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

Abstract

In the present invention, an acquisition unit acquires diagnostic information indicating diagnostic results from a medical examination in which multiple items have been tested. An item extraction unit extracts, from the diagnostic information acquired by the acquisition unit, the diagnostic result of each item for all items. A video generation unit generates videos, each of which explains the diagnostic result of an item extracted by the item extraction unit. A merging unit merges the videos generated per item by the video generation unit and generates a video which explains the medical examination result.

Description

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

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

[0002] Patent Publication No. 2021-162943 proposes a digital medical information providing device that includes a receiving unit that receives medical professional information, video order information, medical record information, or patient information input into an operation terminal by a medical professional or patient, a memory unit that stores multiple videos related to diseases, a generation unit that generates videos related to diseases based on the medical professional information and patient information received by the receiving unit, and a video distribution unit that distributes the videos generated by the generation unit to the patient's communication terminal.

[0003] The technology of Patent Publication No. 2021-162943 generates videos for each stage of treatment for a patient's illness by combining multiple videos that correspond to items selected by a medical professional from multiple videos that have been stored in advance, but there is room for improvement in generating appropriate videos.

[0004] Furthermore, when multiple items are tested and displayed to the user as a single diagnostic result, simply looking at the diagnostic result table may not help the user to understand the diagnostic result. For example, in the case of a health checkup, for example, the diagnostic results of multiple items such as weight, blood sugar level, and cholesterol are tested and presented as a diagnostic result table, but simply looking at the diagnostic result table may not help the user to understand their own health condition.

[0005] Therefore, an object of the present disclosure is to provide an information processing device, an information processing method, and an information processing program that can present diagnostic results that are easier for the user to understand than when viewing a diagnostic result table.

[0006] In order to achieve the above object, an information processing device according to a first aspect of the present disclosure includes a processor, which acquires diagnostic information representing diagnostic results obtained by testing a plurality of items, generates a video from the diagnostic information explaining the diagnostic results for at least two or more of the items, and displays the generated video for each of the items.

[0007] An information processing device according to a second aspect of the present disclosure is the information processing device according to the first aspect, wherein the processor combines and displays the generated videos for each item, or displays the videos for each item in sequence.

[0008] An information processing device according to a third aspect of the present disclosure is the information processing device according to the first aspect, wherein the diagnostic result is a diagnostic result related to health.

[0009] An information processing device according to a fourth aspect of the present disclosure is the information processing device according to the first aspect, wherein the processor generates a video in which a predetermined virtual person or creature explains a diagnosis result.

[0010] An information processing device according to a fifth aspect of the present disclosure is the information processing device according to the fourth aspect, wherein the processor generates a video that explains the diagnosis result by audio.

[0011] An information processing device according to a sixth aspect of the present disclosure is the information processing device according to the fourth aspect, wherein the processor changes the display of the virtual person or creature depending on the item or the diagnosis result.

[0012] An information processing device according to a seventh aspect of the present disclosure is the information processing device according to the fourth aspect, wherein the processor hides a virtual person or creature depending on the item or the diagnosis result.

[0013] An information processing device according to an eighth aspect of the present disclosure is the information processing device according to the first aspect, wherein the processor inputs the diagnosis results for each item into a generative model to generate a video for each item.

[0014] An information processing device according to a ninth aspect of the present disclosure is an information processing device according to the eighth aspect, wherein the generative model is a generative AI model capable of generating data according to input data, and the processor uses the diagnostic results for each item to generate input information to be input to the generative AI model and inputs the information to the generative AI model, thereby generating a video for each item.

[0015] In an information processing device according to a tenth aspect of the present disclosure, in the information processing device according to the first aspect, the processor creates template videos corresponding to the results for each item in advance, and generates a video by selecting the template video corresponding to the diagnosis result.

[0016] An information processing device according to an eleventh aspect of the present disclosure is the information processing device according to the tenth aspect, wherein the template video is a video created in advance for each group by grouping a distribution of a plurality of results for each item.

[0017] An information processing device according to a twelfth aspect of the present disclosure is an information processing device according to the tenth aspect, in which, when there is no template video corresponding to the diagnostic result or when there are multiple template videos, the processor uses the diagnostic result for each item to generate input information to be input into a generative AI model capable of generating data according to the input data, and inputs the information into the generative AI model, thereby generating a video for each item.

