Information processing equipment, methods, programs and systems

Abstract

Efficiently execute tasks using a system that utilizes a large-scale language model. [Solution] A program to be executed by a computer having a processor and memory, the program to cause the processor to perform the following steps: to detect the arrival of a timing based on a date, based on first information about a date for creating a document, which is stored in advance; to input the read second information for creating the document, which is stored in advance, to a generating AI, which is then used to output text information about the document; and to store the output text information.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, method, program, and system.

Background Art

[0002] There is a demand for a technology that efficiently performs predetermined operations such as document creation using an on-premises system.

[0003] For example, Patent Document 1 discloses computer-based process modeling that facilitates understanding policies, modifying actions separately, and modifying relevant code without affecting other code in process management.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, Patent Document 1 does not disclose operations performed by a system using a large language model.

[0006] An objective of the present disclosure is to efficiently execute operations by a system using a large language model.

Means for Solving the Problems

[0007] To solve the above problem, a program according to one aspect of the present disclosure is: A program for causing a computer including a processor and a memory to execute, wherein the program causes the processor to: A step of detecting the arrival of the timing based on the date for creating the document, using first information that has been stored in advance, Upon detecting the arrival of the timing based on the aforementioned date, the AI ​​reads second information stored in advance for creating the document, inputs the read second information and a prompt containing instructions for creating the document into the generating AI, and outputs text information related to the document. The steps include storing the output text information, Make it run. [Effects of the Invention]

[0008] According to this disclosure, business operations can be efficiently performed using a system that utilizes a large-scale language model. [Brief explanation of the drawing]

[0009] [Figure 1] This block diagram shows an example of the configuration of System 1. [Figure 2] Figure 1 is a block diagram showing an example of the functional configuration of the terminal device 10. [Figure 3] This diagram shows the data structure of electronic medical record table 181. [Figure 4] This diagram shows the data structure of document creation table 182. [Figure 5] This diagram shows the data structure of the processing waiting table 183. [Figure 6] This diagram shows the data structure of prompt table 184. [Figure 7] This is a flowchart illustrating an example of the operation of terminal device 10 when creating a document. [Figure 8] This is a schematic diagram illustrating an example of the display screen of the display 141 of the terminal device 10. [Figure 9] This is a schematic diagram illustrating another example of the display screen of the display 141 of the terminal device 10. [Figure 10] This flowchart shows a modified example of the operation of terminal device 10 when creating a document. [Figure 11] This is a block diagram showing the basic hardware configuration of a computer 90. [Mode for Carrying Out the Invention]

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In all the drawings for describing the embodiments, common constituent elements are denoted by the same reference numerals, and repeated descriptions thereof are omitted. Note that the following embodiments do not unduly limit the content of the present disclosure described in the claims. In addition, not all of the constituent elements shown in the embodiments are necessarily essential constituent elements of the present disclosure. Each drawing is a schematic view and is not necessarily strictly illustrated.

[0011] Further, in the following description, the "processor" refers to one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be another type of processor such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core.

[0012] Further, the at least one processor may be a processor in a broad sense such as a hardware circuit (for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing.

[0013] Further, in the following description, an expression such as "xxx table" may be used to describe information from which an output can be obtained for an input, and this information may be data of any structure, or a learning model such as a neural network that generates an output for an input. Therefore, the "xxx table" can be referred to as "xxx information".

[0014] Further, in the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or a part of two or more tables may be a single table.

[0015] Further, in the following description, processes may be described with a "program" as the subject, but since the program is executed by a processor to perform predetermined processes appropriately using a storage unit and / or an interface unit or the like, the subject of the processes may be a processor (or a device such as a controller including the processor).

[0016] The program may be installed in an apparatus such as a computer, or may be stored in, for example, a program distribution server or a computer-readable (e.g., non-transitory) recording medium. Further, in the following description, two or more programs may be implemented as a single program, or a single program may be implemented as two or more programs.

[0017] Further, in the following description, identification numbers are used as identification information for various targets, but other types of identification information (e.g., identifiers including alphabetic characters and codes) other than identification numbers may be adopted.

[0018] Further, in the following description, when describing elements of the same type without distinction, reference signs (or common signs among the reference signs) are used, and when describing elements of the same type with distinction, element identification numbers (or reference signs) may be used.

[0019] Further, in the following description, control lines and information lines indicate those considered necessary for the description, and not all control lines and information lines on a product are necessarily shown. All the components may be connected to each other.

[0020] An information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. Regarding terminal device 10, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0021] <Overview> The system according to this embodiment has functions for efficiently performing tasks such as document creation using a system that utilizes Large Language Models (LLMs). The system pre-stores, for example, first information regarding the deadline for document creation and second information for document creation. The document is a document with a set creation deadline and may include, for example, a referral document (discharge summary) based on a patient's medical record when the patient is discharged from the hospital.

[0022] The system detects, for example, the arrival of a timing based on the deadline for creating a document, using first information. This timing based on the deadline may include, for example, a predetermined time on the deadline, a predetermined time one or more days before the deadline, or a period of low computer activity on the deadline. When the system detects the arrival of a timing based on the deadline, it reads out second information. The system inputs the read second information and a prompt containing instructions to create the document into a large-scale language model, outputs text information about the document, and stores it. For example, if the creation of multiple documents with set deadlines is scheduled, the system may sequentially read the second information and create the documents. According to the system of this embodiment, tasks such as document creation by a system using a large-scale language model can be performed efficiently by executing them based on predetermined timings.

[0023] In the following section, we will explain an example where the document created is a discharge summary based on the patient's medical record upon discharge from the hospital.

