Information processing system, terminal device, information processing method, and program

Abstract

To more easily obtain a work result with high accuracy using artificial intelligence.SOLUTION: In a user terminal 10 of an information processing system 1, an UI display control section 151 receives a work request to a medication history management server 20 by natural language from a user. A prompt generation section 154 transmits contents of the received work request, interface information (API) on information processing which can be used in the medication history management server 20, and a sample of control information to the medication history management server 20 using the interface information to a generation type AI service providing server 40 as a prompt. A medication history management system control section 155 acquires answer information transmitted from the generation type AI service providing server 40 according to transmission of the prompt, and transmits it as the control information to the medication history management server 20. The medication history management server 20 performs work according to the transmitted control information, and transmits a work result to the user terminal 10.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to an information processing system, a terminal device, an information processing method, and a program.

Background Art

[0002] In recent years, efforts have been actively made to assist human work using artificial intelligence or to have artificial intelligence perform work instead. In such technologies, the procedures for performing work are incorporated as rules into artificial intelligence, and the actual work is executed according to these rules, or a machine learning model is prepared by machine learning the sample work serving as teacher data, and the actual work is input into the machine learning model to infer the work result. Note that Patent Document 1 describes a technology for assisting work using artificial intelligence.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, when incorporating the procedures for performing work as rules into artificial intelligence, there are problems that the labor of accurately incorporating the rules into artificial intelligence is complicated and the applicability is lacking. Further, when inferring the work result using a machine learning model, the inferred work result is not always accurate, and it is not easy to reflect specific conditions in the inference. In particular, in fields related to medicine, when obtaining a work result using artificial intelligence, higher accuracy is required, and it may not be appropriate to immediately apply the technology using an existing machine learning model. Thus, in the prior art, it has been difficult to easily obtain highly accurate work results by using artificial intelligence.

[0005] An object of the present invention is to more easily obtain highly accurate work results by using artificial intelligence.

Means for Solving the Problems

[0006] To solve the above problems, an information processing system according to an aspect of the present invention is an information processing system including a terminal device used by a user and a server that executes work in response to a request from the terminal device, wherein the terminal device includes request reception means for receiving a work request to the server in natural language from the user, answer request means for generating, as a prompt for a generative AI, the content of the work request received by the request reception means, interface information of information processing available in the server, and a sample of control information for the server using the interface information, and transmitting the same; work request transmission means for acquiring answer information transmitted from the generative AI in response to the transmission of the prompt and transmitting the same as control information for the server, and is provided with wherein the server is characterized by executing work according to the control information transmitted from the work request transmission means and transmitting a work result to the terminal device.

Advantages of the Invention

[0007] According to the present invention, highly accurate work results can be more easily obtained by using artificial intelligence.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0010] The information processing system according to this embodiment uses generative AI combined with a large language model (LLM), and in response to a user's request by voice or text (i.e., natural language), generates control information for controlling a specific application system (here, a medical history management system). At this time, as a prompt for the generative AI, input text data representing the user's request, a data group of APIs (Application Programming Interfaces) available in a specific application system, and control information serving as a sample for controlling a specific application by the API. Accordingly, without causing a generative AI to learn information related to the control of a specific application system, by inputting a prompt described according to a predetermined condition to a generative AI having general functions, it is possible to obtain a work result for a user's request expressed in natural language, and generate control information (control information for controlling a specific application system). Therefore, according to the present invention, it is possible to more easily obtain a highly accurate work result by using artificial intelligence. Hereinafter, a specific configuration will be described.

[0011] [System Configuration of Information Processing System 1] FIG. 1 is a diagram showing the system configuration of an information processing system 1 according to an embodiment of the present invention. As shown in FIG. 1, the information processing system 1 includes a user terminal 10, a medical history management server 20, a speech recognition server 30, and a generative AI service providing server 40, and the user terminal 10, the medical history management server 20, the speech recognition server 30, and the generative AI service providing server 40 are configured to be communicable with each other via a network 50. In the information processing system 1 according to the present embodiment, the user terminal 10 functions as a client terminal for using the medical history management server 20. Also, in FIG. 1, the system configuration of the information processing system 1 is shown in a form including the speech recognition server 30 and the generative AI service providing server 40, but these servers can also use servers that provide general services operated by a third party other than the operator of the medical history management server 20. Further, each server can be configured by one server computer, or can be configured as a virtual server in a server system configured by a plurality of server computers.

