Processing apparatus, processing program, processing method, and processing system

Abstract

To provide a processing apparatus, a processing program, a processing method, and a processing system that can more appropriately evaluate the oral cavity of an object.SOLUTION: A method in a processing apparatus provided with at least one processor includes: acquiring a subject image including, as a subject, at least part of the oral cavity of an object photographed by a user terminal device that can be used by a user; inputting the subject image to a learned evaluation model for evaluating the state of the oral cavity of the object to acquire first evaluation information indicating a result of evaluation of the state of the oral cavity of the object; on the basis of at least one of attribute information of the object and the first evaluation information and respective attribute information of a plurality of experts who can evaluate the first evaluation information, acquiring second evaluation information indicating a result of evaluation of the first evaluation information, which is input by one or more first experts selected from the plurality of experts; and outputting evaluation result information based on the second evaluation information to the user terminal device.SELECTED DRAWING: Figure 5A

Description

[Technical Field]

[0001] The present disclosure relates to a processing device, a processing program, a processing method, and a processing system capable of processing a subject image including at least a part of a subject's oral cavity as a subject. [Background technology]

[0002] Processing systems for evaluating the oral condition of a subject have been known for some time. For example, Patent Document 1 describes a system for executing "an oral care management method, which comprises creating user information and client information for a person requiring oral care, conducting an assessment on the person requiring oral care to create assessment information, creating an oral care assessment, an oral care plan, and a denture creation plan based on the assessment information, inputting and registering these into a computer via a program, and managing oral care using this information." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2001-167215 Summary of the Invention [Problem to be solved by the invention]

[0004] Therefore, in light of the above-mentioned technology, the present disclosure aims to provide a processing device, processing program, processing method, and processing system that can more appropriately evaluate the oral cavity of a subject through various embodiments. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided a processing device having at least one processor, wherein the at least one processor is configured to acquire a subject image including at least a portion of a subject's oral cavity as a subject, photographed by a user terminal device usable by a user, input the subject image into a learned evaluation model for evaluating the condition of the subject's oral cavity, thereby acquiring first evaluation information indicating the results of the evaluation of the condition of the subject's oral cavity, acquire second evaluation information indicating the results of evaluation of the first evaluation information input by one or more first experts selected from a plurality of experts based on at least one of the subject's attribute information and the first evaluation information and each attribute information of a plurality of experts who can evaluate the first evaluation information, and output evaluation result information based on the second evaluation information to the user terminal device.

[0006] According to one aspect of the present disclosure, there is provided a processing program that, when executed by at least one processor, causes the at least one processor to function in the following manner: acquire a subject image including at least a portion of a subject's oral cavity as a subject, photographed by a user terminal device that can be used by a user; acquire first evaluation information indicating the results of the evaluation of the subject's oral cavity condition by inputting the subject image into a learned evaluation model for evaluating the state of the subject's oral cavity; acquire second evaluation information indicating the results of evaluation of the first evaluation information input by one or more first experts selected from a plurality of experts based on at least one of the subject's attribute information and the first evaluation information and each attribute information of the plurality of experts who can evaluate the first evaluation information; and output evaluation result information based on the second evaluation information to the user terminal device.

[0007] According to one aspect of the present disclosure, there is provided a processing method executed by at least one processor, the processing method including: a step of acquiring a subject image including at least a portion of a subject's oral cavity as a subject, the subject image being photographed by a user terminal device usable by a user; a step of acquiring first evaluation information indicating the results of an evaluation of the subject's oral cavity condition by inputting the subject image into a learned evaluation model for evaluating the state of the subject's oral cavity; a step of acquiring second evaluation information indicating the results of an evaluation of the first evaluation information, input by one or more first experts selected from a plurality of experts based on at least one of the subject's attribute information and the first evaluation information and each attribute information of the plurality of experts who can evaluate the first evaluation information; and a step of outputting evaluation result information based on the second evaluation information to the user terminal device.

[0008] According to one aspect of the present disclosure, the processing system includes a user terminal device configured to capture a subject image including at least a portion of a subject's oral cavity as a subject, and a processing device communicatively connected to the user terminal device. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to provide a processing device, a processing program, a processing method, and a processing system that are capable of more appropriately evaluating the oral cavity of a subject.

[0010] It should be noted that the above effects are merely illustrative for the sake of convenience and are not limiting. In addition to or instead of the above effects, any effect described in this disclosure or an effect obvious to a person skilled in the art may be achieved. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing the configuration of a processing system 1 according to an embodiment of the present disclosure. [Figure 2A] FIG. 2A is a block diagram showing a configuration of a processing device 100 according to an embodiment of the present disclosure. [Figure 2B] FIG. 2B is a block diagram showing a configuration of a terminal device 200 according to an embodiment of the present disclosure. [Figure 3A] FIG. 3A is a diagram conceptually showing a subject management table stored in processing device 100 according to an embodiment of the present disclosure. [Figure 3B] FIG. 3B is a diagram conceptually illustrating an example of a subject image according to an embodiment of the present disclosure. [Figure 3C] FIG. 3C is a diagram conceptually illustrating an expert management table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 4A] FIG. 4A is a diagram showing a processing sequence executed by the processing system 1 according to an embodiment of the present disclosure. [Figure 4B] FIG. 4B is a diagram showing a processing sequence executed by the processing system 1 according to an embodiment of the present disclosure. [Figure 5A] FIG. 5A is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 5B] FIG. 5B is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 5C] FIG. 5C is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram showing a processing flow for generating a trained evaluation model according to an embodiment of the present disclosure. [Figure 7A] FIG. 7A is a diagram showing an example of a first evaluation information screen output on the expert terminal device 200-2 according to an embodiment of the present disclosure. [Figure 7B] FIG. 7B is a diagram showing an example of a second evaluation information screen output on the expert terminal device 200-2 according to an embodiment of the present disclosure. [Figure 7C] FIG. 7C is a diagram showing an example of an evaluation result information screen output on the user terminal device 200-1 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] 1. Overview of Processing System 1 A processing system 1 according to the present disclosure is used to acquire a subject image including at least a portion of a subject's oral cavity as a subject, captured by a user terminal device, and acquire first evaluation information by inputting the subject image into a trained evaluation model. The processing system 1 also selects a first expert from among multiple experts based on at least one of the subject's attributes and the first evaluation information, and the attribute information of the multiple experts. The processing system 1 also acquires second evaluation information, which is a result of evaluating the first evaluation information, from the selected first expert. The processing system 1 also generates evaluation result information based on the acquired second evaluation information and outputs the evaluation result information to the user terminal device.

[0013] As an example, such a processing system 1 acquires first evaluation information, which is an evaluation result of the subject's oral cavity, based on a subject image of the oral cavity of the subject. Then, an expert evaluates the acquired first evaluation information and makes corrections as necessary (corrections may include replacing content, adding content, deleting content, etc.) to generate second evaluation information. Based on the second evaluation information evaluated by the expert, the processing system 1 generates evaluation result information to be reported to the user. Then, the processing system 1 reports the evaluation result information to the user.

[0014] Therefore, when evaluating the state of the oral cavity, the processing system 1 uses the second evaluation information evaluated by an expert, thereby making it possible to provide the user with more accurate evaluation result information.

[0015] Furthermore, the processing system 1 selects an expert from among a plurality of experts to evaluate the first evaluation information and generate the second evaluation information based on attribute information of each expert. That is, the processing system 1 is capable of matching an expert to evaluate the first evaluation information. Therefore, the processing system 1 can match an expert who is most suitable for the evaluation and generate the second evaluation information more appropriately.

[0016] Furthermore, by receiving the evaluation result information, the subject is expected to receive diagnosis and care from a specialist to improve and maintain the condition of the oral cavity. The processing system 1 is capable of matching the subject with the specialist. Therefore, the processing system 1 can introduce the subject to a more appropriate specialist.

[0017] Furthermore, as described above, the processing system 1 is expected to enable experts to provide diagnosis and care to each subject in order to improve and maintain the condition of the subject's oral cavity. The processing system 1 enables experts to offer diagnosis, care, etc. to subjects. Therefore, the processing system 1 can efficiently provide experts with opportunities to provide services such as diagnosis and care.

[0018] In the present disclosure, the term "subject" refers to anyone who is the subject of a subject image capture, including patients, test subjects, evaluation subjects, healthy individuals, and individuals requiring care. In the present disclosure, the term "user" refers to anyone who can use a user terminal device used to capture subject images, including the subject themselves, their guardians, caregivers, service providers, superiors, subordinates, colleagues, teachers, care managers, and administrators. In the present disclosure, the term "expert" is merely a term used to distinguish the subject from the user and does not necessarily require a high level of expertise, license, title, or qualification. In other words, the term "expert" refers to anyone who can evaluate the first evaluation information, which is the result of evaluating the oral condition based on the subject image. This term includes medical professionals such as dentists, doctors, dental hygienists, nurses, clinical laboratory technicians, registered dietitians, physical therapists, occupational therapists, dental technicians, emergency medical technicians, and speech-language-hearing therapists, as well as caregivers, care workers, and acupuncturists.

[0019] Furthermore, as mentioned above, the subject, user, and expert are merely names given to distinguish one from another based on the roles and situations in which they are involved in the processing system 1. Therefore, it is natural that the subject, user, and expert may each be the same person. In addition, the subject, user, and expert may each refer to any individual, or may each refer to any organization to which multiple subjects, users, and experts belong (for example, a medical institution, care facility, or business to which each of the subjects, users, and experts belong).

[0020] Similarly, the user terminal device and the expert terminal device are merely names given to distinguish one from the other based on the attributes of the users in the processing system 1. Therefore, it goes without saying that a user terminal device may function as an expert terminal device, and an expert terminal device may also function as a user terminal device.

[0021] Furthermore, in this disclosure, terms such as "first" and "second" may be used, but these do not necessarily specify a specific order or number, and are merely used to distinguish between connected words. Therefore, in addition to "first" and "second," "third," "fourth," "fifth," etc. may also be connected. Furthermore, the words connected with "first" and "second" do not have to be singular and may naturally be plural. For example, although there are descriptions such as "first evaluation information" and "second evaluation information," there may be multiple pieces of first evaluation information, or multiple pieces of second evaluation information. Furthermore, in this disclosure, terms such as "multiple" may be used, and in some cases, "multiple" may mean an integer of 2 or greater.

[0022] Furthermore, in the present disclosure, "oral condition" may refer to any information indicating the condition of the oral cavity. Examples of such oral conditions include at least one of the conditions of the lips, sublingual, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache; at least one of the conditions of swallowing function and masticatory function; tongue movement, lip movement, and at least one of the conditions of the degree of oral moisture and the degree of mouth opening; and a comprehensive evaluation of these conditions. In particular, the conditions of the lips, sublingual, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache are indicated on an evaluation sheet called the Oral Health Assessment Tool (OHAT), and are preferred as indicators for evaluating the condition of the oral cavity. Furthermore, the indicator of the condition of the oral cavity may be any information indicating a specific value, classification, or category. For example, numerical values ​​such as "0 points," "1 point," and "2 points" may be used as indicators according to any evaluation criteria, or classifications or categories such as "healthy," "slightly poor," and "pathological" may be used as indicators. It may also include whether the patient can open their mouth, whether the teeth and tongue are dirty, whether the gums are swollen or bleeding, whether and to what extent the left and right back teeth fit together, whether or not there are symptoms of choking, whether or not the patient can gargle, whether or not food is stored or remains, etc.