[0024] <1 System Configuration Diagram> Figure 1 is a block diagram showing an example configuration of System 1 (terminal device 10). System 1 shown in Figure 1 is, for example, an on-premise system and includes terminal device 10. Terminal device 10 may communicate with an internal server or other terminal device (not shown) via an internal network 80, for example. Terminal device 10 may also communicate with a hospital system (not shown) via an internal network 80, for example. The hospital system may include, for example, an electronic medical record system and may include medical record information of inpatients.

[0025] Figure 1 shows an example where System 1 includes one terminal device 10, but the number of terminal devices 10 included in System 1 is not limited to one. System 1 may include two or more terminal devices 10.

[0026] The terminal device 10 shown in Figure 1 is an information processing device operated by a user who performs tasks such as document creation. The user is, for example, a person in charge of tasks such as document creation. The user is, for example, a medical professional working in a hospital who creates a discharge summary based on the patient's medical record when the patient is discharged. The terminal device 10 can be implemented as, for example, a stationary PC (Personal Computer), a laptop PC, etc. The terminal device 10 may also be implemented as a mobile device such as a smartphone or tablet.

[0027] The terminal device 10 includes a communication interface 12, an input device 13, an output device 14, memory 15, storage 16, an LLM system 18, and a processor 19. The input device 13 is a device for receiving input operations from the user (e.g., a touch panel, touchpad, mouse or other pointing device, keyboard, etc.). The output device 14 is a device for presenting information to the user (display, speaker, etc.). The terminal device 10 uses the installed LLM system 18 to perform tasks such as document creation at predetermined timings.

[0028] The LLM system 18 is a system built with a large-scale language model (LLM), which is used, for example, in the field of natural language processing (NLP). The LLM can learn from a large amount of text data (web pages, books, articles, etc.) to understand patterns in human language and effectively perform natural language generation (NLG) tasks. The LLM system 18 takes text data and prompts as input to the LLM and causes the LLM to output the input text data and a response based on the prompts. In this embodiment, the LLM is an example of a generative AI and may be implemented by other generative AIs. The generative AI outputs, for example, the input text data, image data, audio data, and a response based on the prompts.

[0029] LLM is used in many NLP tasks, including generating responses to specific questions, automatically generating text, summarizing text, translation, and sentiment analysis. It can also be used in a variety of applications, such as education, entertainment, customer service, and product development. Examples of LLM include the following: • GPT-4 (registered trademark) (OpenAI Inc.) • PaLM2 (registered trademark) (Google Inc.) • StableLM (StableAI Inc.) • Llama2 (Meta Inc.)

[0030] The information processing device consists of a computer equipped with an arithmetic unit and a memory device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. Regarding the terminal device 10, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0031] <1.1 Functional Configuration of Terminal Devices> Figure 2 is a block diagram showing an example of the functional configuration of the terminal device 10 shown in Figure 1. As shown in Figure 2, the terminal device 10 includes a communication unit 120, an input device 13, an output device 14, an audio processing unit 17, a microphone 171, a speaker 172, a camera 160, a location information sensor 150, a storage unit 180, and a control unit 190. Each block included in the terminal device 10 is electrically connected, for example, by a bus.

[0032] The communication unit 120 performs processing such as modulation and demodulation processing for the terminal device 10 to communicate with other devices. The communication unit 120 performs transmission processing on the signal generated by the control unit 190 and transmits it to an external source (for example, the server 20). The communication unit 120 performs reception processing on the signal received from an external source and outputs it to the control unit 190.

[0033] The input device 13 is a device for a user operating the terminal device 10 to input instructions or information. The input device 13 can be implemented, for example, by a touch-sensitive device 131 on which instructions are input by touching the operating surface. If the terminal device 10 is a PC, the input device 13 may be implemented by a reader, keyboard, mouse, etc. The input device 13 converts the instructions input by the user into electrical signals and outputs the electrical signals to the control unit 190. The input device 13 may also include, for example, a receiving port that accepts electrical signals input from an external input device.

[0034] The output device 14 is a device for presenting information to the user operating the terminal device 10. The output device 14 is implemented, for example, by a display 141. The display 141 displays data according to the control of the control unit 190. The display 141 is implemented, for example, by an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0035] The audio processing unit 17 performs, for example, digital-to-analog conversion processing of the audio signal. The audio processing unit 17 converts the signal received from the microphone 171 into a digital signal and provides the converted signal to the control unit 190. The audio processing unit 17 also provides the audio signal to the speaker 172. The audio processing unit 17 is implemented, for example, by an audio processing processor. The microphone 171 receives an audio input and provides the audio signal corresponding to that audio input to the audio processing unit 17. The speaker 172 converts the audio signal received from the audio processing unit 17 into audio and outputs the audio to the outside of the terminal device 10.

[0036] Camera 160 is a device that receives light using a photodetector and outputs it as a shooting signal.

[0037] The location information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. A GPS module is a receiving device used in a satellite positioning system. In a satellite positioning system, signals are received from at least three or four satellites, and the current position of the terminal device 10, which is equipped with a GPS module, is detected based on the received signals. The location information sensor 150 may also detect the current position of the terminal device 10 from the position of the wireless base station to which the terminal device 10 is connected.

[0038] The storage unit 180 is implemented by, for example, memory 15 and storage 16, and stores data and programs used by the terminal device 10. The storage unit 180 stores, for example, an electronic medical record table 181, a document creation table 182, a processing waiting table 183, and a prompt table 184.

[0039] The electronic medical record table 181 is a table that stores information related to the patient's medical record. Further details will be provided later.

[0040] Document creation table 182 is a table that stores information related to tasks such as document creation. Further details will be provided later.