[0012] The user terminal 10 is a terminal device used by a user who utilizes a medication history management system configured by a medication history management server 20, and is constituted by an information processing device such as a smartphone, a mobile phone, a tablet terminal, or a PC (Personal Computer), for example. The user terminal 10 can perform an operation for utilizing the functions of the medication history management server 20 via an input device such as a mouse or a keyboard, and can input, in natural language, the work required by the user by voice input (or text input). Hereinafter, information representing the work required by the user for the medication history management server 20, which is input as natural language by voice (or text), is referred to as an "operation instruction sentence".

[0013] When an operation instruction sentence is input by voice input, the user terminal 10 transmits voice data to a voice recognition server 30, and receives data of a character string representing the operation instruction sentence obtained by voice recognition processing.

[0014] In addition, the user terminal 10 has previously acquired an API (interface information for information processing) that can be used in the medication history management server 20, and stores data of control information (control code representing a predetermined operation expressed using the API), which is a sample for causing the medication history management server 20 to perform a predetermined operation, by the API. Then, the user terminal 10 generates an instruction to generate control information for causing the medication history management server 20 to execute the work represented by the operation instruction sentence, text data representing the operation instruction sentence input by voice (or text) (for example, "Enter the concomitant drug □□ in the medication history of Mr. △ Male of O Mountain"), a data group of APIs that can be used in the medication history management server 20, and control information (control code representing a predetermined operation expressed using the API), which is a sample for controlling the medication history management server 20 by the API, and transmits a prompt including these to a generative AI service providing server 40. Furthermore, in response to transmitting the prompt, the user terminal 10 receives response information (control information for the medication history management server 20) transmitted from the generative AI service providing server 40.

[0015] Also, the user terminal 10 transmits the response information (control information) received from the generative AI service providing server 40 to the medical history management server 20. The response information transmitted from the user terminal 10 (i.e., the control information for the medical history management server 20) corresponds to the content of the control information when the user operates the medical history management server 20 via the input device. Therefore, even when the response information (control information) is transmitted, the medical history management server 20 can execute the process in the same manner as when the user operates the medical history management server 20 via the input device and return the processing result to the user terminal 10.

[0016] FIG. 2 is a schematic diagram showing an example of the specific format of the prompt transmitted from the user terminal 10 to the generative AI service providing server 40. In FIG. 2, the control information of the medical history management server 20 generated by the prompt is referred to as an "execution plan". As shown in FIG. 2, the prompt transmitted to the generative AI service providing server 40 includes (1) An "instruction to create an execution plan" indicating an instruction to generate control information for causing the medical history management server 20 to execute the work represented by the operation instruction (2) A "definition of functions (interfaces) that can be used in the execution plan" representing a data group of APIs available in the medical history management server 20 (3) A "rule at the time of creating the execution plan" representing the conditions for generating the control information (4) A "specification and rule of the execution plan output result format" for specifying the output format of the control information (5) A "natural language instruction from the user" representing the work content specified by the operation instruction Each item is defined. By sending a prompt including each of these items to the generative AI service providing server 40, in the generative AI service providing server 40, using the API defined in the prompt, control information (execution plan) for the medication history management server 20 representing the work content specified in the operation instruction is generated according to the specified rules. When this control information (execution plan) is executed in the medication history management server 20, the processing result specified in the operation instruction will be returned.

[0017] The medication history management server 20 is composed of a PC or a server computer and functions as a medication history management system for performing medication history management operations in a pharmacy. Note that the medication history management system is an example of a business application, and the medication history management server 20 can be appropriately equipped with functions for performing various operations other than the medication history management operation (various business applications such as a receipt computer or an electronic medical record system). For example, the medication history management server 20 can be equipped with a medication history management function for managing the content of prescriptions issued to patients and the history of medications provided to patients, or a function for creating a medical fee statement (receipt) for calculating medical fees. Note that the functions of the medication history management server 20 can be further extended to include an electronic medical record management function for managing electronic medical records, an examination result database function for managing data on examination results such as patients' test values and CT (Computed Tomography) images, etc. As described above, the medication history management server 20 can perform operations using the API from the user terminal 10. When a request is made via the API, when an operation is performed from the user terminal 10 via the input device, or when the response information generated by the generative AI service providing server 40 is sent and a task is requested, the request can be similarly received and the processing result based on the medication history management function, etc. can be returned.

