CN115248760A - Toilet state display system, recording medium, server, and user-side information processing device - Google Patents
Toilet state display system, recording medium, server, and user-side information processing device Download PDFInfo
- Publication number
- CN115248760A CN115248760A CN202210395444.4A CN202210395444A CN115248760A CN 115248760 A CN115248760 A CN 115248760A CN 202210395444 A CN202210395444 A CN 202210395444A CN 115248760 A CN115248760 A CN 115248760A
- Authority
- CN
- China
- Prior art keywords
- information
- server
- user
- stool
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 64
- 230000005540 biological transmission Effects 0.000 claims description 31
- 210000002700 urine Anatomy 0.000 claims description 26
- 210000003608 fece Anatomy 0.000 claims description 19
- 239000000126 substance Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 230000029142 excretion Effects 0.000 description 12
- 238000003384 imaging method Methods 0.000 description 11
- 238000001514 detection method Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000013872 defecation Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000002550 fecal effect Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Bidet-Like Cleaning Device And Other Flush Toilet Accessories (AREA)
- Toilet Supplies (AREA)
Abstract
A toilet status display system, a recording medium, a server, and a user-side information processing device. The stool state display system of the present invention allows a user or the like to confirm an image of excrement and a recognition result based on the stool state of the image by an automatic learning system of an excrement information analysis algorithm, to correct the recognition result when the recognition result is erroneous, to perform relearning using the correction result, and to provide the user or the like with information relating to the stool state using a stool learning model most suitable for each user or the like.
Description
Technical Field
The invention relates to a stool state display system, a recording medium, a server, and a user-side information processing device.
Background
As disclosed in patent document 1 (japanese patent No. 3347817), there is known an apparatus that automatically generates a learning sample image and automatically learns the learning sample image. Patent document 2 (japanese patent laid-open No. 2020-012348) discloses an estimation device for estimating the amount of excrement in a storage tank provided in a toilet bowl. The estimation device is provided with: an input unit to which output data from a detection sensor that detects a state in the storage tank is input; an estimation unit that estimates the amount of excrement in the retention tank based on the output data from the detection sensor input through the input unit; and an output unit that outputs a request for collection of excrement when the amount of excrement estimated by the estimation unit is equal to or greater than a set value.
In a conventional image recognition algorithm, a large number of images are collected to increase a recognition rate, and a large amount of time is required for a job of applying an accurate label to the image. Further, the reference to be given with the correct label is blurred by the person who gives the label, and it is difficult to create a learning-easy model suitable for various use environments. In the conventional art, there is an automatic image generation and accurate label assignment system, but in particular, in excretion, the accurate label assignment criterion changes due to differences in dietary life or the like caused by the locality, and therefore, it is difficult to create a convenient learning model that is optimal for all users.
Disclosure of Invention
The invention relates to a stool state display system, which displays the stool state on a display part,
the stool state display system includes:
a toilet bowl;
a server; and
and a user-side information processing device provided with the display unit.
Wherein the content of the first and second substances,
the toilet includes a toilet seat, an imaging element, and a toilet seat side information processing device.
The toilet bowl side information processing device is provided with a toilet bowl side data sending part and a toilet bowl side control part.
The server includes a server-side receiving unit, a server-side transmitting unit, a server-side storage unit, and a server-side control unit.
The server-side storage unit stores a learning-facilitating model.
The user-side information processing device further includes a user-side input unit, a user-side transmission unit, a user-side reception unit, a user-side storage unit, and a user-side control unit.
In the stool-state display system,
the toilet bowl side control part controls the image pickup element to make the image pickup element shoot the interior of the toilet bowl,
the toilet bowl-side control section controls the toilet bowl-side data transmitting section to transmit the photographed image photographed by the image pickup element to the server as photographed image information,
the server-side control section controls the server-side receiving section to receive the captured image information.
In the stool state display system, the server-side control unit estimates the stool information from at least 1 captured image included in the received captured image information as stool estimation information based on the stool learning model,
the server-side control unit controls the server-side storage unit to store the estimated stool information and the received captured image information in the server-side storage unit,
the server-side control unit controls the server-side transmission unit to transmit the estimated stool information and the captured image information to the user-side reception unit.
And, in the stool state display system,
the user-side control section controls the user-side receiving section to receive the estimated information and the captured image information,
the user-side control unit controls the display unit to display the stool estimation information and the captured image information received by the user-side receiving unit,
the user-side control unit acquires correction information including information on whether or not to correct the estimated excrement information displayed on the display unit via the user-side input unit.
When the correction information includes information indicating that correction of the estimated excrement information is "available", the correction information further includes information related to a content of correction of the estimated excrement information as correction content information.
Further, in the stool state display system,
the user-side control unit controls the user-side transmission unit to transmit the correction information to the server-side reception unit,
the server-side control unit controls the server-side reception unit to receive the correction information transmitted from the user-side transmission unit,
when the received correction information includes information indicating that correction of the estimated excrement information is "available", the server-side control unit controls the server-side storage unit to correct the estimated excrement information stored in the server-side storage unit based on the correction content information.
And, in the stool state display system,
when a predetermined period has elapsed after the stool learning model is stored in the server-side storage unit, or when the number of times the stool estimation information stored in the server-side storage unit is corrected based on the correction content information becomes equal to or more than a predetermined number of times, the server-side control unit generates a new stool learning model based on (i) the correction information and (ii) the captured image information corresponding to the correction information,
the server-side control unit controls the server-side transmission unit to transmit new model generation information including information that the new learning model is generated to the user-side reception unit,
the user-side control unit controls the user-side reception unit to receive new model generation information including information indicating that the new learning model is generated.
And, in the stool state display system,
the user-side control unit controls the display unit to display new model generation information including information indicating that the new learning model is generated, the information being received by the user-side reception unit,
the user-side control unit acquires new model use information including information on whether or not to use the new model for learning via the user-side input unit.
