Information processing device, information processing method and program

Abstract

To watch an object person while protecting personal information and privacy.SOLUTION: An information processing device comprises: an acquisition unit which acquires detection information generated based upon characteristic values related to an object person; a processing unit which performs processing to generate analytic information by analyzing the state of the object person based upon the detection information and also place the detection information, used to generate the analytic information, in a state in which personal information cannot be specified; and an evaluation unit which generates and outputs an evaluation result, obtained by evaluating the state of the object person by the use of the analytic information, to a disclosure destination.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program.

Background Art

[0002] Patent Document 1 discloses a safety confirmation system that can estimate a health state from a living situation without violating the privacy of a resident and automatically report it to a caregiver. In this system, pyroelectric sensors are installed in each room of a house as human sensors for detecting the movement of a resident. Among various facilities in the house, a proximity switch that uses magnetism to detect the opening and closing of a door is attached to the door, a light sensor is attached to the lighting, and a current sensor that detects a magnetic field is attached to electrical devices such as a television as a device sensor.

[0003] The output of each sensor is transmitted to a control device after pseudo-noising each bit of the data in order to protect the privacy of the resident. The control device constructs an operation manual as a standard of a normal living pattern of the resident from the data based on the output of the human sensor and the device sensor, compares it with the actual living pattern, and transmits a report to a remote caregiver based on the result.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In Patent Document 1, it is described that data is encrypted when transmitted based on the output of a sensor for privacy protection. However, there is a risk that a resident can be identified from the data collected by the control device.

[0006] An object of the present disclosure is to provide an information processing apparatus, an information processing method, and a program capable of monitoring a target person while protecting personal information and privacy in view of the above-described problems.

Means for Solving the Problems

[0007] An information processing apparatus according to an aspect of the present disclosure includes an acquisition unit that acquires detection information generated based on characteristic values related to a target person, analyzes the state of the target person based on the detection information to generate analysis information, and processes the detection information used for generating the analysis information to make it in a state where personal information cannot be specified. And a processing unit, and an evaluation unit that generates an evaluation result of evaluating the state of the target person using the analysis information and outputs the evaluation result to a disclosure destination.

[0008] An information processing method according to an aspect of the present disclosure is a process in which a computer acquires detection information generated based on characteristic values related to a target person, analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing process that makes the detection information used for generating the analysis information in a state where personal information cannot be specified. generates an evaluation result of evaluating the state of the target person using the analysis information and outputs the evaluation result to a disclosure destination, and executes.

[0009] A program according to an aspect of the present disclosure is a process of acquiring detection information generated based on characteristic values related to a target person, analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing process that makes the detection information used for generating the analysis information in a state where personal information cannot be specified. generates an evaluation result of evaluating the state of the target person using the analysis information and outputs the evaluation result to a disclosure destination, and causes a computer to execute.

Effects of the Invention

[0010] According to the present disclosure, it is possible to monitor a target person while protecting personal information and privacy.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted as necessary for clarity of explanation.

[0013] According to recent population trends, national analyses have reported that Japan may be in a critical situation due to an increase in the proportion of the elderly in the population and a decrease in the working population. There is also an estimate that the proportion of single-occupancy elderly households will exceed 50% by 2050. In the future, there will be a problem of a shortage of caregivers visiting the homes of individuals who cannot enter nursing facilities.

[0014] In order to respond to the further aging of Japanese society, it is important to understand how to grasp the status of the care recipients in building a "regional comprehensive care system" that comprehensively ensures medical care, nursing care, prevention, housing, and life support. In addition, it is predicted that care staff who care for the recipients will need multiple options such as medical institutions, welfare institutions, private companies, and families depending on the status of the recipients.

[0015] As a method of grasping the status of the recipients, monitoring cameras for watching over are widespread. On the other hand, from the perspective of the privacy of the recipients shown in the monitoring cameras, there is also a problem that installing monitoring cameras in houses is not easily accepted. In addition, even if an abnormality of the recipient is detected based on the video of the monitoring camera, there is also an issue that it cannot be connected to an action of caring for the recipient by care staff. The present disclosure relates to a monitoring system that protects the privacy of the monitored recipients and can evaluate the status of the recipients.

[0016] In the present disclosure, the "recipient" refers to a person to be monitored. The recipients may include, for example, persons receiving care such as the elderly and persons receiving treatment such as patients. Note that as long as a person uses the monitoring system, even a healthy person can be a monitored recipient. In the present disclosure, the "care staff" refers to a person who cares for the recipient. The care staff may include medical staff such as doctors and nurses in medical institutions, staff including care managers in care facilities of private companies, in-charge staff in welfare institutions, and family members.

[0017] Embodiment 1. A configuration example of the information processing apparatus 1 will be described with reference to FIG. 1. The information processing apparatus 1 is applied to a monitoring system installed in a house where the recipient lives. As shown in FIG. 1, the information processing apparatus 1 includes an acquisition unit 2, a processing unit 3, and an evaluation unit 4. The acquisition unit 2 acquires detection information generated based on characteristic values related to the recipient. The "characteristic value" is a value indicating the status and actions of the recipient. The characteristic values include changes in physical characteristics related to the recipient, changes in behavioral characteristics, changes in things caused by the actions of the recipient, and the like.

[0018] In order to collect characteristic values in a natural form while ensuring privacy, various devices that can be used without discomfort in the daily life of the subject are used. Examples of such devices include household electrical appliances such as televisions, refrigerators, washing machines, and air conditioners (hereinafter referred to as home appliances), sanitary appliances such as toilets, and lighting appliances. In addition, communication devices for making voice calls and video calls with family members and others in remote locations can also be used for collecting characteristic values.