[0041] The processing queue table 183 is a table that stores the order in which documents are created. Details will be described later.

[0042] The prompt table 184 is a table that stores information about prompts that serve as instructions to the LLM system 18. Further details will be described later.

[0043] The control unit 190 is realized when the processor 19 reads a program stored in the memory unit 180 and executes instructions contained in the program. The control unit 190 controls the operation of the terminal device 10. By operating according to the program, the control unit 190 performs the functions of an operation reception unit 191, a transmission / reception unit 192, a presentation control unit 193, and a business processing unit 194.

[0044] The operation reception unit 191 processes instructions or information input from the input device 13. Specifically, for example, the operation reception unit 191 receives instructions or information input from a touch-sensitive device 131 or the like.

[0045] Furthermore, the operation reception unit 191 receives voice instructions input from the microphone 171. Specifically, for example, the operation reception unit 191 receives voice signals input from the microphone 171 and converted into digital signals by the voice processing unit 17. The operation reception unit 191 obtains instructions from the user by, for example, analyzing the received voice signals and extracting predetermined nouns.

[0046] The transmitting / receiving unit 192 performs processing to enable the terminal device 10 to send and receive data with an external device in accordance with a communication protocol. Specifically, for example, the transmitting / receiving unit 192 transmits information or instructions from the user to the external device. The transmitting / receiving unit 192 also receives information provided by the external device.

[0047] The presentation control unit 193 controls the output device 14 to present information related to document creation to the user. Specifically, the presentation control unit 194 displays, for example, the scheduled date for document creation on the display 141. The scheduled date for document creation is, for example, the scheduled date of the patient's discharge. The presentation control unit 194 also displays, for example, information related to the timing of document creation on the display 141. This information includes, for example, the waiting time until document creation is completed, the waiting time until document creation begins, a list of documents awaiting creation, and the time required to change the order of the list of documents awaiting creation. The presentation control unit 194 also displays, for example, on the display 141 that document creation is complete.

[0048] The business processing unit 194 performs tasks such as document creation using the LLM system 18. Specifically, the business processing unit 194 detects the arrival of a deadline based on pre-stored first information. The first information is pre-stored in the document creation table 182. The first information includes information about the deadline for creating the document, for example, information about the patient's scheduled discharge date. When the business processing unit 194 detects the arrival of a deadline based on the date, it reads out pre-stored second information and a prompt containing instructions to create the document. The second information is pre-stored in the electronic medical record table 181 and the document creation table 182. The second information includes information for creating the document, for example, information about the patient's medical record. The business processing unit 194 inputs the read second information and the prompt containing instructions to create the document into the LLM system 18 and causes it to output text information about the document. The business processing unit 194 stores the output text information in the storage unit 180.

[0049] The timing based on the deadline is, for example, a predetermined time on the deadline (the patient's scheduled discharge date). The predetermined time may be, for example, midnight. That is, the business processing unit 194 starts creating the document when midnight arrives on the deadline. Specifically, the business processing unit 194 reads the second information, inputs the second information and prompts to the LLM system 18, outputs text information related to the document, and stores it in the storage unit 180. Alternatively, the timing based on the deadline may be, for example, a predetermined time one or more days before the deadline. Alternatively, the timing based on the deadline may be a time when the terminal device 10 is less active on the deadline, or a time when the terminal device 10 is less active one or more days before the deadline. The time of low activity may be set based on the operation log of the terminal device 10. This ensures that, for example, documents are created at night or during idle time when the terminal device 10 is less active, so that document creation does not interfere with the normal operations of the terminal device 10.

[0050] The first information includes information about the deadlines for creating multiple documents, and may include, for example, information about the scheduled discharge dates of multiple patients. The second information includes information for creating multiple documents, and may include, for example, information about the medical records of multiple patients. When the business processing unit 194 detects the arrival of a deadline, it sequentially reads the second information for creating the target document from among the multiple documents. The business processing unit 194 inputs the read target second information and a prompt containing instructions for creating the target document to the LLM system 18, causing it to output text information about the target document.

[0051] The first information includes information about multiple documents with the same due date, and may include, for example, information about multiple patients whose scheduled discharge date is the same. When the business processing unit 194 detects the arrival of a due date, it reads the second information for creating the target document from among the multiple documents in a predetermined order. The predetermined order may be based, for example, on the patient's discharge time. The business processing unit 194 inputs the read target second information and a prompt containing instructions for creating the target document to the LLM system 18, causing it to output text information about the target document.

[0052] The first information may include information about multiple documents with assigned priorities. When the business processing unit 194 detects the arrival of a deadline, it reads the second information for creating the target document from among the multiple documents, in order of priority. Priority is set higher for patients who urgently require the document. Patients who urgently require the document include, for example, patients who need to be discharged urgently or patients who need to be transferred to another hospital urgently. Priority may also be set higher for patients whose deadlines are approaching. The business processing unit 194 inputs the read second information and a prompt containing instructions for creating the target document into the LLM system 18, causing it to output text information about the target document.

[0053] <2 Data Structure> Figures 3 to 6 show the data structure of the tables stored by the terminal device 10. Note that Figures 3 to 6 are examples and do not exclude data not shown. Furthermore, even data listed in the same table may be stored in separate memory areas within the storage unit 180.

[0054] Figure 3 shows the data structure of the electronic medical record table 181. The electronic medical record table 181 shown in Figure 3 is a table that has columns for patient ID and content, with the electronic medical record ID as the key. The electronic medical record table 181 is linked to the hospital's electronic medical record system, and information may be obtained from the electronic medical record system.

[0055] The Electronic Medical Record ID is an item that stores an identifier to uniquely identify the electronic medical record. The Patient ID is an item that stores an identifier to uniquely identify the patient.

[0056] The "Content" field is, for example, an item for storing the contents of an electronic medical record. The "Content" field may include, for example, the patient's scheduled discharge date. The scheduled discharge date may also include, for example, the scheduled discharge time. The "Content" field may also include, for example, patient information as information for creating documents (secondary information). The patient information may include, for example, the patient's medical records (condition, treatment, and progress, etc.).

[0057] Figure 4 shows the data structure of the document creation table 182. The document creation table 182 shown in Figure 4 is a table that has columns for priority, task content, and due date, with task ID as the key.

[0058] The task ID is an item that stores an identifier to uniquely identify a task. Here, the creation of a discharge summary is used as an example of a task.

[0059] Priority is an item that stores the priority of a task. The "Priority" item may be set to, for example, "High," "Medium," or "Low" to indicate the level of priority. The "Priority" item may be set to high for, for example, patients who urgently require documents. Priority may be set to high for, for example, tasks with approaching deadlines. Priority may be set to "High" if the deadline is within the first designated deadline, "Medium" if it is between the first and second designated deadlines, and "Low" if it is between the second and third designated deadlines. Priority may be automatically updated according to the deadline, or it may be manually updated by the user.

[0060] The "Job Description" field stores the details of the tasks to be processed. For example, the "Job Description" field stores the patient ID and the name of the task being processed. The patient ID corresponds to the patient ID shown in Figure 3. In Figure 4, the name of the task being processed is the name of the document to be created (discharge summary).

[0061] The "Due Date" field stores the date (Primary Information) by which the document is created. For example, the "Due Date" field stores the due date based on the patient's scheduled discharge date in electronic medical record table 181. The due date based on the scheduled discharge date may be, for example, the scheduled discharge date itself, or one or more days before the scheduled discharge date.

[0062] Furthermore, the document creation table 182 may, for example, store the text (text information) of the created document when the document creation is completed.

[0063] Figure 5 shows the data structure of the processing queue table 183. The processing queue table 183 shown in Figure 5 is a table that has a column for processing order, with the business ID as the key.

[0064] The Business ID is an item that stores an identifier to uniquely identify a business. The Business ID corresponds to the Business ID shown in Figure 4. The item "Business ID" stores the Business ID read from the document creation table 182 when the timing based on the due date arrives. In other words, the Business IDs stored in the processing waiting table 183 correspond to businesses that are waiting to be processed or are currently being processed.

[0065] The processing order is an item that stores the order in which documents are created. The "processing order" item is determined, for example, according to the "priority" item in the document creation table 182. For example, if the "priority" item in the document creation table 182 is "high", the processing order will be set to be earlier.

[0066] Figure 6 shows the data structure of the prompt table 184. The prompt table 184 shown in Figure 6 is a table that has columns for "Business Content" and "Prompt," with "Prompt ID" as the key.

[0067] The prompt ID is an item that stores an identifier to uniquely identify a prompt.

[0068] The "Job Description" field is an item that stores the details of the tasks to be processed. For example, the "Job Description" field stores the patient ID and the name of the document to be created. The "Job Description" field corresponds to the "Job Description" shown in Figure 5.

[0069] The prompt is an item that stores data related to the prompt, which is an input statement (instruction statement) to the LLM system 18. The prompt is, for example, text information. The text information of the prompt includes, for example, an instruction statement to cause the LLM system 18 to perform a task. In Figure 6, the text information of the prompt is an instruction statement to cause the LLM system 18 to create a document (discharge summary). The text information of the prompt includes, for example, the following: "The information you entered is about patient XX. Please create a discharge summary for patient XX." Furthermore, a prompt may include not only instructions for creating a document but also secondary information (such as patient information). In other words, the prompt and secondary information may be treated as a single piece of data (prompt) rather than separate data. Also, a prompt may include a definition of a discharge summary. A discharge summary is a referral document based on the patient's medical record at the time of discharge, and includes the patient's medical records (condition, treatment, and progress, etc.).

[0070] The item "Prompt" may, for example, store reference information (path) to a prompt file stored in another memory area.

[0071] <3 operations> The operation of terminal device 10 when creating a document will be explained. Figure 7 is a flowchart showing an example of the operation of terminal device 10 when creating a document.

[0072] First, the user who will perform the document creation accesses the terminal device 10. The user inputs each item in the electronic medical record table 181 by, for example, operating the terminal device 10. Information related to the electronic medical record may be output from the hospital system and stored in the electronic medical record table 181. The terminal device 10 creates a document creation table 182 based on the input items in the electronic medical record table 181, for example. The first information includes information related to the deadline for creating the document, for example, the deadline in the document creation table 182. The second information includes information for creating the document, for example, the patient information in the electronic medical record table 181.

[0073] In step S11, the terminal device 10 detects the arrival of a predetermined timing from the first information. Specifically, the business processing unit 194 detects the arrival of a timing based on a due date from the first information stored in the document creation table 182 beforehand. For example, the business processing unit 194 detects the arrival of a timing based on the due date Y1 / M1 / D1 of business IDT001 from the document creation table 182. The due date in the first information is, for example, the patient's scheduled discharge date. The timing based on the due date is, for example, a predetermined time on the due date. The predetermined time may be, for example, midnight. The business processing unit 194 detects the timing when it becomes midnight on the patient's scheduled discharge date and starts creating the document. The timing based on the due date may be, for example, a predetermined time one or more days before the due date. Furthermore, the timing based on the due date may be a time when the terminal device 10 is not very active on the due date, or a time when the terminal device 10 is not very active one or more days before the due date.

[0074] In step S12, the terminal device 10 reads the task. Specifically, when the task processing unit 194 detects the arrival of a deadline-based timing, it checks the task for which it has detected the arrival of a deadline-based timing from the document creation table 182. For example, if the deadline-based timing for task IDT001 has arrived, it checks the task details for task IDT001 ("Patient ID: PA001" and "Discharge Summary"). Then, the task processing unit 194 stores the task ID of the read task in the processing waiting table 183.

[0075] At this time, if there are multiple tasks for which the arrival of a due date has been detected, the task processing unit 194 determines the order in which to process them. For example, if the task processing unit 194 reads multiple tasks with different due dates, it sets the order of tasks with earlier due dates first, and the order of tasks with later due dates second. Also, if the task processing unit 194 reads multiple tasks with the same due date, it sets a predetermined order. This predetermined order, for example, sets the order of tasks with high urgency first, and the order of tasks with low urgency second. Also, if the task processing unit 194 reads multiple tasks with set priorities, it sets the order of tasks with higher priority first, and the order of tasks with lower priority second. The task processing unit 194 then stores the task IDs of the read tasks and the set processing order in the processing waiting table 183.

[0076] In step S13, the terminal device 10 sequentially reads the second information and prompts corresponding to the read task. Specifically, the task processing unit 194 reads the target second information (patient information) from the electronic medical record table 181 according to the set processing order. The task processing unit 194 also reads prompts containing instructions for creating the target document from the prompt table 184 according to the set processing order. Here, for example, the task processing unit 194 first reads the patient information and prompt for task IDT001. The prompt is, for example, "Please create a discharge summary for PA001."

[0077] In step S14, the terminal device 10 inputs the read second information and prompt to the LLM system 18. The business processing unit 194 first inputs, for example, the second information and prompt in business IDT001 to the LLM system 18.

[0078] In step S15, the terminal device 10 outputs text information related to the document (discharge summary). Specifically, the LLM system 18 creates text information related to the document based on the input second information and prompts. The LLM system 18 outputs the created text information. The text information is, for example, the text of the discharge summary in task IDT001 and may also include the medical record of patient IDPA001 (condition, treatment, and progress, etc.).

[0079] In step S16, the terminal device 10 stores the output text information. Specifically, for example, the business processing unit 194 may store the output text information in the document creation table 182 of the storage unit 180. The business processing unit 194 may also store the output text information in correspondence with business IDT001.

[0080] Subsequently, the terminal device 10 repeats steps S13-S16, sequentially executing the creation of documents for business IDs IDT002 and T003. That is, after the terminal device 10 creates the document for business ID DT002 in step S13-S16, it creates the document for business ID DT003 again in step S13-S16.

[0081] The terminal device 10 may, for example, present the scheduled date for document creation in response to a user request before a predetermined timing in step S11 arrives. Alternatively, the terminal device 10 may, for example, present information regarding the timing of document creation in response to a user request after a predetermined timing in step S11 has arrived. This information regarding the timing of document creation may be, for example, the scheduled time until document creation is completed (until step S16 is completed) or the scheduled time until document creation begins (until step S12 is started). This information regarding the timing of document creation may be calculated based on, for example, the processing performance and real-time processing volume of the terminal device 10 (processor 19). The terminal device 10 may also accept a user request and rearrange the order of document creation in the task list. The terminal device 10 may also present how much the document creation process will change by rearranging the order of processing in the task list. The presentation control unit 193 may, for example, present how much faster the time to document completion will be by increasing the priority of document creation.

[0082] <4. Screen Example> Figure 8 is a schematic diagram showing an example of the display screen of the display 141 of the terminal device 10. Figure 8 shows, for example, an example of the screen before a predetermined timing in step S11 shown in Figure 7 occurs.

[0083] The screen shown in Figure 8 includes the first region 1411.

[0084] Area 1411 displays, for example, a list of tasks scheduled for processing. The task list consists of, for example, a task ID, task details, and a scheduled creation date. The task ID is an item that stores an identifier to uniquely identify the task. The task details are an item that stores the content of the task to be processed. The scheduled creation date is the scheduled date on which the task will be completed, for example, the scheduled date on which a document (discharge summary) will be created.

[0085] The presentation control unit 193 may, for example, present the scheduled date for creating the document shown in Figure 8 in response to a request from the user before a predetermined timing in step S11 occurs. The presentation control unit 193 may, for example, present the scheduled date for creating the document one or more days in advance. This allows the user to confirm the scheduled date for creating the document and, if necessary, change it to a new desired date.

[0086] Figure 9 is a schematic diagram showing another example of the display screen of the display 141 of the terminal device 10. Figure 9 shows, for example, an example of a screen related to document creation or after document creation in steps S12-S16 shown in Figure 7.

[0087] The screen shown in Figure 9 includes the first region 1412.

[0088] Area 1412 displays, for example, a list of tasks that are in progress or have been completed. The task list consists of, for example, a task ID, task details, time until completion, and time until start of creation. The task ID is an item that stores an identifier to uniquely identify the task. The task details is an item that stores the content of the task to be processed. The time until completion is the scheduled time until the task is completed, for example, the scheduled time until the document is completed (until step S16 is completed). The time until start of creation is the scheduled time until the task starts, for example, the scheduled time until the document is created (until step S12 starts).

[0089] The presentation control unit 193 may, for example, after a predetermined timing in step S11 has arrived, present information regarding the timing of creating the document shown in Figure 9 in response to a user request. The information regarding the timing of creating the document may be, for example, the scheduled time until the completion of document creation (until step S16 is completed) or the scheduled time until the start of document creation (until step S12 is started). The business processing unit 194 may also accept a user request and rearrange the order of processing in the business list. The presentation control unit 193 may also present how much the document creation will change by rearranging the order of processing in the business list. For example, the presentation control unit 193 may present how much faster the time to complete the document will be by increasing the priority of document creation. This allows the user to check the information regarding the timing of creating the document and, if necessary, rearrange the order of document creation to create the necessary documents first.

[0090] <5 Variations> Figure 10 is a flowchart illustrating a modified operation of the terminal device 10 when creating a document. In the above embodiment, document creation was started when a predetermined timing related to the deadline was detected, but this embodiment is not limited to this. The terminal device 10 may, for example, start creating a document when it receives a document creation request.

[0091] First, the user performing the task accesses the terminal device 10. The user inputs each item in the electronic medical record table 181 by, for example, operating the terminal device 10. Information related to the electronic medical record may be output from the hospital system and stored in the electronic medical record table 181. The terminal device 10 then creates a document creation table 182 based on the input items in the electronic medical record table 181.

[0092] In step S21, the terminal device 10 receives a document creation request from the user. Specifically, the business processing unit 194 receives the document creation request through the user's operation of the input device 13. The acceptance of document creation requests may, for example, be performed at any time. The document creation requested by the user may, for example, be due on the same day and may be a high-priority task. For this reason, the document creation requested by the user may be performed preferentially. The user may request the creation of multiple documents. In this case, the document creation may be performed in a predetermined order.

[0093] In step S22, the terminal device 10 reads the task. Specifically, when the task processing unit 194 receives a task request, it checks the requested task from the document creation table 182. For example, if it receives a request for task IDT001, it checks the details of task IDT001 ("Patient ID: PA001" and "Discharge Summary"). Then, the task processing unit 194 stores the task ID of the read task in the processing waiting table 183. At this time, the task processing unit 194 sets the processing order in the processing waiting table 183 to "1" in order to prioritize the execution of the requested document creation.

[0094] In step S23, the terminal device 10 reads the second information and prompt corresponding to the read task. Specifically, the task processing unit 194 reads the target second information (patient information) from the electronic medical record table 181. The task processing unit 194 also reads the prompt containing the instruction to create the target document from the prompt table 184. Here, for example, the task processing unit 194 first reads the patient information and prompt for task IDT001. The prompt is, for example, "Please create a discharge summary for PA001."

[0095] In step S24, the terminal device 10 inputs the read second information and prompt to the LLM system 18. The business processing unit 194 first inputs, for example, the second information and prompt in business IDT001 to the LLM system 18.

[0096] In step S25, the terminal device 10 outputs text information related to the document (discharge summary). Specifically, the LLM system 18 creates text information related to the document based on the input second information and prompts. The LLM system 18 outputs the created text information. The text information is, for example, the text of the discharge summary in task IDT001 and may also include the medical record of patient IDPA001 (condition, treatment, and progress, etc.).

[0097] In step S26, the terminal device 10 stores the output text information. Specifically, for example, the business processing unit 194 may store the output text information in the document creation table 182 of the storage unit 180. The business processing unit 194 may also store the output text information in correspondence with business IDT001.

[0098] Furthermore, in the above embodiment, the terminal device 10 started operations at midnight on the due date as a predetermined time, but this embodiment is not limited to this. The terminal device 10 may, for example, start document creation to complete it by a desired time (for example, 6:00 a.m.). This allows the terminal device 10 to perform document creation without interfering with its normal operations.

[0099] Furthermore, in the above embodiment, the terminal device 10 created a discharge summary as a document, but this embodiment is not limited to this. The terminal device 10 may, for example, create a repair report document when the repair of a car or other item is completed.

[0100] Furthermore, although the above embodiment described an example of a terminal device 10 equipped with an LLM system 18 in an on-premise system 1, this embodiment is not limited to this. In the system of this embodiment, for example, the terminal device, server, and LLM system may be configured to be independent of each other and communicate with each other via a network.

[0101] <6 Summary> As described above, in this embodiment, the business processing unit 194 detects the arrival of a deadline based on a pre-stored first piece of information regarding the deadline for creating a document. When the business processing unit 194 detects the arrival of a deadline based on a deadline, it reads out a pre-stored second piece of information for creating a document, inputs the read second piece of information and a prompt containing instructions to create the document to the generating AI, and causes it to output text information related to the document. The business processing unit 194 stores the output text information. This makes it possible to execute tasks such as document creation using the generating AI (large-scale language model) at the appropriate timing based on the deadline. Therefore, tasks using a system that utilizes a large-scale language model can be executed efficiently.

[0102] Furthermore, in this embodiment, the timing based on the due date is a predetermined time on the due date. This allows the system to set the document to be created within a predetermined time (creation time) from the predetermined time on the due date, and the document can be created by the time desired by the user.

[0103] Furthermore, in this embodiment, the timing based on the due date is a predetermined time one or more days before the due date. This allows the system to set the document creation to take place on any day before the due date, and to create the document by the time desired by the user.

[0104] Furthermore, in this embodiment, the timing based on the deadline is a time period when computer activity is low on the deadline. This allows the document creation process to be set to occur during downtime on the deadline, ensuring that document creation is performed without disrupting normal business operations.

[0105] Furthermore, in this embodiment, the first information includes information regarding the dates on which multiple documents are to be created. The second set of information includes information for creating multiple documents. In the step of outputting text information, when the business processing unit 194 detects the arrival of a deadline, it sequentially reads the target second set of information, inputs the read second set of information and a prompt containing instructions for creating the target documents into a large-scale language model, and outputs text information related to the target documents. This allows the business to be executed efficiently by sequentially creating the documents, even when multiple documents are scheduled to be created.

[0106] Furthermore, in this embodiment, the first information includes information about multiple documents with the same due date. In the step of outputting text information, when the business processing unit 194 detects the arrival of a due date, it reads the target second information in a predetermined order, inputs the read target second information and a prompt containing instructions for creating the target document into a large-scale language model, and outputs text information about the target document. This allows the business to be executed efficiently by creating the documents in the appropriate order, even when multiple documents are scheduled to be created on the same due date.

[0107] Furthermore, in this embodiment, the first information includes information about the plurality of documents for which priority has been set. In the step of outputting text information, when the business processing unit 194 detects the arrival of the timing based on the due date, it reads the target second information in order of priority, inputs the read target second information and a prompt containing instructions for creating the target document into the large-scale language model, and outputs text information about the target document. This makes it possible to efficiently execute business by creating documents according to priority, even when the creation of multiple documents is scheduled.

[0108] In this embodiment, the business processing unit 194 also receives requests to create documents due on the same day. In the step of outputting text information, the business processing unit 194 prioritizes documents due on the same day, reads the second information for creating such documents, inputs the read second information and a prompt containing instructions for creating the documents due on the same day into a large-scale language model, and outputs text information related to the documents due on the same day. This allows for the priority execution of documents due on the same day that are requested urgently.

[0109] Furthermore, in this embodiment, the presentation control unit 193 displays the scheduled date for document creation. This allows the user to confirm the scheduled date for document creation and, if necessary, change it to a new desired date.

[0110] Furthermore, in this embodiment, the presentation control unit 193 presents information regarding the timing of document creation based on the processor's performance. This allows the user to check the information regarding the timing of document creation and, if necessary, rearrange the order in which documents are created to create the necessary documents first.

[0111] Furthermore, in this embodiment, the presentation control unit 193 indicates that the document creation is complete. This allows the user to confirm the created document.

[0112] <7 Basic Computer Hardware Configuration> Figure 11 is a block diagram showing the basic hardware configuration of computer 90. Computer 90 includes at least a processor 91, main memory 92, auxiliary storage 93, and a communication interface 99. These are electrically connected to each other by a bus.

[0113] The processor 91 is hardware for executing the instruction set written in the program. The processor 91 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0114] Main memory 92 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0115] Auxiliary storage device 93 is a storage device for storing data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, semiconductor memory, etc.

[0116] A communication IF99 is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards.

[0117] A network consists of various mobile communication systems, such as the internet, LANs, and wireless base stations. For example, a network includes 3G, 4G, and 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network also includes connections made directly via USB (Universal Serial Bus) cables, etc.

[0118] Furthermore, by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network, a computer 90 can be virtually realized. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure or case, but also a virtualized computer system.

[0119] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of the computer 90 shown in Figure 10 will be explained. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0120] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0121] The control unit is realized when the processor 91 reads various programs stored in the auxiliary storage device 93, loads them into the main memory device 92, and executes processing according to those programs. The control unit can realize various functional units that perform information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

[0122] The memory unit is implemented by a main memory 92 and an auxiliary memory 93. The memory unit stores data, various programs, and various databases. The processor 91 can also reserve memory areas corresponding to the memory unit in the main memory 92 or the auxiliary memory 93 according to the program. The control unit can also cause the processor 91 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0123] A database, specifically a relational database, is used to manage and link data sets called tables, which are structurally defined by rows and columns. In a database, tables are called tables, the columns of a table are called columns, and the rows of a table are called records. In a relational database, relationships can be established and linked between tables.

[0124] Typically, each table has a key column to uniquely identify records, but setting a key on a column is not mandatory. The control unit can instruct the processor 91 to add, delete, or update records in specific tables stored in the memory unit according to various programs.

[0125] The communication unit is implemented by the communication IF99. The communication unit implements the function of communicating with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 91 to perform information processing on the received information according to various programs. The communication unit can also transmit information output from the control unit to other computers 90.

[0126] Furthermore, each of the above-mentioned configurations, functions, processing units, processing means, etc., may be implemented in hardware, either partially or entirely, by designing them as integrated circuits, for example. The present invention can also be implemented by software program code that realizes the functions of the embodiment. In this case, a storage medium on which the program code is recorded is provided to a computer, and the processor of that computer reads the program code stored in the storage medium. In this case, the program code read from the storage medium itself realizes the functions of the embodiment described above, and the program code itself and the storage medium on which it is stored constitute the present invention. Examples of storage media used to supply such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs, optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, and the like.

[0127] Furthermore, the program code that implements the functions described in this embodiment can be implemented in a wide range of programming or scripting languages, such as assembler, C / C++, Perl, Shell, PHP, and Java (registered trademark).

[0128] Furthermore, the program code for the software that implements the functions of the embodiment may be distributed via a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the computer's processor may read and execute the program code stored in the storage means or storage medium.

[0129] The functions realized by the components described herein may be implemented in a circuit or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), CPUs (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to realize the functions described herein. A processor is considered to be a circuit or processing circuitry, including transistors and other circuits. A processor may be a programmed processor that executes a program stored in memory.

[0130] In this specification, circuitry, unit, and means are hardware programmed to perform or execute the functions described herein. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to perform or execute the functions described herein.

[0131] If the hardware is a processor that is considered to be a type of circuitry, then the circuitry, means, or unit is a combination of hardware and software used to constitute the hardware and / or processor.

[0132] While several embodiments of this disclosure have been described above, these embodiments can be implemented in a variety of other forms, and various omissions, substitutions, and modifications are permitted without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents.

[0133] (Note) The details described in each of the above embodiments are noted below.

[0134] (Note 1) A program to be executed by a computer having a processor and memory, wherein the program is to be executed by the processor, A step of detecting the arrival of the timing based on the date for creating the document, using first information that has been stored in advance, Upon detecting the arrival of the timing based on the aforementioned date, the AI ​​reads second information stored in advance for creating the document, inputs the read second information and a prompt containing instructions for creating the document into the generating AI, and outputs text information related to the document. The steps include storing the output text information, A program that executes the command.

[0135] (Note 2) The timing based on the aforementioned date is the predetermined time on the aforementioned date. The program described in (Note 1).

[0136] (Note 3) The timing based on the aforementioned date is a predetermined time one or more days before the aforementioned date. The program described in (Note 1).

[0137] (Note 4) The timing based on the aforementioned date is the time period on the aforementioned date when the computer's activity is low. The program described in (Note 1).

[0138] (Note 5) The aforementioned first information includes information regarding the deadlines for creating multiple documents, The second information includes information for creating the aforementioned multiple documents, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is sequentially read, the read target second information and a prompt containing instructions for creating the target document are input to a large-scale language model, and text information relating to the target document is output. The program described in (Note 1).

[0139] (Note 6) The first information includes information about the multiple documents for which the same due date is set, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is read in a predetermined order, the read target second information and a prompt containing instructions for creating the target document are input to the large-scale language model, and text information relating to the target document is output. The program described in (Appendix 5).

[0140] (Note 7) The first information includes information about the plurality of documents for which priority has been set, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is read in order of priority, the read target second information and a prompt containing instructions for creating the target document are input to the large-scale language model, and text information relating to the target document is output. The program described in (Appendix 5).

[0141] (Note 8) The steps for accepting requests to prepare documents due on the same day are as follows: The aforementioned processor is to execute, In the step of outputting the text information, the second information for creating the document due on the current day is read, the read second information and a prompt containing instructions for creating the document due on the current day are input to a large-scale language model, and text information relating to the document due on the current day is output. The program described in (Note 1).

[0142] (Note 9) The step of indicating the planned date for creating the aforementioned document, The program described in (Appendix 1) to be executed by the aforementioned processor.

[0143] (Note 10) A step of providing information about the timing of creating the document based on the performance of the aforementioned processor, The program described in (Appendix 1) to be executed by the aforementioned processor.

[0144] (Note 11) The step of indicating that the aforementioned document has been completed is, The program described in (Appendix 1) to be executed by the aforementioned processor.

[0145] (Note 12) A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps performed in any of the inventions described in (Appendix 1) to (Appendix 11).

[0146] (Note 13) An information processing apparatus comprising a control unit and a storage unit, wherein the control unit performs all steps performed in any of the inventions described in (Appendix 1) to (Appendix 11).

[0147] (Note 14) A system comprising means for performing all steps performed in any of the inventions described in (Appendix 1) to (Appendix 11). [Explanation of Symbols]

[0148] 1... System 10…User terminal 12…Communication IF 13…Input device 14…Output device 15…Memory 16…Storage 19… Processor

Claims

1. A program to be executed by a computer having a processor and memory, wherein the program is to be executed by the processor, A step of detecting the arrival of the timing based on the date for creating the document, using first information that has been stored in advance, Upon detecting the arrival of the timing based on the aforementioned date, the AI ​​reads second information stored in advance for creating the document, inputs the read second information and a prompt containing instructions for creating the document to the generating AI, and outputs text information related to the document. The steps include storing the output text information, A program that executes the command.

2. The timing based on the aforementioned date is the predetermined time on the aforementioned date. The program according to claim 1.

3. The timing based on the aforementioned date is a predetermined time one or more days before the aforementioned date. The program according to claim 1.

4. The timing based on the aforementioned date is the time period on the aforementioned date when the computer's activity is low. The program according to claim 1.

5. The aforementioned first information includes information regarding the deadlines for creating multiple documents, The second information includes information for creating the multiple documents, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is sequentially read, the read target second information and a prompt containing instructions for creating the target document are input to a large-scale language model, and text information relating to the target document is output. The program according to claim 1.

6. The first information includes information about the multiple documents for which the same due date is set, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is read in a predetermined order, the read target second information and a prompt containing instructions for creating the target document are input to the large-scale language model, and text information relating to the target document is output. The program according to claim 5.

7. The first information includes information about the plurality of documents for which priority has been set, In the step of outputting the text information, when the arrival of the timing based on the due date is detected, the target second information is read in order of priority, the read target second information and a prompt containing instructions for creating the target document are input to the large-scale language model, and text information relating to the target document is output. The program according to claim 5.

8. The steps for accepting requests to prepare documents due on the same day are as follows: The aforementioned processor is to execute, In the step of outputting the text information, the second information for creating the document due on the current day is read, the read second information and a prompt containing instructions for creating the document due on the current day are input to a large-scale language model, and text information relating to the document due on the current day is output. The program according to claim 1.

9. The step of indicating the planned date for creating the aforementioned document, The program according to claim 1, which is to be executed by the processor.

10. A step of providing information about the timing of creating the document based on the performance of the aforementioned processor, The program according to claim 1, which is to be executed by the processor.

11. The step of indicating that the aforementioned document has been completed is, The program according to claim 1, which is to be executed by the processor.

12. A method to be performed on a computer comprising a processor and memory, wherein the processor performs all steps performed in the invention according to any one of claims 1 to 11.

13. An information processing apparatus comprising a control unit and a storage unit, wherein the control unit performs all steps performed in the invention according to any one of claims 1 to 11.

14. A system comprising means for performing all steps performed in the invention according to any one of claims 1 to 11.

Images