[0018] The voice recognition server 30 is composed of a server computer, receives the voice data transmitted from the user terminal 10, and performs voice recognition processing based on natural language processing on the received voice data. Then, the voice recognition server 30 transmits a character string (a sentence expressed as a natural language) corresponding to the voice data obtained by the voice recognition processing to the user terminal 10.

[0019] The generative AI service providing server 40 is composed of a server computer and implements generative AI using a large language model (LLM). The generative AI service providing server 40 refers to the large language model according to the prompt (information representing a request to the AI) received from the user terminal 10 and generates information that is an answer to the prompt. In the present embodiment, the prompt transmitted from the user terminal 10 to the generative AI service providing server 40 includes text data representing an operation instruction sentence (for example, "Enter concomitant drug □□ in the medical history of Mr. △ of Mount 〇") for the medical history management server 20, a data group of APIs available in the medical history management server 20, and control information (control code representing a predetermined operation expressed using the API) that is a sample for controlling the medical history management server 20 by the API (see FIG. 2). In the present embodiment, the generative AI service providing server 40 that has received the prompt generates control information (execution plan) for the medical history management server 20 representing the work content specified in the operation instruction sentence using the API defined in the prompt according to the rules specified. Then, the generative AI service providing server 40 transmits the answer information generated according to the prompt to the user terminal 10.

[0020] [Specific example of prompt] In this embodiment, the prompt sent to the generative AI service providing server 40 includes, as shown in the format example in FIG. 2, items such as "instruction to create an execution plan", "definition of functions (interfaces) that can be used in the execution plan", "rules for creating an execution plan", "specification and rules for the execution plan output result format", and "instructions in natural language from the user". Note that as a specific description form for describing the instruction sentences constituting the prompt, a description form interpretable by the generative AI service providing server 40, such as a normal language like English or Japanese, or a predetermined programming language, can be adopted. Specifically, as the "instruction to create an execution plan", an instruction sentence representing "Create an execution plan that satisfies the conditions of the goal step by step in XML. Use available functions." is described.

[0021] Also, as the "definition of functions (interfaces) that can be used in the execution plan", [Available functions] (1) Data format conversion function {···} (2) Current date and time acquisition function {···} (3) Medical history screen opening function {···} Various functions (functions that can be used in the medical history management system) such as the above are described.

[0022] Also, as the "rules for creating an execution plan", "Create an execution plan according to the following steps. (i) Make the execution plan as concise as possible. (ii) Create the execution plan as a series of functions to achieve the goal. (iii) ···" Each rule such as the above is described.

[0023] Also, as the "specification and rules for the execution plan output result format", "Create the entire execution plan in the following form. <Plan start> <Function name: ···> ··· <Plan End> The function shall be called according to the following steps. (i) The function has one or more named parameters and one output consisting entirely of strings. The values of the parameters are XML-escaped. (ii) Use the ··· function to save the output from the function and pass it to the next function. (iii) ··· Specifications and rules such as the above are described.

[0024] Also, as "instructions in natural language from the user", <goal>Add bias aspirin to the combination drug and input a height of 175.6 cm and a weight of 62.3 kg< / goal> is described.

[0025] [Specific Example of Execution Plan (Control Information)] Next, a specific example of the execution plan (control information) generated in response to the prompt will be described. Figure 3 is a schematic diagram showing a specific example of the execution plan (control information). As shown in Figure 3, the execution plan (control information) generated by the generative AI service providing server 40 includes the following content. <plan> <!-- First, we need to add the drug "バイアスピリン" to the list of concurrent drugs. --> <function.***.editInspectionItem server_url="http: / / localhost:**** / **** / api" payload='{"inspectionItems":[{"itemType":"Concurrent drug","itemValue":"バイアスピリン"}]}' content_type="application / json" / > <!-- Next, we need to input the patient's height. --> <function.***.editInspectionItem server_url="http: / / localhost:**** / **** / api" payload='{"inspectionItems":[{"itemType":"Height","itemValue":"175.6cm"}]}' content_type="application / json" / > <!-- Finally, we need to input the patient's weight. --> <function.****.editInspectionItem server_url="http: / / localhost:**** / **** / api" payload='{"inspectionItems":[{"itemType":"Weight","itemValue":"62.3kg"}]}' content_type="application / json" / > < / plan> That is, in the example shown in Figure 3, an execution plan (control information) representing the work content requested in the operation instruction text using the APIs available in the medical record management server 20 is generated, and when this execution plan is executed in the medical record management server 20, the work result requested by the user is output.

