State estimation device, state estimation system, and method for controlling state estimation device

Abstract

To provide a state estimation device that can accurately estimate the state of a person to be observed.SOLUTION: A state estimation device comprises: an input unit that receives input of estimation material information used for estimating the state of a person to be observed; a control unit that generates estimation information obtained by estimating the state of the person to be observed by using an estimation model on the basis of the estimation material information received by the input unit; and an output unit that outputs the estimation information generated by the control unit. The control unit acquires difference information indicating the difference between estimation history information obtained through estimation in advance by using the estimation model on the basis of the past estimation material information of the person to be observed and actual information indicating the actual state of the person to be observed, and when determining that the difference information falls out of a predetermined range, changes the estimation model to a corrected estimation model obtained by correcting the estimation model according to the difference information before generating the estimation information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a state estimation device, a state estimation system, and a control method for a state estimation device. [Background technology]

[0002] An abnormality detection device that determines whether or not an occupant has an abnormality based on an estimated value has been disclosed (Patent Document 1). The abnormality detection device disclosed in Patent Document 1 can correct the determination conditions used to determine whether or not an abnormality exists using an estimated value based on an actual measurement value. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-36152 Summary of the Invention [Problem to be solved by the invention]

[0004] Patent Document 1 does not estimate the state of an observed person by taking into consideration the discrepancy between the estimated result that occurs for each observed person, such as a passenger, and actual information that indicates the actual result. The object of the present disclosure is to provide a state estimation device and a state estimation system that can accurately estimate the state of an observed person. [Means for solving the problem]

[0005] A state estimation device according to one aspect of the present disclosure includes an input unit that accepts input of estimation material information used to estimate the state of an observed person, a control unit that generates estimation information that estimates the state of the observed person using an estimation model based on the estimation material information accepted by the input unit, and an output unit that outputs the estimation information generated by the control unit, wherein the control unit acquires difference information that indicates the difference between estimated history information obtained by prior estimation using the estimation model based on the observed person's past estimation material information and actual information that indicates the observed person's actual state, and if it determines that the difference information is outside a predetermined range, it changes the estimation model to a modified estimation model that is modified in accordance with the difference information, and generates the estimation information.

[0006] A state estimation system according to one aspect of the present disclosure includes an input unit that accepts input of estimation material information used to estimate a state of an observed person, a control unit that generates estimation information that estimates the state of the observed person using an estimation model based on the estimation material information accepted by the input unit, and an output unit that outputs the estimation information generated by the control unit, wherein the control unit acquires difference information that indicates a difference between estimation history information obtained by prior estimation using the estimation model based on past estimation material information of the observed person and actual information that indicates an actual state of the observed person, and when it is determined that the difference information is outside a predetermined range, the state estimation system changes the estimation model to a modified estimation model that is modified in accordance with the difference information to generate the estimation information, wherein the difference information is associated with identification information of each of a plurality of observed people, and the control unit accepts the identification information of each of the observed people and acquires the difference information corresponding to the identification information, and the state estimation system includes: a personal authentication server that authenticates the observed people and transmits identification information of the observed people that are successfully authenticated to the state estimation device.

[0007] A control method for a state estimation device according to one aspect of the present disclosure includes the steps of: accepting input of estimation material information used to estimate a state of an observed person; generating estimation information that estimates the state of the observed person using an estimation model based on the estimation material information accepted in the step of accepting input of the estimation material information; and outputting the estimation information generated in the step of generating estimation information. The step of generating estimation information includes acquiring difference information that indicates a difference between estimation history information obtained by prior estimation using the estimation model based on past estimation material information of the observed person and actual information that indicates an actual state of the observed person, and, if it is determined that the difference information is outside a predetermined range, changing the estimation model to a modified estimation model that is modified in accordance with the difference information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram illustrating an example of a configuration of a main part of a state estimation device according to a first embodiment of the present disclosure. [Figure 2] 4 is a flowchart illustrating an example of a state estimation method performed by the state estimation device according to the first embodiment of the present disclosure. [Figure 3] FIG. 10 is a block diagram showing a configuration of a main part of a state estimation system according to a second embodiment of the present disclosure. [Figure 4] 10 is a table showing an example of difference information stored in a storage unit of a state estimation device according to a second embodiment of the present disclosure. [Figure 5] 10 is a table showing an example of difference information stored in a storage unit of a state estimation device according to a second embodiment of the present disclosure. [Figure 6] 10 is a table showing an example of difference information stored in a storage unit of a state estimation device according to a second embodiment of the present disclosure. [Figure 7] 10 is a graph showing an example of pulse information obtained by dividing blood flow information obtained from a subject into beat-by-beat portions. [Figure 8] 8 is a graph showing an example of first-order differential pulse information obtained by first-order differentiation of the pulse information shown in FIG. 7. [Figure 9]8 is a graph showing an example of second-order differential pulse information obtained by second-order differentiation of the pulse information shown in FIG. 7. [Figure 10] FIG. 10 is a diagram showing an example of an estimated blood glucose level output by the state estimation device according to the second embodiment of the present disclosure. [Figure 11] FIG. 10 is a diagram showing an example of an estimated blood glucose level output by the state estimation device according to the second embodiment of the present disclosure. [Figure 12] FIG. 10 is a diagram showing an example of an estimated blood glucose level output by the state estimation device according to the second embodiment of the present disclosure. [Figure 13] 10 is a flowchart illustrating an example of a state estimation method performed by a state estimation device according to a second embodiment of the present disclosure. [Figure 14] FIG. 10 is a block diagram showing an example of a configuration of a main part of a state estimation system according to a first modified example of the second embodiment of the present disclosure. [Figure 15] FIG. 10 is a diagram showing an example of an input screen for inputting update difference information to the state estimation device in the state estimation system according to a first modified example of the second embodiment of the present disclosure. [Figure 16] FIG. 10 is a diagram showing an example of an input screen for inputting update difference information to the state estimation device in the state estimation system according to a first modified example of the second embodiment of the present disclosure. [Figure 17] FIG. 10 is a block diagram illustrating an example of a configuration of a main part of a state estimation system according to a third embodiment of the present disclosure. [Figure 18] 10 is a flowchart illustrating an example of a state estimation method performed by a state estimation device according to a third embodiment of the present disclosure. [Figure 19] FIG. 10 is a block diagram illustrating an example of a configuration of a main part of a state estimation system according to a fourth embodiment of the present disclosure. [Figure 20] 10 is a graph showing an example of pulse information obtained by dividing blood flow information obtained from a subject into beat-by-beat portions. [Figure 21] 10 is a flowchart illustrating an example of a state estimation method performed by a state estimation device according to a fourth embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments and modifications of the present disclosure will be described with reference to the drawings. Note that, hereinafter, identical or corresponding components will be designated by the same reference numerals throughout the drawings, and redundant descriptions thereof will be omitted. Furthermore, the embodiments and modifications described below are merely examples of the present disclosure, and the present disclosure is not limited to the embodiments and modifications. Various modifications other than these embodiments and modifications are possible depending on the design, etc., as long as they do not deviate from the technical concept of the present disclosure.