And, in the stool state display system,
the user-side control part controls the user-side transmission part to transmit the new model usage information to the server,
the server-side control unit controls the server-side reception unit to receive the new model usage information transmitted from the user-side transmission unit,
when the new model usage information includes information on the usage of the new provisional learning model, the server-side control unit controls the server-side storage unit to replace the provisional learning model stored in the server-side storage unit with the new provisional learning model.
A program for operating the stool state display system is also included in the gist of the present invention.
According to the stool state display system of the present invention, the image at the time of defecation (captured image information) and the defecation judgment information (stool estimation information) are displayed on the display unit, and when the user (for example, care-receiver) judges that the displayed judgment information (stool estimation information) is incorrect by the user (for example, care-receiver) stool viewer (for example, care-receiver) or the like, the defecation correction information transmitted by the user (for example, care-receiver) stool viewer (for example, care-receiver) or the like is collected and accumulated in the server. According to the stool state display system of the present invention, the stool learning model most suitable for the user is generated based on the excretion correction information.
Drawings
Fig. 1 is a schematic view of a toilet bowl according to embodiment 1 of the present invention.
Fig. 2 is a block diagram of the stool-state display system according to embodiment 1 of the present invention.
Fig. 3 is a block diagram including a server and a user-side information processing device included in the toilet state display system according to embodiment 1 of the present invention.
Fig. 4 is a diagram showing an example of a display unit of the user-side information processing apparatus according to embodiment 1 of the present invention.
Fig. 5 is a diagram showing an example of a display unit of the user-side information processing apparatus according to embodiment 1 of the present invention.
Fig. 6 is a diagram showing an example of a display unit of the user-side information processing apparatus according to embodiment 1 of the present invention.
Fig. 7 is a diagram showing an example of a display unit of the user-side information processing apparatus according to embodiment 1 of the present invention.
Fig. 8 is a diagram showing an example of a display unit of a user-side information processing device according to embodiment 1 of the present invention.
Fig. 9 is a diagram showing an example of a display unit of a user-side information processing device according to embodiment 1 of the present invention.
Fig. 10 is a flowchart of an automatic learning system of a voidage information analyzing algorithm in embodiment 1 of the present invention.
Fig. 11 is a block diagram of an automatic learning system of a voided information analysis algorithm in embodiment 1 of the present invention.
Fig. 12 is a flowchart of relearning by the automatic learning system of the excretory information analysis algorithm in embodiment 1 of the present invention.
Fig. 13 is a flowchart of another relearning of the automatic learning system of the excretory information analysis algorithm in embodiment 1 of the present invention.
Fig. 14A is a schematic diagram of captured image information in embodiment 1 of the present invention.
Fig. 14B is a schematic diagram of captured image information in embodiment 1 of the present invention.
Fig. 14C is a schematic diagram of captured image information in embodiment 1 of the present invention.
Detailed Description
(embodiment mode 1)
Fig. 1 is a schematic view of a toilet bowl 1 according to embodiment 1 of the present invention.
Fig. 2 is a block diagram of stool-state display system 100 according to embodiment 1 of the present invention.
(brief description)
As shown in fig. 1 and 2, a toilet 1 as a device for performing excretion includes a toilet seat 2, an imaging device 4, a toilet-side information processing device 5, and a toilet bowl 6. The device-specific ID (i.e., the ID specific to the toilet 1) is assigned to the toilet-side information processing device 5. The toilet seat 2 is provided with a switch sensor 3 (i.e., a seating sensor 3) for detecting that a user (e.g., a care recipient) is seated on the toilet seat 2. The toilet seat 2 includes an imaging device 4 for imaging the inside of the toilet seat 1. An example of the imaging device 4 is a camera.
The automatic learning system of the excretion information analysis algorithm according to embodiment 1 of the present invention includes a stool state display system 100.
A stool state display system (100) is provided with a toilet (1), a server (101), and a user-side information processing device (201).
The toilet 1 includes a toilet seat 2, an imaging device 4, a seating sensor 3 (i.e., a switch sensor), a toilet-side information processing device 5 (i.e., a control unit), and a toilet bowl 6. The toilet-side information processing device 5 includes a toilet-side data transmission unit and a toilet-side control unit. The toilet seat side information processing device 5 may include a toilet seat side storage unit.
The server 101 includes a server-side receiving unit, a server-side transmitting unit, a server-side storage unit, and a server-side control unit, as in a server that is generally used. As described later, the server-side storage unit stores the learning model.
Examples of the server 101 are a general server on the internet, a server in a care facility, and a server in home.
Fig. 3 is a block diagram including the server 101 and the user-side information processing device 201 included in the stool state display system 100 according to embodiment 1 of the present invention. As shown in fig. 3, the user-side information processing apparatus 201 includes a display unit 202. The user-side information processing apparatus 201 further includes a user-side input unit, a user-side transmission unit, a user-side reception unit, a user-side storage unit, and a user-side control unit. Examples of the user-side information processing device 201 include a personal computer, a tablet computer, and a smartphone, which are provided with a display that functions as the display unit 202. In the present invention, the user-side information processing apparatus 201 may be referred to as a "UI".
The storage unit is a so-called memory (particularly, a nonvolatile memory). The control unit is a so-called central processing unit.
(description of the operation of toilet bowl 1)
Fig. 10 is a flowchart of an automatic learning system of a fecal information analysis algorithm used in the fecal status display system 100 according to the present embodiment. As shown in step 101 (i.e., S101) in fig. 10, when it is detected that the user is seated on the toilet seat 2, shooting inside the toilet bowl 1 is started using the image pickup element 4. In this way, the toilet-side controller controls the image pickup device 4 so that the image pickup device 4 picks up an image of the inside of the toilet 1 (i.e., the inside of the bowl 6).