[0023] Furthermore, in this disclosure, "evaluation" broadly includes evaluations related to the oral condition of a subject, and therefore includes various evaluations, such as a definitive diagnosis by a dentist or doctor, an evaluation other than a definitive diagnosis by one of the experts listed above, an evaluation to assist in a definitive diagnosis, an evaluation by a trained evaluation model, an evaluation of the evaluation results by a trained evaluation model or other experts (including confirmation or correction of the content), and combinations of these.

[0024] 2. Configuration of Processing System 1 1 is a block diagram showing the configuration of a processing system 1 according to an embodiment of the present disclosure. According to Fig. 1, the processing system 1 includes a processing device 100, a user terminal device 200-1, and an expert terminal device 200-2, which are communicatively connected via a wired or wireless network.

[0025] In the present disclosure, the processing device may be any device capable of performing the processing executed by the processing device 100. That is, various devices, such as an on-premise server device, a cloud server device, a smartphone, a tablet device, a laptop PC, and a desktop PC, can be used as the processing device. Also, any of the terminal devices 200, such as the user terminal device 200-1 and the expert terminal device 200-2, can function as the processing device. Furthermore, in the present disclosure, the storage and processing performed by the processing device may be distributed to other terminal devices, other server devices, etc. That is, the processing device is not limited to one configured from a single housing, and the processing device also includes a combination of the various devices exemplified above.

[0026] Furthermore, in the present disclosure, the user terminal device 200-1 may be any device capable of capturing an image of a subject. In other words, while not limited to the following devices, examples of the user terminal device 200-1 include various devices such as smartphones, tablet devices, laptop PCs, desktop PCs, and imaging devices (including dental imaging devices, digital cameras, medical imaging devices, etc.). Such a user terminal device 200-1 is preferably communicably connected to a system providing management support services for care providers. Such systems provide various management services for care providers, such as accounting and financial management, information management of care recipients, and meals provided at facilities. The processing system 1 is typically used by care providers. However, by using a user terminal device 200-1 connectable to a system providing management support services for care providers, it is possible to use information stored in the system for subject images and evaluation information, and to link generated evaluation result information to the system.

[0027] In addition, in the present disclosure, the expert terminal device 200-2 may be any device that inputs various information and transmits and receives this information. In other words, although it is not limited to the following devices, examples of the expert terminal device 200-2 include various devices such as a smartphone, a tablet device, a laptop PC, and a desktop PC.

[0028] In addition, in the present disclosure, the user terminal device 200-1 and the expert terminal device 200-2 may be collectively referred to as the terminal device 200.

[0029] 1 shows only one each of the processing device 100, the user terminal device 200-1, and the expert terminal device 200-2, but in the present disclosure, multiple of each of these devices may be included. For example, multiple users may each own a user terminal device 200-1, and each user terminal device 200-1 may be included in the processing system 1. Similarly, multiple experts may each own an expert terminal device 200-2, and each expert terminal device 200-2 may be included in the processing system 1. Furthermore, the user terminal device 200-1 and the expert terminal device 200-2 do not need to execute a series of processes on the same terminal device. For example, the user terminal device 200-1 that photographs the subject and the user terminal device 200-1 that receives the evaluation result information may each be separate terminal devices.

[0030] FIG. 2A is a block diagram showing the configuration of a processing device 100 according to an embodiment of the present disclosure. According to FIG. 2A, the processing device 100 includes a processor 111, a memory 112, and a communication interface 113. These components are electrically connected to one another via control lines and data lines. The processing device 100 does not need to include all of the components shown in FIG. 2A; some components may be omitted, or other components may be added. For example, an external memory, a database device, a server device, or the like connected in a communicable manner as a memory may be used. Furthermore, some processing may be distributed and executed by other processing devices, including other server devices. In other words, the processing device 100 is not limited to a single device, but may be distributed across multiple devices depending on the information handling and processing load.

[0031] The processor 111 functions as a control unit that controls other components of the processing system 1 based on a processing program stored in the memory 112. The processor 111 is mainly configured with one or more CPUs, but may also be combined with a GPU, an FPGA, or the like as appropriate. Based on the processing program stored in the memory 112, the processor 111 executes processes for generating first evaluation information based on a subject image, matching experts, and generating evaluation result information based on second evaluation information by the experts. Specifically, the processor 111 executes processes based on the processing program stored in the memory 112, such as "acquiring a subject image including at least a part of the oral cavity of a subject as a subject, which is captured by a user terminal device usable by a user," "acquiring first evaluation information indicating the results of an evaluation of the oral condition of the subject by inputting the subject image into a trained evaluation model for evaluating the oral condition of the subject," and "acquiring second evaluation information indicating the results of an evaluation of the first evaluation information input by one or more first experts selected from multiple experts, based on at least one of the subject's attribute information and the first evaluation information, and the attribute information of each of the multiple experts who can evaluate the first evaluation information."

[0032] The memory 112 is composed of RAM, ROM, non-volatile memory, HDD, SSD, etc., and functions as a storage unit. The memory 112 stores instructions and commands for various control operations of the processing system 1 according to this embodiment as processing programs. Specifically, the memory 112 stores programs that the processor 111 executes, such as "a process of acquiring a subject image including at least a portion of the subject's oral cavity as the subject, captured by a user terminal device usable by the user," "a process of acquiring first evaluation information indicating the results of an evaluation of the subject's oral cavity condition by inputting the subject image into a trained evaluation model for evaluating the oral cavity condition of the subject," and "a process of acquiring second evaluation information indicating the results of an evaluation of the first evaluation information input by one or more first experts selected from multiple experts based on at least one of the subject's attribute information and the first evaluation information and each attribute information of multiple experts who can evaluate the first evaluation information." In addition to these programs, the memory 112 also stores various information stored in a subject management table, an expert management table, etc. It should be noted that this information does not need to be constantly stored in the memory 112 within the processing device 100, but may be stored in a database device installed remotely. In this case, the database device is also included in the memory 112.

[0033] The communication interface 113 functions as a notification unit for transmitting and receiving various information between the user terminal device 200-1, the expert terminal device 200-2, and other processing devices connected via a wired or wireless network. Examples of the communication interface 113 include a wired communication connector such as USB or SCSI, a wireless communication transmitting / receiving device for broadband wireless communication such as wireless LAN, Bluetooth (registered trademark), or LTE, or infrared, and various connection terminals for printed circuit boards or flexible circuit boards.

[0034] FIG. 2B is a block diagram showing the configuration of a terminal device 200 according to an embodiment of the present disclosure. Specifically, FIG. 2B is a block diagram showing the configuration of a device that can be used as a user terminal device 200-1 or an expert terminal device 200-2. The terminal device 200 includes a processor 211, a memory 212, an input interface 213, an output interface 214, a communication interface 215, and a camera 216. These components are electrically connected to each other via control lines and data lines. Note that the terminal device 200 does not need to include all of the components shown in FIG. 2B; some components may be omitted, or other components may be added. Furthermore, for example, when the terminal device 200 functions as the expert terminal device 200-2, the camera 216 may not be included.

[0035] The processor 211 functions as a control unit that controls the other components of the terminal device 200 based on a program stored in the memory 212. The processor 211 is mainly composed of one or more CPUs, but may also be combined with a GPU, FPGA, or the like as appropriate.

[0036] When functioning as the user terminal device 200-1, the processor 211 executes, based on the processing program stored in the memory 112, a process for capturing a subject image of a subject as a subject, etc. Specifically, based on the program stored in the memory 212, the processor 211 executes, based on the program stored in the memory 212, “a process of accepting a user's operation input via the input interface 213 and activating the camera 216,” “a process of accepting a user's operation input via the input interface 213, selecting a subject to be captured from a plurality of subjects, and capturing a subject image including at least a part of the subject's oral cavity as a subject, using the camera 216,” “a process of transmitting the captured subject image to the processing device 100 via the communication interface 215,” “a process of receiving evaluation result information from the processing device 100 via the communication interface 215,” and “a process of outputting the received evaluation result information via the output interface 214,” etc.

[0037] Furthermore, when the processor 211 functions as the expert terminal device 200-2, it executes processing such as evaluating the first evaluation information generated based on the subject image and generating second evaluation information based on the processing program stored in the memory 112. Specifically, based on the program stored in memory 212, processor 211 performs the following operations: "receiving first evaluation information generated based on a subject image from processing device 100 via communication interface 215," "accepting an expert's operational input via input interface 213 and generating second evaluation information that is the result of evaluating the received first evaluation information," "transmitting the generated second evaluation information to processing device 100 via communication interface 215," "transmitting a matching request via communication interface 215 to request the provision of subject information for at least one of multiple subjects," "outputting subject information received based on the matching request via output interface 214," "selecting at least one subject output after accepting an expert's operational input via input interface 213," and "transmitting an offer to provide diagnosis or care to at least one selected subject via communication interface 215."

[0038] The memory 212 is composed of RAM, ROM, nonvolatile memory, HDD, etc., and functions as a storage unit. The memory 212 stores instructions and commands for various controls of the processing system 1 according to this embodiment as programs.

[0039] Specifically, when functioning as user terminal device 200-1, memory 212 stores programs to be executed by processor 211, such as "a process of accepting a user's operational input via input interface 213 and activating camera 216," "a process of accepting a user's operational input via input interface 213, selecting a subject to be photographed from multiple subjects, and photographing a subject image including at least a part of the subject's oral cavity as the subject using camera 216," "a process of transmitting the photographed subject image to processing device 100 via communication interface 215," "a process of receiving evaluation result information from processing device 100 via communication interface 215," and "a process of outputting the received evaluation result information via output interface 214."

[0040] Furthermore, when functioning as the expert terminal device 200-2, the memory 212 stores programs to be executed by the processor 211, such as “a process of receiving, via the communication interface 215, first evaluation information generated based on the subject image from the processing device 100,” “a process of accepting an operation input by an expert via the input interface 213 and generating second evaluation information that is a result of evaluating the received first evaluation information,” “a process of transmitting, via the communication interface 215, a matching request for requesting the provision of subject information of at least one subject out of a plurality of subjects,” “a process of outputting, via the output interface 214, the subject information received based on the matching request,” “a process of accepting an operation input by an expert via the input interface 213 and selecting at least one subject output,” and “a process of transmitting, via the communication interface 215, an offer to provide diagnosis or care to at least one selected subject.”

[0041] The input interface 213 functions as an input unit that accepts operational inputs from a user or expert to the terminal device 200. Examples of the input interface 213 include physical key buttons and a touch panel having an input coordinate system corresponding to the display coordinate system of the display. In the case of a touch panel, icons are displayed on the display, and the operator selects each icon by inputting operational inputs via the touch panel. The method for detecting the operational inputs of the subject using the touch panel may be any method, such as a capacitive method or a resistive method. The input interface 213-2 does not always need to be physically provided on the terminal device 200, and may be connected as needed via a wired or wireless network. Therefore, in addition to the above, a mouse, a keyboard, etc. can also be used as the input interface 213-2.

[0042] The output interface 214 functions as an output unit for outputting various information. An example of the output interface 214 is a display, but the output interface 214 is not limited to this and may be composed of other liquid crystal panels, organic EL displays, plasma displays, printers, etc. Also, a display does not have to be provided. For example, an interface for connecting to a display or the like connectable to the processing device 100 via a wired or wireless network can function as the output interface 214 for outputting display data to the display or the like.

[0043] The communication interface 215 functions as a communication unit for transmitting and receiving information to and from the processing device 100, other terminal devices 200, and other processing devices. Examples of the communication interface 215 include a connector for wired communication such as USB or SCSI, a transmitting and receiving device for wireless communication such as broadband wireless communication such as wireless LAN, Bluetooth (registered trademark), or LTE, or infrared, and various connection terminals for printed circuit boards and flexible circuit boards.