[0010] (First embodiment) A configuration of a state estimating device 1 according to a first embodiment of the present disclosure will be described with reference to Fig. 1. Fig. 1 is a block diagram showing an example of a configuration of a main part of the state estimating device 1 according to the first embodiment of the present disclosure.

[0011] The state estimation device 1 is a device that outputs estimation result information 21 that estimates the state of the observed person 2 based on estimation material information 20 acquired from the observed person 2. As shown in FIG. 1 , the state estimation device 1 is configured to include an input unit 10, a control unit 11 (estimation unit), an output unit 12, and a storage unit 13.

[0012] The estimation material information 20 is information used to estimate the state of the observed person 2, and is information that can be estimated without directly measuring the state of the observed person 2. For example, when estimating the pulse rate as the state of the observed person 2, the estimation material information 20 can be an image of the face of the observed person 2 taken with an imaging device such as a camera, or an image of the fingertips or palm. When estimating the blood pressure or body temperature as the state of the observed person 2, the estimation material information 20 can be an image of the face of the observed person 2 taken with an imaging device. When estimating the blood glucose level as the state of the observed person 2, the estimation material information 20 can be a video of the blood flow in the fingers of the observed person 2 taken with an imaging device. When estimating the emotion (joy, anger, sadness, or happiness) as the state of the observed person 2, the estimation material information 20 can be an image of the face of the observed person 2 taken with an imaging device, the volume, pitch, or speaking rate of the observed person 2, etc. Note that in this specification, the term "image" includes not only still images but also moving images.

[0013] The estimation result information 21 (estimated information) is information indicating the results of estimating the state of the observed person 2, and examples include estimated values ​​such as blood pressure, body temperature, and blood sugar level, or information indicating the estimated emotions of the observed person 2 (e.g., joy, anger, sadness, or happiness).

[0014] The input unit 10 accepts input of estimation material information 20, and the estimation material information 20 accepted by the input unit 10 is transmitted to the control unit 11. If the estimation material information 20 is, for example, a face image or a finger image of the observed person 2, the input unit 10 can be an input interface that accepts a video signal from an imaging device (not shown). If the estimation material information 20 is, for example, the voice of the observed person 2, the input unit 10 can be an input interface that accepts a voice signal from a microphone (not shown). If the state estimation device 1 is configured to include an imaging device or a microphone as an integrated unit, the input unit 10 can be, for example, an imaging device or a microphone.

[0015] The control unit 11 performs various controls on the various units included in the state estimation device 1, and is configured by a processor such as a CPU (Central Processing Unit) or a GPU (Graphic Processing Unit).

[0016] The control unit 11 includes, as a functional block, an estimation unit 30. When the control unit 11 is, for example, a CPU, the estimation unit 30 can be realized by the CPU reading out a program stored in the storage unit 13 into a memory (not shown) and executing the program.

[0017] The estimation unit 30 generates estimation result information 21 by estimating the state of the observed person 2 using an estimation model 23 based on the estimation material information 20 received by the input unit 10. The generated estimation result information 21 is output to the outside of the state estimation device 1 via the output unit 12. When the estimation unit 30 determines that the difference information 22 is outside a predetermined range, the estimation unit 30 changes the estimation model 23 to a modified estimation model 24 modified in accordance with the difference information, thereby generating the estimation result information 21. A method for generating the estimation result information 21 by the estimation unit 30 will be described in detail below.

[0018] The difference information 22 is information indicating the difference between the estimation result (estimation history information) obtained in advance using the estimation model 23 based on the past estimation material information 20 acquired from the observed person 2, and the actual information indicating the actual state of the observed person 2. The actual information of the observed person 2 can be, for example, actual measured values ​​such as blood pressure, body temperature, and blood sugar level obtained from the observed person 2 using measuring equipment or the like. Alternatively, it can be information indicating the emotions of the observed person 2 obtained by directly observing the observed person 2.

[0019] The estimation model 23 is a standard model used when the state estimation device 1 estimates the state of the observed person 2. The estimation model 23 is used when the difference information 22 of the observed person 2 is within a predetermined range. On the other hand, the modified estimation model 24 used when the difference information 22 of the observed person 2 is larger than the predetermined range is referred to as the first modified estimation model 24a, and the modified estimation model 24 used when the difference information 22 of the observed person 2 is smaller than the predetermined range is referred to as the second modified estimation model 24b. The modified estimation models 24 include the first modified estimation model 24a and the second modified estimation model 24b.

[0020] When the estimated historical information is obtained as an estimated value and the actual information is obtained as an actual measurement value, the difference information 22 is a difference value indicating the difference between the measured value and the estimated value. Alternatively, the difference information 22 can be information derived from the difference between the measured value and the estimated value, which indicates the tendency of the magnitude relationship of the estimated value relative to the actual measurement value.

[0021] Furthermore, when the estimated history information and actual information are obtained as information indicating emotions, the difference information 22 is the difference between a standard threshold for distinguishing between different emotions based on the estimated material information 20 (e.g., the volume of the voice) and a threshold that can actually distinguish between the different emotions of the observed person 2.

[0022] The storage unit 13 is a recording medium capable of storing various data, programs, etc. The storage unit 13 includes an area for storing various programs, an area for storing data used in the various programs, an area into which the various programs are loaded, and an area used when the various programs are executed. The storage unit 13 can be configured, for example, with semiconductor memory such as a read-only memory (ROM) or a random access memory (RAM), a hard disk drive (HDD), a solid state drive (SDD), a programmable logic circuit, etc. The storage unit 13 stores the difference information 22, the estimation model 23, and the corrected estimation model 24 described above.

[0023] The difference information 22 may be acquired from an external server (not shown). Alternatively, the storage unit 13 may store estimation history information indicating the estimation result of the state of the observed person 2 generated using the estimation model 23 based on the past estimation material information 20 of the observed person 2, and actual information of the observed person 2, and the control unit 11 may calculate the difference information 22 from the estimation history information and the actual information.