A toilet-side control unit of a toilet-side information processing device 5 (i.e., control means) disposed inside the toilet seat 2 activates the image pickup device 4 upon receiving a seating signal from the seating sensor 3, and controls the image pickup device 4 to pick up an image of the inside of the toilet 1 while the user is seated on the toilet seat 2. The imaging interval is set to 1 second at a predetermined interval, but may be 1 second or more and 1 second or less. The captured image is stored in the toilet-side information processing device 5 (i.e., the control unit, or more precisely, the toilet-side storage unit in the case where the toilet-side storage unit is provided), and the device ID and the imaging time associated with the toilet seat 2 that captured the image are described in the image name. Further, the image which is initially stored after the start of the shooting is stored with an image name to which a text capable of determining the meaning of the image is added.
As shown in step 102 (i.e., S102) in fig. 10, when it is detected that the user is unseated from the toilet seat 2, the toilet seat side control section ends the shooting by the image pickup element 4. The captured image is uploaded (transmitted) from the toilet-side information processing apparatus 5 (i.e., the control unit, strictly speaking, the toilet-side storage portion in the case where the toilet-side storage portion is provided) to the server 101. In this way, the toilet-side control section controls the toilet-side data transmission section to transmit the captured image captured by the image pickup element 4 to the server 101 as captured image information.
As described above, in the toilet state display system 100 according to embodiment 1 of the present invention, first, as shown in step 101 (i.e., S101) of fig. 10, when the seating sensor 3 detects that the user is seated on the toilet seat 2, the toilet seat-side control unit controls the image pickup device 4 so that the image pickup device 4 starts image pickup of the inside of the toilet seat 1.
Next, the toilet-side controller controls the toilet-side storage unit to store a plurality of captured images 502 (see fig. 14A to 14C) captured at predetermined time intervals by the imaging device 4 in the toilet-side storage unit as captured image information 501 (see fig. 14A to 14C). In other words, the captured image information 501 is formed on the toilet seat-side storage unit by sequentially storing the captured images 502 from the image pickup device 4 in the toilet seat-side storage unit with the passage of time. As shown in fig. 14A to 14C, the captured image information 501 includes a plurality of captured images 502, and the device ID and the capturing time 503 of each captured image 502.
Further, as shown in step 102 (i.e., S102) of fig. 10, the toilet-side control section controls the toilet-side data transmitting section to transmit the captured image information 501 to the server 101. In more detail, in step 102 (i.e., S102), the toilet-side control section controls the toilet-side data transmission section to transmit the captured image 502 captured by the image pickup element 4 to the server 101 as the captured image information 501. In addition, the server-side control section controls the server-side receiving section to receive the captured image information 501.
When the seating sensor 3 detects that the user is unseated from the toilet seat 2, the toilet-side control section controls the image pickup element 4 so that the image pickup element 4 stops the shooting of the inside of the toilet 1.
The toilet-side information processing device 5 may not include a toilet-side storage unit. That is, while the image pickup device 4 picks up an image of the inside of the toilet 1 (strictly speaking, the inside of the toilet bowl 6), the toilet bowl-side information processing device 5 may immediately transmit the picked-up image 502 picked up by the image pickup device 4 to the server 101.
(description of image recognition in the Server 101)
As shown in fig. 3, the server 101 includes an input image, a learning unit 102, a recognition unit 103, and a database 110. The user-side information processing apparatus 201 includes a display unit 202 and an erroneous determination correcting unit 203.
The learning unit 102 of the server 101 acquires images of a plurality of excreta in advance, extracts features from the images, and generates a provisional learning model capable of reflecting the features. The generated provisional learning model is stored in the server-side storage unit as a provisional learning model.
The recognition unit 103 has a recognition algorithm in which the generated easy-to-learn model is mounted. The recognition unit 103 outputs a recognition result based on the input image (i.e., the captured image information 501, more specifically, the plurality of captured images 502 included in the captured image information 501).
The database 110 stores the recognition results, i.e., the presence or absence of feces, the shape, the amount, the color, the number of times of dropping of feces, and the like. The database 110 is included in the server-side storage unit.
The captured image information 501 received by the server-side receiving unit is temporarily stored in the server-side storage unit. Next, the recognition unit 103 recognizes the properties of the pieces of text (for example, 1 arbitrary piece of text selected from the group consisting of 7 classes of bristol classification indexes described later) from the captured image information 501 (specifically, at least 1 captured image 502 included in the captured image information 501), and outputs the recognition result from the recognition unit 103. The result output from the recognition unit 103 is stored in the database 110 (i.e., server-side storage unit) as the estimated information.
As is clear from the above description, the server-side control unit estimates, as the feces estimation information, the information of the feces from at least 1 captured image 502 included in the received captured image information 501 based on the feces learning model. Further, the server-side control unit controls the server-side storage unit so that the estimate information and the received captured image information 501 are stored in the server-side storage unit. This is represented in fig. 10 as step 201 (i.e., S201) and step 202 (i.e., S202).
In fig. 10, as shown in step 203 (i.e., S203), the server-side control unit controls the server-side transmitting unit so as to transmit the convenience estimation information and the captured image information 501 to the user-side receiving unit. Further, the user-side control section controls the user-side receiving section so as to receive the estimation information and the captured image information.
(explanation of display in the user-side information processing apparatus 201)
In fig. 10, as shown in step 301 (i.e., S301), the user-side control unit controls the display unit 202 so that the estimate information and the captured image information 501 received by the user-side receiving unit are displayed on the display unit 202. In the display portion 202, a user or the like can input an ID and a password on a Web (World Wide Web) or an application (application) to display a drainage record.