[0019] For example, characteristic values can be collected by detecting the usage status of the device or the approach of the subject near the device. Specifically, a communication device can collect an image of the subject by photographing the subject during a video call. The detection information detected from the image of the subject includes, for example, body temperature, heart rate, blood pressure value, oxygen saturation, expression, eye size (degree of opening), etc. These detection information are also referred to as biometric information hereinafter.

[0020] In addition, the detection information resulting from the subject's behavior based on the collected image may include, for example, fall information, lying position (supine position, prone position, lateral position, etc.) information, excretion information, going out information, medication information, etc. Note that the acquisition unit 2 may acquire excretion information based on imaging data obtained by imaging excrement in the toilet bowl of the toilet. The excretion information may include foreign substances other than excrement (cores of toilet paper, urine pads, etc.) and information regarding the number of excretion acts.

[0021] The going out information may be based on, for example, physical values detected by a sensor that detects the opening and closing of the door of the house. The detection information may include information regarding the on / off of the lighting appliances in the house. The medication information may be based on, for example, a detection signal of a sensor configured to be able to detect the presence of medicine when the medicine is stored in the medicine box. This sensor can be, for example, a weight sensor that detects the weight of the medicine, an optical sensor that senses the opening and closing of the medicine box, etc.

[0022] Detection information based on the voice of the subject may include a CEM value, which is a chaotic theory index value calculated from the voice spoken by the subject, and the content of the speech. The chaotic theory index value is an index value representing the spread of an attractor created from time-series data having chaos. The chaotic theory index value can be, for example, the largest Lyapunov exponent described in M. Sano, Y. Sawada, "Measurement of the Lyapunov Spectrum from a Chaotic Time Series", The American Physical Society, USA, 1985, Vol.55 NO.10, P.1082-1085. Also, the chaotic theory index value may be a macro brain activity index value calculated by the SiCECA algorithm described in Kazuichi Shiomi, "Brain function model considered from speech analysis", Transactions of the Society for Japanese Cognitive Science, Japan, The Japanese Society for Cognitive Science, February 2004, Vol.4, No.1, p.3-12.

[0023] In the following description, it is assumed that the chaotic theory index value is the CEM value defined by the SiCECA algorithm. The CEM value is a feature quantity indicating the activity of the neocortex. Since the neocortex is closely related to the control of the autonomic nervous system (sympathetic nerve / parasympathetic nerve), its active state is useful information for grasping the state of the autonomic nervous system. Since the relationship between the disorder of the autonomic nervous system and mental disorders is already known, by utilizing the simple technology of voice that does not require a dedicated measuring device, it becomes possible to easily know one's own state, and it can be applied to the determination of the onset risk of mental disorders at the pre-disease stage.

[0024] The detection information may be an evaluation of the state of the subject's autonomic nervous system from the CEM value calculated from the subject's voice. The detection information may be generated based on one or more combinations of a plurality of characteristic values. For example, the detection information may be cognitive information that estimates the subject's cognitive function from the subject's expression and speech content. Also, the detection information may be a value that estimates the degree of stress, emotions, etc. based on one or more of the heart rate, blood pressure value, and oxygen saturation.

[0025] The residence of the target person is provided with sensors and the like for acquiring the above-described characteristic values. For example, various facilities in the residence may be provided with a variety of sensors having fewer monitoring elements than a surveillance camera for collecting the above-described characteristic values. Such sensors can detect the actions of the target person and operations of devices resulting from the actions. Such sensors can be, for example, sensors that detect the opening and closing of doors, human presence sensors provided in bathrooms and the like, sensors that detect operations of home appliances, sensors that detect the operating status of home appliances, and the like.

[0026] The processing unit 3 analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing (hereinafter referred to as masking processing) for making the detection information used for generating the analysis information in a state where personal information cannot be specified. In this way, by masking elements related to personal information and privacy in the detection information obtained from each sensor, it becomes possible to exclude the element of "watching over" the target person and realize the "monitoring" of grasping the state of the target person.

[0027] The evaluation unit 4 generates an evaluation result obtained by evaluating the state of the target person using the analysis information, and outputs it to the disclosure destination. Thereby, based on the evaluation result, it becomes possible to lead to an action of caring for the target person by the care staff. For example, the evaluation result can be used for health state management and medical treatment in a medical institution, activities in a welfare institution, and the like. Note that the evaluation result may be transmitted to the target person himself / herself according to the request of the target person. The target person can also use the evaluation result for self-management of the health state.

[0028] Next, the processing performed by the information processing apparatus 1 will be described with reference to FIG. 2. First, the information processing apparatus 1 acquires detection information generated based on characteristic values related to the target person (S11). Next, the information processing apparatus 1 analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing for making the detection information used for generating the analysis information in a state where personal information cannot be specified (S12). Then, the information processing apparatus 1 generates an evaluation result obtained by evaluating the state of the target person using the analysis information, and transmits it to the disclosure destination (S13).

[0029] Thus, according to the present disclosure, by processing the detection information into a state where personal information cannot be identified, it becomes possible to protect personal information and privacy. Further, by generating an evaluation result obtained by evaluating the state of the target person using the analysis information and outputting it to the disclosure destination, it becomes possible to lead to an action of caring for the target person by the care staff based on the evaluation result.

[0030] Note that the information processing apparatus 1 includes a processor, a memory, and a storage device as a configuration (not shown). A program for causing a computer to execute each of the above-described processes is stored in the storage device. The processor causes the program to be read from the storage device into the memory and executes the program. Thereby, the processor realizes the functions of the acquisition unit 2, the processing unit 3, and the evaluation unit 4.

