Defecation prediction support system, defecation prediction support method, and defecation prediction support program

Abstract

To provide a system capable of eliminating a labor of a user (for example, a caregiver) by presenting information as a support for predicting defecation timing of a target person (for example, a care receiver) accurately as compared to a conventional technique even when there is no accumulation of data.SOLUTION: A defecation prediction support system includes: a sensor part that detects flatus of a target person; an acquisition part that acquires target person information regarding the target person; and a presentation part that presents, to a user, flatus information regarding flatus detected by the sensor part and the target person information acquired by the acquisition part. The defecation prediction support system supports defecation prediction of the target person by the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a defecation prediction assistance system, a defecation prediction assistance method, and a defecation prediction assistance program. [Background technology]

[0002] For example, in the field of caregiving, failure to toilet can cause a serious loss of self-esteem for the care recipient, especially when it comes to bowel movements. It is important for caregivers to assist the care recipient as much as possible so that they can perform toileting independently. However, coupled with the decline in the care recipient's own physical strength and awareness of the need to defecate, it can be difficult for caregivers to guide the care recipient to the toilet at the appropriate time.

[0003] However, while many studies have been conducted to date on quickly detecting the state of stool in a diaper (Patent Document 1, Patent Document 2), there is no effective method for predicting bowel movements. Furthermore, while studies have been conducted on systems that use prior excretion rhythms as a reference for predicting bowel movements (Patent Document 3), these systems predict the time of the next bowel movement based on past excretion timing, so they lack immediacy when used, and are based on the assumption that lifestyle habits will not change, and do not take into account changes in dietary or exercise habits, etc. As a result, the accuracy of predictions is poor when accompanied by changes in health status or motor function, and it is necessary to collect and model a large amount of data for each caregiver, which poses significant barriers to use in actual care settings. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-163815 [Patent Document 2] Japanese Patent Publication No. 2022-068409 [Patent Document 3] Japanese Patent Publication No. 2021-121978 Summary of the Invention [Problem to be solved by the invention]

[0005] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a system that presents information that assists in predicting the timing of a subject's (e.g., a care recipient's) defecation more accurately than conventional methods, even when no data is stored, and allows the user (e.g., a caregiver) to guide the care recipient to the toilet at the appropriate time, change diapers at the appropriate time, etc., thereby improving the self-esteem of the subject (e.g., a care recipient) and eliminating the burden on the user of frequently performing heavy work such as guiding the care recipient to the toilet and changing diapers. [Means for solving the problem]

[0006] That is, the defecation prediction assistance system, the defecation prediction assistance method, and the defecation prediction assistance program according to the present invention are as follows. [1] A defecation prediction assistance system comprising: a sensor unit that detects flatus from a subject; an acquisition unit that acquires subject information about the subject; and a presentation unit that presents to a user the flatus information about the flatus detected by the sensor unit and the subject information acquired by the acquisition unit, and assists the user in predicting defecation of the subject. [2] A defecation prediction assistance system comprising: a sensor unit that detects flatus of a subject; an acquisition unit that acquires subject information about the subject; a memory unit that stores flatus information about the flatus detected by the sensor unit and the subject information acquired by the acquisition unit; and an estimation unit that estimates defecation prediction information about the subject's next defecation based on the flatus information and the subject information stored in the memory unit. [3] The defecation prediction assistance system according to [1] or [2], wherein the sensor unit comprises a sensor and a flatulence determination unit that determines whether flatulence has occurred based on a signal output from the sensor. [4] The defecation prediction assistance system described in [3], wherein the flatulence information includes one or more of the type, intensity, and detection time of the signal output from the sensor and determined to be flatulence by the flatulence determination unit. [5] The defecation prediction assistance system according to any one of [1] to [4], wherein the subject information includes identification information for identifying the subject. [6] The bowel movement prediction assistance system according to any one of [1] to [5], wherein the subject information includes at least one of the subject's dietary information, the subject's excretion information, the subject's medication information, and the subject's exercise information. [7] The bowel movement prediction assistance system described in [2], wherein the bowel movement prediction information includes the timing of the next bowel movement and / or assistance information required for the next bowel movement assistance. [8] The bowel movement prediction assistance system according to [3] or [4], wherein the sensor is a sensor capable of detecting gas. [9] The defecation prediction assistance system according to [3] or [4], wherein the sensor performs detection at predetermined time intervals.