Fig. 4 to 9 are diagrams each showing an example of a display unit of the user-side information processing device according to embodiment 1 of the present invention. More specifically, fig. 4 to 9 each show an example of the drainage record shown in the display unit 202. As shown in fig. 4, a graph 205 shows the time when the user sits on the toilet seat 2, when the user excretes, whether the user excretes feces or urine, and if the user urinates, which classification the shape of the user belongs to in 7 classes of the bristol classification index, the color of the user urinate, the amount of the user defecate, and the number of times the user has fallen. If urine is detected, the excretion record is displayed on the display unit 202 as the color and the urine volume of urine are shown in the graph 205.
In the middle, the color, amount, and the like of urine at the time of imaging described in the image determined as urine by the presence or absence of urine detection are displayed as bar-shaped graphs in the graph 205. In this case, the graph may be displayed in the same color as the result of the urine color determination, with the height changed according to the urine volume, or the urine color and the urine volume may be displayed as text in the graph as shown in fig. 5, or the text may be displayed as a comment in the vicinity of the graph as shown in fig. 6.
Further, in the lower stage, the color, amount, and the like of the feces at the time of imaging described in the image determined as the feces by the presence or absence of detection of the feces are displayed as bar-shaped graphs in the graph 205. In this case, the provisional shape recognition determination result may be displayed as text in a figure, or a figure in which the bristol classification index is iconified so as to simulate the provisional shape may be displayed. The graphic may be illustrated in the same color as the free color determination result by changing the height according to the free amount, the free color, the free amount, and the free fall number may be displayed in text in the graphic, or the text may be displayed in the form of a comment in the vicinity of the graphic.
As shown in fig. 7, the user-side information processing device 201 according to the present embodiment can display an image that is the basis of the determination result (i.e., 1 captured image 502 that is the basis of the determination result) by selecting a figure indicating the determination result displayed on the graph 205 by clicking or touching. In addition, the image may be displayed on the chart 205 from the beginning. In this case, the displayed image may be displayed in a pop-up form as the image display area 206 in a window different from the graph 205 as shown in fig. 7, or may be displayed in the image display area 206 provided in the same window as the graph 205 as shown in fig. 8.
As described above, in the stool state display system 100 according to embodiment 1 of the present invention, since the determination results of the feces such as the stool and the urine are displayed on the display unit 202, the viewer (for example, a caregiver) of the user (for example, a care recipient) or the like can easily recognize the presence or absence of the feces of the user or the like, and can easily grasp the health state of the user.
(explanation of correction of determination result)
In addition, the determination result in the recognition algorithm is premised on having high accuracy, but the determination result output by the recognition algorithm is not limited to 100% correct. The user-side information processing device 201 according to the present embodiment can display an image that is the basis of the determination result on the display unit 202, and when the determination result by the recognition algorithm is different from the determination result visually confirmed by the user or the like, the determination result displayed on the display unit 202 can be corrected in the user-side information processing device 201. As shown in fig. 9, the display unit 202 further includes a determination result display box 207, and a determination result text is input below the image or in the vicinity of the image in the determination result display box 207. The determination result display box 207 includes a pull-down box 208. The user-side information processing apparatus 201 of the present embodiment includes an erroneous determination correcting unit that can display the determination result list by clicking or touching the drop-down box 208, and can correct the determination result displayed in the determination result display box 207 by clicking or touching any one of the determination results in the determination result list. At this time, the graph showing the determination result displayed on the graph 205 is also shown anew according to the correction content.
In the recognition algorithm, when the output recognition result is erroneous, the erroneous image is additionally learned together with the excretion correction information, thereby achieving further improvement in recognition accuracy, and therefore, the correction information is very valuable. In general, in order to improve the accuracy of an image-based recognition algorithm, a large number of images to which correct labels are added are required, but even if an image that can be determined is relearned, the effect is poor, and it is preferable to relearned an image for which a determination is mistaken by adding a correct label.
As for the above correction, as shown in step 302 (i.e., S302) in fig. 10, the user-side control unit acquires correction information including information on whether or not to correct the estimated excrement information displayed on the display unit 202 via the user-side input unit. Next, as shown in step 303 (i.e., S303) in fig. 10, the user-side control section controls the user-side transmitting section to transmit the correction information to the server-side receiving section. The server-side control unit controls the server-side receiving unit to receive the correction information transmitted from the user-side transmitting unit.
As described above, the user-side information processing apparatus 201 according to the present embodiment transmits information obtained by correcting the determination result by the user to the server 101. The server-side control unit corrects the image information corresponding to the database 110 and adds the corrected recognition result. When the recognition algorithm is relearned, the images used for learning are selected based on the correction information, and thus the recognition performance can be further improved efficiently. The relearning is described in paragraph number 0076 of patent document 2.
More specifically, as shown in step 304 (i.e., S304) in fig. 10, when the received correction information includes information indicating that the correction of the estimated message information is "present", the server-side control unit controls the server-side storage unit to correct the estimated message information stored in the server-side storage unit based on the correction content information. On the other hand, when the correction information does not include information indicating that the correction of the estimated excrement information is "available", the server-side control unit does not control the server-side storage unit to correct the estimated excrement information stored in the server-side storage unit.
As shown in fig. 10, the image captured by the toilet seat 2 is stored in the server 101 (see S101 and S102 in fig. 10), and the recognition result output by the input to the recognition unit 103 is stored in the database 110 (see S201 and S202 in fig. 10). The user-side information processing apparatus 201 can display the image stored in the server 101 (i.e., the captured image 502) and the recognition result stored in the database 110 on the display unit 202 (see S301 in fig. 10). When the user or the like confirms the image (that is, the captured image 502) and determines that the recognition results are different, the erroneous determination correcting unit 203 can correct the recognition results (see S302). The corrected recognition result is transmitted to the server 101, and the correction result is stored in the database 110 (see S303 and S304 in fig. 10).