[0044] The camera 216 functions as an imaging unit that detects light reflected from the oral cavity, which is the subject, and generates an image of the subject. To detect the light, the camera 216 includes, for example, a CMOS image sensor, a lens system, and a drive system for achieving the desired functions. The image sensor is not limited to a CMOS image sensor; other sensors, such as a CCD image sensor, can also be used. Although not specifically shown, the camera 216 may have an autofocus function, and is preferably set, for example, so that the focus is set on a specific area at the front of the lens. Furthermore, the camera 216 may have a zoom function and is preferably set to capture an image at an appropriate magnification depending on the size of the subject.

[0045] It should be noted that the camera 216 does not necessarily have to be provided when the terminal device 200 functions as the expert terminal device 200-2.

[0046] 3. Various information used in processing in the processing system 1 3A and 3C show various tables that store information that is stored in the processing device 100 and that is sent to and received from each terminal device 200 as the processing progresses. This information is updated and stored as needed as the processing progresses. Note that the information shown in FIGS. 3A and 3B may be stored in the memory 112 of the processing device 100, or may be stored in another database device installed remotely and read out as needed as the processing progresses.

[0047] 3A is a diagram conceptually illustrating a subject management table stored in the processing device 100 according to an embodiment of the present disclosure. According to FIG. 3A, the subject management table stores, in association with subject ID information, a subject image, evaluation information, first evaluation information, second evaluation information, expert (evaluation) information, expert (diagnosis, etc.) information, and other attribute information. Each of these pieces of information is used as attribute information indicating various attributes of the subject.

[0048] "Subject ID information" is information unique to each subject that identifies each subject. For example, subject ID information is generated each time a user registers a new subject. However, subject ID information can be anything that can identify the subject as described above, and various information such as the subject's name or user name can be used.

[0049] A "subject image" is image data that includes at least the oral cavity of a subject as a subject, and is captured using the user terminal device 200-1 or the like. The image data may be one or more still images, one or more videos, or a combination thereof. The subject image is stored by being received from the user terminal device 200-1 via the communication interface 113. The subject image may be the image data itself captured by the user terminal device 200-1, or may be data obtained by performing image processing such as sharpening, screening, and segmentation on the image data. The subject image is typically useful for evaluating the condition of the oral cavity. Note that such a subject image may contain various information analyzed from the image data instead of or in addition to the image data. For example, the subject image may include values, classifications, or categories obtained by inputting the image data into a trained analysis model and quantifying various image features (e.g., data indicating the degree of lip moistness).

[0050] Here, FIG. 3B is a diagram conceptually illustrating an example of a subject image according to an embodiment of the present disclosure. Specifically, FIG. 3B is a diagram illustrating an example of the configuration of subject image C1 captured of a subject whose subject ID information is "A1." According to FIG. 3B, subject image C1 includes one or more images (in FIG. 3B, multiple subject images C1-1 to C1-n). Such subject image C1 can be composed of frames captured in a video, or can be composed of multiple still images captured multiple times.

[0051] Such subject image C1, as shown in images (a) to (d), is an image that includes at least a portion of the subject's oral cavity as a subject. That is, subject image C1 includes, for example, an image of the subject's lips as in image (a), an image of the subject's tongue as in image (b), an image of the subject's oral cavity interior as in image (c), and an image of the subject's teeth and gums as in image (d). Furthermore, subject image C1 is not limited to these, and any image that includes at least a portion of the subject's oral cavity, such as an image of the subject's sublingual area or an image of dentures, can be used. Furthermore, while subject image C1 is an image composed of multiple images, the subject image may naturally be a single image. As mentioned above, an image of dentures is given as an example of a subject image, but the image of dentures includes both an image of the denture attached to the oral cavity and an image of the denture after it has been removed from the oral cavity. That is, at least a portion of the oral cavity that is the subject may include not only the body part itself but also an appliance such as a denture attached to the body.

[0052] Returning to FIG. 3A , the “evaluation information” refers to information that can be used to evaluate the oral condition of the subject. The evaluation information is acquired during the process related to the evaluation of the oral condition by inputting it via the user terminal device 200-1, the expert terminal device 200-2, or another terminal device based on a request from the processing device 100, or by inputting it together with the subject image via the user terminal device 200-1. The evaluation information may also be acquired during a series of processes from a database device storing medical interview information, findings, and medical record information. Examples of such evaluation information include medical interview information and findings such as swelling of the cheeks and gums, tooth fractures, ulcers, subgingival abscesses, the color of each part of the oral cavity, the wetness or dryness of each part of the oral cavity, the state of saliva, and the degree of mouth opening. Other examples of the evaluation information include the results of a saliva swallowing test used to evaluate swallowing function, laryngeal elevation movement, walking speed, muscle mass, and grip strength. Further examples of evaluation information include interview information and observation information, such as the degree of clenching of molars and the behavior of the corners of the mouth, which are used to evaluate masticatory function. Each of these evaluation information can be obtained, for example, by a user or an expert interviewing the subject, by a user or an expert giving the subject's observations, by obtaining output information through image analysis of a subject image (e.g., input into a trained analysis model), or by using other equipment (e.g., a grip strength meter, a tongue pressure meter, a hygrometer, etc.). However, any method of acquisition is acceptable.

[0053] The "first evaluation information" is information indicating the results of evaluating the state of the oral cavity of a subject. Examples of such first evaluation information include information obtained by inputting a subject image into a trained evaluation model, information obtained by inputting evaluation information into a trained evaluation model, information obtained by subjecting the subject image to any image analysis process, information obtained by accepting evaluation results of the subject image by any expert, and combinations thereof. Note that, below, a case will be described in which information obtained by inputting a subject image into a trained evaluation model is used as the first evaluation information, but of course, other information, including the information exemplified above, can also be used.

[0054] The "second evaluation information" is information indicating the results of evaluating the first evaluation information. Examples of such second evaluation information include information evaluated by an arbitrary expert, information acquired by inputting the subject image and / or the first evaluation information into a trained evaluation model, information acquired by inputting the evaluation information and / or the first evaluation information into a trained evaluation model, information acquired by performing arbitrary image analysis processing on the subject image, and combinations thereof. The following describes a case in which information evaluated by an expert selected from multiple experts is used as the second evaluation information. However, other information, including the information exemplified above, can also be used. The second evaluation information may take any form, such as information indicating that the first evaluation information has simply been "checked," information indicating corrections, or all information after the first evaluation information has been corrected. As described above, corrections to the first evaluation information may include various modifications, such as replacing the content of the first evaluation information, adding content to the first evaluation information, or deleting content from the first evaluation information. That is, the second evaluation information may be the first evaluation information to which, for example, the evaluation result of the swallowing function or the evaluation result of the masticatory function has been added.

[0055] In the following, the first evaluation information is generated using a trained evaluation model, and the second evaluation information is generated using an expert. However, this is not limited to this, and the evaluation methods and evaluation entities may be combined in any way, such as the first evaluation information being generated using an expert and the second evaluation information being generated using a trained evaluation model, the first evaluation information being generated using a trained evaluation model and the second evaluation information being generated using another trained evaluation model, or both the first evaluation information and the second evaluation information being generated using the same evaluation method.

[0056] "Expert (evaluation) information" is information indicating the first expert who input the second evaluation information. Typically, expert ID information is stored to identify the expert who input the second evaluation information. Examples of such experts are those exemplified above as experts. However, it is desirable that one or more first experts are selected from among these multiple experts based on at least one of the subject's attribute information and the first evaluation information, and the attribute information of each expert, i.e., the subject and the experts are matched. This makes it possible to select a more appropriate expert as the first expert.

[0057] "Expert (diagnosis, etc.) information" is information indicating a second expert who is a specialist who can provide oral cavity-related services, such as diagnosis and care, to the subject to improve and maintain the condition of the oral cavity. Typically, expert ID information for identifying the expert who can provide the above services is stored. Examples of such experts are those exemplified above. However, it is desirable that one or more second experts be selected from among these multiple experts based on at least one of the subject's attribute information and the second evaluation information, and the attribute information of each expert, i.e., the subject and the expert are matched. This makes it possible to select a more appropriate expert as the second expert.

[0058] "Other attribute information" is information indicating attributes of each subject other than the above-mentioned information. Typical examples of such information include the subject's authentication information, location information indicating the place of residence, age, weight, sex, place of work or school, and information on family members living together. The other attribute information is input, for example, via the input interface 213 of the user terminal device 200-1 and is stored by being received from the user terminal device 200-1 via the communication interface 113.

[0059] FIG. 3C is a diagram conceptually illustrating an expert management table stored in the processing device 100 according to an embodiment of the present disclosure. According to FIG. 3C, the expert management table stores, in association with expert ID information, expertise information, operation information, location information, expert evaluation information, and other attribute information. Each of these pieces of information is used as attribute information indicating various attributes of the experts. Note that each piece of information, such as the expertise information, may be input in advance by the expert terminal device 200-2 or another terminal device. Furthermore, each piece of information, such as the expert information, may be acquired during the exemplary process from, for example, a management device managed by the organization to which each expert belongs.

[0060] "Expert ID information" is information unique to each expert that identifies each expert. For example, the expert ID information is generated each time a new subject is registered by the expert. However, the expert ID information can be anything that can identify the subject as described above, and various information such as the expert's name or user name can be used.

[0061] "Expertise information" is information indicating the area of ​​expertise of each expert. Examples of such expertise information include information indicating the areas that each expert can evaluate and the level of oral condition, information indicating the dentist's specialty such as pediatric dentistry, orthodontics, oral surgery, or dentistry, qualification information such as the qualifications, title, or license held by each expert, information indicating the occupation or position of each expert, information indicating the years of experience of each expert, information indicating the career history of each expert, and combinations thereof. The expert information is preferably used when matching a subject with a first expert or a second expert.

[0062] "Operation information" is information indicating the working hours of each expert. Examples of such operation information include schedule information for each expert, attendance information for each expert, scheduled work information for each expert, and combinations thereof. In other words, operation information may be any information indicating the working hours of each expert, such as information on the hours, dates, days of the week, months, and years when the expert is available to work, or information on the hours, dates, days of the week, months, and years when the expert is unavailable to work. Furthermore, operation information is not limited to the above, and log information such as whether each expert has logged in to a service provided by the processing system 1 or the last time the expert accessed the service may also be used. Operation information is preferably used when matching a target person with a first expert or a second expert.

[0063] "Location information" is information indicating the location where each expert is located. Examples of such location information include coordinates such as latitude and longitude, addresses, postal codes, names of facilities or buildings, names of affiliations, location information detected based on the expert terminal device 200-2, and combinations thereof. The location information is preferably used when matching a subject with a first expert or a second expert.