[0026] [Specific Example of Output Screen] Figure 4 is a schematic diagram showing an example of the output screen displayed on the user terminal 10. As shown in Figure 4, on the output screen (right end area) of the medical record management system in this embodiment, the operation instruction text in natural language input by the user by voice (or text), and the response information (control information) generated according to the operation instruction text are displayed together. In the output screen of the medication history management system, in the area (excluding the rightmost area) where information regarding the patient's medication history is displayed, the output result returned from the medication history management system based on the response information (control information) to the operation instruction sentence is being shown. Therefore, the user can check the operation instruction sentence they input themselves, the response information (control information) generated according to the operation instruction sentence, and the output result returned from the medication history management system by the control information together, and can easily determine whether the appropriate content is output as the intended work result.

[0027] [Hardware Configuration] Next, the hardware configuration of each device in the information processing system 1 will be described. In the information processing system 1, each device is composed of an information processing device such as a PC, a server computer, or a tablet terminal, and their basic configurations are the same.

[0028] FIG. 5 is a diagram showing the hardware configuration of the information processing device 800 that constitutes each device. As shown in FIG. 5, the information processing device 800 that constitutes each device includes a CPU (Central Processing Unit) 811, a ROM (Read Only Memory) 812, a RAM (Random Access Memory) 813, a bus 814, an input unit 815, an output unit 816, a storage unit 817, a communication unit 818, a drive 819, and an imaging unit 820.

[0029] The CPU 811 executes various processes according to the programs recorded in the ROM 812 or the programs loaded from the storage unit 817 into the RAM 813. In the RAM 813, data and the like necessary for the CPU 811 to execute various processes are also appropriately stored.

[0030] The CPU 811, ROM 812, and RAM 813 are interconnected via a bus 814. Connected to the bus 814 are an input unit 815, an output unit 816, a storage unit 817, a communication unit 818, a drive 819, and an imaging unit 820.

[0031] The input unit 815 is composed of various buttons, a microphone, etc., and inputs various information according to instruction operations. The output unit 816 is composed of a display, a speaker, etc., and outputs images and sounds. The storage unit 817 is composed of a hard disk or a DRAM (Dynamic Random Access Memory), etc., and stores various data managed by each server. The communication unit 818 controls communication with other devices via the network 50.

[0032] A removable medium 831 made of a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, etc. is appropriately mounted on the drive 819. The program read from the removable medium 831 by the drive 819 is installed in the storage unit 817 as necessary. The imaging unit 820 is composed of an imaging device equipped with a lens and an image sensor, etc., and captures a digital image of a subject. Note that when the information processing device 800 is configured as a medical history management server 20, a voice recognition server 30, or a generative AI service providing server 40, it is also possible to adopt a configuration in which the imaging unit 820 is omitted. Further, when the information processing device 800 is configured as a tablet terminal, it is also possible to configure the input unit 815 with a touch sensor and arrange it overlapping the display of the output unit 816 to provide a configuration with a touch panel.

[0033] [Functional Configuration] Next, the functional configuration in the information processing system 1 will be described.

[0034] [Functional Configuration of User Terminal 10] FIG. 6 is a block diagram showing the functional configuration of the user terminal 10. As shown in FIG. 6, in the CPU 811 of the user terminal 10, a user interface display control unit (UI display control unit) 151, an API set acquisition unit 152, a speech recognition processing unit 153, a prompt generation unit 154, and a medication history management system control unit 155 function. Further, in the storage unit 817 of the user terminal 10, an API set storage unit 171, a sample information storage unit 172, a prompt storage unit 173, a response information storage unit 174, and a work result storage unit 175 are formed.

[0035] The API set storage unit 171 stores a data group of APIs available in the medication history management server 20. The data group of APIs stored in the API set storage unit 171 is referred to when the user directly operates the medication history management server 20 using the input device while visually recognizing the UI screen, and the necessary APIs are used. Also, the data group of APIs stored in the API set storage unit 171 is referred to for the purpose of generating a prompt for the generative AI service providing server 40 when the user inputs an operation requested of the medication history management server 20 by voice input (or text input), and a part or all of the data group of APIs is included in the prompt and transmitted.

[0036] The sample information storage unit 172 stores various control information (control codes representing various operations expressed using APIs) serving as samples for controlling the medication history management server 20 using APIs. For example, the sample information storage unit 172 stores control information representing an operation example for adding a concomitant drug to the medication history of a specific patient, control information representing an operation example for adding medication guidance content to the medication history of a specific patient, or control information representing an operation example for reading and printing the data of the medication document of a specific patient, etc.