(explanation of relearning in the Server 101)
The correction results are stored in the database 110, and when the number of correction results is greater than or equal to a predetermined number (e.g., 10000) after the previous relearning, or when a predetermined period (e.g., one month) has elapsed after the previous relearning, the server-side control unit relearns the correction results and the image to be corrected, and generates a temporary learning model. In addition, the number of correction results and the period of time for which relearning is performed may also be increased or decreased.
In other words, as shown in step 311 (i.e., S311) in fig. 10, when a predetermined period has elapsed after the stool learning model is stored in the server-side storage unit, or when the number of times the stool estimation information stored in the server-side storage unit is corrected based on the correction content information becomes equal to or more than a predetermined number of times, the server-side control unit generates a new stool learning model based on (i) the correction information and (ii) the captured image information 501 corresponding to the correction information. The generated stool learning model is stored in the server-side storage unit. On the other hand, when the predetermined period of time has not elapsed after the provisional learning model is stored in the server-side storage unit, or when the provisional learning information stored in the server-side storage unit has not been corrected based on the correction content information more than the predetermined number of times, the generation of a new provisional learning model and the subsequent steps 312 to 314 (i.e., S312 to S314) are not performed. As shown in fig. 10, when the predetermined period does not elapse after the stool learning model is stored in the server-side storage unit, or when the number of times the stool estimation information stored in the server-side storage unit is corrected based on the correction content information does not reach the predetermined number of times or more, the state in which the selected stool learning model (i.e., the currently used stool learning model) is used in the server is maintained, and the process returns to step 201 (i.e., S201).
When the user-side information processing apparatus 201 generates the provisional learning model, the server 101 notifies the user-side information processing apparatus 201 that the provisional learning model is generated. In other words, as indicated by step 312 (i.e., S312) in fig. 10, the server-side control unit controls the server-side transmission unit to transmit new model generation information including information indicating that a new learning model is generated to the user-side reception unit. The user-side control unit controls the user-side reception unit to receive new model generation information including information indicating that a new learning model is generated.
Next, the user-side control unit controls the display unit 202 so that the display unit 202 displays new model generation information including information indicating that a new learning model is generated, which is received by the user-side receiving unit. In this way, as shown in step 313 (i.e., S313) in fig. 10, the user, the viewer, and the like can receive the notification from the server 101 and select whether or not to change (i.e., replace) the used provisional learning model (here, the provisional learning model currently used) to a new provisional learning model.
In fig. 10, when the use of a new provisional learning model is selected as shown in step 314 (i.e., S314), the user-side information processing apparatus 201 transmits the used provisional learning model information to the server 101, and the server 101 replaces the provisional learning model used by the user-side information processing apparatus 201 that has transmitted the used provisional learning model information. In other words, when the new stool learning model is selected to be used, the server 101 arranges the new stool learning model in the server 101 (that is, the new stool learning model is stored in the server-side storage unit, and thereafter, the new stool learning model is used for the recognition of the stool behavior in step 201 (that is, S201)). On the other hand, when the selection is made to continue using the currently used toilet learning model, the server 101 continuously arranges the currently used toilet learning model in the server 101 (that is, the currently used toilet learning model is continuously stored in the server-side storage unit, and thereafter, the toilet learning model is used for identifying the behavior of the toilet in S201).
As described above, as shown in steps 313 to 314 (i.e., S313 to S314) in fig. 10, the user-side control unit acquires new model use information including information on whether or not to use a new provisional learning model via the user-side input unit. Then, the user-side control unit controls the user-side transmission unit to transmit the new model usage information to the server. The server-side control unit controls the server-side reception unit to receive the new model usage information transmitted from the user-side transmission unit. When the new model usage information includes information on the usage of a new temporary learning model, the server-side control unit controls the server-side storage unit to replace the temporary learning model stored in the server-side storage unit with the new temporary learning model. On the other hand, when the new model usage information does not include information related to the usage of the new easy-learning model, that is, when an input of "not used" is made to the query "do not use the new easy-learning model", or when the query is ignored, the server-side control unit does not control the server-side storage unit to replace the easy-learning model stored in the server-side storage unit with the new easy-learning model. When the stool state display system 100 is initially used, an initial stool learning model is arranged in the server 101 as a stool learning model (that is, a new stool learning model is stored in the server-side storage unit), and then the initial stool learning model is used for identifying the behavior of the stool in step 201 (that is, S201).
Fig. 11 is a block diagram of an automatic learning system of a stool-state display system 100 according to the present embodiment, which analyzes an algorithm for excretory information. The source of the image and the correction result is the facilities of the toilet 1 provided with the stool state display system 100 of the present embodiment, and the like. For example, as shown in fig. 11, the source of the image and the correction result is constituted by a facility a, a facility B, a facility C, a user Aa, a user Ab, and the like (hereinafter, not shown). In addition, the number of facilities and the number of users can be increased or decreased. At this time, the user information is the device ID of the toilet 1, and the device ID can be associated with each facility in which the toilet 1 is set. In addition, the device ID may not be associated with the facility. With this configuration, a stool learning model (for example, a stool learning model in which a correction result from the facility a is learned, and a stool learning model in which a correction result from the facility B is learned) in which correction results from each facility, a user, a viewer, and the like are learned is generated.
Fig. 12 is a flowchart of the automatic learning system of the excretion information analysis algorithm according to the present embodiment, in which the correction result is used for relearning. When the number of correction results is 1000 or more, or when one month has elapsed since the previous relearning, the server-side control unit relearns the correction results and the correction target images to generate the temporary learning model.
Fig. 13 is a flowchart for using other correction results for relearning in the automatic learning system of the excretion information analysis algorithm according to the present embodiment. When the number of correction results is 100 or more, or when one month has elapsed since the previous relearning, the server-side control unit relearns the correction results and the correction target images to generate the temporary learning model.
The number of correction results and the period of time for which relearning is performed may be increased or decreased, or may be set arbitrarily.