[0024] The output unit 12 may be an output interface that outputs a video signal to a display device (not shown) when the estimation result information 21 is output as a video. Furthermore, the output unit 12 may be an output interface that outputs an audio signal to a speaker (not shown) when the estimation result information 21 is output as audio. Furthermore, the output unit 12 may be an output interface that outputs print data to a printing device (not shown) when the estimation result information 21 is printed and output. Furthermore, in a configuration in which the state estimation device 1 is integrally equipped with a display device, a speaker, or a printing device, the output unit 12 may be, for example, a display device, a speaker, or a printing device.

[0025] (State estimation method) Next, a state estimation method performed by the state estimation device 1 according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a flowchart showing an example of the state estimation method performed by the state estimation device 1 according to the first embodiment of the present disclosure.

[0026] First, when the state estimation device 1 is powered on and an instruction is given to output the estimation result information 21 of the observed person 2, the estimation unit 30 in the state estimation device 1 acquires the estimation material information 20 of the observed person 2 via the input unit 10 (step S11). Furthermore, the estimation unit 30 acquires the difference information 22 from the storage unit 13 (step S12). Note that step S12 may be executed before step S11, and the order of execution of steps S11 and S12 is arbitrary.

[0027] Next, the estimation unit 30 determines whether the difference information 22 acquired in step S12 is within a predetermined range (step S13). Note that the predetermined range is, for example, a range in which the magnitude of the difference information exceeds ±20 mg / dl for blood glucose levels, or a range in which the magnitude of the difference information exceeds ±20 mmHg for blood pressure.

[0028] Here, if it is determined that the difference information 22 is within a predetermined range ("Yes" in step S13), the state of the observed person 2 is estimated using the estimation model 23 (step S14).

[0029] On the other hand, if it is determined that the difference information 22 is outside the predetermined range ("No" in step S13), the state of the observed person 2 is estimated (step S15) using a corrected estimation model 24 selected based on the difference information 22. The corrected estimation model 24 selected in step S15 may be a first corrected estimation model 24a or a second corrected estimation model 24b.

[0030] If the value of the actual information indicating the actual state of the observed person 2 is greater than the value of the estimation result estimated by the estimation model 23, the first modified estimation model 24a is selected, which obtains a value that is smaller by the difference than the estimation result obtained when estimating with the estimation model 23 based on the estimation material information 20.

[0031] Furthermore, if the value of the actual information indicating the actual state of the observed person 2 is smaller than the estimation result estimated by the estimation model 23, the second modified estimation model 24b is selected, which obtains a value that is larger by the difference than the estimation result obtained when estimating using the estimation model 23 based on the estimation material information 20.

[0032] The estimation unit 30 generates the estimation result information 21 using the estimation model 23 or the corrected estimation model 24 based on the estimation material information 20, and then outputs the generated estimation result information 21 to the outside via the output unit 12 (step S16).

[0033] As described above, in the state estimation device 1, the estimation unit 30 in the control unit 11 can generate the estimation result information 21 based on the estimation material information 20 acquired from the observed person 2 and taking the difference information 22 into consideration.

[0034] Therefore, when the state estimation device 1 estimates the state of the observed person 2 using the estimation model 23, even if the estimation result is always larger or smaller than the actual information indicating the actual state, it is possible to generate estimation result information 21 that is corrected to be appropriate. Therefore, even if there are individual differences in the estimation results using the estimation model 23 for each observed person 2, it is possible to obtain estimation result information 21 with high accuracy.

[0035] Therefore, the state estimating device 1 can estimate the state of the observed person 2 with high accuracy.

[0036] (Second embodiment) A condition estimation system 100 according to a second embodiment of the present disclosure will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of a main part of the condition estimation system 100 according to the second embodiment of the present disclosure. Note that the condition estimation system 100 according to the second embodiment will be described using blood glucose levels as an example of information indicating the condition of the observed person 2.

[0037] The state estimation system 100 according to the second embodiment includes a state estimation device 1 and a personal authentication server 40.

[0038] The state estimation device 1 according to the second embodiment differs from the state estimation device 1 according to the first embodiment in that it acquires subject identification information 25 of the subject 2 from an external personal authentication server 40. Furthermore, in the state estimation device 1 according to the second embodiment, estimation material information 20 is blood flow information of the subject 2, and estimation result information 21 is an estimated value of the blood glucose level. In other respects, the state estimation device 1 according to the second embodiment is similar to the state estimation device 1 according to the first embodiment, and therefore similar components are denoted by similar reference numerals and their description will be omitted.

[0039] The state estimation device 1 according to the first embodiment is a device used exclusively for the observed person 2, whereas the state estimation device 1 according to the second embodiment is a device shared by a plurality of observed people 2. For this reason, the state estimation device 1 according to the second embodiment needs to identify the observed person 2 whose state is to be estimated, and generate estimation result information 21 using difference information 22 provided according to the identified observed person 2.

[0040] Therefore, in the state estimation device 1 according to the second embodiment, the estimation unit 30 acquires observed person identification information 25 for identifying the observed person 2 from the personal authentication server 40, and generates estimation result information 21 using difference information 22 corresponding to the observed person 2 identified by the observed person identification information 25. Note that the observed person identification information 25 can be, for example, an ID that can identify the observed person 2.

[0041] The personal authentication server 40 is a server that authenticates the observed person 2 whose state is to be estimated by the state estimation device 1, and transmits observed person identification information 25 (identification information) of the observed person 2 who has been successfully authenticated to the state estimation device 1. The personal authentication server 40 may accept input such as a password from the observed person 2 and perform authentication processing, or may acquire a facial image of the observed person 2 and perform authentication processing based on the acquired facial image.

[0042] In the state estimating device 1, the estimating unit 30 receives blood flow information (estimation material information 20) of the observed person 2 via the input unit 10. The estimating unit 30 also receives observed person identification information 25 from the personal authentication server 40.

[0043] The estimation unit 30 then reads out the difference information 22 corresponding to the observed person identification information 25 from the storage unit 13, and selects the estimation model 23 or the modified estimation model 24 in accordance with the difference information 22. The estimation unit 30 then uses the selected estimation model 23 or modified estimation model 24 to generate an estimated blood glucose level as estimation result information 21 based on the received blood flow information.