[0037] In the prompt memory unit 173, the data of the prompts transmitted from the user terminal 10 to the generative AI service providing server 40 are stored as a history. The data of the prompts generated in the past can be appropriately used in the form of referring to similar prompts when new prompts are generated later.

[0038] In the response information memory unit 174, the data of the response information transmitted from the generative AI service providing server 40 in response to the prompts are stored as a history in association with the transmitted prompts. In the work result memory unit 175, the data of the processing results (work results) of the medical history management server 20 when the user operates the medical history management server 20 via the input device and when the user operates the medical history management server 20 with an operation instruction sentence by voice (or text) are stored as a history.

[0039] The UI display control unit 151 displays a user interface screen (UI screen) generated by the user to execute various processes on the user terminal 10, a screen for operating the medical history management server 20 via the input device, and a screen for the user to input the work required by the user in natural language by voice input (or text input) for operating the medical history management server 20. Also, the UI display control unit 151 displays a screen representing the processing result received from the medical history management server 20.

[0040] The API set acquisition unit 152 acquires the data group of the APIs provided by the medical history management server 20 and stores it in the API set memory unit 171. It is assumed that the API set acquisition unit 152 acquires the data group of the APIs in advance and stores it in the API set memory unit 171 when the user terminal 10 uses the functions of the medical history management server 20.

[0041] When the user of the user terminal 10 inputs an operation on the medication history management server 20 by voice, the voice recognition processing unit 153 records the voice data and transmits the voice data to the voice recognition server 30. Further, the voice recognition processing unit 153 receives the voice recognition result (text data representing an operation instruction) received from the voice recognition server 30 and passes it to the prompt generation unit 154.

[0042] The prompt generation unit 154 adds to the text data representing the operation instruction passed from the voice recognition processing unit 153 a data group of APIs available on the medication history management server 20 and control information (control code representing a predetermined operation expressed using an API) that serves as a sample for controlling the medication history management server 20 by the API, and transmits it as a prompt to the generative AI service providing server 40. Note that, as the format of the prompt, various forms can be used. For example, as shown in FIG. 2, it can be a format including "instruction to create an execution plan", "definition of functions (interfaces) that can be used in the execution plan", "rules for creating the execution plan", "specification and rules for the execution plan output result format", and "instructions in natural language from the user". Further, the prompt generation unit 154 receives the response information (control information) transmitted from the generative AI service providing server 40 in response to the transmitted prompt and passes it to the medication history management system control unit 155.

[0043] The medication history management system control unit 155 transmits the response information (control information) passed from the prompt generation unit 154 to the medication history management server 20 as a work request. Even when the medication history management system control unit 155 transmits the response information (control information) to the medication history management server 20, a processing result is returned to the user terminal 10 in the same manner as when the user views the UI screen and operates the medication history management server 20 via an input device such as a mouse.

[0044] [Operation] Next, the operation of the information processing system 1 will be described.

[0045] [Medication History Management System Control Processing] FIG. 7 is a flowchart showing the flow of the medication history management system control process executed by the information processing system 1. The medication history management system control process starts in response to an instruction to execute the medication history management system control process on the user device 10.

[0046] When the medication history management system control process starts, in step S1, a data group of APIs provided by the medication history management server 20 is acquired and stored in the API set storage unit 171. In step S2, the UI display control unit 151 displays a UI screen generated by the user for executing various processes on the user terminal 10. In step S3, the voice recognition processing unit 153 determines whether an operation instruction sentence (voice or text) for the medication history management server 20 has been input by the user. If the operation instruction sentence for the medication history management server 20 has not been input by the user, it is determined as NO in step S3, and the process proceeds to step S4. On the other hand, if the operation instruction sentence for the medication history management server 20 has been input by the user, it is determined as YES in step S3, and the process proceeds to step S5.

[0047] In step S4, the medication history management system control unit 155 executes an operation on the medication history management server 20 based on the operation content via the input device for the UI screen. After step S4, the process proceeds to step S11. In step S5, the voice recognition processing unit 153 determines whether an operation instruction sentence by voice has been input. If the operation instruction sentence by voice has not been input, it is determined as NO in step S5, and the process proceeds to step S7. On the other hand, if the operation instruction sentence by voice has been input, it is determined as YES in step S5, and the process proceeds to step S6. In step S6, the voice recognition processing unit 153 transmits the voice (voice data of the operation instruction sentence) for the operation on the medical history management server 20 input by the user to the voice recognition server 30 and executes voice recognition processing. In response to this, text data representing the operation instruction sentence is transmitted from the voice recognition server 30.