[0064] "Expert evaluation information" is information showing the evaluation results for each expert. Such expert evaluation information is not limited to the information exemplified below, but examples include the following information. For example, by using "tendency information such as the age group and gender of subjects previously evaluated by each expert" as expert evaluation information, it becomes possible to preferentially match subjects of an age group or gender in which the subject has extensive experience or is skilled. The expert evaluation information is preferably used when matching a subject with a first expert or a second expert. Information showing the accuracy of the second evaluation information previously generated by each expert Information based on the time required to transmit the past second evaluation information to the processing device 100 Information indicating the difficulty of the evaluation of the first evaluation information Information showing the number of first evaluations each expert has evaluated in the past - Trend information such as age group and gender of subjects evaluated by each expert in the past · Reviews from users and target audiences Qualifications held by each expert Title or license or other qualification information Information indicating the occupation or position of each expert Information indicating the years of experience of each expert, and information indicating the career history of each expert -Paper information submitted by each expert Combination of the information listed above

[0065] The information indicating the accuracy of the second evaluation information previously generated by each expert, the information indicating the number of first evaluation information previously evaluated by each expert, trend information such as the age group and gender of the subjects previously evaluated by each expert, and word-of-mouth information from each user or subject may be reset when a certain period of time has passed since the information was input. For example, the information indicating the number of first evaluation information previously evaluated is decremented by one six months after the first evaluation information was evaluated. The expert evaluation information may also be reset when the number of evaluations of the first evaluation information within a given period of time is less than a predetermined number. For example, if the number of evaluations of the first evaluation information within the past six months is less than one (i.e., zero), the expert evaluation information is reset. This allows the expert evaluation information to always reflect the latest situation.

[0066] The "other attribute information" is information indicating attributes of each specialist other than the above-mentioned information. Typical examples of such information include the specialist's affiliation, contact information, operating hours such as consultation hours, availability of home visits, map information, and combinations thereof.

[0067] 4. Processing sequence executed by processing system 1 4A and 4B are diagrams showing processing sequences executed in the processing system 1 according to an embodiment of the present disclosure. Specifically, FIGS. 4A and 4B show processing sequences executed between the processing device 100, the user terminal device 200-1, and the expert terminal device 200-2. Of these, FIG. 4A shows the process for generating evaluation result information on an oral cavity condition, and FIG. 4B shows the process for making an offer by an expert. Each process shown in these processing sequences is mainly executed by a processor in each device processing a program stored in memory.

[0068] (A) Oral cavity condition evaluation result information generation process First, the process of generating evaluation result information of the subject's oral cavity condition will be described. As shown in FIG. 4A, the processor 211 of the user terminal device 200-1 accepts a user's operational input via the input interface 213 and activates the user terminal device 200-1 (S11). The processor 211 then accepts the user's operational input accepted via the input interface 213-1, selects a subject to be evaluated, and activates the camera 216. The processor 211 then uses the activated camera 216 to capture a subject image including at least a portion of the subject's oral cavity as the subject (S12). After capturing the subject image, the processor 211 transmits the captured subject image, subject ID information of the subject, and a request (T11) for evaluating the subject's oral cavity condition to the processing device 100 via the communication interface 215. Although not specifically shown in FIG. 4A, various image processing such as sharpening and screening may be performed on the captured subject image.

[0069] When the processor 111 of the processing device 100 receives the evaluation request via the communication interface 113, it stores the received subject image in the subject management table in association with the received subject ID information (S13). In addition, the processor 111 receives evaluation information and other attribute information from the user terminal device 200-1 or other devices (for example, the expert terminal device 200-2 or a database device) via the communication interface 113 as needed, and stores the information in association with the subject ID information (S14).

[0070] The processor 111 of the processing device 100 reads out the subject image stored in the subject management table, and, if necessary, the evaluation information and other attribute information, based on the received subject ID information, and executes evaluation processing using the subject image, etc. (S15). One example of the evaluation processing is performed by providing the subject image, and, if necessary, the evaluation information and other attribute information as input information to a trained evaluation model, and obtaining information indicating the evaluation result of the subject's oral cavity condition as output information. Details of this processing will be described with reference to FIG. 5A, etc.

[0071] Next, the processor 111 of the processing device 100 generates first evaluation information based on the output information acquired by the evaluation process (S16), and stores the generated first evaluation information in association with the subject ID information in the subject management table. As an example of this process, based on the output information acquired from the trained evaluation model, the first evaluation information is generated in a report format including the input subject image, evaluation information, other attribute information, and values, classifications, or categories indicating the condition of the oral cavity output from the trained evaluation model. Details of this process will be described with reference to FIG. 5A etc.

[0072] Next, the processor 111 of the processing device 100 executes a matching process to select an expert (first expert) who will evaluate the first evaluation information (S17). As an example of this process, the processor 111 selects one or more experts from among a plurality of experts based on at least one of the attribute information of the subject and the first evaluation information, and the attribute information of each expert. At this time, the processor 111 calculates a priority score indicating the matching priority for each expert, and selects one or more experts with the highest score. Details of this process will be described with reference to FIG. 5A, etc.

[0073] Next, when an expert to evaluate the first evaluation information is selected, the processor 111 of the processing device 100 sends an evaluation request (T12) including the first evaluation information, subject ID information, and a request for evaluation of the first evaluation information to the expert terminal device 200-2 of the selected expert via the communication interface 113.

[0074] When the processor 211 of the expert terminal device 200-2 receives an evaluation request via the communication interface 215, it evaluates the received first evaluation information and generates second evaluation information. As an example of this processing, the processor 111 outputs the received first evaluation information via the output interface 214. Then, the processor 111 accepts an operation input from the expert who references the first evaluation information output via the input interface 213, and inputs a confirmation result as to whether the first evaluation information is acceptable as is, or inputs a correction to the first evaluation information. In this way, the processor 111 generates second evaluation information.

[0075] 7A is a diagram showing an example of a first evaluation information screen output on the expert terminal device 200-2 according to an embodiment of the present disclosure. Specifically, FIG. 7A is a diagram showing an example of a first evaluation information screen 10 output via the output interface 214 in S12 of FIG. 4A. According to FIG. 7A, the first evaluation information screen 10 includes at least an evaluation result display area 11 and evaluation information display areas 12a to 12d.

[0076] The evaluation result display area 11 includes information such as "oral evaluation score: 0 points (good)," which is the result of evaluating the condition of the oral cavity, which is output information obtained from the trained evaluation model. Note that while the information "0 points (good)" is displayed in FIG. 7A, "1 point (slightly poor)" or "2 points (pathological)" may also be displayed depending on the output information. Also, while FIG. 7A displays both the numerical value and the classification simultaneously, only one of them may be displayed, or more detailed classifications or numerical values ​​may be displayed in addition to the three classifications. Also, although not shown in FIG. 7A, information indicating the accuracy of the evaluation output from the trained evaluation model may be displayed.

[0077] The evaluation information display areas 12a to 12d are areas prepared for each piece of evaluation information (denoted as evaluation item A to evaluation item D in FIG. 7A). Each of the evaluation information display areas 12a to 12d includes a subject image display area 13 and a status display area 14. The subject image display area 13 displays a subject image that is optimal for evaluating each evaluation item, selected from a plurality of subject images. Such images may be automatically selected by, for example, the processor 111 of the processing device 100 determining in advance which images to display for each evaluation item and matching the determined images with each subject image. This selection method is merely an example, and other methods may of course be used. Furthermore, the status display area 14 displays interview information and findings information stored as evaluation information for each evaluation item.

[0078] In particular, the evaluation result information that is finally output is expected to be referred to by users or subjects, whereas the first evaluation information is information that is referred to by experts. Therefore, there is a high possibility that the experts have more specialized knowledge. Therefore, the first evaluation information that is output on the first evaluation information screen 10 may include content that is different from the evaluation result information. Specifically, the output information obtained from the trained evaluation model displayed in the evaluation result display area 11 may be output as is as more precise numerical values ​​or scores indicating the condition of the oral cavity without any particular classification or division. Furthermore, information indicating the accuracy of the judgment obtained from the trained evaluation model may be output in the evaluation result display area 11. Furthermore, more specialized information such as interview information and observation information may be output from the evaluation information.

[0079] In this way, by displaying information different from the evaluation result information as the first evaluation information to be referred to by the expert, a more accurate evaluation can be achieved.

[0080] For ease of explanation, FIG. 7A illustrates four evaluation information display areas 12a-12d as an example of the evaluation information display area. However, the area may include fewer than four or more than four areas. In particular, it is desirable to include, as indicators for evaluating the condition of the oral cavity, information indicating at least one of the following conditions indicated on the OHAT evaluation sheet: lips, sublingual area, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache; at least one of the following conditions: swallowing function and chewing function; and at least one of the following conditions: tongue movement, lip movement, degree of oral moisture, and degree of mouth opening. Each piece of information regarding swallowing function, chewing function, tongue movement, lip movement, degree of oral moisture, and degree of mouth opening is expected to have an impact on or correlate with the OHAT evaluation. Therefore, displaying this information together with information regarding the OHAT allows experts to make more appropriate evaluations.

[0081] Next, Fig. 7B is a diagram showing an example of a second evaluation information screen output on the expert terminal device 200-2 according to an embodiment of the present disclosure. Specifically, Fig. 7B is a diagram showing an example of the second evaluation information screen 20 output via the output interface 214 in S12 of Fig. 4A. That is, the second evaluation information screen 20 is a screen displaying the second evaluation information after the first evaluation information has been corrected by the expert. According to Fig. 7B, the second evaluation information screen 20 includes at least an evaluation result display area 21 and evaluation information display areas 22a to 22d.

[0082] The evaluation result display area 21 includes information after correction of the information displayed in the evaluation result display area 11 of the first evaluation information screen 10. In the example of FIG. 7B, as a result of evaluation by an expert who referred to the first evaluation information, it is shown that the oral cavity evaluation score has been corrected from "0 points (good)" to "1 point (slightly poor)" by accepting operational input from the expert via the input interface 213. Note that, although the explanation here is based on the premise that the oral cavity evaluation score has been corrected, there are of course cases where the oral cavity evaluation score on the first evaluation information screen 10 is displayed as is without any correction.

[0083] Furthermore, the evaluation information display areas 22a to 22d are areas prepared for each piece of evaluation information (denoted as evaluation item A to evaluation item D in FIG. 7B). Each of the evaluation information display areas 22a to 22d includes a subject image display area 23 and a status display area 24. In the subject image display area 23, a subject image optimal for evaluating each evaluation item is selected from multiple subject images and displayed. The image displayed here is displayed as a result of the expert's evaluation with reference to the first evaluation information. If a more optimal image is found among other images captured as subject images, the image is replaced and displayed by accepting an expert's operational input via the input interface 213. Furthermore, the status display area 24 displays interview information and findings information stored as evaluation information for each evaluation item. In the example of FIG. 7B, the evaluation information for evaluation item A and evaluation item D is corrected by accepting an expert's operational input via the input interface 213 as a result of the expert's evaluation with reference to the actual subject images and evaluation information. Note that the explanation here is based on the assumption that evaluation items A and D have been corrected, but there may be cases where, for example, evaluation items B and C, no corrections are made and the evaluation information on the first evaluation information screen 10 is displayed as is.

[0084] While FIG. 7B illustrates four evaluation information display areas (22a-22d) for ease of explanation, the evaluation information display area may include fewer than four or more than four areas corresponding to the first evaluation information screen 10. In particular, it is desirable to include, as indicators for evaluating the oral condition, information indicating at least one of the following conditions indicated on the OHAT evaluation sheet: lips, sublingual area, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache; at least one of the following conditions: swallowing function and chewing function; and at least one of the following conditions: tongue movement, lip movement, oral moisture, and mouth opening. Information on swallowing function, chewing function, tongue movement, lip movement, oral moisture, and mouth opening is expected to influence or correlate with the OHAT evaluation. Therefore, displaying this information together with information related to the OHAT allows professionals and users providing diagnosis and care to obtain more appropriate information. 7A and 7B, the second evaluation information screen 20 may be provided with a first expert comment input area in which the rationale for checking or correcting the first evaluation information, notes, etc. can be input in free text format. The information input in the first expert comment input area is stored as part of the second evaluation information, and can be referred to as reference information when the second expert makes a diagnosis, for example.

[0085] Returning to Figure 4A again, once the second evaluation information is generated as shown in Figures 7A and 7B, the processor 211 of the expert terminal device 200-2 transmits the generated second evaluation information and subject ID information to the processing device 100 via the communication interface 215.

[0086] When the processor 111 of the processing device 100 receives the second evaluation information, etc. via the communication interface 113, it stores the received second evaluation information in the subject management table in association with the subject ID information received together (S19). When the processor 111 receives the second evaluation information, it stores the expert ID information of the expert who transmitted the evaluation information in association with the subject ID information in the expert (evaluation) information. Furthermore, the processor 111 executes an evaluation process for the expert who evaluated the first evaluation information based on the received second evaluation information (S20). As an example of this process, the processor 111 performs a process for updating the expert evaluation information associated with the expert. Specifically, for example, upon receiving the second evaluation information, the processor 111 updates information indicating the number of first evaluation information pieces previously evaluated by the expert by adding points for one evaluation. Furthermore, the processor 111 updates information based on the time required for transmitting the second evaluation information to the processing device 100 by adding points depending on the speed of transmission of the second evaluation information after transmitting the evaluation request for the first evaluation information. Conversely, for experts who have not transmitted the second evaluation information within a predetermined time, the score is updated so that it is deducted from the information based on the time it took to transmit the second evaluation information to the processing device 100.

[0087] Next, the processor 111 of the processing device 100 reads at least one of the expertise information, operation information, location information, expert evaluation information, and other attribute information of each expert, and executes a matching process to select an expert who can provide oral cavity-related services, such as diagnosis and care, to the subject (S21). As an example of this process, the processor 111 selects one or more experts from among multiple experts based on the expert's attribute information and the second evaluation information. At this time, the processor 111 calculates a priority score indicating the matching priority for each expert, and selects one or more experts with the highest score. The processor 111 then stores the expert ID information of the selected one or more experts in the expert (diagnosis, etc.) information in association with the subject ID information. Details of this process are described in FIG. 5B and other figures. It is desirable that the expert (second expert) selected here be selected from among the experts (first expert) who evaluated the first evaluation information. This ensures the objectivity of the evaluation of the first evaluation information.

[0088] Next, when the processor 111 selects an expert (second expert), it reads out various attribute information associated with the second evaluation information, the expert (diagnosis, etc.) information, and the expert ID information, and generates evaluation result information. Then, the processor 111 transmits the generated evaluation result information via the communication interface 113 to the user terminal device 200-1 that transmitted the evaluation request (T14).

[0089] When the processor 211 of the user terminal device 200-1 receives the evaluation result information via the communication interface 215, it outputs the received evaluation result information via the output interface 214 (S22).

[0090] 7C is a diagram showing an example of an evaluation result information screen output on the user terminal device 200-1 according to an embodiment of the present disclosure. Specifically, FIG. 7C is a diagram showing an example of an evaluation result information screen 30 output via the output interface 214 in S22 of FIG. 4A. According to FIG. 7C, the evaluation result information screen 30 includes at least an evaluation result display area 31, evaluation information display areas 32a to 32d, an expert information display area 35, and a diet recommendation area 37.

[0091] The evaluation result display area 31, like the evaluation result display area 21 of the second evaluation information screen 20, contains information after correction of the information displayed in the evaluation result display area 11 of the first evaluation information screen 10. Note that although the explanation here is based on the assumption that the oral cavity evaluation score has been corrected, there are of course cases where the oral cavity evaluation score of the first evaluation information screen 10 is displayed as is without any correction.

[0092] Similarly to the evaluation information display areas 22a to 22d of the second evaluation information screen 20, the evaluation information display areas 32a to 32d are areas prepared for each piece of evaluation information (referred to as evaluation item A to evaluation item D in FIG. 7C ). Each of the evaluation information display areas 22a to 22d includes a subject image display area 33 and a status display area 34. Similar to the subject image display area 33 of the second evaluation information screen 20, the subject image optimal for evaluating each evaluation item is selected from a plurality of subject images and displayed in the subject image display area 33. Similarly to the status display area 24 of the second evaluation information screen 20, the status display area 34 displays the evaluation information after correction. Similarly to the second evaluation information screen 20, the information displayed in the subject image display area 33 and the status display area 34 may be the information of each area of ​​the first evaluation information screen 10 as is if no corrections have been made.

[0093] The expert information display area 35 also includes various attribute information of the expert (second expert) selected in S21 of Fig. 4A. Specifically, the expert information display area 35 displays, together with the item name "dentist introduction", various attribute information such as the name of the expert's affiliation, the expert's name, address, whether or not home visits are available, working hours such as consultation hours, expert evaluation information, and map information 36. Note that the attribute information listed here is merely an example, and naturally other attribute information may be displayed, and the information of not only one expert but also multiple experts may be displayed.

[0094] Furthermore, the diet recommendation area 37 is an area where the results converted into other scores are displayed according to the oral assessment score and evaluation result information such as swallowing function or chewing function. The information displayed in this area is generated, for example, by the processor 111 referring to a table that shows the correspondence between at least one of the oral assessment score, swallowing function evaluation result, and chewing function evaluation result and other scores. Examples of such other scores include indicators indicating the hardness of food as shown in the Universal Design Food and the Academic Classification 2021 (Diet) Quick Reference Table (for example, any of the indicators "easy to chew," "can be crushed with gums," "can be crushed with tongue," and "no need to chew").

[0095] Furthermore, while the first evaluation information is intended for reference by experts, the evaluation result information that is finally output is expected to be referenced by users or subjects. Therefore, it is quite possible that the experts may have less specialized knowledge than the experts. Therefore, the evaluation result information output on the evaluation result information screen 30 may include content different from that of the first evaluation information. Specifically, the precise numerical values ​​and scores indicating the oral condition of the first evaluation information may be converted into classifications or categories (e.g., "good," "slightly poor," or "pathological") that are easier for users or subjects to understand. Furthermore, information indicating the definitions and meanings of each piece of information displayed on the evaluation result information screen 30 and related information may be added.

[0096] In this way, by displaying evaluation result information that is different from the first evaluation information that experts refer to, it is possible to provide information that is easier for users and subjects to understand and use.

[0097] While FIG. 7C illustrates four evaluation information display areas (12a-12d) for ease of explanation, the evaluation information display area may include fewer than four or more than four. In particular, it is desirable to include, as indicators for evaluating the oral condition, information indicating at least one of the following conditions indicated on the OHAT evaluation sheet: lips, sublingual area, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache; at least one of the following conditions: swallowing function and chewing function; and at least one of the following conditions: tongue movement, lip movement, oral moisture, and mouth opening. Each piece of information regarding swallowing function, chewing function, tongue movement, lip movement, oral moisture, and mouth opening is expected to influence or correlate with the OHAT evaluation. Therefore, displaying this information together with information regarding the OHAT allows the user or subject to gain a more appropriate understanding.

[0098] 7C may also include advertising information (e.g., links to websites for purchasing foods, oral care products, nursing care products, and other items corresponding to the index indicating the hardness of the meal displayed in the recommended diet area 37) according to the evaluation result information (e.g., oral cavity evaluation score, and evaluation results of swallowing function and chewing function). Including such information allows the user or subject to use the evaluation result information more effectively.

[0099] Returning to FIG. 4A again, the processor 211 of the user terminal device 200-1 outputs the evaluation result information as shown in FIG. 7C as the evaluation result of the subject's oral condition. Thereafter, if necessary, it is possible to execute an application process for diagnosis or care with the second specialist included in the evaluation result information. Specifically, the processor 211 of the user terminal device 200-1 accepts an operational input from the user or subject via the input interface 213 and transitions from the evaluation result information screen to an application screen. The processor 211 then accepts an operational input from the user or subject via the input interface 213 and selects on the application screen whether or not to apply to the second specialist included in the evaluation result information (S23). Once the second specialist is selected for application, the processor 211 outputs a visit schedule adjustment screen via the output interface 214 for selecting a desired date and time for the home visit. The processor 211 then accepts an operational input from the user or subject via the input interface 213 and selects a desired visit date and time for the user or subject (S24). Furthermore, the processor 211 outputs a registration screen for the health insurance card, medical interview information, etc. via the output interface 214. Then, the processor 211 accepts operational input from the user or subject via the input interface 213 and registers the health insurance card, medical interview information, etc. (S25). It is possible to register not only the health insurance card but also various other information on the screen, such as a nursing care insurance card, a nursing care insurance burden rate certificate, or a child medical expenses subsidy system medical certificate. When this input is made, the processor 211 transmits application information (T15) including the various information input in S23 to S25 to the expert terminal device 200-2 of the second expert via the communication interface 215. It is also possible to transmit this information via the processing device 100.

[0100] Although not specifically shown in the figure, when the expert terminal device 200-2 receives the application information via the communication interface 215, it outputs the application information via the output interface 214 and selects whether or not to accept the application. If the application is accepted, the second expert will conduct a medical visit on the confirmed visit schedule. This completes the processing sequence.

[0101] In this way, the evaluation result of the oral condition is generated after further evaluation by an expert, rather than using the output information from the trained evaluation model as is. This allows for a more accurate evaluation. Furthermore, by matching the expert who evaluates the first evaluation information based on the expert's attribute information, etc., an appropriate evaluation can be made. Furthermore, by matching with an expert who can provide services such as diagnosis and care for improving and maintaining the oral condition, it becomes possible for users and subjects to maintain better oral conditions. Furthermore, applications for diagnosis, care, etc. can be made via the processing system 1, making it easy for users and subjects to use.

[0102] 4A illustrates a case in which the first expert matched in S18 is a single expert, the second evaluation information in S18 is also a single piece of second evaluation information by the first expert, and the evaluation result information generated in T14 is generated based on a single piece of second evaluation information. However, the processor 111 may match multiple first experts in S18 and receive second evaluation information from each of the multiple first experts in S18. For example, if a single first expert is matched and the second evaluation information is not received, a second first expert is matched again, resulting in a loss of time. By matching multiple first experts as described above and enabling the reception of multiple pieces of second evaluation information, evaluation result information can be generated quickly based on the latest second evaluation information, thereby reducing time loss and enabling the evaluation result information to be transmitted more quickly.

[0103] Furthermore, the processor 111 may generate evaluation result information from the plurality of pieces of second evaluation information generated by the plurality of first experts as described above at T14. For example, the processor 111 may generate evaluation result information from the average of the plurality of pieces of second evaluation information, or may generate evaluation result information from the most frequent evaluation (e.g., majority vote) among the plurality of pieces of second evaluation information. By generating evaluation result information in this manner, it is possible to generate evaluation result information with higher objectivity.

[0104] Furthermore, when acquiring a plurality of pieces of second evaluation information as described above in matching the second experts in S20 and S21, the processor 111 may take a majority vote and add points to the first expert who has made the most evaluations, making it more likely that the first expert will be matched as the second expert. In this way, it becomes possible to match an expert who can make a more accurate judgment as the second expert.

[0105] (B) Professional Offer Processing Next, an offer process will be described in which an expert offers to provide a subject with services such as diagnosis and care to improve and maintain the condition of the oral cavity. According to Fig. 4B, the processor 211 of the expert terminal device 200-2 accepts an operation input from the expert via the input interface 213 and starts an application program used for the service related to the processing system 1 (S31). Then, the processor 211 of the expert terminal device 200-2 transmits a matching request (T31) with the subject to the processing device 100 via the communication interface 215.

