JP2021067996A - Treatment support system - Google Patents

Abstract

To provide a treatment support device for supporting a medical doctor in uniquely constructing an AI for estimating various information on treatment and operating the AI.SOLUTION: Experiences of dentists having an established evaluation are inputted to a dental treatment support server 105 in advance to cause an AI (artificial intelligence) to learn the experiences. Then, it functions such that a dentist having deep experiences gives advice to perform support for making dental treatment to be a constant level or more by inputting opinions or the like to the AI to even a dentist still having a low experience value when determining a disease name, a treatment method, treatment planning, or the like. In such a case, a URL for allowing a terminal device 104b for the AI to directly access an AI processing part is concealed from a user.EFFECT: A malicious third party is prevented from making invalid access to the AI so that an AI created by an individual user can appropriately be operated.SELECTED DRAWING: Figure 1

Description

The present invention relates to a treatment support system mainly operated in a medical field such as a dental treatment field.

The dentist starts treatment through the preparations (1) to (4) below based on the findings of the condition of the tooth periodontal disease prepared for each tooth number.
(1) Determine the name of the disease for each tooth number of the problematic periodontal disease.
(2) Determine the treatment method for each tooth number based on the disease name and findings.
(3) Identify the treatment order of the tooth number from the treatment method of the entire tooth number.
(4) Consult with the patient to determine the optimal treatment sequence.
The tooth number is the oral cavity when the patient is viewed from the front, divided into the upper left, lower left, upper right, and lower right of the median plane, with permanent teeth 1 to 8 and deciduous teeth A to E from front to back. It is a number.

Patent Document 1 discloses a dental treatment support system, which is a prior art of the present invention, that supports a dentist to determine a patient's disease name, formulate a treatment method, and formulate a treatment sequence.

JP-A-2019-80900

The above-mentioned determination of disease names, formulation of treatment methods, and formulation of treatment sequences cannot be performed simply on a regular basis, and tacit knowledge such as observation, experience, or intuition accumulated by dentists is required. For example, avoid simultaneous treatment at two locations on the left and right so as not to interfere with the patient's diet, and decide the treatment method and treatment order so that tooth extraction does not have to be done. That is, at present, the quality of dental treatment depends on the difference in experience of dentists.
If information technology can be used to assist in determining the name of a disease, formulating a treatment method, and formulating a treatment sequence, even an inexperienced dentist can be expected to realize high-quality dental treatment.
Based on the above background, the inventors have invented a dental treatment support system in which the know-how of a dentist is registered in a machine learning system and / or a database, and the know-how can be used by an inexperienced dentist. This is the invention disclosed in Patent Document 1.

In the dental treatment support system according to Patent Document 1, an AI (artificial intelligence) that learns the know-how of a plurality of dentists is constructed by a server operator operating the server, and the dentist who is the user is concerned. It is a usage form system that uses AI. That is, the AI formed on the server is used to provide a common and single type of service to all users under the control of the server operator.
However, since the treatment method and treatment sequence differ depending on the specialized field, there may be no AI suitable for the user's specialized field.
Therefore, if the user can build his / her own AI on the server, it will be possible to build an AI specialized in a specialized field, and the user can select and use the necessary AI from various AIs. It will be possible.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a treatment support system that assists a doctor in constructing and operating an AI that independently estimates various information related to treatment.

In order to solve the above problems, the treatment support system of the present invention realizes an estimation calculation device that executes an estimation calculation process for a predetermined input data by combining approximate function parameters formed by a predetermined learning process. It includes an arithmetic processing unit and an input / output control unit that realizes a predetermined estimation arithmetic device by selecting one from a plurality of approximate function parameters existing corresponding to a specified URL and combining it with the estimation arithmetic processing unit. ..
Further, an AIID master having an AIID field in which all AIIDs, which are identification information for uniquely identifying the estimation arithmetic unit, are stored, and a URL field in which a URL for accessing the estimation calculation device corresponding to the AIID is stored. In response to the inquiry to the estimation arithmetic unit including the AIID sent from the terminal device, the AI usage request conversion processing unit that converts the AIID into a URL based on the AIID master, and the URL obtained from the AI usage request conversion processing unit. It is provided with an AI communication processing unit that makes an inquiry to the input / output control unit based on the above.