[0018] An information processing device according to a thirteenth aspect of the present disclosure is the information processing device according to the first aspect, wherein, when the diagnostic result includes an image, the processor generates a video of an explanation related to the image in addition to the diagnostic result.

[0019] An information processing device according to a fourteenth aspect of the present disclosure is the information processing device according to the first aspect, wherein the processor displays a list of diagnostic results and changes the display mode of the portion explained using video to display the list.

[0020] An information processing device according to a fifteenth aspect of the present disclosure is the information processing device according to the first aspect, wherein the processor generates a moving image in accordance with whether or not to generate a moving image that is predetermined depending on the item or the diagnosis result.

[0021] An information processing method according to a sixteenth aspect of the present disclosure includes acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items, generating a video from the diagnostic information that explains the diagnostic results for at least two or more items, and performing a process of displaying the generated video for each item.

[0022] An information processing program according to a seventeenth aspect of the present disclosure is an information processing program for causing a computer to execute processing including acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items, generating a video explaining the diagnostic results for at least two or more items from the diagnostic information, and displaying the generated video for each item.

[0023] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and an information processing program that can present diagnostic results that are easier for the user to understand than when viewing a diagnostic result table.

[0024] 1 is a diagram illustrating an example of a schematic configuration of an information processing system according to the present embodiment. FIG. 2 is a block diagram illustrating the configuration of the main electrical parts of a client terminal and a server of the information processing system according to the present embodiment. FIG. 3 is a functional block diagram illustrating the functional configuration of a server in the information processing system according to the present embodiment. FIG. 4 is a flowchart illustrating an example of the flow of processing performed by the server of the information processing system according to the present embodiment. FIG. 5 is a diagram illustrating an example of generation of a video for each health checkup item by a video generation unit and combination of the videos by a combination unit. FIG. 6 is a diagram illustrating a case where the video generation unit uses a template video created in advance. FIG. 7 is a diagram specifically illustrating a case where the video generation unit uses a generative model when generating a video explaining a diagnosis result. FIG. 8 is a diagram illustrating an example of generating only audio. FIG. 9 is a diagram illustrating an example of generating a template video for a complex item (cholesterol). FIG. 10 is a diagram illustrating an example of dividing a detailed item into normal and abnormal detailed items and highlighting the corresponding parts. FIG. 11 is a diagram illustrating an example of synchronizing the content of a video with the content of a document explaining visceral fat test results. FIG. 12 is a diagram illustrating a case where two videos are combined. FIG. 13 is a diagram illustrating an example of combining sentences to form one video. FIG. 14 is a diagram illustrating a general-purpose personal computer.

[0025] An example of an embodiment of the present invention will be described in detail below with reference to the drawings. Note that the present invention is not limited to this embodiment. Fig. 1 is a diagram showing an example of the schematic configuration of an information processing system according to this embodiment.

[0026] 1, an information processing system 10 according to this embodiment includes a client terminal 12 and a server 14. The client terminal 12 and the server 14 are each connected to a communication line 16 and are capable of communicating with each other via the communication line 16.

[0027] Examples of the communication line 16 include the Internet, a local area network (LAN), a wide area network (WAN), etc. Although Fig. 1 shows an example in which a plurality of client terminals 12 (two in Fig. 1) are provided, the number of client terminals 12 may be a single one or three or more. The client terminal 12 may be a personal computer, or a mobile terminal such as a tablet terminal or a smartphone.

[0028] In the information processing system 10 according to this embodiment, the server 14 uses diagnostic information representing the diagnostic results for each of a plurality of test items to generate a video explaining the diagnostic results for each item, and combines the generated videos for each item to generate a single video explaining the diagnostic results. The server 14 then transmits the generated video to the client terminal 12, thereby presenting the video explaining the diagnostic results of the health check to the user.

[0029] In this embodiment, an example of a diagnosis will be described in which a health diagnosis is applied. In the following description, a health diagnosis may be referred to as a medical checkup. In addition, in this disclosure, each test item of a medical checkup (e.g., total cholesterol, triglycerides, HDL cholesterol, LDL cholesterol, non-HDL cholesterol, etc.) will be referred to as a detailed item, and the items into which the detailed items are classified (e.g., cholesterol, blood sugar level / diabetes, visceral fat, etc.) will be simply referred to as an item.