[0044] The difference information 22 stored in the storage unit 13 may be, for example, a table showing a correspondence relationship between the ID of the observed person 2 and the difference, as shown in FIG. 4. FIG. 4 is a table showing an example of the difference information 22 stored in the storage unit 13 by the state estimation device 1 according to the second embodiment of the present disclosure. As shown in FIG. 4, for example, the difference information 22 stores the ID of observed person A and the difference (-22 mg / dl) between the estimated blood glucose level generated using the estimation model 23 based on the past blood flow information of observed person A and the actual blood glucose level obtained by measurement of observed person A, in association with each other. Furthermore, the ID of observed person B and the difference (0 mg / dl) between the estimated blood glucose level generated using the estimation model 23 based on the past blood flow information of observed person B and the actual blood glucose level obtained by measurement of observed person B, in association with each other, are also stored.

[0045] In the difference information 22, the difference associated with the observed person 2 may be configured to be updated each time an estimated blood glucose level is calculated based on the blood flow information of the observed person 2. The updated difference value may be the difference between the estimated blood glucose level calculated based on the blood flow information of the observed person 2 using the estimation model 23 and the actual measured blood glucose level. Alternatively, the updated difference value may be the average value of the difference between the estimated blood glucose level previously estimated using the estimation model 23 and the actual measured blood glucose level, and the difference between the estimated blood glucose level currently estimated using the estimation model 23 and the actual measured blood glucose level. For example, if the difference value calculated previously was −21 mg / dl and the difference value calculated this time is, for example, −23 mg / dl, the value updated as the difference information 22 may be −22 mg / dl, which is the average value of the two values. Alternatively, the value updated as the difference information 22 may be −23 mg / dl, which is the minimum value of the two values.

[0046] 5, the difference information 22 can also be table information in which the ID of the observed person 2, an estimated value obtained by estimating based on the blood flow information of the observed person 2 using the estimation model 23, the estimated time when this estimated value was obtained, and the actual blood glucose value obtained by actually measuring the observed person 2 are associated with each other. The actual blood glucose value can be the blood glucose level measured on the observed person 2 at the timing closest to the estimated time. FIG. 5 is a table showing an example of the difference information 22 stored in the storage unit 13 by the state estimation device 1 according to the second embodiment of the present disclosure.

[0047] In this way, the difference information 22 may be a table showing the correspondence between estimated values ​​and actual measured values ​​associated with each observed person 2, rather than the difference itself.

[0048] The actual measurement value included in the difference information 22 may be an actual measurement value obtained at the same time as the estimated value is calculated, or may be an actual measurement value obtained at the timing closest to the estimated time when the estimated value is calculated.

[0049] 6, the difference information 22 may be a table showing a correspondence relationship between the ID of the observed person 2 and information indicating the tendency of the magnitude relationship of the estimated value with respect to the actual measured value, which information is derived from the difference between the blood glucose level estimation result estimated using a standard estimation model 23 based on the blood flow information of the observed person 2 and the actual blood glucose level obtained by measurement of the observed person 2. Fig. 6 is a table showing an example of the difference information 22 stored in the storage unit 13 by the state estimation device 1 according to the second embodiment of the present disclosure.

[0050] Information indicating the tendency of the magnitude relationship of the estimated value relative to the actual measured value may be, for example, "estimated low" if the estimated blood glucose value is smaller than a predetermined range based on the actual measured value, "valid" if the estimated blood glucose value is within a predetermined range based on the actual measured value, or "estimated high" if the estimated blood glucose value is larger than the predetermined range based on the actual measured value.

[0051] The state estimation device 1 is configured to execute authentication processing of the observed person 2 using the personal authentication server 40, and transmit the observed person identification information 25 of the observed person 2 who has been successfully authenticated to the state estimation device 1. However, instead of this personal authentication server 40, the state estimation device 1 may be configured to include an authentication unit and execute authentication processing of the observed person 2. However, a configuration in which authentication processing of the observed person 2 is executed by the personal authentication server 40 provided outside the state estimation device 1 is more advantageous in terms of security, as it can prevent leakage of personal information.

[0052] The estimation model 23 stored in the storage unit 13 can be created, for example, as follows: That is, blood flow information obtained from the subject 2 is separated into pulse information (pulse waveforms) for each beat, as shown in Fig. 7. Each piece of separated pulse information is further differentiated to obtain first-order differential pulse information shown in Fig. 8 and second-order differential pulse information shown in Fig. 9.

[0053] 7 is a graph showing an example of pulse information obtained by dividing the blood flow information obtained from the observed person 2 into beat-by-beat sections. FIG. 8 is a graph showing an example of first-order differential pulse information obtained by first-order differentiation of the pulse information shown in FIG. 7. FIG. 9 is a graph showing an example of second-order differential pulse information obtained by second-order differentiation of the pulse information shown in FIG. 7. In the graphs shown in FIGS. 7, 8, and 9, the horizontal axis represents time, and the vertical axis represents the amount of detection detected from the observed person 2.

[0054] Then, feature quantities are obtained for feature points of the waveforms of the pulse information shown in Fig. 7, the first-order differential pulse information shown in Fig. 8, and the second-order differential pulse information shown in Fig. 9. Examples of feature quantities for the feature points include the first maximum value in each of the pulse information, the first-order differential pulse information, and the second-order differential pulse information, the difference between the first minimum value and the first maximum value, and the time from the starting point to the first maximum value. A large amount of data correlating the feature quantities of multiple feature points with actual measured blood glucose levels is prepared, and machine learning is performed using the prepared data to create estimation model 23.

[0055] The first modified estimation model 24a can be created in the same manner as the estimation model 23 described above, for example, by learning more pulse information obtained from each of the subjects 2 whose blood glucose levels are considered to be slightly higher or higher than the normal range.

[0056] The second modified estimation model 24b can be created in the same manner as the above-mentioned estimation model 23, for example, by learning more pulse information obtained from each of the subjects 2 whose blood glucose levels are considered to be slightly lower or lower than the normal range.

[0057] In the above example, the first modified estimation model 24a and the second modified estimation model 24b are generated by machine learning based on the feature amounts of the waveform feature points of the pulse information, the first-order differential pulse information, and the second-order differential pulse information, but the present invention is not limited to this. For example, the first modified estimation model 24a may be an estimation model that can obtain an estimated value obtained by subtracting a predetermined value from the estimated value of the blood glucose level estimated using the estimation model 23, and the second modified estimation model 24b may be an estimation model that can obtain an estimated value obtained by adding a predetermined value to the estimated value of the blood glucose level estimated using the estimation model 23.

[0058] The estimation model 23 and the corrected estimation model 24 may be created by the control unit 11 included in the state estimation device 1, or may be created by an external server (not shown), and the state estimation device 1 may acquire them from the external server and store them in the memory unit 13.