INDUSTRIAL APPLICABILITY According to the present invention, it is possible to provide a treatment support system that assists a doctor to independently construct and operate an AI that estimates various information related to treatment.
Issues, configurations and effects other than those described above will be clarified by the description of the following embodiments.

It is the schematic which shows the whole structure of the dental treatment support system which concerns on embodiment of this invention. It is a block diagram which shows the hardware configuration of a terminal device. It is a block diagram which shows the hardware composition of the dental treatment support server. It is a block diagram which shows the outline of the software function of the dental treatment support system. It is a table which shows the field structure of various tables. It is a functional block diagram which shows the learning phase of the system standard AI in the AI processing part. It is a functional block diagram which shows the estimation phase of the system standard AI in the AI processing part. It is a figure which shows the learning phase of the user-specific AI in the AI processing unit. It is a figure which shows the estimation phase of the user-specific AI in the AI processing unit. It is a timing chart when a user uses AI through a terminal device.

The present invention is an improved invention of the invention disclosed in Patent Document 1.
Many experienced dentists or clinics often have different specialties. There are various types of dentists, such as dentists who have abundant experience in pediatric treatment and dentists who have abundant experience in non-insurance treatment such as implants. These dentists or dental offices have their own patient database, and their data are valuable.
If each user who uses the dental treatment support system can construct a user's own AI based on the user's own data, it has features that the dental treatment support system does not have in the standard AI. , It can be expected that the use of AI by mutual users will be activated.

For example, if AI provided by a dentist who has abundant experience in pediatric treatment is used, it can be expected that the accuracy of diagnosis for pediatric treatment will be improved.
In addition, if AI provided by a dentist who has abundant experience in non-insurance treatment such as implants is used, it can be expected to improve the selection accuracy of appropriate insert teeth and the like in non-insurance treatment.

The present invention has been made in view of a situation in which the quality of dental treatment depends on differences in the experience of dentists and the like.
An embodiment of the present invention is a dental treatment support system that utilizes AI. AI (artificial intelligence) is made to learn the experience of a well-established dentist in advance. Then, in the embodiment of the present invention, by inputting the findings and the like in this AI, even a dentist who has a low experience value can feel as if he / she has a deep experience in dentistry when determining the disease name, treatment method, treatment plan, etc. It acts as if a doctor advises and helps to bring dental treatment above a certain level.

The AI learning calculation process used by the dental treatment support system executes machine learning that reads data including variable-length text data and performs classification learning. This machine learning is generally realized by AI having a natural language processing function and a function of evaluating inference results. Examples of this machine learning include Machine Learning Studio and LUIS (Language Understanding Intelligent Service) formed in Microsoft's cloud service "AZURE", and IBM's NLC (Natural Language Classifier). From this point onward, the dental treatment support system 101 according to the embodiment of the present invention will use Machine Learning Studio through AZURE.

A unique URL (Uniform Resource Locator) is assigned to the AI formed on AZURE, and the AI is used by transmitting a predetermined input item to this URL.
At this time, if the URL of the AI is known to the user or a third party, the AI will be used inexhaustibly.
That is, in the current AZURE, the system is not constructed on the assumption that a certain AI is used by a specific large number of users.
Therefore, in the dental treatment support system according to the embodiment of the present invention, the URL of the AI is concealed and user authentication is required to prevent the use of the AI by a third party and to charge correctly according to the usage amount of the AI. We are building a mechanism to generate such things.

[Dental treatment support system 101: Overall configuration]
FIG. 1 is a schematic view showing the overall configuration of the dental treatment support system 101 according to the embodiment of the present invention.
The experienced dentist 102 is a dentist who has a good reputation for dental treatment. The experienced dentist 102 connects his / her own terminal device 104a to the dental treatment support server 105 through the Internet 103. Then, the past treatment information (medical record) of the experienced dentist 102 himself is input to the dental treatment support server 105 using the terminal device 104a. The dental treatment support server 105 learns the treatment information input from the terminal device 104a.