[0031] Each component of the information processing apparatus 1 may be realized by dedicated hardware. Further, part or all of each component of each device may be realized by general-purpose or dedicated circuitry, a processor, etc., or a combination thereof. These may be constituted by a single chip or may be constituted by a plurality of chips connected via a bus. Part or all of each component of each device may be realized by a combination of the above-described circuitry, etc. and a program. Further, as the processor, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a quantum processor (quantum computer control chip), etc. may be used.

[0032] Also, when a part or all of each component of the information processing apparatus 1 is realized by a plurality of devices, circuits, etc., the plurality of devices, circuits, etc. may be centrally arranged or distributed. FIG. 3 is a block diagram showing the configuration of the information processing system 101 according to Embodiment 1. As shown in FIG. 3, the information processing system 101 includes an acquisition unit 102, a processing unit 103, and an evaluation unit 104. The detailed operations of each configuration of the information processing system 101 correspond to the operations of each configuration of the information processing apparatus 1 as described above. The devices, circuits, etc. that realize each component in FIG. 3 may be realized in a form in which each is connected via a communication network, such as a client-server system or a cloud computing system. Also, the function of the information processing apparatus 1 may be provided in the form of SaaS (Software as a Service).

[0033] Embodiment 2. A configuration example of the monitoring system 100 will be described with reference to FIG. 4. Here, as an example, an example in which the monitoring system 100 is applied to the residence of the target person is shown. In this example, in particular, an example of calculating the CEM value using the voice data acquired from the target person, evaluating the state of the target person, and providing preventive medicine at the pre-disease stage for the target person will be described. As shown in FIG. 4, the monitoring system 100 includes a server 10, a monitoring terminal 20, and a disclosure terminal 30. The server 10, the monitoring terminal 20, and the disclosure terminal 30 are each connected via the network N. Here, the network N is a wired or wireless communication line, for example, the Internet.

[0034] The monitoring system 100 includes a plurality of disclosure terminals 30. The disclosure terminals 30 are used by care staff such as medical staff in medical institutions, staff in nursing facilities, staff in welfare institutions, and family members, respectively. The disclosure terminals 30 are, for example, personal computers, tablets, smartphones, etc. The disclosure terminal 30 may include a display device for displaying the evaluation results transmitted from the server 10, and a reporting device (both not shown) that performs a reporting operation according to a reporting instruction. The reporting device presents the reporting instruction to the care staff using the disclosure terminal 30 by light emission or voice. Note that information regarding the reporting instruction may be displayed on the display device as text.

[0035] Here, the monitoring system 100 has a function of detecting characteristic values of a target person (detection function), a function of analyzing the state of the target person based on detection information generated from the characteristic values to generate analysis information, and processing the detection information used for generating the analysis information into a state where personal information cannot be specified (processing function), and a function of generating an evaluation result by evaluating the state of the target person using the analysis information and outputting it to the disclosure destination (evaluation function). The monitoring system 100 can transmit the evaluation result to one or more selected disclosure terminals 30 among the plurality of disclosure terminals 30. In the following description, the process of generating analysis information in the processing function may be separately referred to as "analysis process", and the process of processing the detection information into a state where personal information cannot be specified may be separately referred to as "masking process".

[0036] When predicting the state of the target person using the CEM value calculated from the voice data, the monitoring system 100 further has (a) a function of obtaining the normal range of the CEM value (normal range calculation function), (b) a function of comparing the normal range of the obtained chaos theory index value with the CEM value calculated from the voice data for determination to analyze the state of the target person (analysis function), and (c) a function of predicting the state of the target person using the transition of the normal range of the obtained CEM value (trend prediction function). The normal range calculation function may be included in the above-described processing function. Also, the analysis function and the trend prediction function may be included in the above-described evaluation function.

[0037] The monitoring system 100 first acquires a plurality of voice data and performs a process (normal range calculation process) of obtaining the normal range of the chaos theory index value. Then, the monitoring system 100 can determine the state of the subject by comparing the obtained normal range of the chaos theory index value with the CEM value calculated from the voice data for determination. In addition, the monitoring system 100 can execute a process of predicting the state of the subject by using the transition of the obtained normal range of the chaos theory index value.

[0038] <Monitoring terminal 20> The monitoring terminal 20 is an information processing device that realizes a detection function. The monitoring terminal 20 is installed in the subject's residence and transmits and receives data with the server 10 via the network N by wireless communication. The monitoring terminal 20 is, for example, a personal computer, a tablet, a smartphone, etc. The monitoring terminal 20 can be used for video calls with family members or the like in a remote location. The monitoring terminal 20 can acquire the image data and voice data of the subject. FIG. 5 is a block diagram showing the configuration of the monitoring terminal 20 in FIG. 4.

[0039] The monitoring terminal 20 includes a sound collection unit 21, an imaging unit 22, a storage unit 23, a communication unit 24, an input / output unit 25, and a processing unit 26. The sound collection unit 21 is a microphone that collects the voice data of the subject according to the control of the processing unit 26. In order to execute the above-described normal range calculation process, the voice data of the subject is collected. The sound collection unit 21 can collect a plurality of voice data generated during a predetermined period that satisfy a predetermined condition and are uttered by the subject.

[0040] The predetermined conditions may include environmental conditions when collecting the voice data, conditions regarding the speech content of the subject collected as the voice data, and time conditions for obtaining the voice data. The environmental conditions may include sound collection devices such as microphones and the surrounding environment when the subject speaks. The voice data is preferably collected using the same sound collection device such as a microphone. This makes it possible to suppress the variation of the chaos theory index value due to differences in the sound collection devices. Note that the voice data is not limited to the same sound collection device and may be collected using sound collection devices having similar characteristics.

[0041] In addition, it is preferable that a plurality of voice data with the same utterance content spoken by the subject be acquired. This can reduce the fluctuation of the chaos theory index value and make it possible to calculate a more accurate normal range. However, if it is possible to acquire a sufficient amount of voice data for calculating the normal range, the utterance content does not necessarily have to be the same and may be different.