(description of hardware of control Unit)
The automatic learning system of the excretion information analysis algorithm according to the present embodiment is, for example, a computer system. The computer system has a main configuration including a processor (i.e., a central processing unit functioning as a control unit) and a memory (i.e., a storage unit) as hardware. In the server 101 and the user-side information processing device 201, the automatic learning system of the excretion information analysis algorithm operates by a processor (i.e., a central processing unit functioning as a control unit) executing a program recorded in a memory (i.e., a storage unit). In the toilet-side information processing device included in the toilet 1, the automatic learning system of the excretion information analysis algorithm operates by the processor (i.e., the central processing unit functioning as the control unit) executing the program recorded in the memory (i.e., the storage unit).
The program may be recorded in advance in the memory, may be provided via an electric communication line, or may be recorded in a non-transitory recording medium such as a memory card, an optical disk, or a hard disk drive that can be read by the computer system. The processor is constituted by 1 or more electronic circuits including a semiconductor Integrated Circuit (IC) or a large scale integrated circuit (LSI). The integrated circuits such as an IC and an LSI, which are referred to herein, are called system LSI, VLSI (Very Large Scale Integration), or ULSI (Ultra Large Scale Integration), depending on the degree of Integration.
Furthermore, an FPGA (Field-Programmable Gate Array) programmed after the manufacture of an LSI, or a reconfigurable logic device for reconfiguring a bonding relationship inside the LSI or circuit partitioning inside the LSI can also be used as a processor. The plurality of electronic circuits may be integrated into 1 chip or may be distributed over a plurality of chips. The plurality of chips may be collected in 1 device or may be distributed among a plurality of devices. The computer system referred to herein comprises a microcontroller having more than 1 processor and more than 1 memory. Accordingly, the microcontroller is also constituted by 1 or more electronic circuits including a semiconductor integrated circuit or a large scale integrated circuit.
As described above, the stool state display system according to the present invention is used by a reviewer (e.g., a caregiver) or the like in a care facility or the like for health management of a user (e.g., a care recipient) who needs care due to an elderly person or the like. The stool state display system of the present invention is also used in the home of a user, a person (i.e., a viewer) who views the display content (i.e., the estimated presence or absence of stool) of the display unit, or the like. A program for an automatic learning system that causes a computer to execute the excretion information analysis algorithm of the present invention is also included in the present invention.
Claims (19)
1. A stool state display system which causes a display section to display a state of a stool,
the stool state display system includes:
a toilet bowl;
a server; and
a user-side information processing device provided with the display unit,
wherein the content of the first and second substances,
the toilet bowl comprises a toilet seat, an image pickup element and a toilet bowl side information processing device,
the toilet bowl side information processing device is provided with a toilet bowl side data sending part and a toilet bowl side control part,
the server includes a server-side receiving unit, a server-side transmitting unit, a server-side storage unit, and a server-side control unit,
the server-side storage unit stores a learning-facilitating model,
the user-side information processing device further comprises a user-side input unit, a user-side transmission unit, a user-side reception unit, a user-side storage unit, and a user-side control unit,
in the stool-state display system,
the toilet bowl side control part controls the image pickup element to make the image pickup element shoot the interior of the toilet bowl,
the toilet bowl-side control section controls the toilet bowl-side data transmitting section to transmit the photographed image photographed by the image pickup element to the server as photographed image information,
the server-side control section controls the server-side receiving section to receive the captured image information,
the server-side control unit estimates, as stool estimation information, information of the stool from at least 1 captured image included in the received captured image information based on the stool learning model,
the server-side control section controls the server-side storage section to store the estimate information and the received captured image information in the server-side storage section,
the server-side control unit controls the server-side transmission unit to transmit the estimated stool information and the captured image information to the user-side reception unit,
the user-side control section controls the user-side receiving section to receive the estimated information and the captured image information,
the user-side control unit controls the display unit to display the stool estimation information and the captured image information received by the user-side receiving unit,
the user-side control unit acquires correction information including information on whether or not to correct the estimated feces volume information displayed on the display unit via the user-side input unit,
wherein, when the correction information includes information "present" for correcting the estimated excrement information, the correction information further includes information relating to a correction content of the estimated excrement information as correction content information,
the user-side control unit controls the user-side transmission unit to transmit the correction information to the server-side reception unit,
the server-side control unit controls the server-side receiving unit to receive the correction information transmitted from the user-side transmitting unit,
when the received correction information includes correction "existing" information for correcting the stool estimation information, the server-side control unit controls the server-side storage unit to correct the stool estimation information stored in the server-side storage unit based on the correction content information,
when a predetermined period has elapsed after the stool learning model is stored in the server-side storage unit, or when the number of times the stool estimation information stored in the server-side storage unit is corrected based on the correction content information becomes equal to or more than a predetermined number of times, the server-side control unit generates a new stool learning model based on (i) the correction information and (ii) the captured image information corresponding to the correction information,
the server-side control unit controls the server-side transmission unit to transmit new model generation information including information indicating that the new learning model is generated to the user-side reception unit,
the user-side control unit controls the user-side reception unit to receive new model generation information including information indicating that the new learning model is generated,
the user-side control unit controls the display unit to display new model generation information including information indicating that the new learning model is generated, the information being received by the user-side reception unit,
the user-side control unit acquires new model use information including information on whether or not to use the new model,
the user-side control part controls the user-side transmission part to transmit the new model usage information to the server,
the server-side control unit controls the server-side reception unit to receive the new model usage information transmitted from the user-side transmission unit,
when the new model usage information includes information on the usage of the new provisional learning model, the server-side control unit controls the server-side storage unit to replace the provisional learning model stored in the server-side storage unit with the new provisional learning model.
2. A stool state display system according to claim 1,
the temporary estimation information is temporary estimation information in a plurality of facilities.
3. A stool state display system according to claim 1,
the estimated excrement information is estimated excrement information in 1 specific facility.