[0030] 2 is a block diagram showing the main electrical configuration of the client terminal 12 and the server 14 of the information processing system 10 according to this embodiment. Since the client terminal 12 and the server 14 have a general computer configuration, the following description will be given using the server 14 as a representative.

[0031] The server 14 includes a CPU (Central Processing Unit) 14A (an example of a processor), a ROM (Read Only Memory) 14B, a RAM (Random Access Memory) 14C, a storage 14D, an operation unit 14E, a display unit 14F, and a communication I / F (interface) unit 14G. The CPU 14A controls the overall operation of the server 14. The ROM 14B stores various control programs and / or various parameters in advance. The RAM 14C is used as a work area when the CPU 14A executes various programs. The storage 14D stores various data and / or application programs. The operation unit 14E is used to input various information. The display unit 14F is used to display various information. The communication I / F unit 14G is connectable to external devices and transmits and receives various data to and from the external devices. The above components of the client terminal 12 are electrically connected to each other via a system bus 14H. In the server 14 according to the present embodiment, the storage 14D is used as a storage unit, but this is not limiting and other non-volatile storage units such as a hard disk and / or a flash memory may also be used.

[0032] With the above configuration, the server 14 according to this embodiment uses the CPU 14A to access the ROM 14B, RAM 14C, and storage 14D, to obtain various data via the operation unit 14E, and to display various information on the display unit 14F. The server 14 also uses the CPU 14A to control the transmission and reception of various data via the communication I / F unit 14G.

[0033] The information processing system 10 according to this embodiment realizes the functions shown in Fig. 3 by causing the CPU 14A of the server 14 to load an information processing program stored in advance in the ROM 14B into the RAM 14C and execute the program. Fig. 3 is a functional block diagram showing the functional configuration of the server 14 in the information processing system 10 according to this embodiment.

[0034] As shown in FIG. 3, the server 14 in the information processing system 10 according to this embodiment has the functions of an acquisition unit 20, an item extraction unit 22, a video generation unit 24, and a combination unit 26.

[0035] The acquisition unit 20 acquires diagnostic information representing the diagnostic results of a plurality of tests performed on a medical examination item. For example, diagnostic information created at a medical examination center (not shown) may be acquired via a communication line, or diagnostic information stored in advance in a database (DB) 28 may be acquired from the DB 28. As an example of the diagnostic information, data in a portable document format (PDF) that allows text search is applied. Note that hereinafter, the diagnostic information may also be referred to as a document.

[0036] The item extraction unit 22 extracts each item of diagnostic information from the diagnostic information acquired by the acquisition unit 20, and extracts a diagnostic result for each item. For example, by extracting items such as cholesterol, blood sugar level / diabetes, and visceral fat from the diagnostic information as diagnostic result items, the item extraction unit 22 extracts a diagnostic result for each item.

[0037] The video generation unit 24 generates a video explaining the diagnosis results for each item extracted by the item extraction unit 22. The video may be generated, for example, by inputting the diagnosis results for each item extracted by the item extraction unit 22 into a generative model to generate a video for each item. Specifically, a prompt requesting the generation of a video explaining the diagnosis results may be generated as input information to a generative AI model capable of generating data according to input data, and the prompt may then be input to the generative AI model to generate the video. The video may also be generated in two stages. For example, instead of generating the video all at once, a prompt requesting the generation of text to explain the diagnosis results for each extracted item may first be generated and input into an LLM (Large Language Model) to generate text for the explanatory video. The text may then be used to generate a prompt requesting the generation of a video, which may then be input into the generative AI model to generate the video. Note that, since a predetermined explanation may be provided for some items, multiple videos corresponding to the results may be created in advance and stored in the DB 28, etc., and a video may be generated by selecting a template video corresponding to the diagnosis result. The video generating unit 24 may generate a video for all items, or may generate a video for at least two or more items.

[0038] The combining unit 26 combines the videos for each item generated by the video generating unit 24 to generate a video explaining the results of the health check. This makes it possible to display a video explaining the results of the health check, in which the videos for each item are combined. Note that the combining unit 26 may be omitted, and videos explaining the diagnosis results for at least two or more items may be generated and displayed in order.

[0039] Next, specific processing performed by the server 14 of the information processing system 10 configured as described above will be described. Fig. 4 is a flowchart showing an example of the flow of processing performed by the server 14 of the information processing system 10 according to this embodiment. The processing in Fig. 4 starts, for example, when an instruction is given to generate a video of the medical checkup results.