[0042] The time for acquiring the voice data can be a specific time period when the body is not under load. Note that this time period is a guideline, and voice data spoken at a plurality of different arbitrary times may be collected. Since it is known that the chaos theory index value varies depending on the fatigue level of the subject, etc., the subject may appropriately change the time for inputting the voice data in consideration of his / her own fatigue level, etc.

[0043] In addition, the voice data generated in a predetermined period is acquired. Since the plurality of voice data acquired by the sound collection unit 21 serves as basic data for calculating the normal range, it is necessary to have the required amount of data for analysis. When acquiring voice data for the first time in a state where there is no accumulation of the subject's voice data, for example, a plurality of voice data three times a day, in the morning, at noon, and in the evening, for about two weeks are collected. Note that the period for acquiring the voice data can be changed as appropriate.

[0044] The imaging unit 22 is a camera that performs imaging according to the control of the processing unit 26. When the imaging unit 22 images the subject, imaging data is generated. The storage unit 23 is an example of a storage device including a non-volatile memory such as a flash memory or an SSD (Solid State Drive). The storage unit 23 stores a program in which processing including transmission processing of data for evaluating the state of the subject is implemented.

[0045] The communication unit 24 is a communication interface with the network N. The communication unit 24 may establish a short-range wireless communication connection and perform communication. Here, various standards such as Bluetooth (registered trademark), BLE (Bluetooth Low Energy), and UWB (Ultra-Wide Band) can be applied to the short-range wireless communication.

[0046] The input / output unit 25 may include a display device such as a screen, and an input device such as a keyboard. The input / output unit 25 may also be a touch panel that integrates a display device and an input device. The processing unit 26 is a processor that controls the hardware of the watching terminal 20. The processing unit 26 loads a program from the storage unit 23 into a memory (not shown) such as a RAM (Random Access Memory) and executes it. In this way, the processing unit 26 realizes the functions of a generation processing unit 261 and a transmission processing unit 262.

[0047] The generation processing unit 261 acquires daily characteristic values of the subject from the devices installed in the house and sensors installed in each facility via the communication unit 24, and generates various data to be transmitted to the server 10. These characteristic values are various data associated with the subject's behavior, which are generated as the subject lives their natural life. Note that if these characteristic values include information related to privacy or personal information, it is necessary to obtain the subject's consent in advance regarding the acquisition of such information.

[0048] Examples of detection information generated from characteristic values include the following: - Usage data obtained from electricity, gas and water meters - The number of times a door is opened and closed is obtained from a sensor placed at the entrance or other location that counts the number of times the door is opened and locked. - Posture information of the subject obtained from non-visual information such as millimeter wave sensors - Number of baths and bathing time obtained from a human sensor installed in the bathroom - Excretion information (number of bowel movements, condition of stool, presence of foreign objects, etc.) obtained from sensors installed in the toilet that can detect bowel movements ·Audio data and image data in video calls using a telephone, TV, etc.

[0049] The generation processing unit 261 can generate audio data for preventive medical care based on the voice of the target person. For example, when the target person speaks to the monitoring terminal 20 at an arbitrary timing or makes a call using the monitoring terminal 20, audio data is generated. Note that the generation processing unit 261 may perform processes such as converting the input analog audio data into digital audio data and extracting audio data in the pitch frequency band from the digital audio data. The generation processing unit 261 can record the collection time of the audio data together with the audio data. The transmission processing unit 262 transmits the audio data generated by the generation processing unit 261 to the server 10.

[0050] The transmission processing unit 262 can transmit the terminal ID of the monitoring terminal 20 and the ID of the target person together with various data generated by the generation processing unit 261. In the following description, it is assumed that the target person ID is associated with various data.

[0051] <Server 10> The server 10 is an information processing device that realizes a processing function and an evaluation function. When predicting the state of the target person using the CEM value, a normal range calculation process can be performed as an analysis process, and an analysis process and a trend prediction process can be performed as an evaluation process. Note that the server 10 may be composed of a plurality of servers, and each functional block may be realized by a plurality of computers.

[0052] FIG. 6 is a block diagram showing the configuration of the server 10 in FIG. 4. The server 10 includes a storage unit 11, a communication unit 12, and a processing unit 13. The storage unit 11 is an example of a storage device such as a hard disk or a flash memory. The storage unit 11 stores a program 111, a target person information DB (database) 112, a medical information DB 113, a care information DB 114, and an accident information DB 115. The program 111 is a computer program in which at least a part of the above-described analysis process, masking process, evaluation process, etc. are implemented.

[0053] The target person information DB112 is a database that manages various detection information of the target person. In the example shown in FIG. 6, the target person information DB112 manages by associating the target person ID with the detection information of the target person. The medical information DB113 is a database that manages medical information. Examples of medical information include, for example, the medical record information and medication information of the target person. The care information DB114 is a database that manages the information necessary for the care of the target person. Such information may include, for example, information indicating the mental state of the target person and information indicating the physical state. The accident information DB115 is a database that manages the accident information of the target person that occurred within the residence. The accident information may include, for example, information regarding the type of accident (such as a fall) and the location of occurrence. The information stored in these medical information DB113, care information DB114, and accident information DB115 is managed, for example, in association with the target person ID.

[0054] The communication unit 12 is a communication interface with the network N. The processing unit 13 is a processor that controls each component of the server 10. The processing unit 13 causes the program 111 to be read from the storage unit 11 into a memory (not shown) such as a RAM, and executes the program 111. Thereby, the processing unit 13 realizes the functions of the acquisition unit 131, the information determination unit 132, the processing unit 133, the evaluation unit 134, the transmission processing unit 135, and the notification processing unit 136.