[0048] In step S7, the prompt generation unit 154 adds to the text data representing the operation instruction sentence a data group of APIs available in the medical history management server 20 and control information (control code representing a predetermined operation expressed using the API) serving as a sample for controlling the medical history management server 20 by the API, and generates a prompt for the generative AI service providing server 40. In step S8, the prompt generation unit 154 transmits the generated prompt to the generative AI service providing server 40. In response to this, response information (control information) for controlling the medical history management server 20 is transmitted from the generative AI service providing server 40.

[0049] In step S9, the medical history management system control unit 155 acquires the response information (control information) generated by the generative AI service providing server 40. In step S10, the medical history management system control unit 155 transmits the response information (control information) to the medical history management server 20 as a work request. In step S11, the UI display control unit 151 determines whether or not the end of the medical history management system control process has been instructed. If the end of the medical history management system control process has not been instructed, it is determined as NO in step S11 and the process proceeds to step S2. On the other hand, if the end of the medical history management system control process has been instructed, it is determined as YES in step S11 and the medical history management system control process ends.

[0050] Through such processing, in the information processing system 1, when an operation based on natural language by voice input (or text input) is performed on the medical history management server 20, the generative AI service providing server 40 is sent, together with the data of the operation instruction sentence, the API available in the medical history management server 20 and the control information of the sample using this API, so that control information capable of appropriately executing the operation on the medical history management server 20 expressed in natural language can be obtained. Then, by performing an operation on the medical history management server 20 based on this control information, the work result required by the user can be obtained from the medical history management server 20. That is, without causing the generative AI to learn information related to the control of a specific application system, by inputting a prompt described according to a predetermined condition to a generative AI having general functions, control information (control information for controlling a specific application system) capable of obtaining a work result for a user request expressed in natural language can be generated. Therefore, according to the present invention, it becomes possible to more easily obtain a highly accurate work result by using artificial intelligence.

[0051] [Modification Example 1] In the above-described embodiment, an example has been described in which the work performed by the medical history management server 20 (medical history management system) is targeted as the work content when the user inputs the work requested in natural language, but the present invention is not limited to this. For example, when the medical history management server 20 has a function of cooperating with other systems such as a receipt computer, an electronic medical record system, or a server system responsible for regional comprehensive medical care, the user can also input a request for work in natural language regarding the work performed by other systems that cooperate with the medical history management server 20. That is, as an interface for making a work request in natural language to the medical history management server 20, it is also possible to indirectly make a work request in natural language to systems other than the medical history management server 20. This makes it possible to receive a user's work request in natural language without preparing an environment for making a work request in natural language in all systems used by the user.

[0052] [Modification Example 2] In the above-described embodiment, the work requested by the user in natural language can be a single work executed by the medication history management server 20, or can be a series of works combining a plurality of works. That is, as a work requested by the user in natural language, a series of works such as "processing for adding a concomitant drug to the medication history" and "processing for adding data of test values related to the concomitant drug to the medication history" are defined, and a unique name (for example, "adding concomitant drug and test value", etc.) specific to the defined series of works can be attached. When the user inputs the unique name attached to the above series of works in natural language to the user terminal 10, the user terminal 10 recognizes the defined series of works and transmits a prompt to the generative AI service providing server 40 to generate control information for causing the medication history management server 20 to execute these series of works. This enables the user to more easily obtain a plurality of work results by inputting a combination of a plurality of works executed daily as a single work request (operation instruction text) in natural language.

[0053] As described above, the information processing system 1 according to the present embodiment includes the user terminal 10 and the medication history management server 20. The user terminal 10 includes a UI display control unit 151, a prompt generation unit 154, and a medication history management system control unit 155. The UI display control unit 151 receives a work request from the user in natural language to the medication history management server 20. The prompt generation unit 154 transmits, as a prompt, the content of the work request received by the UI display control unit 151, the interface information (API) of the information processing available in the medication history management server 20, and a sample of the control information for the medication history management server 20 using the interface information to the generative AI service providing server 40. In response to the transmission of the prompt, the medication history management system control unit 155 acquires the response information transmitted from the generative AI service providing server 40 and transmits it as control information for the medication history management server 20. The medication history management server 20 executes operations according to the control information transmitted from the medication history management system control unit 155 and transmits the operation results to the user terminal 10. As a result, when an operation based on natural language by voice input (or text input) is performed on the medication history management server 20, the interface information (API) available in the medication history management server 20 and the control information of the sample using this interface information (API) are transmitted to the generative AI service providing server 40 together with the data of the operation instruction text, so that control information capable of appropriately executing the operation on the medication history management server 20 expressed in natural language can be obtained. Then, by performing an operation on the medication history management server 20 based on this control information, the operation result required by the user can be obtained from the medication history management server 20. Therefore, it becomes possible to more easily obtain a highly accurate operation result by using artificial intelligence.