[0059] In the state estimation device 1, when the estimation unit 30 receives blood flow information via the input unit 10, it calculates feature quantities of waveform feature quantities of each of the pulse information, first-order differential pulse information, and second-order differential pulse information from the blood flow information. The estimation unit 30 then calculates an estimated blood glucose level from the calculated feature quantities using the estimation model 23 or corrected estimation model 24 selected based on the difference information 22. The estimation unit 30 outputs the calculated estimated blood glucose level to the outside via the output unit 12.

[0060] For example, when the estimated value of the blood glucose level is output to an external display device via the output unit 12, the estimated value of the blood glucose level can be displayed on the display screen of the display device, for example, as shown in Fig. 10 to Fig. 12, respectively. Fig. 10 to Fig. 12 are diagrams showing examples of estimated values ​​of the blood glucose level output by the state estimation device 1 according to the second embodiment of the present disclosure. Fig. 10 shows an example of a display when the estimated value of the blood glucose level is obtained using the second modified estimation model 24b, Fig. 11 shows an example of a display when the estimated value of the blood glucose level is obtained using the estimation model 23, and Fig. 12 shows an example of a display when the estimated value of the blood glucose level is obtained using the first modified estimation model 24a.

[0061] 10, when the estimated blood glucose level of the observed person A is obtained using the estimation model 23, the estimated value is lower than the actually measured value. For this reason, an upward arrow is displayed in the lower right corner of the display screen on which the estimated blood glucose level is displayed, indicating that the second modified estimation model 24b has been used to obtain a higher estimated value than the estimated value obtained using the estimation model 23.

[0062] For subject B shown in Fig. 11, when the estimated blood glucose level is calculated using estimation model 23, the value is the same as or close to the actually measured value. For this reason, no arrow is displayed in the lower right corner of the display screen where the estimated blood glucose level is displayed.

[0063] 12, when the estimated blood glucose level of subject C is obtained using estimation model 23, the estimated value is higher than the actually measured value. For this reason, a downward arrow is displayed in the lower right corner of the display screen on which the estimated blood glucose level is displayed, indicating that the first modified estimation model 24a has been used to obtain a lower estimated value than the estimated value obtained using estimation model 23.

[0064] As shown in FIGS. 10 to 12, instruction buttons for "record," "cancel," and "reset" are displayed below the estimated blood glucose value. For example, when the "record" instruction button is selected, the estimated blood glucose value displayed on the display screen is recorded on a recording medium or the like. When the "cancel" instruction button is selected, the estimated blood glucose value is canceled. When the "reset" instruction button is selected, the state estimation device 1 is instructed to generate an estimated blood glucose value again.

[0065] As described above, in the state estimation device 1 according to the second embodiment, the display screen showing the estimated blood glucose value displays whether the estimated blood glucose value was generated using estimation model 23, the first modified estimation model 24a, or the second modified estimation model 24b.

[0066] (State estimation method) The state estimation device 1 having the above configuration can implement a state estimation method for the observed person 2, as shown in Fig. 13. Fig. 13 is a flowchart showing an example of the state estimation method performed by the state estimation device 1 according to the second embodiment of the present disclosure.

[0067] First, when the state estimation device 1 is powered on and an instruction is given to output estimation result information 21 of the state of the observed person 2, the estimation unit 30 in the state estimation device 1 acquires estimated material information 20 (blood flow information) of the observed person 2 via the input unit 10 (step S21). Furthermore, the estimation unit 30 acquires observed person identification information 25 of the observed person 2 from the personal authentication server 40 (step S22). The estimation unit 30 acquires difference information 22 corresponding to the observed person 2 from the storage unit 13 based on the observed person identification information 25 acquired in step S22 (step S23). Note that steps S22 and S23 may be executed before step S21 is executed.

[0068] The subsequent processing from step S24 to step S27 shown in FIG. 13 is similar to the processing from step S13 to step S16 shown in FIG. 2, and therefore a description thereof will be omitted.

[0069] As described above, in the state estimation device 1, the estimation unit 30 in the control unit 11 can generate the estimation result information 21 based on the estimation material information 20 acquired from the observed person 2 and taking the difference information 22 into consideration.

[0070] Therefore, when the state estimation device 1 estimates the state of the observed person 2 using the estimation model 23, even if the estimation result is always larger or smaller than the actual information indicating the actual state, it is possible to generate estimation result information 21 that is corrected to be appropriate. Therefore, even if there are individual differences in the estimation results using the estimation model 23 for each observed person 2, it is possible to obtain estimation result information 21 with high accuracy.

[0071] Therefore, the state estimating device 1 can estimate the state of the observed person 2 with high accuracy.

[0072] (First Modification) Next, a configuration of a state estimation system 100 according to a first modified example of the second embodiment of the present disclosure will be described with reference to Fig. 14. Fig. 14 is a block diagram showing an example of a configuration of a main part of the state estimation system 100 according to the first modified example of the second embodiment of the present disclosure.

[0073] The state estimation system 100 according to the first modified example of the second embodiment differs from the state estimation system 100 according to the second embodiment in that the difference information 22 stored in the storage unit 13 can be changed to update difference information input from outside.

[0074] More specifically, in the state estimation system 100 according to the first modified example of the second embodiment, the state estimation device 1 further includes a difference information input unit 14, and the control unit 11 further includes, as a functional block, a difference information update unit 31. When the control unit 11 is, for example, a CPU, the CPU can realize the difference information update unit 31 by reading a program stored in the storage unit 13 into a memory (not shown) and executing the program.

[0075] As for other configurations, the state estimation system 100 according to the first modified example of the second embodiment has a similar configuration to the state estimation system 100 according to the second embodiment, and therefore similar components are denoted by the same reference numerals, and the description thereof will be omitted.

[0076] The difference information input unit 14 receives input of update difference information and an instruction to update the difference information 22 from the outside, and the update difference information and the instruction to update the difference information 22 received by the difference information input unit 14 are transmitted to the control unit 11. For example, the difference information input unit 14 can be an input interface that receives the update difference information and the instruction to update the difference information 22 from an input device (not shown). Furthermore, if the state estimation device 1 is configured to be integrally equipped with an input device, the difference information input unit 14 can be an input device such as a touch panel.