[0055] The acquisition unit 141 acquires various detection information transmitted from the monitoring terminal 20. The information determination unit 132 determines from which sensor provided in the target person's residence these detection information are collected.

[0056] Among the multiple sensors installed in the house, there are some that output detection information capable of identifying the target person, such as the face and personal information of the target person. That is, the information determination unit 132 can determine whether the acquired detection information is information capable of identifying the target person based on the detection information by determining in which of the multiple sensors the detection information was generated. When the detection information is information capable of identifying the target person, the information determination unit 132 can transmit the detection information to the processing unit 133.

[0057] The processing unit 133 performs analysis processing to analyze the state of the target person based on the detection information and generate analysis information, and performs masking processing on the detection information used for generating the analysis information to make it impossible to identify personal information. The processing unit 133 can process information related to the personal information / privacy of the detection information and register it in the target person information DB112 as data edited to a state where the individual cannot be identified from the data alone. Note that this data is registered in the target person information DB112 in association with the target person ID.

[0058] The processing unit 133 first performs analysis processing. When the detection information is image data, the processing unit 133 can, for example, analyze emotions or estimate the cognitive state using a model generated by a technology related to machine learning such as AI (artificial intelligence) based on the expression of the target person.

[0059] Also, when the detection information is audio data, the processing unit 133 can, for example, perform chaos analysis on a plurality of time-series audio data and calculate CEM values respectively. For the calculation of CEM values, for example, the technology described in Japanese Patent No. 5812265 can be used. For example, the processing unit 133 can convert the input analog audio data into digital audio data, extract the audio data in the pitch frequency band from the digital audio data, and process the extracted audio data to calculate the chaos theory index value.

[0060] Note that the pitch frequency is the frequency determined by the vibration of the vocal cords of the subject, and it is information excluding the influence of the shape of the vocal tract from the vocal cords to the lips. As a filter for extracting voice data in the pitch frequency band, any principle can be used, such as a filter that allows only data in the pitch frequency band to pass through, or a filter that attenuates data outside the pitch frequency band.

[0061] Note that since there are individual differences in CEM values, it is impossible to determine normal / abnormal just by looking at the CEM values. Therefore, as described above, the normal range of CEM values for the past 14 days can be estimated (normal range calculation process), and the normal / abnormal state of the subject can be visualized.

[0062] The processing unit 133 performs statistical processing on CEM values for two weeks and can calculate the normal range for each subject. Information regarding the normal range is input to the evaluation unit 134. The processing unit 133 can obtain the future normal range, for example, by obtaining the moving average of the time-series normal range and linearly approximating the moving average. For example, when obtaining the normal range from voice data for two weeks (14 days), the processing unit 133 can, as an example, obtain the 14-day moving average of the upper and lower limit values of the time-series normal range, respectively. Note that the moving average of the normal range can be calculated by adding the CEM value calculated from the new voice data and excluding the oldest CEM value.

[0063] In addition, the processing unit 133 executes a masking process. The processing unit 133 performs the masking process when it is determined in the information determination unit 132 that the detected information is information that can identify the subject. The masking process is a process of processing the detected information into a state where personal information cannot be identified. An example of the masking process is a process of deleting the detected information after performing the analysis process.

[0064] Therefore, when the detection information is image data, the processing unit 133 can discard the image data after extracting analysis information represented by numerical values by performing estimation of emotions, cognitive states, etc. from the image data. Further, the masking process for the image data may be a process that makes it impossible to recognize a part that can identify a person included in the image. The parts that can identify a person include the face, clothes, background, etc. For example, the processing unit 133 may perform a process of detecting parts in the image using a model generated by a technique related to machine learning such as AI (artificial intelligence). Note that examples of the process that makes it impossible to recognize a part that can identify a person include a mosaic process, a filling process, a cutting process, etc.

[0065] Also, when the detection information is audio data, the processing unit 133 can discard the original audio data after extracting the CEM value by performing, for example, an analysis process. Note that the masking process may be a process of deleting personal information (for example, name, subject ID, etc.) of the person associated with the audio data from the audio data. Further, when the detection information is excretion information, only the result information obtained by numerically evaluating the state of the excreted matter can be extracted, and then the excretion information can be discarded. Thereby, it becomes possible to protect personal information and ensure privacy. Note that any known technique can be adopted for the analysis process and the masking process in the server 10.

[0066] The evaluation unit ********** generates an evaluation result obtained by evaluating the state of the subject using the analysis information. The evaluation unit 134 can evaluate the state of the subject with reference to the medical information DB 113, the care information DB 114, and the accident information DB 115 from the analysis information.

[0067] For example, when the attitude information measured by the millimeter wave sensor is input, the evaluation unit 134 can determine whether the subject has fallen or drowned, taking into account the position within the residence and the like. Further, the evaluation unit 134 can generate risk values such as forgetting to take medicine / duplicate taking of medicine based on the opening / closing number information / time information / weight change information before and after opening / closing of the medicine box measured by the optical sensor / weight sensor.

[0068] In addition, the evaluation unit 134 can evaluate the tendency of increase / decrease in the number of times of going out based on the time-series changes such as the number of times / hours of going out from home detected by the insole sensor provided in the shoes worn by the subject or the millimeter wave sensor. The evaluation unit 134 can prevent frailty by generating advice information to encourage the elderly with a decreased going-out frequency to go out.

[0069] Furthermore, the evaluation unit 134 can estimate the degree of cognitive function decline based on biometric information such as information indicating the brain activity level calculated from voice data and emotional information obtained from the facial expressions of image data. The voice data and image data can be obtained, for example, from remote video calls using a smartphone, a PC, or the like. The evaluation unit 134 can create an evaluation result that prompts attention to the family in a remote location and the staff of the nursing facility according to the state of the subject's cognitive function. Also, in cooperation with a security company or the like, it is possible to provide a service to prevent special fraud damage by phone based on the state of the subject's cognitive function. In addition, the evaluation unit 134 can estimate the health state of the subject from the toilet usage situation, excretion information, or biometric information of the subject obtained from smart home appliances or the like.