4. A stool state display system according to claim 1,
the estimated information is estimated information of 1 specific user.
5. A stool state display system according to claim 1,
the feces are feces.
6. A stool state display system according to claim 1,
the stool is urine.
7. A computer-readable recording medium storing a computer program for operating a stool state display system for displaying a state of a stool on a display unit,
the stool state display system includes:
a toilet bowl;
a server; and
a user-side information processing device provided with the display unit,
wherein the content of the first and second substances,
the toilet bowl comprises a toilet seat, an image pickup element and a toilet bowl side information processing device,
the toilet bowl side information processing device is provided with a toilet bowl side data transmitting part and a toilet bowl side control part,
the server includes a server-side receiving unit, a server-side transmitting unit, a server-side storage unit, and a server-side control unit,
the server-side storage unit stores a learning model,
the user-side information processing device further comprises a user-side input unit, a user-side transmission unit, a user-side reception unit, a user-side storage unit, and a user-side control unit,
when the program is executed by means of a processor,
the toilet bowl side control part controls the image pickup element to make the image pickup element shoot the inside of the toilet bowl,
the toilet bowl-side control section controls the toilet bowl-side data transmitting section to transmit the photographed image photographed by the image pickup element to the server as photographed image information,
the server-side control section controls the server-side receiving section to receive the captured image information,
the server-side control unit estimates, as stool estimation information, information of the stool from at least 1 captured image included in the received captured image information based on the stool learning model,
the server-side control unit controls the server-side storage unit to store the estimated stool information and the received captured image information in the server-side storage unit,
the server-side control unit controls the server-side transmission unit to transmit the estimated stool information and the captured image information to the user-side reception unit,
the user-side control section controls the user-side receiving section to receive the estimated information and the captured image information,
the user-side control unit controls the display unit to display the estimate information and the captured image information received by the user-side receiving unit,
the user-side control unit acquires correction information including information on whether or not to correct the estimated feces volume information displayed on the display unit via the user-side input unit,
wherein, in a case where the correction information includes information "existing" for correcting the estimated urine information, the correction information further includes information relating to a content of correction of the estimated urine information as correction content information,
the user-side control unit controls the user-side transmission unit to transmit the correction information to the server-side reception unit,
the server-side control unit controls the server-side receiving unit to receive the correction information transmitted from the user-side transmitting unit,
when the received correction information includes correction "existing" information for correcting the stool estimation information, the server-side control unit controls the server-side storage unit to correct the stool estimation information stored in the server-side storage unit based on the correction content information,
when a predetermined period has elapsed after the stool learning model is stored in the server-side storage unit, or when the number of times the stool estimation information stored in the server-side storage unit is corrected based on the correction content information becomes equal to or more than a predetermined number of times, the server-side control unit generates a new stool learning model based on (i) the correction information and (ii) the captured image information corresponding to the correction information,
the server-side control unit controls the server-side transmission unit to transmit new model generation information including information indicating that the new learning model is generated to the user-side reception unit,
the user-side control unit controls the user-side reception unit to receive new model generation information including information indicating that the new learning model is generated,
the user-side control unit controls the display unit to display new model generation information including information indicating that the new learning model is generated, the information being received by the user-side reception unit,
the user-side control unit acquires new model use information including information on whether or not to use the new model,
the user-side control part controls the user-side transmission part to transmit the new model usage information to the server,
the server-side control unit controls the server-side reception unit to receive the new model usage information transmitted from the user-side transmission unit,
in a case where the new model usage information includes information on usage of the new easy learning model, the server-side control unit controls the server-side storage unit to replace the easy learning model stored in the server-side storage unit with the new easy learning model.
8. The computer-readable recording medium of claim 7,
the temporary estimation information is temporary estimation information in a plurality of facilities.
9. The computer-readable recording medium of claim 7,
the estimated excrement information is estimated excrement information in 1 specific facility.
10. The computer-readable recording medium of claim 7,
the estimated excrement information is the excrement estimated information of a specific 1 user.
11. The computer-readable recording medium of claim 7,
the feces are feces.
12. The computer-readable recording medium of claim 7,
the stool is urine.
13. A server used in a stool state display system for displaying the state of stool on a display unit,
the server includes a server-side receiving unit, a server-side transmitting unit, a server-side storage unit, and a server-side control unit,
the server-side storage unit stores a learning model,
the server-side control portion controls the server-side receiving portion to receive captured image information containing a captured image inside a toilet bowl communicably connected with the server from the toilet bowl,
the server-side control unit estimates, as stool estimation information, the stool information from at least 1 captured image included in the received captured image information based on the stool learning model,
the server-side control unit controls the server-side storage unit to store the estimated stool information and the received captured image information in the server-side storage unit,
the server-side control unit controls the server-side transmission unit to transmit the estimated stool information and the captured image information to a user-side information processing device communicably connected to the server,
the server-side control unit controls the server-side reception unit to receive correction information including information on whether or not to correct the estimated information from the user-side information processing apparatus,
the server-side control unit controls the server-side storage unit to correct the estimated urine information stored in the server-side storage unit based on the correction content information when the received correction information includes information indicating that correction of the estimated urine information is present,
when a predetermined period has elapsed after the provisional learning model is stored in the server-side storage unit, or when the provisional learning information stored in the server-side storage unit has been corrected based on the correction content information a predetermined number of times or more, the server-side control unit generates a new provisional learning model based on (i) the correction information and (ii) the captured image information corresponding to the correction information,
the server-side control unit controls the server-side transmission unit to transmit new model generation information including information indicating that the new learning model is generated to the user-side information processing apparatus,
the server-side control unit controls the server-side reception unit to receive new model use information including information on whether or not to use the new learning model from the user-side information processing apparatus,
when the new model usage information includes information on the usage of the new provisional learning model, the server-side control unit controls the server-side storage unit to replace the provisional learning model stored in the server-side storage unit with the new provisional learning model.
