, 200-1, 200-2... Terminal device, 200A... First terminal device, 200B... Second terminal device, 200C... Third terminal device, 200D... Fourth terminal device, 210... Processing unit, 220... Memory unit, 230... Communication unit, 240... Display unit, 250... Operation unit, 300, 300-1, 300-2... Headset, 400... Wearable device, 500, 500-1, 500-2... Camera, 600... Foot pressure sensor, NW... Network, RE1, RE2, RE3... Region, OB1, OB2, OB21-OB24, OB31, OB32, OB41, OB42... Object

Claims

1. A processing unit that receives a registration request for know-how information including information used in assistance, the know-how information including output information output to an assistant and input information for outputting the output information, and the output information and the input information being associated with each other; A storage unit that stores the know-how information based on the registration request; Comprising: The processing unit: Obtains state information that is calculated based on information acquired from an external sensor or input from the outside and represents the state of the care recipient; Obtains association information that associates a change in the state information based on the state information obtained at a first timing and the state information obtained at a second timing different from the first timing with the know-how information used for assisting the care recipient between the first timing and the second timing; The state information includes at least one of a degree of care required indicating the degree to which the care recipient needs assistance and an evaluation result of the care recipient's ADL (Activities of Daily Living); The processing unit: An information processing apparatus that determines the importance of the know-how information such that the importance of the know-how information associated with a change in the state information when at least one of the degree of improvement in the degree of care required or the evaluation result of the ADL between the first timing and the second timing is high is higher than the importance of the know-how information associated with a change in the state information when at least one of the degree of improvement in the degree of care required or the evaluation result of the ADL is low.

2. In Claim 1, The storage unit: Stores attribute information representing the attributes of the care recipient; The processing unit: An information processing apparatus that identifies important know-how information, which is know-how information determined to have an importance of a predetermined level or more in assisting a care recipient having a given attribute, based on the association information corresponding to the care recipient determined to have the given attribute based on the attribute information.

3. In Claim 2, The processing unit: An information processing apparatus that identifies, as the important know-how information, those with a significant partial regression coefficient based on regression analysis and significance testing using a value related to the state information as a target variable and information indicating use / non-use of the know-how information as an explanatory variable.

4. In Claim 2 or 3, The processing unit: When it is determined that a given care recipient has the given attribute, an information processing apparatus that presents, as recommended know-how information recommended for assisting the given care recipient, the know-how information being used for assisting the given care recipient and the know-how information suitable for the given attribute based on the important know-how information.

5. In any one of Claims 1 to 4, the processing unit An information processing apparatus that calculates the state information based on the know-how information used for assisting the care recipient and the output data of sensors arranged in the living environment of the care recipient.

6. In Claim 5, the processing unit An information processing apparatus that, when it is determined that the number of the output data of the sensors is insufficient during a given determination period, outputs an instruction to perform a specific action to the care recipient or a caregiver who assists the care recipient.

7. A computer receives a registration request for know-how information including information that is information used in assistance and in which output information output to a caregiver and input information for outputting the output information are associated with each other, stores the know-how information based on the registration request, acquires state information calculated based on information acquired from an external sensor or input from the outside and representing the state of the care recipient, acquires association information associating the change in the state information based on the state information acquired at a first timing and the state information acquired at a second timing different from the first timing with the know-how information used for assisting the care recipient between the first timing and the second timing, the state information includes at least one of a care-need degree representing the degree to which the care recipient needs assistance and an evaluation result of the care recipient's ADL (Activities of Daily Living), determines the importance of the know-how information such that the importance of the know-how information associated with the change in the state information when at least one of the improvement degrees of the care-need degree or the ADL evaluation result between the first timing and the second timing is high is higher than the importance of the know-how information associated with the change in the state information when at least one of the improvement degrees of the care-need degree or the ADL evaluation result is low, executing the above.

Images