[0077] More specifically, for example, if the external input device or the difference information input unit 14 is a touch panel, a table showing the difference information 22 stored in the storage unit 13 is displayed on the input screen of the touch panel, as shown in Fig. 15. In addition, in this table, a change button is displayed in parallel with the difference information corresponding to each observed person 2. Fig. 15 is a diagram showing an example of an input screen for inputting update difference information to the state estimation device 1 in the state estimation system 100 according to a first modified example of the second embodiment of the present disclosure.

[0078] Here, when the operator of the state estimating device 1 changes the information indicating the difference for the observed person B, for example, the operator selects the change button displayed in parallel with the difference corresponding to the observed person B.

[0079] When a change button is selected, a pull-down menu for updating the difference associated with the selected change button is displayed on the input screen, as shown in Fig. 16. In the example shown in Figs. 15 and 16, in addition to information indicating the difference that was deemed "appropriate" before the change, the pull-down menu displays options for "lower estimated value" and "higher estimated value." Note that Fig. 16 is a diagram showing an example of an input screen for inputting update difference information to the state estimation device 1 in the state estimation system 100 according to a first modified example of the second embodiment of the present disclosure.

[0080] When the operator issues an instruction to update the difference information 22 by selecting an appropriate option from the options displayed in the pull-down menu on the input screen, the state estimation device 1 changes the difference information included in the difference information 22 to information of the selected option. That is, in the state estimation device 1, the difference information update unit 31 changes the difference information included in the difference information 22 stored in the storage unit 13 to new difference information selected on the input screen, based on the instruction to update the difference information 22.

[0081] Here, three types of difference information, "low estimated value," "reasonable," and "high estimated value," are set as information on the difference associated with each observed person 2, but the information is not limited to these three and may be more than three. Furthermore, the information on the difference is not limited to the above-mentioned character expression and may be a numerical value.

[0082] (Third embodiment) Next, a state estimation system 200 according to a third embodiment of the present disclosure will be described with reference to Fig. 17. Fig. 17 is a block diagram showing an example of a configuration of a main part of the state estimation system 200 according to the third embodiment of the present disclosure.

[0083] The state estimation system 100 according to the second embodiment has a configuration in which the difference information 22 is stored in the storage unit 13 included in the state estimation device 1. In contrast, the state estimation system 200 according to the third embodiment differs in that it further includes an information management server 60 that stores the difference information 22, and is configured so that the state estimation device 1 acquires the difference information 22 from the information management server 60. In other respects, the state estimation system 200 according to the third embodiment has the same configuration as the state estimation system 100 according to the second embodiment, and therefore similar components are denoted by similar reference numerals and their description will be omitted.

[0084] The information management server 60 is communicably connected to the state estimation device 1, and includes a server input unit 61, a server control unit 62, and a server storage unit 63, as shown in FIG.

[0085] The server input unit 61 receives the difference information 22 from the outside, and the difference information 22 received by the server input unit 61 is transmitted to the server control unit 62. For example, the server input unit 61 can be an input interface that receives the difference information 22 from an input device (not shown). Furthermore, if the information management server 60 is configured to include an input device as an integrated unit, the server input unit 61 can be an input device such as a touch panel.

[0086] The server control unit 62 performs various controls on the units included in the information management server 60, and is configured by a processor such as a CPU (Central Processing Unit) or a GPU (Graphic Processing Unit).

[0087] The server control unit 62 includes, as a functional block, a difference information recording unit 70. If the server control unit 62 is, for example, a CPU, the difference information recording unit 70 can be realized by the CPU reading out a program stored in the server storage unit 63 into a memory (not shown) and executing it.

[0088] The difference information recording unit 70 records the difference information 22 received via the server input unit 61 in the server storage unit 63 .

[0089] The server storage unit 63 is a recording medium capable of storing various data, programs, etc. The server storage unit 63 includes an area for storing various programs, an area for storing data used in the various programs, an area into which the various programs are loaded, and an area used when the various programs are executed. The server storage unit 63 may be configured, for example, with semiconductor memory such as a read-only memory (ROM) or a random access memory (RAM), a hard disk drive (HDD), a solid state drive (SDD), a programmable logic circuit, etc. The server storage unit 63 stores the difference information 22 described above. The difference information 22 stored in the server storage unit 63 may be input from the outside via the server input unit 61, as described above.

[0090] Alternatively, the server memory unit 63 may store a history of the estimated results (estimated blood glucose values) of the state of the subject 2 estimated using the estimation model 23 and a history of actual information of the subject 2 corresponding to the estimated blood glucose values ​​(actual measured blood glucose values), and the server control unit 62 may calculate the difference information 22 from both histories.

[0091] (State estimation method) The state estimation device 1 included in the state estimation system 200 according to the third embodiment of the present disclosure can implement a state estimation method for an observed person 2, as shown in Fig. 18. Fig. 18 is a flowchart showing an example of the state estimation method performed by the state estimation device 1 according to the third embodiment of the present disclosure.

[0092] First, when the power of the state estimation device 1 is turned on and an instruction is given to output the estimation result information 21 of the state of the observed person 2, the estimation unit 30 in the state estimation device 1 acquires the estimation material information 20 (blood flow information) of the observed person 2 via the input unit 10 (step S31).

[0093] Furthermore, the estimation unit 30 acquires the observed person identification information 25 of the observed person 2 from the personal authentication server 40 (step S32). The estimation unit 30 transmits the observed person identification information 25 acquired in step S32 to the information management server 60, and requests difference information 22 corresponding to the observed person identification information 25. In response to this request from the state estimation device 1, the difference information 22 is transmitted from the information management server 60. In this way, the estimation unit 30 acquires the difference information 22 from the information management server 60 (step S33). Note that steps S32 and S33 may be executed before step S31 is executed.

[0094] The subsequent processing from step S34 to step S37 shown in FIG. 18 is similar to the processing from step S13 to step S16 shown in FIG. 2, and therefore a description thereof will be omitted.

[0095] As described above, in the state estimation device 1, the estimation unit 30 in the control unit 11 can generate the estimation result information 21 based on the estimation material information 20 acquired from the observed person 2 and taking the difference information 22 into consideration.

[0096] Therefore, when the state estimation device 1 estimates the state of the observed person 2 using the estimation model 23, even if the estimation result is always larger or smaller than the actual information indicating the actual state, it is possible to generate estimation result information 21 that is corrected to be appropriate. Therefore, even if there are individual differences in the estimation results using the estimation model 23 for each observed person 2, it is possible to obtain estimation result information 21 with high accuracy.

[0097] Therefore, the state estimating device 1 can estimate the state of the observed person 2 with high accuracy.