The inexperienced dentist 106 is an inexperienced dentist in dental treatment. This inexperienced dentist 106 connects his own terminal device 104b to the dental treatment support server 105 through the Internet 103. Then, using the terminal device 104b, information (medical record) such as the findings of the patient 107 who is about to perform medical treatment is input to the dental treatment support server 105. The dental treatment support server 105 estimates the disease name of the patient 107, the treatment method, and the treatment order based on the information such as the findings input from the terminal device 104b, and outputs the result to the terminal device 104b.
Hereinafter, when the terminal device 104a and the terminal device 104b are not distinguished, they are referred to as the terminal device 104.

[Terminal device 104: Hardware configuration]
FIG. 2 is a block diagram showing a hardware configuration of the terminal device 104.
The terminal device 104 made of a general personal computer includes a CPU 202, a ROM 203, a RAM 204, a display unit 205, an operation unit 206, a non-volatile storage 207, and a NIC 208 connected to the bus 201.
The display unit 205 and the operation unit 206 of the terminal device 104 may be used in place of the display unit 307 and the operation unit 308 of the dental treatment support server 105.

[Dental treatment support server 105: Hardware configuration]
FIG. 3 is a block diagram showing a hardware configuration of the dental treatment support server 105.
The dental treatment support server 105 includes a CPU 302, a ROM 303, a RAM 304, a non-volatile storage 305, a NIC 306, and an RTC (Real Time Clock) 309 connected to the bus 301.
The dental treatment support server 105 can be diverted from a personal computer. In that case, it may have a display unit 307 and an operation unit 308. Here, since the display unit 307 and the operation unit 308 are not indispensable to the dental treatment support server 105, they are shown by dotted lines.

[Dental treatment support system 101: Outline of software functions]
FIG. 4 is a block diagram showing an outline of software functions of the dental treatment support system 101.
The dental treatment support server 105 is a cloud web service. For convenience of illustration, FIGS. 3 and 4 are illustrated with a single computer resource.

The terminal device 104 includes a display unit 205 and an operation unit 206 connected to the input / output control unit 401. The information generated by the user operating the operation unit 206 is transmitted from the input / output control unit 401 to the dental treatment support server 105 via the Internet 103. Further, the information received by the input / output control unit 401 from the dental treatment support server 105 via the Internet 103 is displayed on the display unit 205.

The dental treatment support server 105 functions as a web server for the terminal device 104. The input / output control unit 403 executes communication with the terminal device 104 by a well-known HTTPS (Hypertext Transfer Protocol Secure).
When the terminal device 104 accesses the dental treatment support server 105, the AI selection screen processing unit 402 is started through the input / output control unit 403.
The AI selection screen processing unit 402 refers to the user master 404 to perform predetermined login authentication, and then refers to the user use AI table 405 to create a list of AIs available to the user of the terminal device 104. Further, the dental treatment support server 105 creates an HTML document constituting the AI selection screen based on the created AI list, and returns it to the terminal device 104.

When the user operates the terminal device 104 to select the AI to be used and sends a predetermined input item including the patient's age and the oral disease site to the dental treatment support server 105, the AI usage request conversion of the dental treatment support server 105 is performed. The processing unit 406 receives this through the input / output control unit 403. The AI usage request conversion processing unit 406 refers to the AIID master 407 and converts the AIID of the AI selected by the user into a URL. The AIID is identification information for uniquely identifying a plurality of AIs formed in the AI processing unit 409 of the dental treatment support server 105. Then, the input / output control unit 403 delivers the URL received from the AI usage request conversion processing unit 406 and a predetermined input item to the AI communication processing unit 408.
The AI communication processing unit 408 functions as a web client for the AI processing unit 409. Further, the AI processing unit 409 is a web server that provides the AI resource specified by the URL. The AI communication processing unit 408 connects to the AI processing unit 409 by accessing the URL received from the AI usage request conversion processing unit 406, and transmits a predetermined input item to the AI processing unit 409.