[10] The presenting unit presents one or more of the flatus information, the subject information, and the defecation prediction information to the user via light and / or sound; The defecation prediction assistance system according to any one of [1] to [9], wherein the subject information does not identify the subject.

[11] The defecation prediction assistance system according to any one of [1] to

[10] , wherein the presentation unit further comprises a terminal that presents one or more of the flatus information, the subject information, and the defecation prediction information to the user.

[12] The defecation prediction assistance system according to

[11] , wherein the terminal displays the defecation prediction information by one or more of a pop-up screen, a change in color tone of the display screen, and a change in brightness of the display screen.

[13] The defecation prediction assistance system described in [2] or [7], wherein the estimation unit estimates the next defecation prediction information of the subject using a machine learning model obtained based on training data including the flatus information and the subject information stored in the memory unit.

[14] A defecation prediction assistance method, which detects flatus from a subject using a sensor unit, acquires subject information about the subject, and presents the flatus information about the flatus detected by the sensor unit and the acquired subject information to a user.

[15] A defecation prediction assistance method that detects flatus from a subject using a sensor unit, acquires subject information about the subject, stores the flatus information about the flatus detected by the sensor unit and the acquired subject information, and estimates defecation prediction information about the subject's next defecation based on the stored flatus information and subject information.

[16] A defecation prediction assistance program characterized by causing a computer to function as an estimation unit that estimates defecation prediction information regarding the subject's next defecation using a machine learning model obtained based on training data including flatus information regarding the subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit.

[17] A machine learning device comprising: a teacher data receiving unit that acquires teacher data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit; and a machine learning model generation unit that generates a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the teacher data acquired by the teacher data receiving unit.

[18] A machine learning method for acquiring training data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit, and generating a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the acquired training data.

[19] A machine learning program that causes a computer to function as a data receiving unit that acquires training data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit, and a machine learning model generation unit that generates a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the training data acquired by the data receiving unit. [Effects of the Invention]

[0007] According to the present invention, even in the absence of accumulated data, by presenting information that assists in predicting the timing of a subject's defecation more accurately than conventional methods, the user (e.g., a caregiver) can guide the person being cared for to the toilet at the appropriate time or change their diaper at the appropriate time, thereby improving the self-esteem of the subject (e.g., the person being cared for) and eliminating the burden on the user of frequently performing heavy tasks such as guiding the person to the toilet and changing their diaper. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is an overall schematic diagram of a defecation prediction assistance system according to an embodiment of the present invention; [Figure 2] 3A and 3B are diagrams illustrating the structure of the vicinity of a sensor unit of the defecation prediction assistance system according to the present embodiment. [Figure 3] 1A and 1B are schematic diagrams showing a procedure for assisting defecation prediction and prediction results using the defecation prediction assistance system according to the present embodiment. [Figure 4] 1A and 1B are schematic diagrams showing a procedure for assisting defecation prediction and prediction results using the defecation prediction assistance system according to the present embodiment. [Figure 5] FIG. 2 is a schematic diagram showing sensors used in the defecation prediction assistance system according to the present embodiment. [Figure 6] FIG. 10 is a schematic diagram showing a machine learning device according to another embodiment of the present invention. [Figure 7] 1 is a diagram illustrating a structure near a sensor unit of a defecation prediction assistance system according to an embodiment of the present invention. FIG. [Figure 8] 8 is a graph showing the results of flatus detection by the sensor unit shown in FIG. 7. DETAILED DESCRIPTION OF THE INVENTION

[0009] An embodiment of the present invention will be described below with reference to the drawings.

[0010] <Configuration of the defecation prediction assistance system according to this embodiment> The defecation prediction assistance system 100 of this embodiment assists a user in predicting defecation of a subject, and, for example, as shown in FIG. 1, includes a sensor unit 1 that detects flatus from the subject, an acquisition unit 2 that acquires subject information about the subject, and a presentation unit 3 that presents to the user the flatus information about the flatus detected by the sensor unit 1 and the subject information acquired by the acquisition unit.

[0011] The sensor unit 1 includes a sensor 11 that detects substances that constitute the odor emitted from the subject's body (hereinafter also referred to as odor substances), and a flatulence determination unit 12 that determines whether the odor is caused by the subject's flatulence based on a signal related to the odor substance detected by the sensor 11.

[0012] The sensor unit 1 may be placed, for example, inside a hollow mat or cushion placed on a bed or chair on which the subject is lying, or may be connected to the inside of the aforementioned mat or cushion via a tube, as shown in Figure 2.

[0013] The tube is preferably, for example, 10 cm to 10 m in length so as not to interfere with the movement of the subject or user at the bedside, etc. Furthermore, it is preferable to use a coil tube made of a flexible material such as nylon or urethane as such a tube.

[0014] A pump may also be used to guide the air inside the mattress to the sensor unit 1 by, for example, reducing the pressure inside the tube. This pump is preferably operable within a voltage range of, for example, 1.5 V or more and 2 V or less. Setting the pump's operating pressure to 2 V or less is preferable because the operating noise of the pump can be reduced sufficiently to allow it to be used at the bedside. Setting the pump's operating voltage to 1.5 V or more makes it possible to guide sufficient air to the sensor unit 1 even when using the coiled tube described above, which has an outer diameter of 6 mm or less (an inner diameter of approximately 5 mm or less) and a length of 5 m or more.

[0015] The sensor 11 is not particularly limited and may be one or more of the following sensors capable of detecting odor-related substances: a semiconductor gas sensor, a gas sensor using an organic polymer, an alcohol detection device, etc. In this embodiment, an example of such a sensor 11 is an odor sensor equipped with a sensor element 111 having an odorant-receiving layer whose electrical conductivity changes upon adsorption of an odor-related substance, and a voltmeter 112 for measuring the change in electrical conductivity of the odorant-receiving layer. Details of the odor sensor employed in this embodiment will be described later.

[0016] The flatulence determination unit 12 receives a signal related to an odor detected by the aforementioned sensor 11 and determines whether the signal is due to flatulence by the subject, for example, by comparing the intensity of one or more pre-specified types of signals with a predetermined threshold value for each of these signals. Specifically, the flatulence determination unit 12 may receive a signal relating to an odor detected continuously or intermittently by the sensor 11, compare the intensity of this signal, for example, a signal relating to a component characteristic of intestinal gas, with a predetermined threshold every 10 seconds, and determine that flatulence has occurred if the intensity of the detected signal is greater than the threshold. In addition, the flatulence determination unit 12 may calculate the signal intensity ratio of the signal detected by the sensor 11 within a predetermined time period for multiple components characteristic of these intestinal gases, compare it with the signal intensity ratio calculated in advance for the subject's flatulence, and determine that flatulence has occurred if the difference between these signal intensity ratios falls within a predetermined range. Note that, examples of the components characteristic of intestinal gas include hydrogen, hydrogen sulfide, etc. These components may be detected by one type of sensor or by multiple types of sensors 11.

[0017] This flatulence determination unit 12 is physically one or more general-purpose computers COM that have analog electrical circuits including buffers, amplifiers, etc., digital electrical circuits including a CPU, memory, DSP, etc., and A / D converters and the like interposed between them, and this computer COM is configured to function as the flatulence determination unit 12 by the CPU and its peripheral devices working together in accordance with a predetermined program stored in the memory.

[0018] The acquisition unit 2, like the flatus determination unit 12 described above, is a computer COM that performs its functions, and is connected to external databases, input devices, etc., to acquire subject information from these.

[0019] The presentation unit 3 receives the flatulence information and subject information output from the acquisition unit 2 and presents the flatulence information and / or subject information to the user, and may include, for example, one or more of a display device, a lighting device, a sound device, a vibration generating device, etc., arranged in the room where the user is working.

[0020] The aforementioned presentation unit 3 does not present the aforementioned flatulence information and / or subject information to the user, but may, for example, present to the user defecation prediction information regarding the subject's next defecation estimated by the estimation unit 4.

[0021] In this case, the computer may be configured to perform the functions of the estimation unit 4. The computer may also be configured to perform the functions of the storage unit 5 that stores and accumulates the teacher data acquired and created by the acquisition unit 2, and the machine learning model generation unit 6 that generates a machine learning model by performing machine learning based on the teacher data accumulated in the storage unit 5.

[0022] The estimation unit 4 is configured to estimate the subject's next bowel movement using the machine learning model generated by the machine learning model generation unit 6 and the flatus information and subject information newly received by the acquisition unit 2, and output bowel movement prediction information to the presentation unit 3.

[0023] <Defecation prediction assistance method using the defecation prediction assistance system according to this embodiment> As a method for assisting in defecation prediction using the defecation prediction assistance system 100 configured in this manner, for example, two methods as shown in FIGS. 3 and 4 can be mentioned.

[0024] First, the flow shown in FIG. 3 will be described. In the flow shown in FIG. 3, first, the odor emitted from the subject's body is detected by the sensor 11 placed near the subject.

[0025] The sensing by the sensor 11 is preferably performed at predetermined intervals, and the intervals are preferably set to a frequency of, for example, 0.1 Hz or more and 100 Hz or less.

[0026] When the flatus determination unit 12 detects flatus based on the signal related to the smell detected by the sensor 11, flatus information related to this flatus is output to the acquisition unit 2 (S1-1).

[0027] The flatulence information output here includes, for example, flatulence signal information relating to the signal value (type and intensity of the signal) caused by chemical substances contained in the flatulence detected by sensor 11, and flatulence time information relating to the time when this signal was detected.

[0028] The acquisition unit 2 also receives flatulence information from the sensor unit 1 (flatulence determination unit 12) and also receives subject information relating to the subject whose defecation is to be predicted (S1-2), and outputs this flatulence information and subject information in a linked state to the presentation unit 3 and / or memory unit 5.

[0029] The subject information received by the acquisition unit includes, for example, one or more of identification information, dietary information, excretion information, medication information, exercise information, and the like.

[0030] The identification information includes, for example, subject identification information for identifying the subject himself / herself, such as the subject's name, age, and gender, and / or sensor identification information for identifying the sensor 11 placed near the subject's body.

[0031] The timing and amount of defecation are thought to be particularly influenced by the subject's most recent meal. Therefore, it is preferable that the meal information include, for example, one or more of the following: meal type information relating to the subject's past meal types; meal amount information relating to the subject's past meal amounts; and meal time information relating to the subject's past meal times.

[0032] The timing and amount of defecation are greatly affected by the time since the last defecation, etc. Therefore, it is preferable that the excretion information includes, for example, one or more of excretion type information relating to the subject's past excretion types (defecation, urination, flatulence), excretion amount information relating to the subject's past excretion amounts, defecation difficulty information relating to the difficulty of defecation during the subject's past defecation, and excretion time information relating to the subject's past excretion times.

[0033] If the subject is taking medications that affect bowel movements, such as laxatives, medication information is also important information about the subject. Therefore, it is preferable that the medication information includes, for example, one or more of medication type information regarding the type of medication given to the subject in the past, medication amount information regarding the amount of medication given to the subject in the past, and medication time information regarding the time of medication given to the subject in the past.

[0034] Since bowel movements may be encouraged by the subject's physical activity, it is preferable that the exercise information include one or more of the following: exercise type information regarding the type and / or intensity of the subject's past exercise; exercise amount information regarding the amount of exercise the subject has done in the past; and exercise time information regarding the amount of time the subject has exercised in the past.

[0035] The presentation unit 3, which has received the subject information and flatulence information from the acquisition unit 2, presents the subject information and / or information to the user (S1-3). There are no particular limitations on the method for presenting this information, but it is preferable that the information be presented in such a way that the identity of the subject is not known to anyone other than the user.

[0036] An example of such a presentation method is a method using an illumination device and / or an audio device placed in a position where the user can notice it even while doing other work, and a display device (such as a display connected to a computer) as the presentation unit 3. Using such a presentation unit 3, the user may first be notified that flatus has been detected in any of the subjects by light or sound from the illumination device or audio device, and the user who notices this light or sound may check details of the subject information displayed on the display of a terminal device or the like.

[0037] Next, based on the flatus information and / or subject information presented by the presentation unit 3, the user predicts the subject's next bowel movement.

[0038] In this case, the user is preferably someone who can predict the subject's next bowel movement from the flatulence information and subject information, and such users may include, for example, nursery school teachers, nurses, caregivers, and other skilled caregivers.

[0039] 4, for example, first the acquisition unit 2 acquires flatus information previously detected by the sensor unit 1 and subject information about the subject from whom the flatus information was obtained (including actual defecation results after the flatus information was obtained) (S2-1). Then, for example, the acquisition unit 2 links these to generate a set of data (teaching data) containing, as components, the flatus information and the subject information linked to the flatus information.

[0040] The storage unit 5 receives the training data from the acquisition unit 2, and stores and accumulates the training data.

[0041] Once the training data is accumulated in the memory unit 5 as described above, the machine learning model generation unit 6 generates a machine learning model that predicts defecation based on the flatus information and subject information, based on the training data accumulated in the memory unit 5 (S2-2).

[0042] After the machine learning model is generated in this way, the acquisition unit 2 acquires flatulence information obtained by the sensor unit 1 for the subject whose next bowel movement is to be predicted, and sends it to the estimation unit 4 (S2-3).

[0043] The estimation unit 4 estimates the subject's next bowel movement based on the machine learning model generated by the machine learning model generation unit 6, the flatus information, and the subject information (S2-4), and outputs bowel movement prediction information as the estimation result to the presentation unit 3.

[0044] The aforementioned defecation prediction information includes one or more of the following: time information regarding the timing of the subject's next defecation (date and time of the next defecation, remaining time until the next defecation, etc.), assistance information regarding the assistance required to assist the subject's next defecation, etc.

[0045] Examples of assistance information include the condition of the subject's stool at the time of their next bowel movement (information such as whether the stool is hard or loose, and index values ​​such as the Bristol scale) and the amount of stool at the time of the subject's next bowel movement.

[0046] The presentation unit 3, which has received the defecation prediction information from the estimation unit 4, presents the defecation prediction information to the user (S2-5).

[0047] In this case, a preferred example of the presentation unit 3 is a small terminal (such as a smartphone) equipped with a display device that can be easily checked by each individual user. The defecation prediction information is preferably displayed in an easy-to-understand manner on the display by installing a necessary application on the small terminal, and may be presented to the user as a pop-up on the display, or may be presented to the user by changing the color tone and / or brightness of the display, for example.

[0048] More preferably, the two flows shown in Figures 3 and 4 should be realized by a single defecation assistance system, and a set of data linking flatus information obtained by a flow using an expert user as shown in Figure 3 with subject information (including actual defecation results) should be used as training data in a defecation prediction assistance system that uses machine learning as shown in Figure 4.

[0049] <Odor sensor> As described above, at least one of the sensors 11 included in the sensor unit 1 according to this embodiment is an odor sensor including one or more sensor elements 111. The sensor element 111 comprises a substrate, an odorant receiving layer formed on the substrate, and metal wiring for electrically connecting the odorant receiving layer to the aforementioned voltmeter 112, as shown in Figure 5, for example.

[0050] [substrate] The substrate may be any of a wide variety of substrates commonly used in electronic circuits, including substrates made of one or more materials selected from the group consisting of glass epoxy, paper, and glass cloth.

[0051] [Odor receptor layer] The odorant receiving layer preferably contains, for example, a resin composition whose electrical conductivity differs when odorant a is adsorbed and when odorant b, a substance different from odorant a, is adsorbed, and is made of such a resin composition.

[0052] This resin composition contains, for example, a resin (A) and a conductive carbon material (B).

[0053] (Resin (A)) The resin (A) contained in the resin composition according to one embodiment of the present invention is not particularly limited, but preferably contains at least one resin selected from the group consisting of urethane resin, polyalkylene oxide resin, acrylic resin, fluorine-containing resin, vinyl polymer resin, silicone resin, polyamide resin, polyester resin, epoxy resin, phenol resin, polyphenylene oxide resin, polyimide resin, polybutadiene resin, styrene-butadiene resin, and polyisoprene resin.

[0054] (Conductive carbon material (B)) The conductive carbon material (B) is, for example, a carbon material having a volume resistivity of 0.1 Ω cm or less. This conductive carbon material (B) is dispersed in the resin composition, and the conductive carbon material (B) contacts each other to form conductive paths, thereby imparting conductivity to the resin composition.

[0055] Specific examples of the conductive carbon material (B) include carbon black, carbon nanotubes, and graphene.

[0056] The conductive carbon material (B) is preferably in the form of fibers or spheres.

[0057] When the conductive carbon material (B) is fibrous, the fiber diameter is preferably 0.1 μm to 10 μm, more preferably 0.1 μm to 5 μm, and when the conductive carbon material (B) is fibrous, the fiber length is preferably 0.1 μm to 10 μm, more preferably 1 μm to 10 μm.

[0058] When the conductive carbon material (B) is spherical, the primary particle diameter is preferably 10 nm or more and 200 nm or less, and more preferably 20 nm or more and 150 nm or less. The primary particle diameter is more preferably 100 nm or less, since this can further improve the conductivity in the resin composition and the sensitivity of the sensor 11.

[0059] The primary particle diameter of the conductive carbon material (B) can be measured, for example, by a transmission electron microscope (TEM). The primary particle diameter of the conductive carbon material (B) can be measured by observing the particle diameter using a microscope and analyzing the image using an image processing device (for example, a digital microscope VHX-700F manufactured by Keyence Corporation). The primary particle diameter of the conductive carbon material (B) can also be determined by other known methods. Furthermore, when the conductive carbon material (B) is a known material or a commercially available product, the primary particle diameter may be a literature value, a catalog value, or the like.

[0060] The content of the conductive carbon material (B) is preferably 5% by weight or more and 30% by weight or less, relative to 100% by weight of the total of the resin (A) and the conductive carbon material (B), from the viewpoint of ensuring that the sensor element 111 formed from the resin composition exhibits sufficient conductivity as an odor sensor and sufficient sensitivity as the odor sensor.

[0061] The resin composition may further contain a surfactant in addition to the resin (A) and the conductive carbon material (B) described above, as long as the effects of the present invention are obtained. The surfactant preferably acts as a dispersant for the conductive carbon material (B) described below, and for example, one or more surfactants can be appropriately selected from anionic surfactants, cationic surfactants, amphoteric surfactants, and nonionic surfactants. The resin composition may further contain other components in addition to those described above, and the other components can be suitably used within a range in which both the effects of the present invention and the effects of the other components can be obtained.

[0062] [Metal wiring] The metal wiring is disposed so as to be in contact with the odorant receiving layer described above, and includes, for example, a first metal wiring and a second metal wiring.

[0063] These first and second metal wirings are preferably made of copper, gold, or the like, and preferably have a flat cross-sectional shape.

[0064] The width of each of the first and second metal wirings as viewed perpendicular to the surface of the substrate is preferably 10 μm to 2 mm, more preferably 10 μm to 1 mm, and the height, i.e., thickness, of each of the first and second metal wirings as viewed parallel to the surface of the substrate is preferably 1 μm to 100 μm, more preferably 10 μm to 50 μm.

[0065] It is preferable that the first metal wiring and the second metal wiring are not in direct contact with each other, but are arranged substantially parallel to each other as shown in FIG.

[0066] As described above, the distance between the first metal wiring and the second metal wiring arranged approximately in parallel is preferably 1 μm or more and 3 mm or less, and more preferably 1 μm or more and 1.5 mm or less.

[0067] The distance between the first metal wiring and the second metal wiring is preferably a predetermined distance (e.g., 500 μm) or less when the electrical conductivity of the odorant receiving layer (i.e., the electrical conductivity of the sensor element 111) is low.

[0068] The length of the first metal wiring and the second metal wiring in contact with the odorant receiving layer is preferably 100 μm or more and 50 mm or less, and more preferably 500 μm or more and 30 mm or less.

[0069] [Method of manufacturing sensor element] Examples of methods for manufacturing a sensor element having an odorant-receiving layer and metal wiring as described above include the following.

[0070] First, the resin (A), conductive carbon material (B), and optionally surfactants and solvents constituting the resin composition are mixed and kneaded uniformly with a mixer to prepare a slurry containing the resin composition. Next, this slurry is applied to cover the metal wiring arranged on the substrate, and if a solvent is added, the solvent is removed by drying to form an odorant receiving layer. This odorant receiving layer is preferably formed so as to contact both the first metal wiring and the second metal wiring, and so that the portion covering the first metal wiring and the portion covering the second metal wiring are continuous.

[0071] The above-mentioned solvent may be blended into the resin composition from the viewpoint of increasing the compatibility between the resin (A) and the surfactant, increasing the dispersibility of the conductive carbon material (B) in the resin composition, or increasing the coatability of the resin composition.

[0072] Specific examples of the solvent include one or more selected from the group consisting of N-methyl-2-pyrrolidone, propylene glycol monomethyl ether acetate, ethyl butyrate, butyl butyrate, ethyl acetate, N,N-dimethylformamide, N,N-dimethylacetamide, toluene, and xylene.

[0073] The content of the solvent in the slurry containing the resin composition can be appropriately determined from the above viewpoints. For example, from the viewpoint of coatability, the content of the solvent is preferably 100 parts by weight or more and 10,000 parts by weight or less per 100 parts by weight of the total of the resin (A) and the conductive carbon material (B).

[0074] <Effects of this embodiment> The defecation prediction assistance system 100 according to this embodiment configured as described above can save the user (e.g., a caregiver) time and effort by presenting information that assists in predicting the defecation timing of a subject (e.g., a care recipient) more accurately than before, even when there is no accumulated data, and can immediately start using the presented information in combination with the user's experience as a tool for predicting defecation. Therefore, there is no need for the expertise required for data accumulation and creation of training data, or for preparing a database system, and there are advantages such as no preparation time being required and high immediacy.

[0075] Furthermore, once a certain amount of training data has been accumulated, it is also possible to provide defecation prediction information that can predict the subject's next defecation. In this case, the user is not required to have a high level of expertise in nursing or caregiving, and for example, an individual user who is caring for or looking after a family member or relative at home can easily predict the subject's next defecation. The accumulation of training data can be carried out simultaneously with the implementation of the above-mentioned form of information presentation that assists the user in predicting the subject's defecation timing, thereby providing excellent effects in terms of both immediacy and accuracy when applied to the field. Furthermore, even if changes in health conditions lead to changes in dietary or exercise habits or the use of laxatives, a high level of prediction accuracy can be maintained by taking into account the degree of impact of these factors based on flatus data.

[0076] By presenting the user with the condition and amount of stool as defecation prediction information, it is possible to prepare in advance the methods for guiding the user to the restroom and the necessary assistance tools and systems for assisting with defecation, such as changing underwear and diapers.

[0077] Since the sensor 11 has the configuration described in the above embodiment, it is possible to detect flatus of the subject with higher accuracy.

[0078] By setting the sensing interval by the sensor 11 within the range of 0.1 Hz to 100 Hz, the amount of data does not become too large, and even if the timing of flatulence and the timing of sensing by the sensor are out of sync, the odorous substances contained in the flatus can be reliably detected before they diffuse and become too diluted.

[0079] <Other embodiments of the present invention> The present invention is not limited to the above-described embodiment. For example, the defecation prediction assistance system does not necessarily have to perform both the flow shown in Figure 3 and the flow shown in Figure 4 described in the above embodiment, as long as it assists the user in predicting defecation using either method.For example, it may omit one or more of the estimation unit, memory unit, and machine learning model generation unit from the above-mentioned configuration.

[0080] The flatulence information and subject information are not limited to the above-mentioned methods, and may be manually input by the user to the acquisition unit, or may be directly input to the acquisition unit from one or more measuring devices including the sensor.

[0081] The notification unit may also be a lighting device or the like that can emit visible light of multiple colors and / or that can control the light emission pattern, such as the blinking interval, and notify the person of the flatus by changing the light emission pattern or color for each person. In this way, the user can easily notify which of multiple people has detected flatus.

[0082] Some or all of the functions of the flatus determination unit may be performed by a sensor rather than a computer.

[0083] Furthermore, some of the functions previously performed by the computer may be performed by sensors and / or terminal devices connected to the sensors, and other parts of the functions previously performed by the computer may be performed by a machine learning device consisting of an independent server device that can communicate with multiple sensors via the Internet, for example, and may collect training data from sensors used by an unspecified number of users and distribute defecation prediction information or machine learning models estimated using a machine learning model to each of multiple sensors.

[0084] In this case, the machine learning device may include, for example, an acquisition unit (also called a teacher data receiving unit) that receives teacher data, a memory unit, and a machine learning model generation unit, as shown in Figure 6, which accumulates teacher data output from multiple sensors, generates a machine learning model, and outputs the machine learning model generated for each sensor.

[0085] In addition, some or all of the above-described embodiments and modified embodiments may be combined as appropriate, and it goes without saying that various modifications are possible within the scope of the spirit thereof. [Example]

[0086] The present invention will be further described below with reference to specific examples, but it goes without saying that the present invention is not limited to these. In this example, as shown in Figure 7, a chair cushion with a hollow core covered with a cloth cover was connected to the sensor unit of the defecation prediction system of the present invention via a tube, and it was verified whether flatulence could be detected when a subject flatulenced while sitting on the cushion.

[0087] The tube used was a 5m long coil tube made of urethane. The outer diameter of this tube was 6mm and the inner diameter was about 4mm. A commercially available small pump was used as a pump to supply air to the sensor unit through this tube, and the voltage supplied to the pump was between 1.5V and 2V. The sensor unit used was equipped with one or more of the above-mentioned odor sensors and other gas sensors, and was capable of measuring odor-related substances such as carbon dioxide (CO2), volatile organic compounds (VOC), reducing gases (RED), oxidizing gases (OX), ammonia (NH3), sulfur, and hydrogen (H2).

[0088] FIG. 8 shows the substance detection signal when a subject actually farts in the above-described configuration. The results in FIG. 8 show that the detected signal values ​​for many components change significantly at the timing of flatulence. As can be seen in Figure 8, the system of the present invention can accurately detect changes in the signal intensity of each component during flatulence, and can therefore accurately determine whether flatulence has occurred based on the detection results.This can then be displayed to the user as flatulence information together with subject information, or the next bowel movement can be predicted using machine learning or the like based on the flatulence information and subject information. [Explanation of symbols]

[0089] 100···Defecation Prediction Assistance System 1. Sensor section 11 Sensor 12...Fart judgment department 2...Acquisition part 3...Presentation part 4... Estimation part 5...Storage section 6 Machine learning model generation part

Claims

1. a sensor unit that detects flatus from a subject; an acquisition unit that acquires subject information related to the subject; a presentation unit that presents to a user flatus information regarding flatus detected by the sensor unit and the subject information acquired by the acquisition unit, A defecation prediction assistance system that assists the user in predicting the defecation of the subject.

2. a sensor unit that detects flatus from a subject; an acquisition unit that acquires subject information related to the subject; a storage unit that stores flatus information regarding flatus detected by the sensor unit and the subject information acquired by the acquisition unit; an estimation unit that estimates defecation prediction information regarding the subject's next defecation based on the flatus information and the subject information stored in the memory unit.

3. 3. The defecation prediction assistance system according to claim 1, wherein the sensor unit comprises a sensor and a flatus determination unit that determines whether flatus has occurred based on a signal output from the sensor.

4. 4. The defecation prediction assistance system according to claim 3, wherein the flatulence information includes one or more of the type, intensity, and detection time of a signal output from the sensor and determined to be flatulence by the flatulence determination unit.

5. 3. The defecation prediction assistance system according to claim 1, wherein the subject information includes identification information for identifying the subject.

6. 3. The defecation prediction assistance system according to claim 1, wherein the subject information includes at least one of dietary information of the subject, excretion information of the subject, medication information of the subject, and exercise information of the subject.

7. The defecation prediction assistance system according to claim 2 , wherein the defecation prediction information includes information on the timing of the next defecation and / or information on assistance required for the next defecation.

8. The defecation prediction assistance system according to claim 3 , wherein the sensor is a sensor capable of detecting gas.

9. 4. The defecation prediction assistance system according to claim 3, wherein the sensor performs detection at predetermined time intervals.

10. the presenting unit presents one or more of the flatus information, the subject information, and the defecation prediction information to the user via light and / or sound; The defecation prediction assistance system according to claim 1 or 2, wherein the subject information does not identify the subject.

11. The defecation prediction assistance system according to claim 1 or 2, wherein the presenting unit further comprises a terminal that presents one or more of the flatus information, the subject information, and the defecation prediction information to the user.

12. The defecation prediction assistance system according to claim 11, wherein the terminal displays the defecation prediction information by one or more of a pop-up screen, a change in color tone of a display screen, and a change in brightness of a display screen.

13. 3. The defecation prediction assistance system according to claim 2, wherein the estimation unit estimates defecation prediction information regarding the subject's next defecation using a machine learning model obtained based on training data including the flatus information and the subject information stored in the storage unit.

14. A defecation prediction assistance method that detects flatus of a subject using a sensor unit, acquires subject information about the subject, and presents the flatus information about the flatus detected by the sensor unit and the acquired subject information to a user.

15. A defecation prediction assistance method that detects flatus from a subject using a sensor unit, acquires subject information about the subject, stores the flatus information about the flatus detected by the sensor unit and the acquired subject information, and estimates defecation prediction information about the subject's next defecation based on the stored flatus information and subject information.

16. A defecation prediction assistance program that causes a computer to function as an estimation unit that estimates defecation prediction information regarding a subject's next defecation using a machine learning model obtained based on training data including flatus information regarding the subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit.

17. A machine learning device comprising: a teacher data receiving unit that acquires teacher data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit; and a machine learning model generation unit that generates a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the teacher data acquired by the teacher data receiving unit.

18. A machine learning method that acquires training data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit, and generates a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the acquired training data.

19. A machine learning program that causes a computer to function as a teacher data receiving unit that acquires teacher data including flatus information regarding a subject's flatus detected by a sensor unit and subject information regarding the subject acquired by an acquisition unit, and a machine learning model generation unit that generates a machine learning model for estimating bowel movement prediction information regarding the subject's next bowel movement based on the teacher data acquired by the teacher data receiving unit.

Images