[0070] In addition, the evaluation unit 134 can predict the state of the subject based on the transition of the normal range of the above-described CEM value. The evaluation unit 134 can predict the future state of the subject by linearly approximating the moving average of the average value of the CEM values for one day in a time series and comparing it with the future normal range. As an example, the evaluation unit 134 can classify the subject into three classes: "normal state", "nervous state", and "fatigue state". When the CEM value for determination is within the "normal range", that is, when the CEM value is a value between the lower limit value and the upper limit value of the normal range, the evaluation unit 134 determines that the subject is in the "normal state".

[0071] It is known that the heart rate, pulse rate, sweating amount, and eye movement increase when the sympathetic nerve among the autonomic nerves becomes dominant, and conversely, decrease when the parasympathetic nerve becomes dominant. In contrast, it has been found that for the CEM value, the index value CEM decreases when the sympathetic nerve becomes dominant, and the index value CEM increases when the parasympathetic nerve becomes dominant. Therefore, for example, after calculating the normal range, if the newly calculated CEM value for determination is smaller than the lower limit value of the normal range and is equal to or greater than a predetermined threshold smaller than the lower limit value, it can be determined that the subject is in a "nervous state". Also, if it is smaller than the predetermined threshold, it can be determined that the subject is in a "fatigue state". Note that the present invention is not limited to this example, and the state of the subject may be predicted based on other criteria.

[0072] The evaluation unit 134 generates an evaluation result in which the health state, physical condition management information, medication information, etc. of the subject are reported. The transmission processing unit 135 can transmit the generated evaluation result to at least one disclosure terminal 30. Note that the subject may select a disclosure destination that discloses a report including the evaluation result regarding the subject's own state at the subject's own will. The disclosure terminal 30 can disclose the state of the subject to the care staff by displaying the evaluation result or the like. As a result, the care staff at the disclosure destination can provide appropriate care corresponding to the state of the subject to the subject.

[0073] Note that the evaluation results may be sent to the subject himself / herself. Thereby, it is also possible for the subject himself / herself to utilize the evaluation results to improve self-care awareness such as health management and physical condition management. Further, the evaluation results may include advice information according to the subject's condition. Here, the advice information is, for example, information that proposes methods for maintaining health, improving symptoms, preventive methods, etc. For example, by having the subject develop exercise habits and going-out habits according to the advice information, it becomes possible to assist in promoting the healthy age.

[0074] In addition, the advice information may include information regarding medical acts, assistance acts, nursing care acts, etc. that care staff perform on the subject according to the subject's condition. Thereby, since the care staff can perform care for the subject with reference to the advice information, the burden on the care staff can be reduced. Further, the advice information may include information for reducing the crime risk. Thereby, the monitoring system 100 can achieve prevention of crime victimization and also function as a safety net for subjects including the elderly.

[0075] Note that the detection information can be used as data for evaluating the abnormal state of the subject. Therefore, when the consent of the subject himself / herself is obtained, the detection information may be sent to a secure server associated with the monitoring system 100, excluding the basic information that identifies an individual such as the subject's name. The server can machine-learn the collected data as teacher data and update the learning model for evaluating the "abnormal state", and can improve the determination accuracy of the abnormal state of the subject. Note that incentives such as a discount on the usage fee of the monitoring system 100 may be given to the subject who has consented to the utilization of the detection information.

[0076] Note that among the sensors installed in the house, there are some that output emergency detection information for notifying an abnormal state of the target person. Examples of the emergency detection information include information that requires emergency attention such as the target person's fall. When the information determination unit 132 determines that the detection information is output from a sensor that notifies an abnormal state of the target person, it can attach a flag to the detection information and preferentially store it in the storage unit 11. This flag is information indicating the priority of the process in which the evaluation unit 134 executes the evaluation using the analysis information of the emergency detection information prior to the evaluation using the analysis information of the detection information other than the emergency detection information. In addition, the processing unit 133 can execute the masking process on the emergency detection information with a flag attached thereto prior to the detection information other than the emergency detection information.

[0077] Note that the information determination unit 132 may determine whether the detection information is emergency detection information by, for example, analyzing image data or audio data as the detection information to detect an abnormality of the target person. For example, when the audio data includes abnormal sounds such as the sound of broken glass, screams such as "help", or screams, the server 10 may determine the audio data as emergency detection information.

[0078] In addition, when it is determined in the information determination unit 132 that the detection information notifies an abnormal state of the target person, that is, when an abnormality flag is attached to the detection information, the notification processing unit 136 can transmit a notification instruction to the disclosure terminal 30. The disclosure terminal 30 can issue an alert to notify the care staff of the abnormal state of the target person by light emission, sound, etc. according to the notification instruction. Note that the alert notifying the abnormality of the target person may be displayed on the disclosure terminal 30 as characters or an image.

[0079] Note that when the information determination unit 132 detects an abnormal state of the target person that requires emergency attention, it may calculate the risk level from the location information, etc. inside the dwelling where the target person is located. When the risk level exceeds a predetermined value, the notification processing unit 136 may automatically transmit, for example, the state of the target person, the location of the dwelling, etc. to the 119 emergency call.

[0080] Further, even if each piece of detection information does not involve urgency, the information determination unit 132 may determine that it is a high risk by combining the detection information from a plurality of sensors. Also in this case, the notification processing unit 136 may output a notification instruction to a notification destination suitable for the response.