[0040] In step 100, the CPU 14A acquires diagnostic information and proceeds to step 102. That is, the acquisition unit 20 acquires diagnostic information representing the diagnostic results of tests performed on multiple items in a health checkup. For example, the diagnostic information may be acquired from a health checkup center via the communication line 16, or may be acquired from diagnostic information previously stored in the DB 28.

[0041] In step 102, the CPU 14A extracts the items and the diagnostic results for each item, and then proceeds to step 104. That is, the item extraction unit 22 extracts each item of diagnostic information from the diagnostic information acquired by the acquisition unit 20, and extracts the diagnostic results for each item. For example, the items of the diagnostic results, such as cholesterol, blood sugar level / diabetes, visceral fat, etc., are extracted, and the diagnostic results for each item are extracted from the diagnostic information.

[0042] In step 104, the CPU 14A performs video generation processing and proceeds to step 106. In the video generation processing, the video generation unit 24 generates a video that explains the diagnosis result for each item extracted by the item extraction unit 22. The video generation unit 24 may generate the video using a generative model such as LLM and / or generative AI. Alternatively, a template video may be generated in advance and a template video may be selected according to the diagnosis result. Alternatively, a generative model may be used to generate a video for a complex item including multiple detailed items, and a pre-created template video may be selected for a simple item.

[0043] In step 106, the CPU 14A combines the videos for each item to generate one video, and then the series of processes is completed. That is, the combining unit 26 combines the videos for each item generated by the video generating unit 24 to generate a video that explains the results of the health check.

[0044] By performing processing in this manner, the server 14 can generate a video explaining the diagnostic results of the health check, making it possible to present diagnostic results that are easier for the user to understand than when viewing a diagnostic result table.

[0045] The following describes the processing performed by the information processing system 10 according to this embodiment, using a specific example.

[0046] FIG. 5 is a diagram for explaining an example of the generation of a video for each medical checkup item by the video generation unit 24 and the combination of the videos by the combination unit 26.

[0047] The video generator 24 extracts each medical checkup item and the diagnosis result for each item from the diagnostic information such as PDF etc. For example, in the example of Fig. 5, items such as "Introduction", "Cholesterol", "Blood Sugar Level / Diabetes", "Visceral Fat", etc. and the diagnosis results are extracted from the diagnostic information.

[0048] 5, for the "Introduction" item, a prompt is generated using the overall result and input to the generative AI model, generating a video explaining the diagnosis result for "Introduction." For example, a video is generated in which an avatar of a virtual person and / or creature explains, "Your score is slightly off the standard value, but this will not affect your daily life."

[0049] For the "cholesterol" item, a prompt is generated using the lipid results and input into the generative AI model to generate a video explaining the "cholesterol" diagnosis. For example, a video is generated in which an avatar explains, "Your LDL and trigreid levels are normal... but your HDL is low and needs improvement..."

[0050] For the "Blood Glucose Level / Diabetes" item, an animation is selected from a template created in advance. In the example of Fig. 5, a template animation is selected that explains, for example, "Your HbA1c is a little high..." depending on the diagnosis result.

[0051] For the item "visceral fat," an animation is also selected from templates created in advance. In the example of Fig. 5, a template animation that explains "It's normal..." or the like is selected according to the diagnosis result.

[0052] Then, the combining unit 26 combines the generated videos for each item to generate one explanatory video.

[0053] FIG. 6 is a diagram for explaining a case where the video generating unit 24 uses a template video created in advance.

[0054] If the diagnosis results for the health checkup items are simple, an avatar explanatory video corresponding to the diagnosis results may be created in advance and stored in DB 28, and a template video corresponding to the diagnosis results may be selected.

[0055] In the example of Figure 6, three template videos are created in advance for the results of the visceral fat item, and a template for the pre-created avatar video is selected according to the document of the visceral fat result. Figure 6 shows a case where a template video indicating that the visceral fat value is normal, a template video indicating that the visceral fat value is slightly higher than the standard, and a template video indicating that the visceral fat value is significantly higher than the standard value are created in advance, and the visceral fat result is normal. In addition, in the example of Figure 6, a template video explaining that the avatar is normal is selected, and an avatar explanatory video is combined with the result document of the health checkup person to create a video for visceral fat.

[0056] In this way, when the diagnostic results are simple, the processing load for creating a video explaining the diagnostic results can be reduced by creating a template video in advance.