The AI processing unit 409 includes an input / output control unit 410 which is a web server program and an estimation calculation processing unit 411 which is an arithmetic processing engine of AI.
The input / output control unit 410 combines the approximation function parameter 412, the label table 413, and the estimation calculation processing unit 411 based on the URL specified by the AI communication processing unit 408 to form a desired AI (classification estimator). Then, the input predetermined input item is given to the estimation calculation processing unit 411 to obtain the estimation result.
Hereinafter, the AI formed in the AI processing unit 409, which will be described in the embodiment of the present invention, is obtained by combining the approximation function parameter 412 formed by the predetermined learning process and the label table 413 in the estimation calculation processing unit 411. It is a classification estimator to be realized, and has a function as an estimation calculation device that executes estimation calculation processing for predetermined input data. The approximate function parameter is a group of coefficients for realizing the approximate function, which is updated by the learning process in machine learning.

The estimation result generated by AI is handed over to the AI communication processing unit 408 through the input / output control unit 410, and finally returned to the terminal device 104 via the input / output control unit 403.
When the execution of AI is completed normally, the AI usage request conversion processing unit 406 logs a series of execution results in the AI usage log table 415.

An estimation calculation device that uses machine learning including AI has a learning phase in which an estimation calculation function is generated and updated, and an estimation phase in which input data is actually given to execute the estimation calculation.
In the AI processing unit 409, in addition to the estimation calculation processing unit 411 that executes the estimation phase, there is a learning calculation processing unit 414 that executes a learning phase that generates and updates a desired AI.

The learning calculation processing unit 414 of the AI processing unit 409 reads data including variable-length text data and executes machine learning that performs classification learning. This machine learning is generally realized by AI having a natural language processing function and a function of evaluating inference results. Examples include Machine Learning Studio and LUIS (Language Understanding Intelligent Service) formed in Microsoft's cloud service "AZURE", and IBM's NLC (Natural Language Classifier).

For example, the following four types of AI can be formed by the AI processing unit 409.
(1) A treatment plan AI that outputs a treatment plan when the patient age, oral disease site, and oral disease name are input.
The treatment plan AI provides reference information when a dentist formulates a treatment plan by outputting a treatment plan inferred from the oral disease site and the name of the oral disease disease together with a probability.
(2) Finding AI that outputs findings when the patient age, oral disease site and oral disease name are input.
When the patient age, the oral disease site and the oral disease name are input, the finding AI outputs the text of the finding created by another dentist together with the probability. The dentist can infer the accuracy of the oral disease name by looking at the text of this finding.

(3) When the patient age, the site of the oral disease, and the content of the first treatment are input, the name of the oral disease is output, and the treatment disease name AI.
The treatment disease name AI provides reference information for the dentist to determine the disease name to be described in the medical record by outputting the patient age, the oral disease site, and the disease name inferred from the actual treatment contents together with the probability.
(4) Finding disease name AI that outputs the name of oral disease when the patient age, the site of oral disease and the findings are input.
Finding disease name AI provides reference information for medical examination by a dentist by outputting the patient age, the site of oral disease, and the name of the disease inferred from the text of the finding together with the probability.
As is clear from the above explanation, each AI has two types of input items, that is, the patient age and the oral disease site, which are common and indispensable. These input items are indispensable for improving the estimation accuracy of AI. In other words, there appears to be some correlation between the site of oral disease and oral disease and the age of the patient.

In FIG. 4, the AI processing unit 409 is shown inside the dental treatment support server 105 so as to form a part of the dental treatment support server 105, but as described above, the dental treatment support server 105 is in the cloud. It is formed in a web service. Therefore, the AI processing unit 409 may be constructed as a web server separate from the dental treatment support server 105.