[0081] Here, with reference to FIG. 7, the flow of information processing by the monitoring system 100 will be described. Here, an example of evaluating the state of a target person based on the voice data of the target person will be described in detail. It is assumed that the normal range calculation process of the CEM value based on the voice data has been executed in advance. Specifically, the monitoring terminal 20 generates a plurality of voice data from the speech content of employees during a predetermined period that satisfies a predetermined condition, and outputs the plurality of voice data to the server 10. The server 10 performs chaos analysis on the acquired plurality of time-series voice data, and performs the calculation process of each CEM value. Further, the server 10 performs statistical processing of the CEM value and calculates the normal range.

[0082] After the normal range is calculated, in daily life, the monitoring terminal 20 collects the characteristic values of the target person (S101), and transmits the detection information based on the characteristic values to the server 10 (S102). Specifically, the monitoring terminal 20 generates voice data for determination, and outputs the voice data for determination to the server 10.

[0083] Then, the server 10 determines whether the detection information is generated by any of the plurality of sensors, and determines whether the detection information is emergency detection information of the target person (S103). For example, when the voice data includes abnormal sounds such as the sound of broken glass, screams such as "help", and screams, the server 10 may determine the voice data as emergency detection information. If it is emergency detection information (S103, YES), the server 10 outputs a notification instruction to the disclosure terminal 30 (S104). The disclosure terminal 30 performs a notification operation according to the notification instruction (S105).

[0084] If it is NO in S103, the process proceeds to S106. The server 10 determines whether the detection information is information generated by any of the plurality of sensors, and thereby determines whether the detection information is information capable of identifying the target person (S106). If the detection information is information capable of identifying the target person (S106, YES), first, the server 10 executes an analysis process on the detection information to generate analysis information (S107). That is, the server 10 calculates the CEM value from the voice data for determination.

[0085] After executing the analysis process, the server 10 executes a masking process on the detection information (S108). After that, the server 10 evaluates the state of the target person using the analysis information and generates an evaluation result (S109). Specifically, the server 10 can plot the CEM value for determination on a graph showing the normal range to visualize the state of the target person. Also, the server 10 can predict the state of the employee based on the transition of the normal range. Note that for the technique of predicting the state of the target person based on the CEM value, reference can be made to the content described in Japanese Patent Application No. 2023-164146. If it is NO in S106, the masking process in S108 can be skipped and the analysis process and evaluation process can be executed.

[0086] Then, the server 10 transmits the evaluation result including the advice information to the disclosure terminal 30 and the monitoring terminal 20 (S110). For example, when a family member wishes to receive the evaluation result of the target person, the server 10 can create a report on the items for which the target person has given consent and transmit it to the disclosure terminal 30 used by the family member. Note that the server 10 can also make the report in a format according to the request of the disclosure terminal 30. If a problem or sign of abnormality is derived from the state of the target person, the server 10 can transmit a report prompting attention to the disclosure terminal 30 suitable for the care of the target person.

[0087] As described above, according to the embodiment, the monitoring system 100 can collect the characteristic values of the subject generated in daily life in a form in which the subject does not feel stress, and evaluate the state of the subject. Further, after obtaining the analysis information from the detection information based on the characteristic values, by editing the detection information into a state where an individual cannot be identified, it is possible to protect the personal information and privacy of the subject.

[0088] In addition, the care staff can perform appropriate medical actions, assistance actions, nursing actions, talking to the subject, etc. according to the state of the subject. Furthermore, the subject himself / herself can grasp his / her own health condition and improve self-care awareness. Also, through the advice information from the monitoring system 100, it is possible to encourage the subject to change his / her behavior and promote health improvement. According to the present disclosure, it is possible to realize the monitoring system 100 that prevents solitary death in single elderly households and does not let the elderly subject fall into a lonely state.

[0089] In the above example, the program includes a set of instructions (or software code) for causing a computer to perform one or more functions described in the embodiment when loaded into the computer. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, the computer-readable medium or tangible storage medium includes RAM, ROM (read-only memory), flash memory, SSD, or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc, or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage, or other magnetic storage devices. The program may be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, the transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0090] The present disclosure has been described with reference to the embodiments above, but the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure. And each embodiment can be combined with other embodiments as appropriate.

[0091] Each drawing is merely an example for explaining one or more embodiments. Each drawing is not associated with only one specific embodiment, but may be associated with one or more other embodiments. As can be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with the features or steps shown in one or more other drawings to create, for example, embodiments that are not explicitly illustrated or described. Not all of the features or steps shown in any one drawing for explaining exemplary embodiments are necessarily essential, and some features or steps may be omitted. The order of the steps described in any drawing may be changed as appropriate.