[0057] 7 is a diagram specifically illustrating a case where the video generator 24 uses a generative model when generating a video explaining a diagnosis result. In the example of FIG. 7, a video is generated for the item of cholesterol.

[0058] The video generation unit 24 generates prompts to be input to the generated AI model from the diagnosis results for each item extracted by the item extraction unit 22. For example, if the diagnosis results show that the bad cholesterol and triglycerides are normal and the good cholesterol is lower than normal, the following prompts are generated:

[0059] "Generate an advice sentence for the following results: LDL cholesterol is normal, Trigresroid is normal, and HDL cholesterol is lower than normal."

[0060] The generated prompt is input to the LLM to generate text for the explanatory video. In the example of Figure 7, the LLM generates the sentence "LDL and Trigresroid are normal... but HDL is low and needs improvement...".

[0061] An avatar explanatory video is generated by generating a prompt for generating an avatar video using the text for the explanatory video generated by the LLM and inputting the prompt into the generative AI model. For example, an avatar explanatory video is generated by generating a prompt such as "Create a video in which an avatar explains, 'LDL and Trigresroid are normal... but HDL is low and needs improvement...'" and inputting the prompt into the generative AI model.

[0062] The result document of the medical examinee and the generated avatar explanatory video are then combined to create a video explaining the diagnosis result for the item (cholesterol in the example of FIG. 7).

[0063] Note that since generating an avatar is time-consuming and costly, only audio may be generated. For example, the avatar may be hidden depending on the item or diagnosis result. Specifically, since generating an avatar requires a generation processing time by the generation AI model, the avatar may be hidden depending on the processing time by the generation AI model, such as generating and displaying avatars only for items with poor diagnosis results. Alternatively, for complex items with multiple detailed items, the document content is more important than the avatar, so the avatar may be hidden, the document may be enlarged, and only audio may be displayed in a natural manner. Figure 8 shows an example of generating only audio.

[0064] The example of Fig. 8 shows an example in which only audio is generated for the cholesterol diagnosis result described above. That is, the video generator 24 generates a prompt similar to that shown in Fig. 7 and inputs it into the LLM to generate text for an explanatory video, and then generates only audio based on the text.

[0065] The video generator 24 then synthesizes the document showing the diagnosis result of the examinee with only the generated voice to create a video explaining the diagnosis result for the item (cholesterol in the example of FIG. 8 ). At this time, instead of displaying the avatar video, the display of the health check data may be enlarged, as shown in FIG. 8 .

[0066] The display of the avatar may also be changed depending on the item or the diagnosis result. For example, if the diagnosis result is easier to understand when displayed in a large graphic, the avatar may be displayed small or may not be displayed at all. Furthermore, for an item where the diagnosis result should be conveyed using the avatar's facial expressions and / or facial movements, the avatar may be displayed larger than a predetermined size that is normally displayed. Furthermore, the display of the avatar may be changed in various ways, such as displaying a bright smiling avatar when the diagnosis result is good and an angry avatar when the diagnosis result is bad.

[0067] Furthermore, the video may be generated according to a predetermined setting for whether or not to generate a video depending on the item or the diagnosis result. For example, as described above, in the case of a complex item, no video may be generated. Alternatively, if the diagnosis result is metabolic syndrome, videos may be generated only for users suspected of having metabolic syndrome, and no videos may be generated for users whose numerical values ​​indicate that they are clearly underweight.

[0068] Furthermore, when generating template videos for complex items with multiple detailed items, examinees may be grouped based on the distribution of their test results to date, and an explanatory avatar video for that group may be generated as a template. For example, as shown in FIG. 9 , if a certain examinee's results indicate that they belong to a certain group, a pre-generated video is used. On the other hand, if they do not belong to a certain group or belong to multiple groups, a video explaining the diagnosis result is generated each time based on the diagnosis result. This reduces the amount of avatar videos generated each time as much as possible. FIG. 9 is a diagram illustrating an example of generating template videos for a complex item (cholesterol). While FIG. 9 shows a two-dimensional example, complex items have many test items and are actually multidimensional.

[0069] If there is no template video corresponding to the diagnosis result, or if there are multiple template videos, a video for each item may be generated by generating and inputting a prompt to be input into the generation AI model using the diagnosis result for each item. In other words, in addition to when there is no template video, if there are multiple template videos, an appropriate template video may not be selected, so an appropriate video can be generated by generating a video that explains the diagnosis result.