FIG. 5 is a table showing the field configurations of various tables.
The user master 404 has a login ID field, a password hash value field, a user ID field, and other fields.
In the login ID field, a login ID for authenticating when the user uses the dental treatment support server 105 is stored.
The password hash value field stores the hash value of the password.
A user ID that uniquely identifies a user is stored in the user ID field.
Various information about the user is stored in the other fields.
In the dental treatment support server 105 according to the embodiment of the present invention, in addition to the user ID, the AI ID of another person can be acquired and the AI can be used immediately even if the user ID is leaked. The user master 404 has a login ID and a password hash value for authentication.

The user-used AI table 405 has a user ID field and an AIID field.
The user ID field is the same as the user ID field of the user master 404.
In the AIID field, AIID which is identification information for uniquely identifying the AI available to the user of the user ID described in the user ID field is stored.
Therefore, in the user use AI table 405, the user ID and the AIID have a one-to-many relationship.

The AIID master 407 has an AIID field, a user ID field, a URL field, and a usage fee field.
The AIID field is substantially the same as the AIID field of the user-used AI table 405, and all AIIDs that are identification information for uniquely identifying the AI are stored.
In the user ID field, the user ID of the user who creates and owns the AI of the AIID described in the AIID field is stored.
In the URL field, the URL for accessing the AI corresponding to the AIID is stored.
The usage fee field stores the usage fee of AI set by the user when creating the AI.

The AI usage log table 415 has a usage date / time field, a user ID field, an AIID field, an execution result field, a usage fee field, and other fields.
The user ID field is the same as the user ID field of the user use AI table 405. That is, the user ID of the user who uses the AI specified by the AIID described in the AIID field is stored.
The AIID field is the same as the AIID field in the user-used AI table 405. That is, the AI ID of the AI used by the user specified by the user ID described in the user ID field is stored.
In the usage date and time field, the date and time when the user specified by the user ID described in the user ID field uses the AI specified by the AIID described in the AIID field is stored.
The execution result field stores information indicating whether or not the AI has been executed normally as a result of execution.
The usage fee field stores the usage fee of AI generated as a result of the user using AI. That is, it is a copy of the value of the field having the same name in the AIID master 407.
In the other fields, various information related to user access (for example, User Agent of HTTP (S), etc.) is stored.

[Dental treatment support system 101: Construction and operation of system standard AI]
FIG. 6 is a functional block diagram showing a learning phase of the system standard AI in the AI processing unit 409.
FIG. 7 is a functional block diagram showing an estimation phase of the system standard AI in the AI processing unit 409.
Note that in FIGS. 6 and 7, various data processing processes performed when data is delivered to the AI processing unit 409 inside the dental treatment support server 105 are omitted.

First, in order to configure the system standard AI, the dental treatment support server 105 creates the system standard approximation function parameter 601 in the learning phase.
The system standard label table 602 is a table that holds labels corresponding to teacher data.
The terminal device 104 provides input data and teacher data to the AI processing unit 409 of the dental treatment support server 105.
The teacher data input from the terminal device 104 may be a long natural language sentence or a record of a table having a plurality of fields. By assigning a label that uniquely identifies these records instead of these indefinite teacher data and inputting them in place of the teacher data, the burden on the learning calculation processing unit 414 is reduced, and the system standard approximation function parameter 601 Reduce the data capacity of.

In the estimation phase, the estimation calculation processing unit 411 outputs the label and the probability as the estimation result as the estimation list 701.
The input / output control unit 410 of the AI processing unit 409 does not return the estimation list 701 to the terminal device 104 as it is, but refers to the system standard label table 602, replaces the label with the original estimation result, and replaces the label with the original estimation result, and the terminal device 104. Reply to.

[Dental treatment support system 101: Construction and operation of user-specific AI]
FIG. 8 is a diagram showing a user-specific AI learning phase in the AI processing unit 409.
FIG. 9 is a diagram showing a user-specific AI estimation phase in the AI processing unit 409.
Since there is no change in the terminal device 104 as compared with FIGS. 6 and 7, the illustration is omitted.
The system standard approximation function parameter 601 and the system standard label table 602 that constitute the system standard AI created in FIG. 6 are copied to the user-specific approximation function parameter 801 and the user-specific label table 802, respectively, and then the user owns the data. To learn using.
Therefore, by combining the estimation calculation processing unit 411, the user-specific approximation function parameter 801 and the user-specific label table 802, an AI reflecting the user-specific learning data is constructed and functions.