[0092] Some or all of the above embodiments can be described as follows in the appended claims, but are not limited thereto. (Appended Claim A1) An acquisition unit that acquires detection information generated based on characteristic values regarding a target person; A processing unit that analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing operation to make the detection information used for generating the analysis information in a state where personal information cannot be specified; An evaluation unit that generates an evaluation result of evaluating the state of the target person using the analysis information and outputs it to a disclosure destination; Comprising An information processing apparatus. (Appended Claim A2) Further comprising an information determination unit that determines whether the detection information is information that can identify the target person based on the detection information; The processing unit performs the processing operation when the detection information is information that can identify the target person. The information processing apparatus described in Supplementary Note A1. (Supplementary Note A3) The detection information includes a plurality of pieces of detection information acquired by a plurality of detection units each capable of acquiring different characteristic values regarding the subject. The information determination unit determines whether the detection information is information capable of identifying the subject by determining in which of the plurality of detection units the detection information is generated. The information processing apparatus described in Supplementary Note A1 or A2. (Supplementary Note A4) When the detection information is emergency detection information requiring emergency handling, the information determination unit generates information indicating the priority of processing so that the evaluation unit executes the evaluation using the analysis information of the emergency detection information earlier than the evaluation using the analysis information of the detection information other than the emergency detection information. The information processing apparatus described in any one of Supplementary Notes A1 to A3. (Supplementary Note A5) The processing unit executes the processing on the emergency detection information earlier than the detection information other than the emergency detection information. The information processing apparatus described in Supplementary Note A4. (Supplementary Note A6) When the detection information is emergency detection information requiring emergency handling, it further includes a notification processing unit that outputs a notification instruction. The information processing apparatus described in Supplementary Note A4 or A5. (Supplementary Note A7) The processing is a process of discarding the detection information used for analysis after generating the analysis information. The information processing apparatus described in any one of Supplementary Notes A1 to A6. (Supplementary Note A8) The characteristic value is the voice of the subject, the processing unit performs chaos analysis on the voice data spoken by the subject, calculates a chaos-theoretic index value, and discards the voice data on which the chaos analysis has been performed. The information processing apparatus described in any one of Supplementary Notes A1 to A7. (Supplementary Note B1) A computer, A process of acquiring detection information generated based on characteristic values related to a target person, a process of analyzing the state of the target person based on the detection information to generate analysis information, and performing a processing operation to make the detection information used for generating the analysis information in a state where personal information cannot be specified, a process of generating an evaluation result of evaluating the state of the target person using the analysis information and outputting it to a disclosure destination, and executing an information processing method. (Appendix C1) A process of acquiring detection information generated based on characteristic values related to a target person, a process of analyzing the state of the target person based on the detection information to generate analysis information, and performing a processing operation to make the detection information used for generating the analysis information in a state where personal information cannot be specified, a process of generating an evaluation result of evaluating the state of the target person using the analysis information and outputting it to a disclosure destination, causing a computer to execute a program.

[0093] Some or all of the elements (for example, configurations and functions) described in Appendices A2 to A8 subordinate to Appendix A1 (device) may be subordinate to Appendices B1 (method) and C1 (program) in the same subordinate relationship as Appendices A2 to A8. Some or all of the elements described in any appendix may be applied to various hardware, software, recording means for recording software, systems, and methods.

Explanation of Reference Numerals

[0094] 1 Information processing apparatus 2 Acquisition unit 3 Processing unit 4 Evaluation unit 10 Server 11 Storage unit 111 Program 112 Target person information DB 113 Medical information DB 114 Nursing care information DB 115 Accident information DB 12 Communication Unit 13 Processing Unit 131 Acquisition Unit 132 Information Judgment Unit 133 Processing and Processing Unit 134 Evaluation Unit 135 Transmission Processing Unit 136 Notification Processing Unit 20 Monitoring Terminal 21 Sound Collection Unit 22 Imaging Unit 23 Memory Unit 24 Communication Unit 25 Input / Output Unit 26 Processing Unit 261 Generation Processing Unit 262 Transmission Processing Unit 27 Measurement Unit 30 Disclosure Terminal 100 Monitoring System 101 Information Processing System 102 Acquisition Unit 103 Processing and Processing Unit 104 Evaluation Unit

Claims

1. An acquisition unit that acquires detection information generated based on characteristic values related to a target person; A processing unit that analyzes the state of the target person based on the detection information to generate analysis information, and performs a processing operation to make the detection information used for generating the analysis information in a state where personal information cannot be specified; An evaluation unit that generates an evaluation result obtained by evaluating the state of the target person using the analysis information and outputs the evaluation result to a disclosure destination; An information processing apparatus comprising: An information processing apparatus.

2. The information processing apparatus further includes an information determination unit that determines whether or not the detection information is information that can identify the target person based on the detection information, wherein the processing unit performs the processing operation when the detection information is information that can identify the target person. The information processing apparatus according to claim 1.

3. The detection information includes a plurality of pieces of detection information obtained by a plurality of detection units each capable of obtaining different characteristic values related to the target person, and the information determination unit determines whether or not the detection information is information that can identify the target person by determining in which of the plurality of detection units the detection information is generated. The information processing apparatus according to claim 2.

4. When the detection information is emergency detection information that requires emergency attention, the information determination unit generates information indicating a processing priority so that the evaluation unit performs an evaluation using the analysis information of the emergency detection information prior to an evaluation using the analysis information of the detection information other than the emergency detection information. The information processing apparatus according to claim 3.

5. The processing unit performs the processing operation on the emergency detection information prior to performing the processing operation on the detection information other than the emergency detection information. The information processing apparatus according to claim 4.

6. The information processing apparatus further includes a notification processing unit that outputs a notification instruction when the detection information is emergency detection information that requires emergency attention. The information processing apparatus according to claim 4.

7. The processing operation is a process of discarding the detection information used in the analysis after generating the analysis information. The information processing apparatus according to claim 1.

8. The characteristic value is the voice of the target person, and the processing unit performs chaos analysis on voice data spoken by the target person to calculate a chaos theory index value, and discards the voice data on which the chaos analysis has been performed. The information processing apparatus according to claim 1.

9. A computer performs: a process of acquiring detection information generated based on characteristic values related to a target person; A process of analyzing the state of the target person based on the detection information to generate analysis information, and performing a processing of making the detection information used for generating the analysis information in a state where personal information cannot be specified; A process of generating an evaluation result of evaluating the state of the target person using the analysis information and outputting it to a disclosure destination; executing An information processing method.

10. A process of acquiring detection information generated based on characteristic values related to a target person; A process of analyzing the state of the target person based on the detection information to generate analysis information, and performing a processing of making the detection information used for generating the analysis information in a state where personal information cannot be specified; A process of generating an evaluation result of evaluating the state of the target person using the analysis information and outputting it to a disclosure destination; causing a computer to execute A program.

Images