[0098] (Fourth embodiment) Next, a state estimation system 300 according to a fourth embodiment of the present disclosure will be described with reference to Fig. 19. Fig. 19 is a block diagram showing an example of a configuration of a main part of the state estimation system 300 according to the fourth embodiment of the present disclosure.

[0099] The state estimation system 300 according to the fourth embodiment differs from the state estimation system 200 according to the third embodiment in that the server storage unit 63 further stores an estimated ingredient information history 80, and in that the server control unit 62 further includes a difference information update determination unit 71 and a difference information update unit 72 as functional blocks. Another difference is that when the state estimation device 1 requests difference information 22 from the information management server 60, the state estimation system 300 transmits estimated ingredient information 20 received via the input unit 10 to the information management server 60. In other respects, the state estimation system 300 according to the fourth embodiment is similar to the state estimation system 200 according to the third embodiment, and therefore similar components are denoted by the same reference numerals, and their description will be omitted.

[0100] The estimated ingredient information history 80 stored in the server storage unit 63 is information indicating the history of the estimated ingredient information 20 received from the state estimating device 1.

[0101] The difference information update determination unit 71 determines whether or not it is necessary to update the difference information 22 by referring to the estimated material information history 80 stored in the server storage unit 63. Furthermore, if it is determined that it is necessary to update the difference information 22, the difference information update determination unit 71 controls the difference information update unit 72 to update the difference information 22. For example, if the control unit 11 is a CPU, the difference information update determination unit 71 and the difference information update unit 72 can be realized by the CPU reading out a program stored in the server storage unit 63 into a memory (not shown) and executing it.

[0102] For example, when the difference information update determination unit 71 receives pulse information having a pulse waveform shown in Fig. 20 as the estimation material information 20 from the state estimation device 1, it can determine whether or not it is necessary to update the difference information 22 based on the received pulse information as follows: Fig. 20 is a graph showing an example of pulse information obtained by dividing the blood flow information obtained from the observed person 2 into beats.

[0103] First, let us assume that the rising angle θ of the pulse waveform from the starting point of the pulse waveform to the first maximum point in the pulse information shown in Fig. 20 is an important feature for estimating the blood glucose level of the subject 2. As shown in Fig. 20, if the time width from the starting point to the maximum point is α and the difference in the detected amount between the starting point and the maximum point is β, the rising angle θ can be evaluated by tan θ = β ÷ α. Here, tan θ is defined as the feature tθ.

[0104] The difference information update determination unit 71 stores the feature amount tθ calculated based on the pulse information of the blood flow information received from the state estimation device 1 together with the request for the difference information 22 in the server storage unit 63 in association with the difference information 22.

[0105] In this way, the information management server 60 is configured to store the feature tθ in the server storage unit 63 each time the state estimation device 1 estimates the blood glucose level of the person being observed 2. This allows the information management server 60 to grasp the time-series changes in the feature tθ up to that point. Therefore, when estimating the blood glucose level of the person being observed 2, the difference information update determination unit 71 compares the feature tθ calculated based on the blood flow information received from the state estimation device 1 with the time-series changes in the feature tθ from the past. When the calculated feature tθ falls outside a predetermined range based on the time-series changes in the past feature tθ, or when a feature tθ outside the predetermined range has been obtained a predetermined number of times, the difference information update determination unit 71 determines that the blood glucose level trend of the person being observed 2 has changed and determines that the difference information 22 corresponding to the person being observed 2 needs to be updated. The predetermined range may be a range of ±10% of the average value of the past feature tθ. The predetermined number of times may be, for example, four or more times out of the last five estimations (a probability of 80% or more in the last five estimations).

[0106] When the difference information update determination unit 71 determines that the difference information 22 needs to be updated, the difference information update unit 72 updates the difference information 22 .

[0107] The update of the difference information 22 by the difference information update unit 72 may, for example, accept input of update difference information and update the difference information 22 stored in the server storage unit 63, similar to the difference information update unit 31 included in the state estimation device 1 in the state estimation system 100 according to the first modified example of the second embodiment shown in FIG. 14 .

[0108] Alternatively, the difference information update unit 72 receives from the state estimation device 1 an estimation result estimated by the estimation model 23 based on the estimation material information 20 (blood flow information) received from the state estimation device 1, and calculates the difference between the received estimation result and the actually measured blood glucose level. Then, the difference information update unit 72 may be configured to update the difference information 22 with the newly calculated difference.

[0109] In addition, if the actual blood glucose value stored in the server memory unit 63 has not been updated for a long period of time, the server control unit 62 may be configured to control the display to prompt the operator of the state estimation system 300 to input the actual blood glucose value when the differential information update determination unit 71 determines that the differential information 22 needs to be updated.

[0110] In the above description, the difference information update determination unit 71 uses the rising angle θ of the waveform of the pulse of the blood flow information as information for determining whether or not the difference information 22 needs to be updated. However, the information for determining whether or not the difference information 22 needs to be updated is not limited to the rising angle θ of the waveform of the pulse, and may be another feature obtained from the pulse information, or a feature obtained from first-order differential pulse information obtained by first-order differentiation of the pulse information, or second-order differential pulse information obtained by second-order differentiation of the pulse information, or a combination of these multiple types of feature amounts.

[0111] In the above description, an example has been given in which the state estimation device 1 receives blood flow information from an external device as the estimation material information 20. However, the estimation material information 20 received from an external device may include other types of information in addition to blood flow information.

[0112] In this configuration, in which multiple types of estimation material information 20 are received from the outside to estimate the state of the observed person 2, if the feature value of at least one of the pieces of information contained in the received estimation material information 20 is significantly different from the time series changes of past feature values, the difference information update determination unit 71 determines that the difference information 22 corresponding to the observed person 2 needs to be updated.

[0113] (State estimation method) The state estimation device 1 included in the state estimation system 300 according to the fourth embodiment of the present disclosure can implement a state estimation method for an observed person 2, as shown in Fig. 21. Fig. 21 is a flowchart showing an example of the state estimation method performed by the state estimation device 1 according to the fourth embodiment of the present disclosure.

[0114] First, when the power supply of the state estimation device 1 is turned on and an instruction is given to output the estimation result information 21 of the state of the observed person 2, the estimation unit 30 in the state estimation device 1 acquires the estimation material information 20 (blood flow information) of the observed person 2 via the input unit 10 (step S41).

[0115] Furthermore, the estimation unit 30 acquires the observed person identification information 25 of the observed person 2 from the personal authentication server 40 (step S42). The estimation unit 30 transmits the estimated material information 20 (blood flow information) acquired in step S41 to the information management server 60 together with the observed person identification information 25 acquired in step S42 (step S43).