When a user creates his or her own AI, the AI processing unit 409 generates a URL for using the AI. After that, a new AIID corresponding to the URL is generated by the AI management processing unit (not shown), and is additionally recorded as a new record in the AIID master 407. At that time, the usage fee determined by the user is also recorded in the usage fee field of the record.
When another user uses the new AI, the AIID is copied from the AIID master 407 to the user-used AI table 405.
Through the above processing, the AI originally created by a certain user is used and shared by a plurality of other users.

[Dental treatment support system 101: Use of user-specific AI]
FIG. 10 is a timing chart when the user uses AI through the terminal device 104.
When the menu display request operation is performed by the user operating the terminal device 104, the menu display request is transmitted from the terminal device 104 to the AI selection screen processing unit 402 of the dental treatment support server 105 together with the user ID (S1001).

The AI selection screen processing unit 402 refers to the user master 404 and the user use AI table 405, creates a list of AIIDs available to the user of the terminal device 104, and creates an AI selection screen HTML document based on the list. Then, the AI selection screen HTML document is returned (S1002).

When the terminal device 104 receives the AI selection screen HTML document from the AI selection screen processing unit 402 of the dental treatment support server 105, the terminal device 104 displays the available AI menu on the display unit 205 (S1003).
The user selects the AI to be used, inputs a predetermined input item, and transmits the AI to the dental treatment support server 105 (S1004).

The user ID, AIID, and predetermined input items transmitted from the terminal device 104 are input to the AI usage request conversion processing unit 406. The AI usage request conversion processing unit 406 refers to the AIID master 407 and replaces the AIID received from the terminal device 104 with a URL. Then, the URL and a predetermined input item are passed to the AI communication processing unit 408 (S1005).
The AI communication processing unit 408 that has received the URL and a predetermined input item from the AI usage request conversion processing unit 406 functions as a web client for the AI processing unit 409. The AI communication processing unit 408 connects to the AI processing unit 409 by accessing the URL, and transmits a predetermined input item to the AI processing unit 409 by a well-known HTTPS (S1006).

The AI processing unit 409 that received the access request from the AI communication processing unit 408 activates the AI specified by the URL, gives a predetermined input item received from the AI communication processing unit 408 to the AI, executes it, and executes the estimation result. To get. Then, the answer, which is the estimation result, is returned to the AI communication processing unit 408 (S1007).
The AI communication processing unit 408 transfers the response received from the AI processing unit 409 to the AI usage request conversion processing unit 406 (S1008).
Upon receiving the response from the AI communication processing unit 408, the AI usage request conversion processing unit 406 transfers (replies) the response to the terminal device 104 and additionally records the AI usage log in the AI usage log table 415 (S1009). .. At this time, the AI usage request conversion processing unit 406 searches the AIID master 407 by AIID and posts the value of the usage charge field of the hit record to the usage charge field of the new record of the AI usage log table 415.
The terminal device 104 that has received the response from the dental treatment support server 105 displays the response on the display unit 205 (S1010).

In the AI usage log table 415, information indicating when and which user used which AI, and the AI usage fee are accumulated. Therefore, if the AI usage log table 415 is narrowed down by the usage date and time and the user ID that match the predetermined usage period, and then the values in the usage fee fields are added up, the usage fee that the user should pay in the predetermined AI usage period is added. Can be calculated. Further, after narrowing down the records of the AIID master 407 by the user ID, the AIID in the AIID field of the hit record is held as a search key. Then, if the AI usage log table 415 is narrowed down by the usage date and time matching the predetermined usage period and the previously held AIID, and the values of the usage charge fields are added up, the user who created the AI uses the predetermined AI. It becomes possible to calculate the usage fee obtained during the period.
Therefore, by referring to the AI usage log table 415 and the AIID master 407, the user who created the AI can collect the usage fee from the user who used the AI.