[0054] In response to the transmission of the control information, the UI display control unit 151 of the user terminal 10 outputs the operation result transmitted from the medication history management server 20, the control information, and the work request (operation instruction text) in natural language input by the user to the medication history management server when the control information was generated. As a result, the user can check the operation instruction text entered by the user, the response information (control information) generated according to the operation instruction text, and the output result returned from the medication history management system by the control information, and can easily determine whether the appropriate content is output as the target work result.

[0055] The prompt generation unit 154 transmits to the generative AI including information specifying the output format of the response information in the prompt. The medication history management system control unit 155 acquires the response information output in the output format from the generative AI service providing server 40, and transmits the response information to the medication history management server 20 as control information. As a result, it is possible to easily obtain control information in a form that can appropriately instruct the work required by the user.

[0056] The prompt generation unit 154 transmits to the generative AI service providing server 40 a prompt including information specifying the rules for generating response information in the prompt. The medication history management system control unit 155 acquires the response information generated according to the rules from the generative AI service providing server 40, and transmits the response information to the medication history management server 20 as control information. As a result, the generative AI service providing server 40 can be made to generate control information according to the rules assumed by the user.

[0057] As an operation represented in natural language, an operation name representing a series of operations combining a plurality of operations is defined. The UI display control unit 151 receives an operation name as a work request to the medication history management server 20 in natural language from the user. The prompt generation unit 154 transmits to the generative AI service providing server 40 a prompt for acquiring the response information for each of the series of operations defined as the operation name. The medication history management system control unit 155 acquires the response information transmitted from the generative AI service providing server 40, and transmits it to the medication history management server 20 as control information for acquiring the work result of each of a series of works defined as the work name. Thus, by inputting a combination of a plurality of works executed daily as a single work request (operation instruction sentence) in natural language, the user can more easily obtain a plurality of work results.

[0058] The medication history management server 20 has a function of cooperating with other systems. When the work request from the user to the medication history management server 20 in natural language is related to other systems, the medication history management server 20 executes the work according to the control information, executes the work related to other systems, and transmits the work result including the work related to other systems to the user terminal 10. Thus, it becomes possible to receive the work request in the natural language of the user without preparing an environment for making a work request in natural language in all the systems used by the user.

[0059] Note that the present invention is not limited to the above-described embodiments, and modifications, improvements, etc. within the range that can achieve the object of the present invention are included in the present invention. For example, the medication history management server 20, the voice recognition server 30, and the generative AI service providing server 40 in the above-described embodiments can be configured by an on-premises server or a cloud server. In addition to being configured by each device in the above-described embodiments, the information processing system 1 according to the present invention can also implement the functions of a plurality of devices in the above-described embodiments in one device, or distribute the functions of one device to a plurality of devices for implementation.

[0060] The above-described series of processes can be executed by hardware or by software. In other words, the functional configurations in the above-described embodiments are merely examples and are not particularly limited. That is, it suffices if any computer constituting the information processing system 1 has a function capable of executing the above-described series of processes as a whole, and the functional blocks used for realizing this function are not limited to the specifically shown examples. Also, one functional block may be configured by hardware alone, by software alone, or by a combination thereof.

[0061] In addition, a recording medium including a program for executing the above-described series of processes is not only constituted by a removable medium distributed separately from the apparatus main body in order to provide the program to the user, but also constituted by a recording medium or the like provided to the user in a state pre-installed in the apparatus main body.

[0062] As described above, embodiments of the present invention have been described, but the present invention is not limited to the above-described embodiments. Also, the effects described in this embodiment are merely an enumeration of the most suitable effects resulting from the present invention, and the effects according to the present invention are not limited to those described in this embodiment.

Explanation of Reference Numerals

[0063] 1 Information processing system, 10 User terminal, 20 Medication history management server, 30 Speech recognition server, 40 Generative AI service providing server, 50 Network, 151 User interface display control unit (UI display control unit), 152 API set acquisition unit, 153 Speech recognition processing unit, 154 Prompt generation unit, 155 Medication history management system control unit, 171 API set storage unit, 172 Sample information storage unit, 173 Prompt storage unit, 174 Answer information storage unit, 175 Work result storage unit, 800 Information processing device, 811 CPU, 812 ROM, 813 RAM, 814 Bus, 815 Input unit, 816 Output unit, 817 Storage unit, 818 Communication unit, 819 Drive, 820 Imaging unit, 831 Removable medium

Claims

1. An information processing system including a terminal device used by a user and a server that executes operations in response to requests from the terminal device, wherein the terminal device has a request receiving means for receiving an operation request to the server in natural language from the user, and an answer request means for transmitting, as a prompt to a generative AI that generates control information representing an execution plan for the server, the content of the operation request received by the request receiving means, interface information of information processing available on the server, and a sample of control information for the server using the interface information, and an operation request transmitting means for acquiring answer information transmitted from the generative AI in response to the transmission of the prompt and transmitting it as control information to the server, characterized in that the server executes an operation according to the control information transmitted from the operation request transmitting means and transmits an operation result to the terminal device.

2. The information processing system according to claim 1, wherein the terminal device includes an operation result output means for outputting the operation result transmitted from the server, the control information, and an operation request to the server in natural language input by the user when the control information was generated, in response to the transmission of the control information.

3. The answer request means transmits to the generative AI including information specifying an output format of the answer information in the prompt, and the operation request transmitting means acquires the answer information output in the output format from the generative AI and transmits the answer information to the server as the control information. The information processing system according to claim 1 or 2, characterized in that.

4. The answer request means transmits to the generative AI including information specifying a rule for generating the answer information in the prompt, and the operation request transmitting means acquires the answer information generated according to the rule from the generative AI and transmits the answer information to the server as the control information. The information processing system according to claim 1 or 2, characterized in that.

5. An operation name representing a series of operations combining a plurality of operations is defined as an operation represented in natural language, and the request receiving means receives the operation name as an operation request to the server in natural language from the user. The response request means transmits the prompt for acquiring the response information of each of the series of operations defined as the operation name to the generative AI, The operation request transmission means acquires the response information transmitted from the generative AI, and transmits it to the server as the control information for acquiring the operation result of each of the series of operations defined as the operation name. The information processing system according to claim 1 or 2, characterized in that.

6. The server, Is equipped with a function to cooperate with other systems, When the operation request from the user to the server in natural language is related to the other system, the operation is executed according to the control information, the operation related to the other system is executed, and the operation result including the operation related to the other system is transmitted to the terminal device. The information processing system according to claim 1 or 2, characterized in that.

7. A terminal device constituting an information processing system including a terminal device used by a user and a server that executes an operation in response to a request from the terminal device, Request reception means for receiving an operation request from the user to the server in natural language, Answer request means for transmitting, as a prompt, to a generative AI that generates control information representing an execution plan for the server, the content of the operation request received by the request reception means, interface information of information processing available on the server, and a sample of control information for the server using the interface information, Operation request transmission means for acquiring the response information transmitted from the generative AI in response to the transmission of the prompt and transmitting it as control information to the server, A terminal device characterized by comprising.

8. An information processing method executed by an information processing system including a terminal device used by a user and a server that executes an operation in response to a request from the terminal device, The terminal device, A request reception step of receiving an operation request from the user to the server in natural language, An answer request step of transmitting, as a prompt, to a generative AI that generates control information representing an execution plan for the server, the content of the operation request received in the request reception step, interface information of information processing available on the server, and a sample of control information for the server using the interface information, A work request transmission step of acquiring response information transmitted from the generative AI in response to the transmission of the prompt and transmitting it as control information to the server including wherein the server executes a task according to the control information transmitted in the work request transmission step and transmits a task result to the terminal device, and an information processing method characterized by this

9. In a computer constituting a terminal device in an information processing system including a terminal device used by a user and a server that executes a task in response to a request from the terminal device a request reception function for receiving a work request to the server in natural language from the user a response request function for transmitting, as a prompt, to a generative AI that generates control information representing an execution plan for the server, the content of the work request received by the request reception function, interface information of information processing available on the server, and a sample of control information for the server using the interface information a work request transmission function for acquiring response information transmitted from the generative AI in response to the transmission of the prompt and transmitting it as control information to the server A program characterized by realizing these

Images