[0116] Furthermore, the estimation unit 30 requests the difference information 22 corresponding to the observed person identification information 25. In response to this request from the state estimation device 1, the difference information 22 is transmitted from the information management server 60. In this manner, the estimation unit 30 acquires the difference information 22 from the information management server 60 (step S44). Note that step S42 may be executed before step S41, and the order of steps S41 and S42 is arbitrary.

[0117] The subsequent processing from step S45 to step S48 shown in FIG. 21 is similar to the processing from step S13 to step S16 shown in FIG. 2, and therefore a description thereof will be omitted.

[0118] As described above, in the state estimation device 1, the estimation unit 30 in the control unit 11 can generate the estimation result information 21 based on the estimation material information 20 acquired from the observed person 2 and taking the difference information 22 into consideration.

[0119] Therefore, when the state estimation device 1 estimates the state of the observed person 2 using the estimation model 23, even if the estimation result is always larger or smaller than the actual information indicating the actual state, it is possible to generate estimation result information 21 that is corrected to be appropriate. Therefore, even if there are individual differences in the estimation results using the estimation model 23 for each observed person 2, it is possible to obtain estimation result information 21 with high accuracy.

[0120] Therefore, the state estimating device 1 can estimate the state of the observed person 2 with high accuracy.

[0121] In the state estimation system 300 according to the fourth embodiment, the information management server 60 stores the difference information 22 and the estimated material information history 80 in the server storage unit 63, and the server control unit 62 determines whether or not it is necessary to update the difference information 22. However, the control unit 11 of the state estimation device 1 may be configured to determine whether or not it is necessary to update the difference information 22. In this configuration, the server control unit 62 of the information management server 60 does not include the difference information update determination unit 71 as a functional block, but the control unit 11 of the state estimation device 1 further includes the difference information update determination unit 71 as a functional block.

[0122] In the state estimation device 1, the control unit 11 obtains the feature tθ based on the blood flow information received via the input unit 10. The control unit 11 also obtains information on time-series changes in the past feature tθ, which is stored in association with the difference information 22 of the observed person 2, from the information management server 60, and compares it with the feature tθ. When the obtained feature tθ is compared with the time-series changes in the past feature tθ and finds that it falls outside a predetermined range based on the time-series changes in the past feature tθ, or when a feature tθ outside the predetermined range has been obtained a predetermined number of times, the control unit 11 determines that the blood glucose level trend of the observed person 2 has changed, and determines that the difference information 22 corresponding to the observed person 2 needs to be updated.

[0123] When the control unit 11 determines that the difference information 22 needs to be updated, it transmits instruction information to the information management server 60 to instruct the information management server 60 to update the difference information 22. In the information management server 60, the difference information update unit 72 of the server control unit 62 updates the difference information 22 in accordance with the instruction information transmitted from the state estimation device 1. [Explanation of symbols]

[0124] 1. State Estimation Device 2 Observed person 10 Input section 11 Control section 12 Output section 13 Storage section 14 Difference information input section 20 Estimated material information 21 Estimation result information 22 Difference Information 23 Estimation model 24 Corrected estimation model 24a First revised estimation model 24b Second adjusted estimation model 25 Observed Person Identification Information 30 Estimation part 31 Difference information update section 40 Personal authentication server 60 Information Management Server 61 Server Input Section 62 Server control unit 63 Server storage unit 70 Differential information recording unit 71 Difference information update judgment unit 72 Difference information update section 80 Estimated Material Information History 100 State Estimation System 200 State Estimation System 300 State Estimation System

Claims

1. an input unit that receives input of estimation material information used to estimate the state of the observed person; a control unit that generates estimation information by estimating the state of the observed person using an estimation model based on the estimation material information received by the input unit; an output unit that outputs the estimated information generated by the control unit, The control unit acquires difference information indicating a difference between estimated history information obtained by estimating in advance using the estimation model based on the past estimation material information of the observed person and actual information indicating the observed person's actual state, and when it determines that the difference information is outside a predetermined range, changes the estimation model to a corrected estimation model corrected in accordance with the difference information, thereby generating the estimation information. State estimator.

2. the difference information is associated with identification information of each of the plurality of subjects; The state estimation device according to claim 1 , wherein the control unit receives identification information of the observed person and acquires the difference information corresponding to the identification information.

3. The difference information is a difference value indicating the difference between an estimated value obtained by estimating in advance using the estimation model based on the past estimation material information of the observed person and an actual measurement value indicating the actual state of the observed person obtained by measuring the observed person. The state estimation device according to claim 1 .

4. The difference information is information that indicates a tendency of a magnitude relationship between an estimated value obtained by estimating in advance using the estimation model based on the past estimation material information of the observed person and an actual measurement value that indicates an actual state of the observed person and is obtained by measuring the observed person. The state estimation device according to claim 1 .

5. a storage device that stores the difference information; a difference information input unit that receives input of update difference information, the control unit updates the difference information stored in the storage device with the update difference information received by the difference information input unit. The state estimation device according to claim 1 .

6. the control unit extracts a first feature amount from the estimation material information received by the input unit, compares the extracted first feature amount with a second feature amount extracted from the estimation material information previously received by the input unit, and, if the first feature amount falls outside a predetermined range based on the second feature amount, performs control to update the difference information. The state estimation device according to claim 1 .

7. The state estimating device according to claim 1 , wherein the state of the observed person is biological information of the observed person.

8. The state estimation device according to claim 2; a personal authentication server that authenticates the observed person and transmits the identification information of the observed person who has been successfully authenticated to the state estimating device. State estimation system.

9. The apparatus further includes an information management server that includes a server storage device that stores the difference information in association with the identification information of each of the observed persons, and that, upon receiving the identification information from the state estimation device, transmits the difference information corresponding to the identification information to the state estimation device. The state estimation system according to claim 8 .

10. a step of receiving input of estimation material information used to estimate the state of the observed person; generating estimation information by estimating the state of the observed person using an estimation model based on the estimation material information received in the step of receiving input of the estimation material information; and outputting the estimated information generated in the generating step of the estimated information, the step of generating the estimated information includes a step of acquiring difference information indicating a difference between estimated history information obtained by pre-estimation using the estimation model based on the past estimation material information of the observed person and actual information indicating an actual state of the observed person, and changing the estimation model to a modified estimation model modified in accordance with the difference information when it is determined that the difference information is outside a predetermined range. A control method for a state estimation device.

Images