The usage charge field of the AI usage log table 415 is provided for facilitating the usage charge total processing, and is not always essential. By associating the AIID field of the AI usage log table 415 with the AIID field of the AIID master 407 and referring to the usage charge field of the AIID master 407, the above-mentioned usage charges can be added up.
Further, the timing for calculating the usage fee may be executed by the AI usage request conversion processing unit 406 in real time at the time of step S1009, or may be executed by batch processing or the like on the monthly fee calculation day or the like. In this case, the AI usage request conversion processing unit 406 functions as an AI usage charge calculation unit. Further, the functional block that functions as the AI usage charge calculation unit may be provided as an independent program different from the AI usage request conversion processing unit 406 instead of the AI usage request conversion processing unit 406.

As described in step S1006, the AI communication processing unit 408 is a web client for the AI processing unit 409 that functions as a web server. When accessing the AI processing unit 409, the AI communication processing unit 408 accesses the AI processing unit 409 using a user ID unique to the AI processing unit 409.
That is, the input / output control unit 403, the AI usage request conversion processing unit 406, and the AI communication processing unit 408 are interposed between the user's terminal device 104 and the AI processing unit 409, and the AI utilization transmitted from the terminal device 104. Acts as a kind of application proxy that acts on behalf of the request.
In the access of the terminal device 104 to the AI, the URL for directly accessing the AI processing unit 409 is hidden from the user by the AI usage request conversion processing unit 406. Therefore, it is possible to prevent unauthorized access to the AI by a malicious third party and appropriately operate the AI created by each user.

In FIG. 10, the data flow is that the terminal device 104 reaches the AI processing unit 409 via the AI usage request conversion processing unit 406 and the AI communication processing unit 408. However, the AI communication is performed directly from the terminal device 104. The flow may be such that the AI processing unit 409 is reached via the processing unit 408. In this case, the procedure is that the AI communication processing unit 408 causes the AI usage request conversion processing unit 406 to perform the conversion processing of the URL from the AIID, and then accesses the AI processing unit 409. Then, the AI communication processing unit 408 executes the log recording for the AI usage log table 415. In this case, the AI usage request conversion processing unit 406 or the AI communication processing unit 408 displays the AI usage log table 415 in response to the AI communication processing unit 408 receiving a predetermined response from the AI through the input / output control unit 410. It functions as an AI usage log recording processing unit that provides a log recording function for additionally recording new records.
That is, the communication between the AI communication processing unit 408 and the AI processing unit 409 is as shown in FIG. 10, but the form of communication between the terminal device 104 and the AI communication processing unit 408 takes various forms. obtain.

The dental treatment support system 101 described above is a treatment support system for a dental treatment site. However, the application of the present invention is not limited to dental treatment sites.
First, the present invention is applicable not only to dental treatment but also to various medical settings such as internal medicine, surgery, ophthalmology, and otolaryngology. In this case, the input data of the estimation calculation processing unit has the patient age, the diseased part, and a predetermined natural language sentence. That is, it replaces a wide range of diseased parts from the oral diseased part.
In medical services other than dental treatment, it is considered that there are few opportunities for the treatment disease name AI to be created. On the other hand, in the medical field, there is a medical treatment plan called "clinical path" for treatment, examination, meal, etc. from hospitalization to discharge. Therefore, there is a high possibility that a "medical treatment plan AI" similar to the treatment plan AI in the dental field will be created and operated. Furthermore, there is a possibility that a finding AI that outputs findings when the patient age, disease site and disease name are entered, and a finding disease name AI that outputs the disease name when the patient age, disease site and findings are entered, will be created and used. high.

In addition, the present invention is not limited to the category of a system that supports medical practice, but is applied to all industrial fields such as nail salons, beauty salons, animal hospitals, etc. Applicable.

In the embodiment of the present invention, the dental treatment support system 101 is disclosed.
In the access of the terminal device 104 to the AI, the URL for directly accessing the AI processing unit 409 is hidden from the user by the AI usage request conversion processing unit 406. Therefore, it is possible to prevent unauthorized access to the AI by a malicious third party and appropriately operate the AI created by each user.
Further, when the use of AI is completed, log recording is executed in the AI use log table 415. The AI usage log table 415 enables the user who created the AI to collect a usage fee from the user who used the AI.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, and other modifications and applications are provided as long as they do not deviate from the gist of the present invention described in the claims. including.

101 ... Dental treatment support system, 102, 106 ... Dentist, 103 ... Internet, 104 ... Terminal device, 105 ... Dental treatment support server, 107 ... Patient, 201 ... Bus, 202 ... CPU, 203 ... ROM, 204 ... RAM, 205 ... Display unit, 206 ... Operation unit, 207 ... Non-volatile storage, 208 ... NIC, 301 ... Bus, 302 ... CPU, 303 ... ROM, 304 ... RAM, 305 ... Non-volatile storage, 306 ... NIC, 307 ... Display unit , 308 ... Operation unit, 309 ... RTC, 401 ... Input / output control unit, 402 ... AI selection screen processing unit, 403 ... Input / output control unit, 404 ... User master, 405 ... User usage AI table, 406 ... AI usage request conversion Processing unit, 407 ... AIID master, 408 ... AI communication processing unit, 409 ... AI processing unit, 410 ... Input / output control unit, 411 ... Estimated calculation processing unit, 412 ... Approximate function parameters, 413 ... Label table, 414 ... Learning calculation Processing unit, 415 ... AI usage log table, 601 ... system standard approximation function parameter, 602 ... system standard label table, 701 ... estimation list, 801 ... user-specific approximation function parameter, 802 ... user-specific label table

Claims (5)

An estimation calculation processing unit that realizes an estimation calculation device that executes an estimation calculation process for a predetermined input data by combining approximate function parameters formed by a predetermined learning process.
An input / output control unit that realizes a predetermined estimation calculation device by selecting one from a plurality of the approximation function parameters existing corresponding to the specified URL and combining it with the estimation calculation processing unit.
An AIID master having an AIID field in which all AIIDs, which are identification information for uniquely identifying the estimation arithmetic unit, are stored, and a URL field in which the URL for accessing the estimation arithmetic unit corresponding to the AIID is stored. When,
In response to an inquiry to the estimation arithmetic unit including the AIID transmitted from the terminal device, an AI usage request conversion processing unit that converts the AIID into the URL based on the AIID master.
A treatment support system including an AI communication processing unit that makes an inquiry to the input / output control unit based on the URL obtained from the AI usage request conversion processing unit. The input data of the estimation calculation processing unit has a patient age, a disease site, and a predetermined natural language sentence.
The treatment support system according to claim 1. In addition
A user ID field that stores a user ID that uniquely identifies a user using the estimation arithmetic unit, an AIID field that stores the AIID of the estimation arithmetic unit used by the user, and the estimation arithmetic unit that the user uses. An AI usage log table having a usage date and time field in which the date and time of use of
The AI communication processing unit includes an AI usage log recording processing unit that additionally records a new record in the AI usage log table in response to receiving a predetermined response from the estimation arithmetic unit through the input / output control unit. The treatment support system according to claim 2. The AIID master further
A user ID field in which the user ID of the user who creates and owns the estimation arithmetic unit identified by the AIID described in the AIID field is stored, and
It has a usage fee field in which the usage fee of the estimation calculation device is stored, which is set by the user when the estimation calculation device is created.
In addition
The treatment support system according to claim 3, further comprising an AI usage fee calculation unit that calculates a usage fee to be paid by the user in a predetermined AI usage period by searching the AI usage log table. The AI usage fee calculation unit further has a function of calculating the usage fee obtained by the user who created the estimation calculation device in a predetermined AI usage period by searching the AIID master and the AI usage log table.
The treatment support system according to claim 4.

Images