14. The server according to claim 13, wherein,
the correction content information includes information for correcting at least one of the color of the stool, the volume of the stool, the number of times of dropping of the stool, the color of the urine, and the volume of the urine.
15. The server according to claim 13, wherein,
the new stool learning model is generated based on information for correcting at least one of the color of the stool, the stool volume, the number of times of dropping of the stool, the color of the urine, and the urine volume.
16. A user-side information processing device used in a stool state display system for displaying the state of a stool on a display unit,
the user-side information processing device comprises the display unit, a user-side input unit, a user-side transmission unit, a user-side reception unit, a user-side storage unit, and a user-side control unit,
the user-side control section controls the user-side receiving section to receive, from a server communicably connected to the user-side information processing apparatus, stool estimation information and captured image information including a captured image in a toilet bowl,
wherein the stool estimation information includes information of the stool estimated based on a stool learning model from at least 1 captured image included in the received captured image information,
the user-side control unit controls the display unit to display the estimated excrement information and the captured image information received by the user-side receiving unit,
the user-side control unit acquires correction information including information on whether or not to correct the estimated feces volume information displayed on the display unit via the user-side input unit,
wherein, when the correction information includes information that "has" a correction to correct the estimated excrement information, the correction information includes information relating to a content of correction of the estimated excrement information as correction content information,
the user side control part controls the user side transmission part to transmit the correction information to the server,
the user-side control unit controls the user-side reception unit to receive, from the server, new model generation information including information indicating that a new learning model is generated based on the correction information and the captured image information corresponding to the correction information,
the user-side control unit controls the display unit to display new model generation information including information indicating that the new learning model is generated, the information being received by the user-side reception unit,
the user-side control unit acquires new model use information including information on whether or not to use the new model,
the user-side control unit controls the user-side transmission unit to transmit the new model usage information to the server.
17. The user-side information processing apparatus according to claim 16,
the new provisional learning model is generated based on (i) the correction information and (ii) the captured image information corresponding to the correction information, when a predetermined period of time has elapsed after the provisional learning model is stored in the server, or when the provisional estimation information stored in the server has been corrected based on the correction content information a predetermined number of times or more.
18. The user-side information processing apparatus according to claim 16,
the correction content information includes information for correcting at least one of the color of the stool, the stool volume, the number of times of dropping of the stool, the color of the urine, and the urine volume.
19. The user-side information processing apparatus according to claim 16,
the new stool learning model is generated based on information for correcting at least one of the color of the stool, the volume of the stool, the number of times of dropping of the stool, the color of the urine, and the volume of the urine.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021-073731 | 2021-04-26 | ||
| JP2021073731A JP7454766B2 (en) | 2021-04-26 | 2021-04-26 | Stool status display system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115248760A true CN115248760A (en) | 2022-10-28 |
Family
ID=83697826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210395444.4A Pending CN115248760A (en) | 2021-04-26 | 2022-04-15 | Toilet state display system, recording medium, server, and user-side information processing device |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP7454766B2 (en) |
| CN (1) | CN115248760A (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019245359A1 (en) | 2018-06-21 | 2019-12-26 | N.V. Nutricia | Method and system for characterizing stool patterns of young infants |
| JP2020012348A (en) | 2018-07-20 | 2020-01-23 | 積水化学工業株式会社 | Estimation device, learning model, computer program, temporary toilet, and server device |
| US11010938B2 (en) | 2019-04-03 | 2021-05-18 | Uih America, Inc. | Systems and methods for positron emission tomography image reconstruction |
| JP7394602B2 (en) | 2019-05-17 | 2023-12-08 | 株式会社Lixil | Judgment device |
-
2021
- 2021-04-26 JP JP2021073731A patent/JP7454766B2/en active Active
-
2022
- 2022-04-15 CN CN202210395444.4A patent/CN115248760A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| JP7454766B2 (en) | 2024-03-25 |
| JP2022168354A (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10733430B2 (en) | Toilet usage management system and cat toilet | |
| Park et al. | A mountable toilet system for personalized health monitoring via the analysis of excreta | |
| JP7107338B2 (en) | Defecation recording system, defecation recording method and defecation recording program | |
| WO2020235473A1 (en) | Determining device, determining method, and program | |
| CN114467020B (en) | Judging device | |
| JP6209696B1 (en) | Nursing care recording device | |
| WO2017115444A1 (en) | Health monitoring system, health monitoring method, and health monitoring program | |
| CN115248760A (en) | Toilet state display system, recording medium, server, and user-side information processing device | |
| CN114430474A (en) | Excreta status display system | |
| WO2021042710A1 (en) | Toilet and flushing control method and device therefor | |
| WO2022254702A1 (en) | Examination guidance device and examination guidance method | |
| WO2021192476A1 (en) | Excreta determination method, excreta determination device, and excreta determination program | |
| CN116071695A (en) | Excrement image display system, toilet stool, and excrement image display method | |
| JP2022136106A (en) | Defecation recording system, defection recording method, and defection recording program | |
| CN110178185A (en) | Support method and support system | |
| WO2021085369A1 (en) | Meal amount measuring device and method | |
| JP7507348B2 (en) | Flight status display system and program for operating same | |
| JP2023170313A (en) | Excretion image display system and toilet bowl | |
| WO2022254740A1 (en) | Information processing method, information processing device, and information processing program | |
| JP2024051961A (en) | Toilet device and excrement analysis system | |
| CN111666794A (en) | Pet monitoring method and pet monitoring system | |
| JP7464181B2 (en) | Health management system and health management method | |
| JP7160417B1 (en) | Management device, method and program | |
| CN117396981A (en) | Information processing method, information processing device, and information processing program | |
| JPWO2022254740A5 (en) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |