System

Abstract

To provide a system which improves efficiency of input and analysis of a nursing care diary and proposes an appropriate care action.SOLUTION: A system comprises a reception part, a conversion part, an editing part, an analysis part, and a proposal part. The reception part receives voice input from a care giver. The conversion part converts voice data received by the reception part to text data. The editing part re-edits the text data converted by the conversion part. The analysis part analyzes the information of a nursing care diary re-edited by the editing part. The proposal part proposes a care action on the basis of the information analyzed by the analysis part.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, entering and analyzing nursing care diaries requires time and effort, and there is room for improvement in the efficiency of nursing care work.

[0005] The system according to the embodiment aims to improve the efficiency of inputting and analyzing the care diary and to propose appropriate care responses. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a conversion unit, an editing unit, an analysis unit, and a suggestion unit. The reception unit accepts voice input from a caregiver. The conversion unit converts the voice data accepted by the reception unit into text data. The editing unit re-edits the text data converted by the conversion unit. The analysis unit analyzes information in the care diary re-edited by the editing unit. The suggestion unit suggests care responses based on the information analyzed by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can improve the efficiency of inputting and analyzing the nursing diary, and can suggest appropriate nursing care responses. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The nursing care diary input system according to the embodiment of the present invention is a system that accepts voice input from a caregiver, converts the voice data into text data, and optimizes and re-edits the input document using a generation AI. This system accepts voice input from a caregiver, converts the voice data into text data. Next, the generation AI re-edits the text data to make it an easy-to-read document. Furthermore, the generation AI analyzes the information in the nursing care diary, grasps the situation of the care recipient, and proposes appropriate care responses. This series of processes reduces the time and improves the efficiency of nursing care work. For example, a caregiver inputs the contents of the nursing care diary by voice. For example, the content such as "This morning, the care recipient went for a walk. In the afternoon, he / she underwent rehabilitation" is input by voice. This voice data is converted into text data by the generation AI. Next, the generation AI re-edits the text data. For example, grammar is corrected and expressions are unified to make the document easy to read. This makes the contents of the nursing care diary consistent, making it easy for other caregivers and medical staff to understand. Furthermore, the generation AI analyzes the information in the nursing care diary. For example, the change in the physical condition and behavioral patterns of the care recipient are analyzed based on the data of past nursing care diaries. This allows the system to grasp the condition of the person receiving care and propose appropriate care responses. Finally, the system notifies the caregiver of the care response proposed by the generation AI. For example, the system may make a specific suggestion such as, "The condition of the person receiving care is deteriorating, so the frequency of future rehabilitation sessions should be reduced." This allows the caregiver to take appropriate measures according to the condition of the person receiving care. This system reduces the time and efficiency of care work, and reduces the burden on the caregiver. In addition, by providing appropriate responses to the person receiving care, the quality of care is improved. This allows the care diary input system to efficiently process the voice input of the caregiver, optimize the care diary, and propose care responses.

[0029] The nursing diary input system according to the embodiment includes a reception unit, a conversion unit, an editing unit, an analysis unit, and a proposal unit. The reception unit receives voice input from a caregiver. The voice input includes, for example, voice input using a microphone, voice input through a smartphone app, and the like, but is not limited to such examples. The conversion unit converts the voice data received by the reception unit into text data using a generation AI. The generation AI converts the voice data into text data, for example, using a text generation AI (for example, LLM). The conversion unit can also convert the voice data into text data using the generation AI. For example, the generation AI converts the voice data into text data using a voice recognition technology. The editing unit re-edits the text data converted by the conversion unit using the generation AI. The re-editing includes, for example, grammar correction, unification of expressions, deletion of unnecessary information, and the like, but is not limited to such examples. For example, the generation AI corrects grammar using a grammar check tool. The generation AI can also unify expressions using natural language processing technology. Furthermore, the generation AI can delete unnecessary information to create an easy-to-read document. The analysis unit uses the generation AI to analyze the information of the nursing care diary re-edited by the editing unit. The analysis includes, for example, data mining technology, statistical analysis, machine learning algorithms, etc., but is not limited to such examples. For example, the generation AI analyzes changes in the physical condition and behavior patterns of the care recipient based on data of the past nursing care diary. The generation AI can also grasp the situation of the care recipient and propose appropriate nursing care responses. The suggestion unit uses the generation AI to propose nursing care responses based on the information analyzed by the analysis unit. The suggestions include, for example, suggestions for nursing care schedules and suggestions for improving nursing care methods, but are not limited to such examples. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the physical condition of the care recipient is deteriorating. The generation AI can also propose appropriate nursing care responses based on the behavior patterns of the care recipient. As a result, the nursing care diary input system according to the embodiment can efficiently process the voice input of the caregiver, optimize the nursing care diary, and propose nursing care responses.

[0030] The reception unit receives voice input from the caregiver. Voice input includes, but is not limited to, voice input using a microphone and voice input through a smartphone app. Specifically, in order to allow the caregiver to easily record the diary by voice while performing daily care work, it is recommended that the reception unit use a device with a high-sensitivity microphone and a noise canceling function. When using a smartphone app, the app has a function of converting voice input into text in real time and provides an interface that makes it easy for the caregiver to check the input content. In addition, when performing voice input, it is important to prepare a wealth of training data to improve the accuracy of the voice recognition engine so that it can handle the speed and accent of the caregiver's speech. Furthermore, in order to minimize misrecognition that may occur during voice input, the reception unit can register specific keywords and phrases in advance and improve the accuracy of voice recognition. This allows the caregiver to perform voice input without stress, and the diary recording work becomes more efficient.

[0031] The conversion unit converts the voice data received by the reception unit into text data using the generation AI. The generation AI converts the voice data into text data, for example, using a text generation AI (for example, LLM). The conversion unit can also convert the voice data into text data using the generation AI. For example, the generation AI converts the voice data into text data using a voice recognition technology. Specifically, the generation AI uses a voice recognition model to analyze the voice data and convert the spoken content into text with high accuracy. The voice recognition model is trained in advance with a large amount of voice data and corresponding text data, and is optimized to handle the caregiver's speech patterns and technical terms. Furthermore, the generation AI improves the conversion accuracy by removing noise from the voice data and extracting a clear voice signal. The generation AI can also generate easy-to-read text data by understanding the context of the voice data and inserting appropriate punctuation and line breaks. This allows the conversion unit to quickly and accurately convert the caregiver's voice input into text data and provide data necessary for subsequent processing.

[0032] The editing department re-edits the text data converted by the conversion department using the generation AI. Re-editing includes, for example, grammar correction, unification of expressions, and deletion of unnecessary information, but is not limited to such examples. For example, the generation AI corrects grammar using a grammar check tool. The generation AI can also unify expressions using natural language processing technology. Furthermore, the generation AI can also delete unnecessary information to create a document that is easy to read. Specifically, the generation AI automatically detects grammatical errors in the text data and makes appropriate corrections. For example, it checks and corrects the agreement of subject and predicate, the agreement of tense, and the appropriate placement of punctuation marks. In addition, the generation AI unifies different expressions that have the same meaning and maintains consistency throughout the document. For example, the expressions "provide meals" and "serve meals" are unified to "provide meals". Furthermore, the generation AI deletes redundant expressions and unnecessary information to create a concise and easy-to-read document. For example, the sentence "The weather was nice today, so I went for a walk" is simplified to "I went for a walk". This enables the editorial department to turn the converted text data into a high-quality nursing care diary.

[0033] The analysis unit uses the generation AI to analyze the information in the nursing diary re-edited by the editing unit. Examples of the analysis include, but are not limited to, data mining technology, statistical analysis, and machine learning algorithms. For example, the generation AI analyzes the changes in the physical condition and behavioral patterns of the care recipient based on the data in the past nursing diary. The generation AI can also grasp the situation of the care recipient and propose appropriate nursing care responses. Specifically, the generation AI analyzes the data in the nursing diary in chronological order to extract trends in the changes in the physical condition and behavioral patterns of the care recipient. For example, it analyzes data such as food intake, sleep time, and exercise amount to predict changes in physical condition. The generation AI can also use an anomaly detection algorithm to detect patterns that are different from the norm at an early stage and issue a warning to the caregiver. Furthermore, the generation AI derives the optimal nursing care method by comparing it with past data in order to propose nursing care responses according to the individual situation of the care recipient. For example, if the physical condition of the care recipient tends to deteriorate during a specific time period, it is suggested that special care be provided during that time period. This enables the analysis unit to perform advanced analysis of the data in the care diary, grasp the health condition of the person being cared for in real time, and support appropriate care responses.

[0034] The suggestion unit uses the generation AI to suggest care responses based on the information analyzed by the analysis unit. The suggestions include, but are not limited to, suggestions for care schedules and suggestions for improving care methods. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the health of the care recipient is deteriorating. The generation AI can also suggest appropriate care responses based on the behavioral patterns of the care recipient. Specifically, the generation AI automatically generates an optimal care schedule based on the health and behavioral data of the care recipient. For example, meal times, rehabilitation times, rest times, etc. are optimized to reduce the burden on the care recipient. In addition, the generation AI refers to the latest nursing care technologies and research results to suggest specific improvement measures for improving the care method. For example, if a specific rehabilitation method is not effective, another method is suggested. In addition, the generation AI predicts points of caution and risks in daily life based on the behavioral patterns of the care recipient and provides specific advice to the caregiver. As a result, the suggestion unit suggests specific care responses to keep the health of the care recipient in an optimal state, and high-quality care can be achieved while reducing the burden on the caregiver.

[0035] The conversion unit can convert the voice data into text data using the generation AI. The generation AI converts the voice data into text data using, for example, a text generation AI (for example, LLM). The generation AI can also convert the voice data into text data using voice recognition technology. For example, the generation AI takes voice data as input and outputs text data. The generation AI analyzes the content of the voice data and converts it into appropriate text data. As a result, the use of the generation AI improves the conversion accuracy of the voice data. The generation AI can also analyze, for example, the content of the voice data and correct grammar and expressions. The generation AI generates appropriate text data based on the content of the voice data. For example, the generation AI analyzes the content of the voice data and corrects grammar and standardizes expressions. As a result, the use of the generation AI improves the conversion accuracy of the voice data and can generate accurate text data.

[0036] The editorial department can use the generation AI to correct grammar or standardize expressions to create a well-organized document. The generation AI, for example, corrects grammar using a grammar check tool. The generation AI can also standardize expressions using natural language processing technology. For example, when correcting grammar, the generation AI uses a grammar check tool to detect and correct grammatical errors. In addition, when standardizing expressions, the generation AI uses natural language processing technology to standardize terms and apply style guides. As a result, the use of the generation AI improves the consistency and readability of the document. For example, when correcting grammar or standardizing expressions, the generation AI can also delete unnecessary information to create an easy-to-read document. When correcting grammar or standardizing expressions, the generation AI analyzes the contents of the document and makes appropriate corrections. As a result, the use of the generation AI improves the consistency and readability of the document, and a document that can be easily understood by other caregivers and medical staff can be generated.

[0037] The analysis unit can use the generation AI to perform a detailed analysis of changes in the physical condition or behavioral patterns of the care recipient based on data from the past nursing diary. The generation AI, for example, uses data mining technology to analyze data from the past nursing diary. The generation AI can also use statistical analysis to analyze changes in the physical condition and behavioral patterns of the care recipient. For example, the generation AI analyzes changes in the physical condition of the care recipient based on data from the past nursing diary. When analyzing the behavioral patterns of the care recipient, the generation AI uses a machine learning algorithm to identify the behavioral patterns. This makes it possible to accurately grasp the situation of the care recipient and propose appropriate care responses by using the generation AI. For example, the generation AI analyzes changes in the physical condition and behavioral patterns of the care recipient based on data from the past nursing diary and propose appropriate care responses. The generation AI uses data mining technology and statistical analysis when grasping the situation of the care recipient and proposing appropriate care responses. This makes it possible to accurately grasp the situation of the care recipient and propose appropriate care responses by using the generation AI.

[0038] The suggestion unit can suggest a care response to the care recipient using the generation AI. The generation AI, for example, suggests a care schedule. The generation AI can also suggest improvements to the care method. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the health of the care recipient is deteriorating. The generation AI can also suggest an appropriate care response based on the behavioral patterns of the care recipient. As a result, by using the generation AI, it is possible to quickly suggest an appropriate care response. For example, the generation AI analyzes changes in the health of the care recipient and behavioral patterns, and suggests an appropriate care response. The generation AI uses data mining technology and statistical analysis when grasping the situation of the care recipient and proposing an appropriate care response. As a result, by using the generation AI, it is possible to quickly suggest an appropriate care response.

[0039] The suggestion unit can notify the caregiver of the care response proposed by the generation AI. The generation AI notifies the caregiver of the suggestion by using, for example, a smartphone notification. The generation AI can also notify the caregiver of the suggestion by using an email notification. For example, the generation AI notifies the caregiver that the frequency of rehabilitation should be reduced because the health of the care recipient is deteriorating. The generation AI can also notify the caregiver of an appropriate care response based on the behavior pattern of the care recipient. In this way, by using the generation AI, it is possible to promptly notify the caregiver of an appropriate response. The generation AI notifies the caregiver of the suggestion by using, for example, a smartphone notification or an email notification. The generation AI notifies the caregiver of an appropriate care response based on the change in the health of the care recipient and the behavior pattern. In this way, by using the generation AI, it is possible to promptly notify the caregiver of an appropriate response.

[0040] The reception unit can analyze the past voice input history of the caregiver and select the optimal reception method. For example, the reception unit preferentially suggests a voice input method that the caregiver has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the past voice input history of the caregiver. For example, the reception unit analyzes the past voice input history of the caregiver and suggests the most efficient reception method. In this way, the optimal reception method can be provided by analyzing the past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the past voice input history of the caregiver to the generation AI and cause the generation AI to select the optimal reception method.

[0041] The reception unit can perform filtering based on the caregiver's current work situation and stress level when receiving the voice input. For example, when the caregiver is busy, the reception unit preferentially receives only important voice input. When the caregiver is relaxed, the reception unit can also receive all voice input and collect detailed information. For example, when the caregiver is stressed, the reception unit receives only simple voice input to reduce the burden. This makes it possible to reduce the burden on the caregiver by filtering the voice input according to the caregiver's work situation and stress level. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the caregiver's work situation and stress level to the generation AI and cause the generation AI to execute filtering.

[0042] When receiving a voice input, the reception unit can preferentially receive a highly relevant input in consideration of the geographical location information of the caregiver. For example, when the caregiver is in a specific facility, the reception unit preferentially receives a voice input related to the facility. When the caregiver is moving, the reception unit can also preferentially receive a voice input related to the destination. For example, when the caregiver is at home, the reception unit preferentially receives a voice input related to the home. In this way, by considering the geographical location information of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to perform preferential reception of highly relevant input.

[0043] The reception unit can analyze the social media activity of the caregiver and receive related inputs when receiving the voice input. The reception unit, for example, preferentially receives related voice inputs based on information shared by the caregiver on social media. The reception unit can also preferentially receive voice inputs related to current interests from the social media activity of the caregiver. For example, the reception unit analyzes the social media activity of the caregiver and preferentially receives voice inputs including important information. In this way, by analyzing the social media activity of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to perform preferential reception of related inputs.

[0044] The conversion unit can optimize the conversion algorithm by considering the speech pattern and accent of the caregiver when converting the voice data. For example, the conversion unit learns the speech pattern of the caregiver and applies an optimal conversion algorithm. The conversion unit can also apply an algorithm to prevent erroneous conversion by considering the caregiver's accent. For example, the conversion unit adjusts the conversion algorithm according to the speech rate of the caregiver. As a result, the conversion accuracy is improved by considering the speech pattern and accent of the caregiver. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input data of the speech pattern and accent of the caregiver to the generation AI and cause the generation AI to optimize the conversion algorithm.

[0045] The conversion unit can improve conversion accuracy by referring to the caregiver's past speech history when converting voice data. For example, the conversion unit preferentially converts specific terms and phrases based on the caregiver's past speech history. The conversion unit can also learn frequently used words from the caregiver's past speech history to improve conversion accuracy. For example, the conversion unit analyzes the caregiver's past speech history and applies an algorithm to prevent erroneous conversion. As a result, the conversion accuracy is improved by referring to the past speech history. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the caregiver's past speech history data to the generation AI and cause the generation AI to improve the conversion accuracy.

[0046] The conversion unit can adjust the conversion algorithm in consideration of the geographical location information of the caregiver when converting the voice data. For example, when the caregiver is in a specific facility, the conversion unit preferentially converts terms related to the facility. When the caregiver is on the move, the conversion unit can also preferentially convert terms related to the destination. For example, when the caregiver is at home, the conversion unit preferentially converts terms related to the home. In this way, by considering the geographical location information of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to adjust the conversion algorithm.

[0047] The conversion unit can analyze the social media activity of the caregiver and preferentially convert related utterances when converting the voice data. The conversion unit preferentially converts related utterances based on, for example, information shared by the caregiver on social media. The conversion unit can also preferentially convert utterances related to current interests from the social media activity of the caregiver. For example, the conversion unit analyzes the social media activity of the caregiver and preferentially converts utterances containing important information. In this way, by analyzing the social media activity of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI or may be performed without using AI. For example, the conversion unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to perform preferential conversion of related utterances.

[0048] When editing a document, the editing unit can select an optimal editing method by referring to the caregiver's past editing history. For example, the editing unit preferentially uses frequently used expressions based on the caregiver's past editing history. The editing unit can also learn specific grammar and expressions from the caregiver's past editing history and select an optimal editing method. For example, the editing unit analyzes the caregiver's past editing history and selects an editing method for maintaining the consistency of the document. In this way, the optimal editing method can be provided by referring to the past editing history. A part or all of the above-mentioned processing in the editing unit may be performed, for example, using AI or may be performed without using AI. For example, the editing unit can input the caregiver's past editing history data to the generation AI and cause the generation AI to select the optimal editing method.

[0049] The editing unit can correct grammar and standardize expressions based on the caregiver's speech content when editing the document. The editing unit corrects grammar, for example, based on the caregiver's speech content. The editing unit can also standardize expressions based on the caregiver's speech content. For example, the editing unit makes corrections to maintain the consistency of the document based on the caregiver's speech content. As a result, the consistency of the document is improved by correcting grammar and standardizing expressions based on the speech content. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the caregiver's speech content data to the generation AI and cause the generation AI to correct grammar and standardize expressions.

[0050] The editing unit can determine the priority of editing based on the submission time of the caregiver when editing the document. For example, the editing unit prioritizes editing when the submission deadline of the caregiver is approaching. The editing unit can also edit according to the normal editing schedule when the caregiver submits with plenty of time. For example, the editing unit adjusts the priority of editing based on the submission time of the caregiver. This enables efficient editing by determining the priority of editing based on the submission time. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the submission time data of the caregiver to the generation AI and cause the generation AI to determine the priority of editing.

[0051] The editing unit can improve the accuracy of editing by referring to the literature related to the caregiver when editing the document. For example, the editing unit complements the contents of the document by referring to the literature related to the caregiver. The editing unit can also learn appropriate expression methods from the literature related to the caregiver and reflect them in the document. For example, the editing unit makes corrections to maintain the consistency of the document based on the literature related to the caregiver. As a result, the accuracy of editing is improved by referring to the related literature. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the literature data related to the caregiver to the generation AI and cause the generation AI to perform improvement of the accuracy of editing.

[0052] During the analysis, the analysis unit can predict the current situation by referring to past nursing diary data. For example, the analysis unit predicts a change in the physical condition of the care recipient based on the past nursing diary data. The analysis unit can also predict the behavior pattern of the care recipient from the past nursing diary data. For example, the analysis unit predicts an appropriate nursing care response based on the current situation by referring to the past nursing diary data. In this way, the current situation can be accurately predicted by referring to the past data. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the past nursing diary data to the generation AI and cause the generation AI to execute a prediction of the current situation.

[0053] The analysis unit can analyze changes in physical condition and behavioral patterns based on the caregiver's speech content during analysis. The analysis unit, for example, analyzes changes in the physical condition of the care recipient based on the caregiver's speech content. The analysis unit can also analyze the behavioral patterns of the care recipient from the caregiver's speech content. For example, the analysis unit refers to the caregiver's speech content and analyzes appropriate care responses based on the care recipient's physical condition and behavior. As a result, the situation of the care recipient can be accurately grasped by analyzing based on the speech content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caregiver's speech content data to the generation AI and cause the generation AI to execute analysis of changes in physical condition and behavioral patterns.

[0054] The analysis unit can analyze the change in the analysis based on the time of submission by the caregiver during the analysis. The analysis unit analyzes the change in the physical condition of the care recipient based on the time of the care diary submitted by the caregiver, for example. The analysis unit can also analyze the change in the behavior pattern of the care recipient from the time of submission by the caregiver. For example, the analysis unit refers to the time of submission by the caregiver and analyzes an appropriate care response. In this way, by analyzing the change based on the time of submission, it is possible to propose an appropriate care response. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data of the submission time of the caregiver to the generation AI and cause the generation AI to execute the analysis of the change.

[0055] The analysis unit can perform the analysis by referring to the caregiver-related market data during the analysis. For example, the analysis unit analyzes changes in the physical condition of the care recipient based on the caregiver-related market data. The analysis unit can also analyze the behavioral pattern of the care recipient from the caregiver-related market data. For example, the analysis unit refers to the caregiver-related market data and analyzes appropriate care responses. In this way, by referring to the related market data, a more accurate analysis can be performed. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caregiver-related market data to the generation AI and cause the generation AI to perform the analysis.

[0056] At the time of proposal, the proposal unit can select the optimal proposal method by referring to the past proposal history of the caregiver. For example, the proposal unit preferentially uses a frequently used proposal method based on the past proposal history of the caregiver. The proposal unit can also learn a specific proposal method from the past proposal history of the caregiver and select the optimal proposal method. For example, the proposal unit analyzes the past proposal history of the caregiver and selects a method for maintaining the consistency of the proposal. In this way, the optimal proposal method can be provided by referring to the past proposal history. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the past proposal history data of the caregiver to the generation AI and cause the generation AI to select the optimal proposal method.

[0057] The suggestion unit can adjust the level of detail of the proposal based on the contents of the caregiver's speech when making a proposal. The suggestion unit makes a detailed proposal based on, for example, the contents of the caregiver's speech. The suggestion unit can also make a concise proposal from the contents of the caregiver's speech. For example, the suggestion unit refers to the contents of the caregiver's speech and makes adjustments to maintain the consistency of the proposal. As a result, it is possible to provide an appropriate proposal by adjusting the level of detail of the proposal based on the contents of the speech. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input the caregiver's speech content data to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0058] The suggestion unit can select the optimal suggestion method by considering the geographical location information of the caregiver when making a suggestion. For example, when the caregiver is in a specific facility, the suggestion unit can prioritize a suggestion related to the facility. When the caregiver is on the move, the suggestion unit can also prioritize a suggestion related to the destination. For example, when the caregiver is at home, the suggestion unit prioritizes a suggestion related to the home. In this way, by considering the geographical location information, it is possible to provide a highly relevant suggestion. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to select the optimal suggestion method.

[0059] At the time of making a proposal, the suggestion unit can adjust the means of the proposal by analyzing the social media activity of the caregiver. For example, the suggestion unit prioritizes relevant proposals based on information shared by the caregiver on social media. The suggestion unit can also prioritize proposals related to current interests from the social media activity of the caregiver. For example, the suggestion unit analyzes the social media activity of the caregiver and prioritizes proposals including important information. In this way, it is possible to provide highly relevant proposals by analyzing the social media activity. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to adjust the means of the proposal.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] When accepting the voice input of the caregiver, the reception unit can learn the past input patterns of the caregiver and suggest the optimal input method. For example, the reception unit preferentially suggests a voice input method that the caregiver has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the past voice input history of the caregiver. In this way, the optimal reception method can be provided by analyzing the past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the past voice input history of the caregiver to the generation AI and cause the generation AI to select the optimal reception method.

[0062] The conversion unit can optimize the conversion algorithm by considering the speech pattern and accent of the caregiver when converting the voice data. For example, the conversion unit learns the speech pattern of the caregiver and applies an optimal conversion algorithm. The conversion unit can also apply an algorithm to prevent erroneous conversion by considering the caregiver's accent. As a result, the conversion accuracy is improved by considering the speech pattern and accent of the caregiver. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input data of the speech pattern and accent of the caregiver to the generation AI and cause the generation AI to optimize the conversion algorithm.

[0063] When editing a document, the editing unit can select the optimal editing method by referring to the caregiver's past editing history. For example, frequently used expressions are used preferentially based on the caregiver's past editing history. The editing unit can also learn specific grammar and expressions from the caregiver's past editing history and select the optimal editing method. This makes it possible to provide the optimal editing method by referring to the past editing history. Some or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the caregiver's past editing history data to the generation AI and cause the generation AI to select the optimal editing method.

[0064] During the analysis, the analysis unit can predict the current situation by referring to past nursing diary data. For example, the analysis unit predicts changes in the physical condition of the care recipient based on the past nursing diary data. The analysis unit can also predict the behavioral pattern of the care recipient from the past nursing diary data. This makes it possible to accurately predict the current situation by referring to past data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input past nursing diary data to a generation AI and cause the generation AI to predict the current situation.

[0065] At the time of proposal, the proposal unit can select the optimal proposal method by referring to the past proposal history of the caregiver. For example, based on the past proposal history of the caregiver, a frequently used proposal method is preferentially used. The proposal unit can also learn a specific proposal method from the past proposal history of the caregiver and select the optimal proposal method. In this way, the optimal proposal method can be provided by referring to the past proposal history. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the past proposal history data of the caregiver to the generation AI and cause the generation AI to select the optimal proposal method.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The reception unit receives voice input from a caregiver. Voice input includes, for example, voice input using a microphone or voice input through a smartphone app. Step 2: The conversion unit converts the voice data received by the reception unit into text data using the generation AI. The generation AI converts the voice data into text data using, for example, a text generation AI (e.g., LLM) or a voice recognition technology. Step 3: The editorial department uses the generation AI to re-edit the text data converted by the conversion department. Re-editing includes correcting grammar, standardizing expressions, deleting unnecessary information, etc. The generation AI performs these processes using grammar checking tools and natural language processing technology. Step 4: The analysis department uses the generation AI to analyze the information in the nursing diary reedited by the editing department. The analysis includes data mining techniques, statistical analysis, and machine learning algorithms. The generation AI analyzes changes in the physical condition and behavioral patterns of the care recipient based on past nursing diary data. Step 5: The proposal unit uses the generation AI to propose care responses based on the information analyzed by the analysis unit. The proposals include suggestions for care schedules and suggestions for improving care methods. The generation AI proposes appropriate care responses when the care recipient's physical condition deteriorates or based on behavioral patterns.

[0068] (Example 2) The nursing care diary input system according to the embodiment of the present invention is a system that accepts voice input from a caregiver, converts the voice data into text data, and optimizes and re-edits the input document using a generation AI. This system accepts voice input from a caregiver, converts the voice data into text data. Next, the generation AI re-edits the text data to make it an easy-to-read document. Furthermore, the generation AI analyzes the information in the nursing care diary, grasps the situation of the care recipient, and proposes appropriate care responses. This series of processes reduces the time and improves the efficiency of nursing care work. For example, a caregiver inputs the contents of the nursing care diary by voice. For example, the content such as "This morning, the care recipient went for a walk. In the afternoon, he / she underwent rehabilitation" is input by voice. This voice data is converted into text data by the generation AI. Next, the generation AI re-edits the text data. For example, grammar is corrected and expressions are unified to make the document easy to read. This makes the contents of the nursing care diary consistent, making it easy for other caregivers and medical staff to understand. Furthermore, the generation AI analyzes the information in the nursing care diary. For example, the change in the physical condition and behavioral patterns of the care recipient are analyzed based on the data of past nursing care diaries. This allows the system to grasp the condition of the person receiving care and propose appropriate care responses. Finally, the system notifies the caregiver of the care response proposed by the generation AI. For example, the system may make a specific suggestion such as, "The condition of the person receiving care is deteriorating, so the frequency of future rehabilitation sessions should be reduced." This allows the caregiver to take appropriate measures according to the condition of the person receiving care. This system reduces the time and efficiency of care work, and reduces the burden on the caregiver. In addition, by providing appropriate responses to the person receiving care, the quality of care is improved. This allows the care diary input system to efficiently process the voice input of the caregiver, optimize the care diary, and propose care responses.

[0069] The nursing diary input system according to the embodiment includes a reception unit, a conversion unit, an editing unit, an analysis unit, and a proposal unit. The reception unit receives voice input from a caregiver. The voice input includes, for example, voice input using a microphone, voice input through a smartphone app, and the like, but is not limited to such examples. The conversion unit converts the voice data received by the reception unit into text data using a generation AI. The generation AI converts the voice data into text data, for example, using a text generation AI (for example, LLM). The conversion unit can also convert the voice data into text data using the generation AI. For example, the generation AI converts the voice data into text data using a voice recognition technology. The editing unit re-edits the text data converted by the conversion unit using the generation AI. The re-editing includes, for example, grammar correction, unification of expressions, deletion of unnecessary information, and the like, but is not limited to such examples. For example, the generation AI corrects grammar using a grammar check tool. The generation AI can also unify expressions using natural language processing technology. Furthermore, the generation AI can delete unnecessary information to create an easy-to-read document. The analysis unit uses the generation AI to analyze the information of the nursing care diary re-edited by the editing unit. The analysis includes, for example, data mining technology, statistical analysis, machine learning algorithms, etc., but is not limited to such examples. For example, the generation AI analyzes changes in the physical condition and behavior patterns of the care recipient based on data of the past nursing care diary. The generation AI can also grasp the situation of the care recipient and propose appropriate nursing care responses. The suggestion unit uses the generation AI to propose nursing care responses based on the information analyzed by the analysis unit. The suggestions include, for example, suggestions for nursing care schedules and suggestions for improving nursing care methods, but are not limited to such examples. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the physical condition of the care recipient is deteriorating. The generation AI can also propose appropriate nursing care responses based on the behavior patterns of the care recipient. As a result, the nursing care diary input system according to the embodiment can efficiently process the voice input of the caregiver, optimize the nursing care diary, and propose nursing care responses.

[0070] The reception unit receives voice input from the caregiver. Voice input includes, but is not limited to, voice input using a microphone and voice input through a smartphone app. Specifically, in order to allow the caregiver to easily record the diary by voice while performing daily care work, it is recommended that the reception unit use a device with a high-sensitivity microphone and a noise canceling function. When using a smartphone app, the app has a function of converting voice input into text in real time and provides an interface that makes it easy for the caregiver to check the input content. In addition, when performing voice input, it is important to prepare a wealth of training data to improve the accuracy of the voice recognition engine so that it can handle the speed and accent of the caregiver's speech. Furthermore, in order to minimize misrecognition that may occur during voice input, the reception unit can register specific keywords and phrases in advance and improve the accuracy of voice recognition. This allows the caregiver to perform voice input without stress, and the diary recording work becomes more efficient.

[0071] The conversion unit converts the voice data received by the reception unit into text data using the generation AI. The generation AI converts the voice data into text data, for example, using a text generation AI (for example, LLM). The conversion unit can also convert the voice data into text data using the generation AI. For example, the generation AI converts the voice data into text data using a voice recognition technology. Specifically, the generation AI uses a voice recognition model to analyze the voice data and convert the spoken content into text with high accuracy. The voice recognition model is trained in advance with a large amount of voice data and corresponding text data, and is optimized to handle the caregiver's speech patterns and technical terms. Furthermore, the generation AI improves the conversion accuracy by removing noise from the voice data and extracting a clear voice signal. The generation AI can also generate easy-to-read text data by understanding the context of the voice data and inserting appropriate punctuation and line breaks. This allows the conversion unit to quickly and accurately convert the caregiver's voice input into text data and provide data necessary for subsequent processing.

[0072] The editing department re-edits the text data converted by the conversion department using the generation AI. Re-editing includes, for example, grammar correction, unification of expressions, and deletion of unnecessary information, but is not limited to such examples. For example, the generation AI corrects grammar using a grammar check tool. The generation AI can also unify expressions using natural language processing technology. Furthermore, the generation AI can also delete unnecessary information to create a document that is easy to read. Specifically, the generation AI automatically detects grammatical errors in the text data and makes appropriate corrections. For example, it checks and corrects the agreement of subject and predicate, the agreement of tense, and the appropriate placement of punctuation marks. In addition, the generation AI unifies different expressions that have the same meaning and maintains consistency throughout the document. For example, the expressions "provide meals" and "serve meals" are unified to "provide meals". Furthermore, the generation AI deletes redundant expressions and unnecessary information to create a concise and easy-to-read document. For example, the sentence "The weather was nice today, so I went for a walk" is simplified to "I went for a walk". This enables the editorial department to turn the converted text data into a high-quality nursing care diary.

[0073] The analysis unit uses the generation AI to analyze the information in the nursing diary re-edited by the editing unit. Examples of the analysis include, but are not limited to, data mining technology, statistical analysis, and machine learning algorithms. For example, the generation AI analyzes the changes in the physical condition and behavioral patterns of the care recipient based on the data in the past nursing diary. The generation AI can also grasp the situation of the care recipient and propose appropriate nursing care responses. Specifically, the generation AI analyzes the data in the nursing diary in chronological order to extract trends in the changes in the physical condition and behavioral patterns of the care recipient. For example, it analyzes data such as food intake, sleep time, and exercise amount to predict changes in physical condition. The generation AI can also use an anomaly detection algorithm to detect patterns that are different from the norm at an early stage and issue a warning to the caregiver. Furthermore, the generation AI derives the optimal nursing care method by comparing it with past data in order to propose nursing care responses according to the individual situation of the care recipient. For example, if the physical condition of the care recipient tends to deteriorate during a specific time period, it is suggested that special care be provided during that time period. This enables the analysis unit to perform advanced analysis of the data in the care diary, grasp the health condition of the person being cared for in real time, and support appropriate care responses.

[0074] The suggestion unit uses the generation AI to suggest care responses based on the information analyzed by the analysis unit. The suggestions include, but are not limited to, suggestions for care schedules and suggestions for improving care methods. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the health of the care recipient is deteriorating. The generation AI can also suggest appropriate care responses based on the behavioral patterns of the care recipient. Specifically, the generation AI automatically generates an optimal care schedule based on the health and behavioral data of the care recipient. For example, meal times, rehabilitation times, rest times, etc. are optimized to reduce the burden on the care recipient. In addition, the generation AI refers to the latest nursing care technologies and research results to suggest specific improvement measures for improving the care method. For example, if a specific rehabilitation method is not effective, another method is suggested. In addition, the generation AI predicts points of caution and risks in daily life based on the behavioral patterns of the care recipient and provides specific advice to the caregiver. As a result, the suggestion unit suggests specific care responses to keep the health of the care recipient in an optimal state, and high-quality care can be achieved while reducing the burden on the caregiver.

[0075] The conversion unit can convert the voice data into text data using the generation AI. The generation AI converts the voice data into text data using, for example, a text generation AI (for example, LLM). The generation AI can also convert the voice data into text data using voice recognition technology. For example, the generation AI takes voice data as input and outputs text data. The generation AI analyzes the content of the voice data and converts it into appropriate text data. As a result, the use of the generation AI improves the conversion accuracy of the voice data. The generation AI can also analyze, for example, the content of the voice data and correct grammar and expressions. The generation AI generates appropriate text data based on the content of the voice data. For example, the generation AI analyzes the content of the voice data and corrects grammar and standardizes expressions. As a result, the use of the generation AI improves the conversion accuracy of the voice data and can generate accurate text data.

[0076] The editorial department can use the generation AI to correct grammar or standardize expressions to create a well-organized document. The generation AI, for example, corrects grammar using a grammar check tool. The generation AI can also standardize expressions using natural language processing technology. For example, when correcting grammar, the generation AI uses a grammar check tool to detect and correct grammatical errors. In addition, when standardizing expressions, the generation AI uses natural language processing technology to standardize terms and apply style guides. As a result, the use of the generation AI improves the consistency and readability of the document. For example, when correcting grammar or standardizing expressions, the generation AI can also delete unnecessary information to create an easy-to-read document. When correcting grammar or standardizing expressions, the generation AI analyzes the contents of the document and makes appropriate corrections. As a result, the use of the generation AI improves the consistency and readability of the document, and a document that can be easily understood by other caregivers and medical staff can be generated.

[0077] The analysis unit can use the generation AI to perform a detailed analysis of changes in the physical condition or behavioral patterns of the care recipient based on data from the past nursing diary. The generation AI, for example, uses data mining technology to analyze data from the past nursing diary. The generation AI can also use statistical analysis to analyze changes in the physical condition and behavioral patterns of the care recipient. For example, the generation AI analyzes changes in the physical condition of the care recipient based on data from the past nursing diary. When analyzing the behavioral patterns of the care recipient, the generation AI uses a machine learning algorithm to identify the behavioral patterns. This makes it possible to accurately grasp the situation of the care recipient and propose appropriate care responses by using the generation AI. For example, the generation AI analyzes changes in the physical condition and behavioral patterns of the care recipient based on data from the past nursing diary and propose appropriate care responses. The generation AI uses data mining technology and statistical analysis when grasping the situation of the care recipient and proposing appropriate care responses. This makes it possible to accurately grasp the situation of the care recipient and propose appropriate care responses by using the generation AI.

[0078] The suggestion unit can suggest a care response to the care recipient using the generation AI. The generation AI, for example, suggests a care schedule. The generation AI can also suggest improvements to the care method. For example, the generation AI suggests that the frequency of rehabilitation should be reduced if the health of the care recipient is deteriorating. The generation AI can also suggest an appropriate care response based on the behavioral patterns of the care recipient. As a result, by using the generation AI, it is possible to quickly suggest an appropriate care response. For example, the generation AI analyzes changes in the health of the care recipient and behavioral patterns, and suggests an appropriate care response. The generation AI uses data mining technology and statistical analysis when grasping the situation of the care recipient and proposing an appropriate care response. As a result, by using the generation AI, it is possible to quickly suggest an appropriate care response.

[0079] The suggestion unit can notify the caregiver of the care response proposed by the generation AI. The generation AI notifies the caregiver of the suggestion by using, for example, a smartphone notification. The generation AI can also notify the caregiver of the suggestion by using an email notification. For example, the generation AI notifies the caregiver that the frequency of rehabilitation should be reduced because the health of the care recipient is deteriorating. The generation AI can also notify the caregiver of an appropriate care response based on the behavior pattern of the care recipient. In this way, by using the generation AI, it is possible to promptly notify the caregiver of an appropriate response. The generation AI notifies the caregiver of the suggestion by using, for example, a smartphone notification or an email notification. The generation AI notifies the caregiver of an appropriate care response based on the change in the health of the care recipient and the behavior pattern. In this way, by using the generation AI, it is possible to promptly notify the caregiver of an appropriate response.

[0080] The reception unit can estimate the caregiver's emotion and optimize the timing of voice input reception based on the estimated emotion of the caregiver. For example, when the caregiver is stressed, the reception unit delays the timing of voice input reception to provide time for the caregiver to relax. When the caregiver is relaxed, the reception unit can also immediately accept the voice input and promote smooth input. For example, when the caregiver is in a hurry, the reception unit advances the timing of voice input reception to allow the caregiver to input information quickly. This allows the burden on the caregiver to be reduced by adjusting the timing of voice input reception according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to execute emotion estimation.

[0081] The reception unit can analyze the past voice input history of the caregiver and select the optimal reception method. For example, the reception unit preferentially suggests a voice input method that the caregiver has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the past voice input history of the caregiver. For example, the reception unit analyzes the past voice input history of the caregiver and suggests the most efficient reception method. In this way, the optimal reception method can be provided by analyzing the past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the past voice input history of the caregiver to the generation AI and cause the generation AI to select the optimal reception method.

[0082] The reception unit can perform filtering based on the caregiver's current work situation and stress level when receiving the voice input. For example, when the caregiver is busy, the reception unit preferentially receives only important voice input. When the caregiver is relaxed, the reception unit can also receive all voice input and collect detailed information. For example, when the caregiver is stressed, the reception unit receives only simple voice input to reduce the burden. This makes it possible to reduce the burden on the caregiver by filtering the voice input according to the caregiver's work situation and stress level. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the caregiver's work situation and stress level to the generation AI and cause the generation AI to execute filtering.

[0083] The reception unit can estimate the caregiver's emotion and optimize the priority of the voice input to be received based on the estimated emotion of the caregiver. For example, when the caregiver is stressed, the reception unit preferentially receives important voice input. When the caregiver is relaxed, the reception unit can also receive all voice inputs equally. For example, when the caregiver is in a hurry, the reception unit preferentially receives voice inputs with high urgency. In this way, important information can be preferentially processed by determining the priority of the voice inputs according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to execute optimization of the priority of the voice inputs.

[0084] When receiving a voice input, the reception unit can preferentially receive a highly relevant input in consideration of the geographical location information of the caregiver. For example, when the caregiver is in a specific facility, the reception unit preferentially receives a voice input related to the facility. When the caregiver is moving, the reception unit can also preferentially receive a voice input related to the destination. For example, when the caregiver is at home, the reception unit preferentially receives a voice input related to the home. In this way, by considering the geographical location information of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to perform preferential reception of highly relevant input.

[0085] The reception unit can analyze the social media activity of the caregiver and receive related inputs when receiving the voice input. The reception unit, for example, preferentially receives related voice inputs based on information shared by the caregiver on social media. The reception unit can also preferentially receive voice inputs related to current interests from the social media activity of the caregiver. For example, the reception unit analyzes the social media activity of the caregiver and preferentially receives voice inputs including important information. In this way, by analyzing the social media activity of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to perform preferential reception of related inputs.

[0086] The conversion unit can estimate the caregiver's emotion and adjust the conversion accuracy of the voice data based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the conversion unit converts the voice data into text data with normal conversion accuracy. When the caregiver is stressed, the conversion unit can also increase the conversion accuracy to prevent erroneous conversion. For example, when the caregiver is in a hurry, the conversion unit prioritizes the conversion speed and quickly converts the voice data into text data. This makes it possible to prevent erroneous conversion and generate accurate text data by adjusting the conversion accuracy according to the emotion of the caregiver. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the conversion accuracy.

[0087] The conversion unit can optimize the conversion algorithm by considering the speech pattern and accent of the caregiver when converting the voice data. For example, the conversion unit learns the speech pattern of the caregiver and applies an optimal conversion algorithm. The conversion unit can also apply an algorithm to prevent erroneous conversion by considering the caregiver's accent. For example, the conversion unit adjusts the conversion algorithm according to the speech rate of the caregiver. As a result, the conversion accuracy is improved by considering the speech pattern and accent of the caregiver. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input data of the speech pattern and accent of the caregiver to the generation AI and cause the generation AI to optimize the conversion algorithm.

[0088] The conversion unit can improve conversion accuracy by referring to the caregiver's past speech history when converting voice data. For example, the conversion unit preferentially converts specific terms and phrases based on the caregiver's past speech history. The conversion unit can also learn frequently used words from the caregiver's past speech history to improve conversion accuracy. For example, the conversion unit analyzes the caregiver's past speech history and applies an algorithm to prevent erroneous conversion. As a result, the conversion accuracy is improved by referring to the past speech history. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input the caregiver's past speech history data to the generation AI and cause the generation AI to improve the conversion accuracy.

[0089] The conversion unit can estimate the caregiver's emotion and determine the priority of the text data to be converted based on the estimated emotion of the caregiver. For example, when the caregiver is stressed, the conversion unit preferentially converts important voice data into text data. When the caregiver is relaxed, the conversion unit can also convert all voice data into text data equally. For example, when the caregiver is in a hurry, the conversion unit preferentially converts urgent voice data into text data. This allows important information to be preferentially processed by determining the priority of text data according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the conversion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to execute the determination of the priority of the text data.

[0090] The conversion unit can adjust the conversion algorithm in consideration of the geographical location information of the caregiver when converting the voice data. For example, when the caregiver is in a specific facility, the conversion unit preferentially converts terms related to the facility. When the caregiver is on the move, the conversion unit can also preferentially convert terms related to the destination. For example, when the caregiver is at home, the conversion unit preferentially converts terms related to the home. In this way, by considering the geographical location information of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI, or may be performed without using AI. For example, the conversion unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to adjust the conversion algorithm.

[0091] The conversion unit can analyze the social media activity of the caregiver and preferentially convert related utterances when converting the voice data. The conversion unit preferentially converts related utterances based on, for example, information shared by the caregiver on social media. The conversion unit can also preferentially convert utterances related to current interests from the social media activity of the caregiver. For example, the conversion unit analyzes the social media activity of the caregiver and preferentially converts utterances containing important information. In this way, by analyzing the social media activity of the caregiver, highly relevant information can be preferentially processed. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using AI or may be performed without using AI. For example, the conversion unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to perform preferential conversion of related utterances.

[0092] The editing unit can estimate the caregiver's emotion and adjust the expression method of the document based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the editing unit edits the document using a normal expression method. When the caregiver is stressed, the editing unit can also edit the document using a concise and easy-to-understand expression method. For example, when the caregiver is in a hurry, the editing unit edits the document using an expression method that can be quickly understood. In this way, by adjusting the expression method of the document according to the emotion of the caregiver, an easy-to-read document can be generated. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editing unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the expression method of the document.

[0093] When editing a document, the editing unit can select an optimal editing method by referring to the caregiver's past editing history. For example, the editing unit preferentially uses frequently used expressions based on the caregiver's past editing history. The editing unit can also learn specific grammar and expressions from the caregiver's past editing history and select an optimal editing method. For example, the editing unit analyzes the caregiver's past editing history and selects an editing method for maintaining the consistency of the document. In this way, the optimal editing method can be provided by referring to the past editing history. A part or all of the above-mentioned processing in the editing unit may be performed, for example, using AI or may be performed without using AI. For example, the editing unit can input the caregiver's past editing history data to the generation AI and cause the generation AI to select the optimal editing method.

[0094] The editing unit can correct grammar and standardize expressions based on the caregiver's speech content when editing the document. The editing unit corrects grammar, for example, based on the caregiver's speech content. The editing unit can also standardize expressions based on the caregiver's speech content. For example, the editing unit makes corrections to maintain the consistency of the document based on the caregiver's speech content. As a result, the consistency of the document is improved by correcting grammar and standardizing expressions based on the speech content. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the caregiver's speech content data to the generation AI and cause the generation AI to correct grammar and standardize expressions.

[0095] The editing unit can estimate the caregiver's emotion and adjust the length of the document based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the editing unit edits the document to a normal length. When the caregiver is stressed, the editing unit can also edit a short and concise document. For example, when the caregiver is in a hurry, the editing unit edits a short document that focuses on the main points. This allows for the generation of an easy-to-read document by adjusting the length of the document according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editing unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the length of the document.

[0096] The editing unit can determine the priority of editing based on the submission time of the caregiver when editing the document. For example, the editing unit prioritizes editing when the submission deadline of the caregiver is approaching. The editing unit can also edit according to the normal editing schedule when the caregiver submits with plenty of time. For example, the editing unit adjusts the priority of editing based on the submission time of the caregiver. This enables efficient editing by determining the priority of editing based on the submission time. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the submission time data of the caregiver to the generation AI and cause the generation AI to determine the priority of editing.

[0097] The editing unit can improve the accuracy of editing by referring to the literature related to the caregiver when editing the document. For example, the editing unit complements the contents of the document by referring to the literature related to the caregiver. The editing unit can also learn appropriate expression methods from the literature related to the caregiver and reflect them in the document. For example, the editing unit makes corrections to maintain the consistency of the document based on the literature related to the caregiver. As a result, the accuracy of editing is improved by referring to the related literature. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the literature data related to the caregiver to the generation AI and cause the generation AI to perform improvement of the accuracy of editing.

[0098] The analysis unit can estimate the caregiver's emotion and adjust the display method of the analysis based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the analysis unit displays the analysis result in a normal display method. When the caregiver is stressed, the analysis unit can also display the analysis result using a simple and easy-to-understand display method. For example, when the caregiver is in a hurry, the analysis unit displays the analysis result using a display method that focuses on the main points. In this way, by adjusting the display method according to the emotion of the caregiver, it is possible to provide an easy-to-understand analysis result. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the display method.

[0099] During the analysis, the analysis unit can predict the current situation by referring to past nursing diary data. For example, the analysis unit predicts a change in the physical condition of the care recipient based on the past nursing diary data. The analysis unit can also predict the behavior pattern of the care recipient from the past nursing diary data. For example, the analysis unit predicts an appropriate nursing care response based on the current situation by referring to the past nursing diary data. In this way, the current situation can be accurately predicted by referring to the past data. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the past nursing diary data to the generation AI and cause the generation AI to execute a prediction of the current situation.

[0100] The analysis unit can analyze changes in physical condition and behavioral patterns based on the caregiver's speech content during analysis. The analysis unit, for example, analyzes changes in the physical condition of the care recipient based on the caregiver's speech content. The analysis unit can also analyze the behavioral patterns of the care recipient from the caregiver's speech content. For example, the analysis unit refers to the caregiver's speech content and analyzes appropriate care responses based on the care recipient's physical condition and behavior. As a result, the situation of the care recipient can be accurately grasped by analyzing based on the speech content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caregiver's speech content data to the generation AI and cause the generation AI to execute analysis of changes in physical condition and behavioral patterns.

[0101] The analysis unit can estimate the caregiver's emotion and adjust the importance of the analysis based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the analysis unit displays the analysis result with normal importance. When the caregiver is stressed, the analysis unit can also display important analysis results with priority. For example, when the caregiver is in a hurry, the analysis unit displays analysis results with high urgency with priority. This allows important information to be provided with priority by adjusting the importance according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the analysis unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the importance.

[0102] The analysis unit can analyze the change in the analysis based on the time of submission by the caregiver during the analysis. The analysis unit analyzes the change in the physical condition of the care recipient based on the time of the care diary submitted by the caregiver, for example. The analysis unit can also analyze the change in the behavior pattern of the care recipient from the time of submission by the caregiver. For example, the analysis unit refers to the time of submission by the caregiver and analyzes an appropriate care response. In this way, by analyzing the change based on the time of submission, it is possible to propose an appropriate care response. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the data of the submission time of the caregiver to the generation AI and cause the generation AI to execute the analysis of the change.

[0103] The analysis unit can perform the analysis by referring to the caregiver-related market data during the analysis. For example, the analysis unit analyzes changes in the physical condition of the care recipient based on the caregiver-related market data. The analysis unit can also analyze the behavioral pattern of the care recipient from the caregiver-related market data. For example, the analysis unit refers to the caregiver-related market data and analyzes appropriate care responses. In this way, by referring to the related market data, a more accurate analysis can be performed. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the caregiver-related market data to the generation AI and cause the generation AI to perform the analysis.

[0104] The suggestion unit can estimate the caregiver's emotion and adjust the expression method of the proposal based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the suggestion unit makes a suggestion using a normal expression method. When the caregiver is stressed, the suggestion unit can also make a suggestion using a simple and easy-to-understand expression method. For example, when the caregiver is in a hurry, the suggestion unit makes a suggestion using an expression method that can be quickly understood. In this way, by adjusting the expression method according to the emotion of the caregiver, an easy-to-understand suggestion can be provided. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the expression method.

[0105] At the time of proposal, the proposal unit can select the optimal proposal method by referring to the past proposal history of the caregiver. For example, the proposal unit preferentially uses a frequently used proposal method based on the past proposal history of the caregiver. The proposal unit can also learn a specific proposal method from the past proposal history of the caregiver and select the optimal proposal method. For example, the proposal unit analyzes the past proposal history of the caregiver and selects a method for maintaining the consistency of the proposal. In this way, the optimal proposal method can be provided by referring to the past proposal history. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the past proposal history data of the caregiver to the generation AI and cause the generation AI to select the optimal proposal method.

[0106] The suggestion unit can adjust the level of detail of the proposal based on the contents of the caregiver's speech when making a proposal. The suggestion unit makes a detailed proposal based on, for example, the contents of the caregiver's speech. The suggestion unit can also make a concise proposal from the contents of the caregiver's speech. For example, the suggestion unit refers to the contents of the caregiver's speech and makes adjustments to maintain the consistency of the proposal. As a result, it is possible to provide an appropriate proposal by adjusting the level of detail of the proposal based on the contents of the speech. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input the caregiver's speech content data to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0107] The suggestion unit can estimate the caregiver's emotion and determine the priority of the suggestions based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the suggestion unit makes suggestions with normal priority. When the caregiver is stressed, the suggestion unit can also give priority to important suggestions. For example, when the caregiver is in a hurry, the suggestion unit gives priority to suggestions with high urgency. In this way, important suggestions can be provided preferentially by determining the priority of the suggestions according to the emotion of the caregiver. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to execute the determination of the priority of the suggestions.

[0108] The suggestion unit can select the optimal suggestion method by considering the geographical location information of the caregiver when making a suggestion. For example, when the caregiver is in a specific facility, the suggestion unit can prioritize a suggestion related to the facility. When the caregiver is on the move, the suggestion unit can also prioritize a suggestion related to the destination. For example, when the caregiver is at home, the suggestion unit prioritizes a suggestion related to the home. In this way, by considering the geographical location information, it is possible to provide a highly relevant suggestion. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the geographical location information of the caregiver to the generation AI and cause the generation AI to select the optimal suggestion method.

[0109] At the time of making a proposal, the suggestion unit can adjust the means of the proposal by analyzing the social media activity of the caregiver. For example, the suggestion unit prioritizes relevant proposals based on information shared by the caregiver on social media. The suggestion unit can also prioritize proposals related to current interests from the social media activity of the caregiver. For example, the suggestion unit analyzes the social media activity of the caregiver and prioritizes proposals including important information. In this way, it is possible to provide highly relevant proposals by analyzing the social media activity. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI or may be performed without using AI. For example, the suggestion unit can input the social media activity data of the caregiver to the generation AI and cause the generation AI to adjust the means of the proposal.

[0110] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0111] When accepting the voice input of the caregiver, the reception unit can learn the past input patterns of the caregiver and suggest the optimal input method. For example, the reception unit preferentially suggests a voice input method that the caregiver has frequently used in the past. The reception unit can also select the optimal reception method for a specific time period from the past voice input history of the caregiver. In this way, the optimal reception method can be provided by analyzing the past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the past voice input history of the caregiver to the generation AI and cause the generation AI to select the optimal reception method.

[0112] The conversion unit can optimize the conversion algorithm by considering the speech pattern and accent of the caregiver when converting the voice data. For example, the conversion unit learns the speech pattern of the caregiver and applies an optimal conversion algorithm. The conversion unit can also apply an algorithm to prevent erroneous conversion by considering the caregiver's accent. As a result, the conversion accuracy is improved by considering the speech pattern and accent of the caregiver. A part or all of the above-mentioned processing in the conversion unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversion unit can input data of the speech pattern and accent of the caregiver to the generation AI and cause the generation AI to optimize the conversion algorithm.

[0113] When editing a document, the editing unit can select the optimal editing method by referring to the caregiver's past editing history. For example, frequently used expressions are used preferentially based on the caregiver's past editing history. The editing unit can also learn specific grammar and expressions from the caregiver's past editing history and select the optimal editing method. This makes it possible to provide the optimal editing method by referring to the past editing history. Some or all of the above-mentioned processing in the editing unit may be performed using, for example, AI, or may be performed without using AI. For example, the editing unit can input the caregiver's past editing history data to the generation AI and cause the generation AI to select the optimal editing method.

[0114] During the analysis, the analysis unit can predict the current situation by referring to past nursing diary data. For example, the analysis unit predicts changes in the physical condition of the care recipient based on the past nursing diary data. The analysis unit can also predict the behavioral pattern of the care recipient from the past nursing diary data. This makes it possible to accurately predict the current situation by referring to past data. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input past nursing diary data to a generation AI and cause the generation AI to predict the current situation.

[0115] At the time of proposal, the proposal unit can select the optimal proposal method by referring to the past proposal history of the caregiver. For example, based on the past proposal history of the caregiver, a frequently used proposal method is preferentially used. The proposal unit can also learn a specific proposal method from the past proposal history of the caregiver and select the optimal proposal method. In this way, the optimal proposal method can be provided by referring to the past proposal history. A part or all of the above-mentioned processing in the proposal unit may be performed, for example, using AI or may be performed without using AI. For example, the proposal unit can input the past proposal history data of the caregiver to the generation AI and cause the generation AI to select the optimal proposal method.

[0116] The reception unit can estimate the caregiver's emotion and optimize the timing of voice input reception based on the estimated emotion of the caregiver. For example, when the caregiver is stressed, the timing of voice input reception is delayed to provide time for the caregiver to relax. When the caregiver is relaxed, the reception unit can also immediately accept voice input and promote smooth input. This can reduce the burden on the caregiver by adjusting the timing of voice input reception according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to execute emotion estimation.

[0117] The conversion unit can estimate the caregiver's emotion and adjust the conversion accuracy of the voice data based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the conversion unit converts the voice data into text data with normal conversion accuracy. When the caregiver is stressed, the conversion unit can also increase the conversion accuracy to prevent erroneous conversion. This makes it possible to prevent erroneous conversion and generate accurate text data by adjusting the conversion accuracy according to the emotion of the caregiver. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the conversion unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the conversion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the conversion accuracy.

[0118] The editing unit can estimate the caregiver's emotions and adjust the expression method of the document based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the editing unit edits the document using a normal expression method. When the caregiver is stressed, the editing unit can also edit the document using a simple and easy-to-understand expression method. This allows the document to be generated as an easy-to-read document by adjusting the expression method of the document according to the emotion of the caregiver. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the editing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the editing unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the expression method of the document.

[0119] The analysis unit can estimate the caregiver's emotion and adjust the display method of the analysis based on the estimated caregiver's emotion. For example, when the caregiver is relaxed, the analysis result is displayed in a normal display method. When the caregiver is stressed, the analysis unit can also display the analysis result using a simple and easy-to-understand display method. This makes it possible to provide an easy-to-understand analysis result by adjusting the display method according to the caregiver's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the analysis unit can input the caregiver's emotion data to the generation AI and cause the generation AI to adjust the display method.

[0120] The suggestion unit can estimate the caregiver's emotion and adjust the expression method of the suggestion based on the estimated emotion of the caregiver. For example, when the caregiver is relaxed, the suggestion is made using a normal expression method. When the caregiver is stressed, the suggestion unit can also make a suggestion using a simple and easy-to-understand expression method. This makes it possible to provide an easy-to-understand suggestion by adjusting the expression method according to the emotion of the caregiver. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input the emotion data of the caregiver to the generation AI and cause the generation AI to adjust the expression method.

[0121] The process flow of the second embodiment will be briefly described below.

[0122] Step 1: The reception unit receives voice input from a caregiver. Voice input includes, for example, voice input using a microphone or voice input through a smartphone app. Step 2: The conversion unit converts the voice data received by the reception unit into text data using the generation AI. The generation AI converts the voice data into text data using, for example, a text generation AI (e.g., LLM) or a voice recognition technology. Step 3: The editorial department uses the generation AI to re-edit the text data converted by the conversion department. Re-editing includes correcting grammar, standardizing expressions, deleting unnecessary information, etc. The generation AI performs these processes using grammar checking tools and natural language processing technology. Step 4: The analysis department uses the generation AI to analyze the information in the nursing diary reedited by the editing department. The analysis includes data mining techniques, statistical analysis, and machine learning algorithms. The generation AI analyzes changes in the physical condition and behavioral patterns of the care recipient based on past nursing diary data. Step 5: The proposal unit uses the generation AI to propose care responses based on the information analyzed by the analysis unit. The proposals include suggestions for care schedules and suggestions for improving care methods. The generation AI proposes appropriate care responses when the care recipient's physical condition deteriorates or based on behavioral patterns.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0125] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0126] For example, the reception unit can receive voice input from the caregiver using the microphone 38B of the smart device 14. The conversion unit is realized by the specific processing unit 290 of the data processing device 12, and converts voice data into text data using a generation AI. The editing unit is realized by the specific processing unit 290 of the data processing device 12, and re-edits the text data using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes information in the care diary using a generation AI. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests care responses using a generation AI. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0127] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0128] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0134] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0137] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0142] For example, the reception unit can receive voice input from the caregiver using the microphone 238 of the smart glasses 214. The conversion unit is realized by the specific processing unit 290 of the data processing device 12, and converts voice data into text data using a generation AI. The editing unit is realized by the specific processing unit 290 of the data processing device 12, and re-edits the text data using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes information in the care diary using a generation AI. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests care responses using a generation AI. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0143] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0144] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0150] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0151] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0152] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0153] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0154] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0156] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0158] For example, the reception unit can receive voice input from the caregiver using the microphone 238 of the headset type terminal 314. The conversion unit is realized by the specific processing unit 290 of the data processing device 12, and converts voice data into text data using a generation AI. The editing unit is realized by the specific processing unit 290 of the data processing device 12, and re-edits the text data using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes information in the care diary using a generation AI. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests care responses using a generation AI. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0159] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0160] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0163] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0165] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0166] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0167] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0168] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0169] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0170] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0171] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0173] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0175] For example, the reception unit can receive voice input from the caregiver using the microphone 238 of the robot 414. The conversion unit is realized by the specific processing unit 290 of the data processing device 12, and converts voice data into text data using a generation AI. The editing unit is realized by the specific processing unit 290 of the data processing device 12, and re-edits the text data using a generation AI. The analysis unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes information in the care diary using a generation AI. The suggestion unit is realized by the specific processing unit 290 of the data processing device 12, and suggests care responses using a generation AI. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0176] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0177] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0178] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0179] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0180] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0181] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0184] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0185] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0186] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0187] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0188] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0189] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0190] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0191] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0192] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0193] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0194] (Appendix 1) a reception unit that receives voice input from a caregiver; a conversion unit that converts the voice data received by the reception unit into text data; an editing unit that re-edits the text data converted by the conversion unit; An analysis unit that analyzes information of the nursing care diary re-edited by the editing unit; A suggestion unit that proposes a care response based on the information analyzed by the analysis unit is provided. A system characterized by: (Appendix 2) The conversion unit is Converting voice data into text data using generative AI 2. The system of claim 1, (Appendix 3) The editorial department: Generative AI corrects grammar or standardizes expressions to produce a well-organized document 2. The system of claim 1, (Appendix 4) The analysis unit includes: Generative AI performs detailed analysis of changes in the care recipient's physical condition or behavioral patterns based on past care diary data 2. The system of claim 1, (Appendix 5) The suggestion unit, Generative AI proposes care responses to care recipients 2. The system of claim 1, (Appendix 6) The suggestion unit, Notify the caregiver of the care response suggested by generative AI 2. The system of claim 1, (Appendix 7) The reception unit is Estimating the caregiver's emotions and optimizing the timing of voice input based on the estimated emotions 2. The system of claim 1, (Appendix 8) The reception unit is Analyze the caregiver's past voice input history and select the optimal reception method 2. The system of claim 1, (Appendix 9) The reception unit is When accepting voice input, it filters it based on the caregiver's current workload and stress level. 2. The system of claim 1, (Appendix 10) The reception unit is Estimate the caregiver's emotions and optimize the priority of voice inputs based on the estimated emotions of the caregiver. 2. The system of claim 1, (Appendix 11) The reception unit is When accepting voice input, the system takes into account the caregiver's geographic location information to prioritize relevant input. 2. The system of claim 1, (Appendix 12) The reception unit is Analyze caregiver's social media activity and receive relevant input when receiving voice input 2. The system of claim 1, (Appendix 13) The conversion unit is Estimating the caregiver's emotions and adjusting the conversion accuracy of the voice data based on the estimated emotions of the caregiver 2. The system of claim 1, (Appendix 14) The conversion unit is When converting voice data, the conversion algorithm is optimized by taking into account the caregiver's speech patterns and accents. 2. The system of claim 1, (Appendix 15) The conversion unit is When converting voice data, the accuracy of the conversion is improved by referring to the caregiver's past speech history. 2. The system of claim 1, (Appendix 16) The conversion unit is Estimate the caregiver's emotions and determine the priority of text data to be converted based on the estimated caregiver's emotions. 2. The system of claim 1, (Appendix 17) The conversion unit is When converting voice data, the conversion algorithm is adjusted to take into account the caregiver's geographic location. 2. The system of claim 1, (Appendix 18) The conversion unit is When converting voice data, the system analyzes caregivers' social media activity and prioritizes conversion of relevant utterances. 2. The system of claim 1, (Appendix 19) The editorial department: Estimate the caregiver's emotions and adjust the way the document is expressed based on the estimated emotions of the caregiver 2. The system of claim 1, (Appendix 20) The editorial department: When editing a document, the system selects the optimal editing method by referring to the caregiver's past editing history. 2. The system of claim 1, (Appendix 21) The editorial department: When editing documents, grammar corrections and standardization of expressions are performed based on the content of the caregiver's speech. 2. The system of claim 1, (Appendix 22) The editorial department: Estimating the caregiver's emotions and adjusting the length of the document based on the estimated emotions of the caregiver 2. The system of claim 1, (Appendix 23) The editorial department: When editing documents, prioritize edits based on when the caregiver submitted them 2. The system of claim 1, (Appendix 24) The editorial department: When editing documents, refer to relevant literature for caregivers to improve editing accuracy. 2. The system of claim 1, (Appendix 25) The analysis unit includes: Estimate caregiver sentiment and adjust how analytics are displayed based on the estimated caregiver sentiment 2. The system of claim 1, (Appendix 26) The analysis unit includes: During analysis, past nursing diary data is referenced to predict the current situation. 2. The system of claim 1, (Appendix 27) The analysis unit includes: During the analysis, changes in physical condition and behavioral patterns are analyzed based on the caregiver's speech. 2. The system of claim 1, (Appendix 28) The analysis unit includes: Estimate the caregiver's emotions and adjust the importance of the analysis based on the estimated caregiver's emotions 2. The system of claim 1, (Appendix 29) The analysis unit includes: During analysis, analyze changes in analysis based on caregiver submission time 2. The system of claim 1, (Appendix 30) The analysis unit includes: When conducting the analysis, the relevant market data of caregivers is referred to. 2. The system of claim 1, (Appendix 31) The suggestion unit, Estimate the caregiver's emotions and adjust the way the suggestions are presented based on the estimated caregiver's emotions 2. The system of claim 1, (Appendix 32) The suggestion unit, When making a proposal, the system selects the optimal proposal method by referring to the caregiver's past proposal history. 2. The system of claim 1, (Appendix 33) The suggestion unit, When making suggestions, adjust the level of detail of the suggestions based on what the caregiver says 2. The system of claim 1, (Appendix 34) The suggestion unit, Estimate the caregiver's emotions and prioritize suggestions based on the estimated caregiver's emotions 2. The system of claim 1, (Appendix 35) The suggestion unit, When making a proposal, the optimal proposal method is selected taking into account the caregiver's geographic location information. 2. The system of claim 1, (Appendix 36) The suggestion unit, When making recommendations, analyze caregiver social media activity to tailor recommendations 2. The system of claim 1, [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives voice input from a caregiver; a conversion unit that converts the voice data received by the reception unit into text data; an editing unit that re-edits the text data converted by the conversion unit; An analysis unit that analyzes information of the nursing care diary re-edited by the editing unit; A suggestion unit that proposes a care response based on the information analyzed by the analysis unit is provided. A system characterized by:

2. The conversion unit is Converting voice data into text data using generative AI 2. The system of claim 1 .

3. The editorial department: Generative AI corrects grammar or standardizes expressions to produce a well-organized document 2. The system of claim 1 .

4. The analysis unit includes: Generative AI performs detailed analysis of changes in the physical condition or behavioral patterns of the care recipient based on past nursing diary data.

2. The system of claim 1 .

5. The suggestion unit, Using generative AI to suggest care responses to care recipients 2. The system of claim 1 .

6. The suggestion unit, Notify the caregiver of the care response suggested by the generated AI 2. The system of claim 1 .

7. The reception unit is Estimating the caregiver's emotions and optimizing the timing of voice input based on the estimated emotions 2. The system of claim 1 .

8. The reception unit is Analyze the caregiver's past voice input history and select the optimal reception method 2. The system of claim 1 .

9. The reception unit is When accepting voice input, it filters it based on the caregiver's current workload and stress level.

2. The system of claim 1 .

10. The reception unit is Estimate the caregiver's emotions and optimize the priority of voice inputs based on the estimated emotions of the caregiver.

2. The system of claim 1 .

Images