[0106] When the processor 111 of the processing device 100 receives a matching request via the communication interface 113, it reads out attribute information of the expert based on the expert ID information of the expert who sent the matching request. The processor 111 then executes a matching process for selecting one or more subjects from the subject management table based on the read-out attribute information and the attribute information of each subject (S32). As an example of this process, the processor 111 selects one or more subjects from among the multiple subjects based on the attribute information of the expert and the second evaluation information of each subject. Details of this process will be described with reference to FIG. 5C and other figures.

[0107] When one or more subjects are selected, the processor 111 of the processing device 100 sends a list of attribute information (T32) of the selected subjects, etc., via the communication interface 113 to the expert terminal device 200-2 that sent the matching request.

[0108] When the processor 211 of the expert terminal device 200-2 receives attribute information and the like of the subject via the communication interface 215, it outputs the various pieces of information received via the output interface 214. Then, the processor 211 accepts an operational input from the expert via the input interface 213 and selects one or more subjects to whom an offer is to be sent from the list of subjects (S33). When the subject is selected, the processor 211 transmits an offer (T33) to the selected subject via the communication interface 215, including information that diagnosis and care of the oral condition are possible.

[0109] The offer includes attribute information of each expert, and may also include text information freely written by each expert, detailed information about the services provided by each expert, price information for each service, or a combination of these.

[0110] When the processor 111 of the processing device 100 receives the offer via the communication interface 113, it transfers the offer to the user terminal device 200-1 that has transmitted the subject image of the selected target person. When the processor 211 of the user terminal device 200-1 receives the offer via the communication interface 215, it outputs the received offer via the output interface 214 (S34).

[0111] After outputting the offer, the processor 211 of the user terminal device 200-1 can execute application processing for diagnosis, care, etc., with the second specialist included in the evaluation result information, as necessary. Specifically, the processor 211 of the user terminal device 200-1 accepts operational input from the user or subject via the input interface 213 and transitions from the offer display screen to an application screen. The processor 211 then accepts operational input from the user or subject via the input interface 213 and selects on the application screen whether or not to apply to the second specialist who sent the offer (S35). Once the second specialist has been selected for application, the processor 211 outputs a visit schedule adjustment screen via the output interface 214 for selecting a desired date and time for the home visit. The processor 211 then accepts operational input from the user or subject via the input interface 213 and selects the user's or subject's desired visit date and time (S36). Furthermore, the processor 211 outputs a registration screen for a health insurance card, medical interview information, etc. via the output interface 214. The processor 211 then accepts operational input from the user or subject via the input interface 213 and registers the health insurance card, medical interview information, etc. (S37). It should be noted that not only health insurance cards but also various other information can be registered on this screen, such as nursing care insurance cards, nursing care insurance burden rate certificates, or child medical expense subsidy system medical certificates. When these inputs are made, the processor 211 transmits application information (T34) including the various information input in S23 to S25 to the expert terminal device 200-2 of the second expert via the communication interface 215. It should be noted that this transmission can also be made via the processing device 100.

[0112] Although not specifically shown in the figure, when the expert terminal device 200-2 receives the application information via the communication interface 215, it outputs the application information via the output interface 214 and selects whether or not to accept the application. If the application is accepted, the second expert will conduct a medical visit on the confirmed visit schedule. This completes the processing sequence.

[0113] In this way, by having the specialist offer diagnosis or care services to the user or subject, it becomes possible to effectively utilize the various information stored in the subject management table and to provide the specialist with opportunities to provide these services. Furthermore, applications for diagnosis or care can be made via the processing system 1, making it easy for the user or subject to use.

[0114] 5. Processing flow executed by the processing device 100 5A to 5C are diagrams showing processing flows executed by the processing device 100 according to an embodiment of the present disclosure. Specifically, FIG. 5A shows the processing flows executed by the processing device 100 from S15 to S19 in the processing sequence of FIG. 4A. FIG. 5B shows the processing flows executed in S20 and S21 in the processing sequence of FIG. 4A. FIG. 5C shows the processing flow executed in S32 in the processing sequence of FIG. 4B. Each processing flow is mainly performed by the processor 111 of the processing device 100 by reading and executing a program stored in the memory 112.

[0115] (A) Processing flow executed in S15 to S19 in FIG. 4A 5A, the processor 111 reads out the subject image stored in the subject management table based on the subject ID information received from the user terminal device 200-1 (S111), and also reads out the evaluation information (S112). Note that, although the evaluation information is read out and used to generate the first evaluation information in the following, the evaluation information is not necessarily required, and only the subject image information may be used.

[0116] Next, the processor 111 reads out the subject image information and the evaluation information, and inputs this information into the trained evaluation model (S113). The trained evaluation model is a model used to evaluate the subject image for evaluating the state of the oral cavity of the subject, and is a model generated by training the training subject image and the training evaluation information based on evaluation result information indicating the results of evaluating the state of the oral cavity of the subject.

[0117] Here, Fig. 6 is a diagram showing a processing flow related to generation of a trained evaluation model according to an embodiment of the present disclosure. Specifically, Fig. 6 is a diagram showing a processing flow related to generation of a trained evaluation model used in S113 of Fig. 5. The processing flow may be executed by the processor 111 of the processing device 100, or may be executed by a processor of another device.

[0118] 6, the processor 111 executes a step of acquiring a learning subject image including at least a portion of the subject's oral cavity as the subject, and evaluation information such as the subject's medical interview information and findings information (S411). Next, the processor 111 executes a processing step of assigning learning evaluation result information indicating the results of an evaluation of the subject's oral cavity condition as correct label information to the subject who is the subject of the subject image (S412). The learning evaluation result information is, for example, information input by an expert such as a dentist by referring to the subject image or by actually visually inspecting the subject's oral cavity.

[0119] Then, processor 111 executes a step of storing the assigned correct label information as evaluation result information for learning in association with the learning object image and the learning evaluation information (S413). Note that although the object image itself is used here, feature amounts obtained from the object image may also be used. Furthermore, the object image may be the image data itself captured by user terminal device 200-1, or may be image data after image processing such as sharpening has been performed on the image data.

[0120] Once the learning subject images, learning evaluation information, and associated correct label information are obtained, the processor 111 executes a step of performing machine learning of an evaluation pattern of the subject's oral condition using these (S414). For example, the machine learning is performed by providing a set of this information to a neural network that combines neurons, and repeating learning while adjusting the parameters of each neuron so that the output from the neural network is the same as the correct label information. Then, a step of acquiring a trained evaluation model is executed (S415). The acquired trained evaluation model may be stored in the memory 112 of the processing device 100 or in another device connected to the processing device 100 via a wired or wireless network.

[0121] Here, the trained evaluation model can also be generated using machine learning techniques such as neural networks, convolutional neural networks, multi-layer neural networks (MLP), long short-term memory (LSTM), gated recurrent units (GRU), graph neural networks (GNN), and transformers; gradient boosting decision trees (GBDT) such as LightGBM (Light Gradient Boosting Machine), XGBoost, and CatBoost; ridge regression, logistic regression, support vector regression (SVR), nearest neighbor methods, decision trees, regression trees, and random forests.

[0122] Returning to FIG. 5A again, the processor 111 inputs the subject image and evaluation information of the subject into the trained evaluation model generated as described above, thereby acquiring output information from the trained evaluation model (S114). After acquiring the output information, the processor 111 generates first evaluation information based on the acquired output information (S115). As an example of this process, the processor 111 generates the first evaluation information in a report format based on the acquired output information, the first evaluation information including the input subject image, evaluation information, other attribute information, and a value, classification, or category indicating the oral cavity condition output from the trained evaluation model. The processor 111 may also use, for example, a large-scale language model (LLM) in this process. The processor 111 generates a prompt for generating the first evaluation information based on the output information, the subject image, the evaluation information, and other attribute information, and inputs the prompt into the large-scale language model. The processor 111 then acquires the first evaluation information as an output from the large-scale language model. The processor 111 stores the acquired first evaluation information in the subject management table in association with the subject ID information.

[0123] Next, the processor 111 executes a process for extracting a first expert in order to select an expert (first expert) who will evaluate the first evaluation information (S116). As an example of the process, the processor 111 executes the process by filtering experts that can be selected as the first expert based on predetermined information.

[0124] This predetermined information can be, for example, at least one of the subject's attribute information and the first evaluation information. For example, the processor 111 refers to the subject's first evaluation information, and if the subject's oral condition is "slightly poor" or "pathological," it filters out professionals qualified to diagnose and treat oral conditions, such as dentists, doctors, dental hygienists, and nurses. If the oral condition is "good," it filters out professionals other than the above, such as caregivers, care workers, and speech-language-hearing therapists. Furthermore, for example, the processor 111, based on information on the subject's swallowing function and masticatory function, filters out professionals qualified to diagnose and treat oral conditions, such as dentists, doctors, dental hygienists, and nurses, if the swallowing function and masticatory function are "poor." If these functions are "good," it filters out professionals other than the above, such as caregivers, care workers, and speech-language-hearing therapists. In this way, when the generated first evaluation information or the swallowing function or the masticatory function indicates "poor" or "slightly poor," it is expected that the degree of difficulty of evaluation by an expert will be higher than when it indicates "good." Therefore, the processor 111 can extract a more appropriate expert by estimating the degree of difficulty of evaluation based on the first evaluation information and filtering based on that degree of difficulty.

[0125] Furthermore, the predetermined information may be the accuracy of the first evaluation information acquired as output information in S114. For example, when the trained evaluation model evaluates the condition of the oral cavity as "pathological," the trained evaluation model acquires the accuracy that the condition of the oral cavity is pathological. If the accuracy is close to 100%, the condition is determined to be "pathological." If the accuracy is close to 0%, the condition is determined to be "good." In other words, when the condition is not close to either 100% or 0%, the difficulty of evaluation by the trained evaluation model is high, and it can be said that the trained evaluation model is in a state of uncertainty. Therefore, the processor 111 determines whether the accuracy is lower than a first threshold (e.g., "70%) and higher than a second threshold (a value lower than the first threshold, e.g., "30%)." When the processor 111 determines that the accuracy is lower than the first threshold and higher than the second threshold, it means that the difficulty of the evaluation is high, and therefore filters out professionals who are qualified to diagnose and treat oral conditions, such as dentists, doctors, dental hygienists, and nurses. On the other hand, when the processor 111 determines that the accuracy is equal to or higher than the first threshold or equal to or lower than the second threshold, it means that the difficulty of the evaluation is relatively low, and therefore filters out professionals other than the above professionals, such as caregivers, care workers, and speech-language-hearing therapists.

[0126] Next, the processor 111 calculates a priority score for each of the read experts and selects an expert (first expert) who will evaluate the first evaluation information (S117). As an example of this processing, the processor 111 reads attribute information of each expert and calculates a priority score by adding up points assigned to each attribute information or weighting the points. Then, the processor 111 selects one or more experts with a high priority score. The following information is an example of the attribute information used in this processing:

[0127] (Expert evaluation information) Based on information on the accuracy of other second evaluation information indicating the results of evaluating other first evaluation information, an expert with high accuracy is given a bonus based on the accuracy information of other second evaluation information. (This information is obtained by the processor 111, for example, by receiving feedback on the second evaluation information from the second expert when a diagnosis or care is performed by the second expert. Alternatively, the processor 111 selects multiple experts to evaluate the first evaluation information and obtains second evaluation information from each expert. The processor 111 then calculates the deviation between the average of the multiple pieces of second evaluation information obtained and the second evaluation information performed by each expert. Alternatively, the processor 111 selects multiple experts to evaluate the first evaluation information and obtains second evaluation information from each expert. The processor 111 then performs a majority vote among the multiple pieces of second evaluation information obtained and gives a bonus to the expert who provided the most evaluation results.) Based on information about the time it takes to transmit other second evaluation information to the processing device, an expert who takes a shorter time is given a bonus, or an expert who takes a longer time or does not transmit is deducted a bonus (this information is obtained by measuring the time from when the processor 111 transmits the first evaluation information to the expert until it receives the second evaluation information, and adding a bonus according to that time. Also, an expert who does not transmit second evaluation information despite the processor 111 transmitting first evaluation information is given a bonus, and this information is obtained by deducting a bonus). Based on the word-of-mouth information of each subject or user, experts with high word-of-mouth ratings are given additional points (this processing is performed by the processor 111 by performing language analysis on word-of-mouth information previously input by the subject or user in free text format, converting it into a score, and adding points according to the score. This processing is also performed by the processor 111 by acquiring the evaluation score of each expert by the user or subject, and adding points according to the evaluation score.)

[0128] (Operation information) Based on the schedule information, attendance information, and work schedule information of each expert, points are added to the experts who are currently working.

[0129] (Specialist Information) Based on the expert information of each expert, the expert who has a high degree of agreement with the subject's first evaluation information and evaluation information will be given additional points.

[0130] (location information) Based on the location information of each expert, points are added to experts who are located within a certain range of the target's location information.

[0131] The attribute information and the methods of adding, subtracting, and weighting points listed here are merely examples, and other attribute information of the experts or other attribute information of the subjects may be used. Furthermore, the experts to be selected may be a predetermined number of experts selected based on the priority score, or any predetermined number of experts selected in descending order of priority score.

[0132] Next, when a first expert is selected, the processor 111 transmits the first evaluation information of the subject to the expert terminal device 200-2 of the selected expert via the communication interface 113 (S118). Furthermore, when the transmission is performed, the processor 111 stores the time of transmission in association with the expert ID information of each expert.

[0133] Next, the processor 111 determines whether or not second evaluation information has been received from the expert terminal device 200-2 of one or more experts that transmitted the first evaluation information via the communication interface 113 (S119). If the result of this determination indicates that the second evaluation information has been received, the processor 111 stores the second evaluation information received from each expert in association with the subject ID information (S120).

[0134] On the other hand, if the second evaluation information is not received within a predetermined time, the processor 111 selects another first expert in the same manner as in S116 and S117 (S121). Then, the processor 111 executes the processing from S118 onwards again, such as transmitting the first evaluation information to the other selected first expert. This ends the processing flow.

[0135] (B) Processing flow executed in S20 and S21 of FIG. 4A According to FIG. 5B, the processor 111 reads out the second evaluation information stored in the subject management table (S211). Then, the processor 211 evaluates the expert (first expert) who transmitted the second evaluation information based on the read second evaluation information and the like, and generates expert evaluation information (S212). As an example of this processing, the processor 111 stores the time at which the second evaluation information was received from each expert, and calculates the elapsed time from the transmission time of the first evaluation information stored in S118 of FIG. 5A. The processor 111 stores the calculated time as the expert evaluation information. Furthermore, when the processor 111 receives second evaluation information from multiple experts, the processor 111 calculates the average value of the received multiple pieces of second evaluation information. The processor 111 then calculates the deviation from the calculated average value for each piece of second evaluation information. The processor 111 stores the calculated value indicating the deviation as the expert evaluation information. 5A, if the processor 111 does not receive the second evaluation information within a predetermined time, the processor 111 stores the fact as expert evaluation information for the expert who did not send the second evaluation information. The stored expert evaluation information is used when calculating the priority score from the next time onward.

[0136] The processor 111 executes processing related to extraction of an expert (second expert) who can provide services such as diagnosis and care to the subject (S213). As an example of this processing, the processor 111 executes processing by filtering experts who can be selected as the second expert based on predetermined information. This predetermined information may include, for example, expert (evaluation) information from the attribute information of the subject. That is, the processor 111 refers to the expert (evaluation) information, reads out the expert ID information of the expert (first expert) who made the evaluation on the first evaluation information, and excludes the expert from the experts to be extracted in S213.

[0137] In addition, in this embodiment, the second expert is expected to, for example, visit the location of the subject and provide home visit medical care. Therefore, the predetermined information includes, for example, location information associated with the subject and location information of each expert. That is, the processor 111 references the location information associated with the subject's subject ID information and extracts experts whose location information is located within a predetermined range from the location information. Home visit medical care can only be provided by those located within a predetermined range from the subject, so it is possible to appropriately filter experts.

[0138] The predetermined information may include at least one of the subject's attribute information and the second evaluation information. For example, the processor 111 refers to the subject's second evaluation information, and if the subject's oral condition is "slightly poor" or "pathological," it filters out professionals qualified to diagnose and treat oral conditions, such as dentists, doctors, dental hygienists, and nurses. If the oral condition is "good," it filters out professionals other than the above, such as caregivers, care workers, and speech-language-hearing therapists. Furthermore, for example, the processor 111, based on information on the subject's swallowing function and masticatory function, filters out professionals qualified to diagnose and treat oral conditions, such as dentists, doctors, dental hygienists, and nurses, if the swallowing function and masticatory function are "poor." If these functions are "good," it filters out professionals other than the above, such as caregivers, care workers, and speech-language-hearing therapists. In this way, when the generated second evaluation information or the swallowing function or chewing function indicates "poor" or "slightly poor," there is a higher possibility that a more specialized diagnosis or care will be required than when the second evaluation information indicates "good." Therefore, the processor 111 can appropriately filter experts.

[0139] Next, the processor 111 reads out at least one of the expertise information, operation information, expert evaluation information, and other attribute information of each expert, and selects an expert who can provide oral cavity-related services such as diagnosis and care to the subject (S214). As an example of this process, the processor 111 selects one or more experts from among the multiple experts based on the expert's attribute information and the second evaluation information. Specifically, the processor 111 reads out the attribute information of each expert, and calculates a priority score by adding up or weighting the points assigned to each attribute information. Then, the processor 111 selects one or more experts with a high priority score. The attribute information used in this process includes, for example, the following information:

[0140] (Expert evaluation information) Based on the accuracy information of the second evaluation information indicating the result of evaluating the first evaluation information, the expert with high accuracy is given a score (for example, the same process as that for the expert evaluation information in S117 is executed). Based on the information on the time it takes to transmit other second evaluation information to the processing device, the expert who takes a shorter time is given a bonus, or the expert who is slow or does not transmit is given a bonus. Based on the word-of-mouth information of each subject or user, experts with high word-of-mouth ratings are given additional points (this processing is performed by the processor 111 by performing language analysis on word-of-mouth information previously input by the subject or user in free text format, converting it into a score, and adding points according to the score. This processing is also performed by the processor 111 by acquiring the evaluation score of each expert by the user or subject, and adding points according to the evaluation score.)

[0141] (Operation information) Based on the schedule information, attendance information, and work schedule information of each expert, points are added to experts who are available on a specific date and time (for example, the date and time desired by the employer or the subject).

[0142] (Specialist Information) Based on the expert information of each expert, the experts who have a high degree of agreement with the subject's second evaluation information and evaluation information will be given additional points.

[0143] The attribute information and the methods of adding, subtracting, and weighting points listed here are merely examples, and other attribute information of the experts or other attribute information of the subjects may be used. Furthermore, the experts to be selected may be a predetermined number of experts selected based on the priority score, or any predetermined number of experts selected in descending order of priority score.

[0144] Next, when the processor 111 selects an expert (second expert), it reads out various attribute information associated with the second evaluation information, the expert (diagnosis, etc.) information, and the expert ID information, and generates evaluation result information. Then, the processor 111 transmits the generated evaluation result information via the communication interface 113 to the user terminal device 200-1 that transmitted the evaluation request (S215).

[0145] The evaluation result information generated here is shown in FIG. 7C as an example, but may naturally have other contents. Furthermore, the processor 111 can also generate the evaluation result information by using, for example, a large-scale language model (LLM). The processor 111 generates a prompt for generating the evaluation result information based on various attribute information associated with the second evaluation information, expert (diagnosis, etc.) information, and expert ID information, and inputs the prompt to the large-scale language model. The processor 111 then obtains the evaluation result information as an output from the large-scale language model. This completes the processing flow.

[0146] (C) Processing flow executed in S32 of FIG. 4B This processing flow is executed when an expert makes an offer to a target person to generate a list of target persons to whom an offer is made. According to FIG. 5C , upon receiving a matching request via the communication interface 113, the processor 111 reads location information from the attribute information of the expert based on the expert ID information of the expert who sent the matching request (S313). In this embodiment, as described above, the second expert is expected to visit the target person's location and provide home visit medical care, for example. Therefore, it is desirable that the target person to whom the second expert can make an offer is also a target person located within a range where home visit medical care can be provided. Therefore, the processor 111 extracts, based on the target person's attribute information, targets located within a predetermined range from the location identified based on the expert's location information read in S313 (S312).

[0147] Next, processor 111 further narrows down the candidates based on at least one of the second evaluation information and the evaluation information associated with the candidate ID information of each candidate and the expertise information of the expert who sent the matching request (S313). As an example of this process, similar to the process performed in S213 of FIG. 5B, processor 111 refers to the expertise information of the expert, and if the expert is a dentist, doctor, dental hygienist, nurse, or other qualified expert capable of diagnosing and treating oral conditions, narrows down the candidates to candidates whose oral conditions in the second evaluation information are "slightly poor" or "pathological." If the expert is any other qualified expert, processor 111 narrows down the candidates to candidates whose oral conditions are "good." Furthermore, processor 111 refers to the expertise information of the expert, and if the expert is a dentist, doctor, dental hygienist, nurse, or other qualified expert capable of diagnosing and treating oral conditions, narrows down the candidates to candidates whose oral conditions are "poor" or "good." If the expert is any other qualified expert, processor 111 narrows down the candidates to candidates whose swallowing function or masticatory function is "poor." If the expert is any other qualified expert, processor 111 narrows down the candidates to candidates whose swallowing function or masticatory function is "good." In this way, when the generated second evaluation information or the swallowing function or chewing function indicates "poor" or "slightly poor," there is a high possibility that a more specialized diagnosis or care will be required than when the function is "good." Therefore, the processor 111 can appropriately filter candidates to be matched based on the specialized information of the experts.

[0148] Next, the processor 111 refers to the expert (evaluation) information in the subject ID information of each subject, reads out the expert ID information of the expert who made the evaluation on the first evaluation information, and further excludes the expert from the experts narrowed down in S313 (S314). This makes it possible to further increase the objectivity of the evaluation on the first evaluation information.

[0149] Next, the processor 111 reads out attribute information and the like of one or more subjects narrowed down in S312 to S314, and generates a list (S315). Then, the processor 111 transmits the generated list as subject information of the matched subjects to the expert terminal device 200-2 that transmitted the matching request via the communication interface 113. This ends the processing flow.

[0150] As described above, in this embodiment, it is possible to provide a processing device, a processing program, a processing method, and a processing system that are capable of more appropriately evaluating the oral cavity of a subject.

[0151] 5. Variations As described above, one embodiment according to the present disclosure has been described based on FIGS. 1 to 7C. However, various modified examples are also applicable, not limited to those described above. Note that, although each modified example will be described below, it is also possible to use each modified example in appropriate combination. Furthermore, although the modified examples will be described below in detail, the remaining parts can be implemented in the same manner as the embodiment described with reference to FIGS. 1 to 7C.

[0152] (A) Evaluation Information In the above embodiment, various information such as lip condition, tongue condition, saliva viscosity, number of remaining teeth, denture condition, oral hygiene condition, tooth and tongue stains, swelling of cheeks and gums, bleeding gums, whether or not and to what extent the left and right molars are aligned, whether or not there is a choking symptom, whether or not gargling is performed, whether food is stored or remains, broken teeth, ulcers, subgingival abscesses, the color of each part of the oral cavity, the wetness or dryness of each part of the oral cavity, saliva condition, degree of mouth opening, swallowing function, and chewing function can be used as evaluation information. The above embodiment describes a case where this information can be acquired as interview information or finding information by input by a user or an expert or by detection using other devices. However, instead, it may be acquired by image analysis based on subject images. For example, a trained analysis model can be acquired by providing a learner with pairs of training object images and correct label information that labels each training object image based on the results of evaluating each subject for the above-mentioned states, and repeating learning while adjusting the parameters of each neuron. Thus, by inputting object images into the trained analysis model, processor 111 can acquire information indicating each of the above-mentioned states as output information.

[0153] (B) Billing process In the above embodiment, for example, in FIGS. 4B and 5C, a case has been described in which a matching request is sent from the expert terminal device 200-2 to the processing device 100, thereby allowing information on matched subjects to be provided from the processing device 100. At this time, the processor 111 can also perform billing processing on the expert using the expert terminal device 200-2 that received the matching request. For example, the processor 111 sends a payment request to the expert terminal device 200-2 according to the number of subjects included in the list generated in S315 of FIG. 5C. Then, the processor 111 confirms that payment for the payment request has been confirmed or that payment information has been input (e.g., payment information input by credit card), and then sends the list to the expert terminal device 200-2. The processor 111 then acquires information such as the number of offers generated in the expert terminal device 200-2 and sent to the user terminal device 200-1 of the user, and the number of cases in which diagnosis or care services have actually been provided by the expert thereafter, and sends a payment request to the expert terminal device 200-2 based on the information. In this way, by performing the billing process for the provision of information, it becomes possible to operate the service by the processing system 1 more smoothly.

[0154] In the above embodiment, the case where the subject or user acquires evaluation result information based on a subject image including at least a portion of the oral cavity as a subject has been described. In this case, the processor 111 can also perform a billing process for the user who made the evaluation request or the user who acquired the evaluation result information. For example, before transmitting the evaluation request at T11 in FIG. 4A , the processor 111 transmits a payment request for a predetermined amount to the user terminal device 200-1. Then, the processor 111 confirms that the payment for the payment request has been confirmed or that the payment information has been input (e.g., the payment information has been input by credit card), and then controls the screen to transition to a transmission screen for the evaluation request. Alternatively, the processor 111 transmits the evaluation result information at T14 in FIG. 4A , but transmits only part of the evaluation result information and a payment request for the predetermined amount for transmitting the remaining evaluation result information. Then, the processor 111 confirms that the payment for the payment request has been confirmed or that the payment information has been input (e.g., the payment information has been input by credit card), and then controls the screen to transmit the remaining evaluation result information.

[0155] (C) Where to send the offer In the above embodiment, FIG. 4B illustrates a case in which a matching request is sent from the expert terminal device 200-2 to the processing device 100, thereby allowing the expert terminal device 200-2 to send an offer to the matched subject to the user terminal device 200-1. However, the destination of the offer is not limited to the user terminal device 200-1, and it can also be sent to another device, such as a subject terminal device that can be used by the subject. Furthermore, it does not necessarily have to be transferred via the processing device 100, and it can also be sent directly to each device, such as the user terminal device 200-1 or a subject terminal device that can be used by the subject. Furthermore, the method of transmission is not limited to electronic transmission via email or SNS, but can also be a transmission method using a physical medium, such as mail or direct mail.

[0156] (D) Payment of Remuneration In the above embodiment, FIGS. 1 to 7C illustrate a case where an expert selected as a first expert is easily extracted as an expert (second expert) providing services such as diagnosis and care by using a priority score or the like. However, in addition to this, it is also possible to pay a reward to the expert selected as a first expert each time the expert generates second evaluation information. Specifically, the processor 111 stores information indicating the number of cases in which second evaluation information has been transmitted within a predetermined period in the expert management table, calculates a reward amount according to the number of cases each time the period expires, and notifies each expert terminal device 200-2 of the reward amount. At this time, the processor 111 can also weight the reward amount by referring to the expert evaluation information of each expert. For example, the processor 111 can weight the reward amount according to the speed of transmission of the second evaluation information after transmitting an evaluation request for the first evaluation information. Furthermore, the processor 111 can weight the reward amount if the number of cases in which second evaluation information has been generated within a predetermined period exceeds a predetermined number.

[0157] The processor 111 may also rank each expert (e.g., assign a rank such as bronze, silver, gold, or platinum) according to the expert evaluation information of each expert. At this time, the processor 111 may transmit an account information screen on which the rank (bronze, silver, gold, or platinum) assigned to each expert is visible, for example, by receiving an information display request from the expert terminal device 200-2 of each expert. The processor 111 may also weight the amount of remuneration paid to each expert according to the rank. By visually checking the rank assigned to each expert, experts can be motivated to improve their skills and techniques in order to achieve a higher rank.

[0158] (E) Search by user or target In the above embodiment, for example, FIG. 4B illustrates a case in which an expert can search for a target person and send a matching offer. Conversely, a user or target person can search for an expert who can provide diagnosis or care and perform matching. Specifically, the processor 211 of the user terminal device 200-1 accepts input from the user or target person via the input interface 213 and inputs search criteria for a desired expert who can provide diagnosis or care. The processor 211 transmits the input search criteria to the processing device 100 via the communication interface 215. When the processor 111 of the processing device 100 receives the search criteria via the communication interface 113, it references various attribute information in the expert management table (FIG. 3C) and extracts experts that match the received search criteria. When an expert is extracted, the processor 111 transmits location information, expert information, expert evaluation information, and other attribute information associated with the expert ID information of the extracted expert to the user terminal device 200-1 via the communication interface 113.

[0159] When the processor 211 of the user terminal device 200-1 receives various information about the extracted experts via the communication interface 215, it outputs the received information via the output interface 214. The processor 211 accepts an operation input by the user or subject via the input interface 215 and selects a desired expert. The processor 211 of the user terminal device 200-1 transmits an offer of diagnosis or care to the expert terminal device 200-2 of the desired expert via the communication interface 213, via the processing device 100 as necessary. Specifically, the same processes as S23 to S25 in Fig. 4A are performed.

[0160] As a result, once a diagnosis or care is determined, an expert will actually visit and provide the diagnosis or care through appropriate processing. Therefore, for example, the user or subject can more easily search for experts other than the second expert included in the evaluation result information. In addition, it becomes possible to more effectively utilize the various information about experts stored in the expert management table.

[0161] The processes and procedures described herein can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination thereof. Specifically, the processes and procedures described herein can be realized by implementing logic corresponding to the processes in media such as integrated circuits, volatile memory, nonvolatile memory, magnetic disks, and optical storage. Furthermore, the processes and procedures described herein can be implemented as computer programs and executed by various computers, including processing devices and server devices.

[0162] Although processes and procedures described herein are described as being performed by a single device, software, component, or module, such processes or procedures may be performed by multiple devices, multiple software, multiple components, and / or multiple modules. Furthermore, although various information described herein is described as being stored in a single memory or storage unit, such information may be stored in multiple memories within a single device or multiple memories distributed across multiple devices. Furthermore, software and hardware elements described herein may be realized by integrating them into fewer components or by decomposing them into more components. [Explanation of symbols]

[0163] 1 Processing System 100 Processing equipment 200-1 User terminal device 200-2 Expert terminal device

Claims

1. A processing device comprising at least one processor, the at least one processor: Acquire a subject image including at least a part of the oral cavity of the subject as a subject, the subject image being captured by a user terminal device that can be used by a user; acquiring first evaluation information indicating a result of evaluation of the oral cavity state of the subject by inputting the subject image into a trained evaluation model for evaluating the oral cavity state of the subject; acquiring second evaluation information indicating a result of evaluating the first evaluation information, which is input by one or more first experts selected from the plurality of experts, based on at least one of the attribute information of the subject and the first evaluation information and each attribute information of a plurality of experts who can evaluate the first evaluation information; outputting evaluation result information based on the second evaluation information to the user terminal device; a processing unit configured to perform processing for:

2. The processing device described in claim 1, wherein the trained evaluation model is generated by learning based on training subject images of at least a portion of the subject's oral cavity and training evaluation information indicating the results of evaluating the condition of the subject's oral cavity.

3. The processing device according to claim 1 , wherein the first evaluation information is acquired by inputting the subject image and evaluation information associated with the subject into the trained evaluation model.

4. The treatment device according to claim 1 , wherein the condition of the oral cavity includes at least one of the conditions of the lips, the sublingual area, the gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache.

5. The treatment device according to claim 1, wherein the condition of the oral cavity includes at least one of the conditions of the lips, sublingual, gums or oral mucosa, saliva, remaining teeth, dentures, oral hygiene, and toothache, and at least one of the conditions of swallowing function and chewing function.

6. The processing device according to claim 1 , wherein the attribute information of the experts includes expert evaluation information indicating an evaluation result for each expert.

7. The processing device described in claim 6, wherein the expert evaluation information includes at least one of the accuracy of other second evaluation information indicating the results of evaluating other first evaluation information, the time until the other second evaluation information is transmitted to the processing device, and the difficulty of evaluating the other first evaluation information.

8. The processing device according to claim 6 , wherein the attribute information of the experts further includes at least one of operation information, expertise information, and location information of each expert.

9. The processing device according to claim 1 , wherein the evaluation result information includes attribute information of one or more second experts selected from the plurality of experts based on the second evaluation information and attribute information of each of the plurality of experts.

10. The processing device of claim 9 , wherein the second expert is a different expert from the first expert.

11. The processing device according to claim 9 , wherein the second expert is an expert located within a predetermined range from the position information associated with the subject.

12. The processing device according to claim 1 , wherein the at least one processor is configured to execute a process for providing attribute information of the subject in response to a request from at least one of the plurality of experts.

13. When executed by at least one processor, Acquire a subject image including at least a part of the oral cavity of the subject as a subject, the subject image being captured by a user terminal device that can be used by a user; acquiring first evaluation information indicating a result of evaluation of the oral cavity state of the subject by inputting the subject image into a trained evaluation model for evaluating the oral cavity state of the subject; acquiring second evaluation information indicating a result of evaluating the first evaluation information, which is input by one or more first experts selected from the plurality of experts, based on at least one of the attribute information of the subject and the first evaluation information and each attribute information of a plurality of experts who can evaluate the first evaluation information; outputting evaluation result information based on the second evaluation information to the user terminal device; A processing program that causes the at least one processor to function in such a manner.

14. A processing method executed by at least one processor, comprising: acquiring a subject image including at least a part of the oral cavity of a subject as a subject, the subject image being captured by a user terminal device usable by a user; a step of acquiring first evaluation information indicating a result of evaluation of the oral cavity state of the subject by inputting the subject image into a trained evaluation model for evaluating the oral cavity state of the subject; acquiring second evaluation information indicating a result of evaluation of the first evaluation information, which is input by one or more first experts selected from the plurality of experts, based on at least one of the attribute information of the subject and the first evaluation information and each attribute information of the plurality of experts who can evaluate the first evaluation information; outputting evaluation result information based on the second evaluation information to the user terminal device; A processing method comprising:

15. a user terminal device configured to capture a subject image including at least a portion of the subject's oral cavity as a subject; The processing device according to claim 1, which is communicatively connected to the user terminal device; A processing system comprising:

Images