[0070] In addition, for complex items with multiple detailed items, the detailed items may be divided into normal detailed items and abnormal detailed items, and videos of each may be generated with the relevant parts highlighted. Figure 10 is a diagram showing an example of dividing the detailed items into normal detailed items and abnormal detailed items and highlighting the relevant parts.

[0071] In this case, when extracting multiple items, the item extraction unit 22 extracts the positions of detailed items within the items. For example, as shown in Figure 10, the coordinate values ​​of the results of each detailed item on the document are detected. In the example of Figure 10, the y coordinate of total cholesterol is 350-600, the y coordinate of triglycerides is 600-850, the y coordinate of HDL cholesterol is 850-950, the y coordinate of LDL cholesterol is 950-1250, and the y coordinate of non-HDL cholesterol is 1250-1550.

[0072] The video generation unit 24 generates a comment summarizing the detailed items that are normal. In the example of FIG. 10 , total cholesterol and HDL cholesterol are set as detailed items that are normal, and the generated comment summarizing the detailed items is, "Total cholesterol and HDL cholesterol are fine. Please maintain them as they are." For this comment, for example, as described above, text for the explanatory video is generated using the LLM, and an avatar explanatory video is generated using the generation AI model.

[0073] The video generation unit 24 also generates a comment summarizing the abnormal detailed items. In the example of FIG. 10 , triglycerides, LDL cholesterol, and non-HDL cholesterol are set as abnormal detailed items, and the generated comment summarizing the detailed items is, "Caution is required for triglycerides, LDL cholesterol, and non-HDL cholesterol. In this case..." For this comment, for example, as described above, text for the explanatory video is generated using the LLM, and an avatar explanatory video is generated using the generative AI model.

[0074] The video generating unit 24 then combines the generated videos for each item to generate a video that explains the diagnosis result for each item. At this time, the document may be displayed as a list of the diagnosis results, and the display mode may be changed by highlighting or pointing to a position corresponding to the document explanation based on the coordinate values ​​of the results of each detailed item extracted by the item extracting unit 22, as shown in Figure 10.

[0075] By generating a video in this manner, the video generating unit 24 can generate an explanatory video that is divided into items with no abnormality and items with an abnormality, making it possible to provide an easy-to-understand explanation.

[0076] Furthermore, by changing the display mode of the position corresponding to the explanation, it becomes easier to understand what is being explained.

[0077] Although an example of generating a video by dividing each detailed item into whether or not there is an abnormality has been described above, a video may also be generated by dividing each item of the health check result into whether or not there is an abnormality, rather than by dividing each detailed item into whether or not there is an abnormality.

[0078] Furthermore, it is preferable that the video generating unit 24 synchronizes the contents of the document with the contents of the video for each item. Fig. 11 is a diagram showing an example in which the contents of the document explaining the test results of visceral fat are synchronized with the contents of the video.

[0079] In the example of Figure 11, the document showing the visceral fat test results includes a section for the health check results (images), a section for the health check results (numerical values), a section for advice on the health check results, and an explanation of the test measurement method.

[0080] In the document displayed during the explanation, the contents are divided into sections such as medical examination results (numerical values), medical examination results (images, graphs, etc.), advice on the results, and test measurement methods, and each section has its coordinates.

[0081] The video generation unit 24 generates advice sentences for each content, measures the corresponding video and audio time, and associates the measurement time with the corresponding document. The video and audio of the overall explanation, "We will inform you of the visceral fat test results," is then output, and the entire document is displayed. Next, the video and audio of the medical checkup result "numerical value" is output, and the corresponding medical checkup result "numerical value" is displayed by enlarging and / or highlighting. Next, the video and audio of the medical checkup result "image" is output, and the medical checkup result (image) is displayed as the corresponding document. Next, the video and audio of the medical checkup method, "The visceral fat area will be calculated using a CT scan," is output, and the corresponding document is displayed as an explanation of the test measurement method. Finally, the video and audio of advice, "Continue to watch your weight," is output, and the corresponding document is displayed as the advice on the medical checkup result.

[0082] The method of joining videos may be to simply join two videos together, or to join sentences together to form one video.

[0083] When simply joining avatar videos, the transition time between the two videos is known, but joining the avatar videos requires video editing. FIG. 12 is a diagram illustrating joining two videos. In the example of FIG. 12, an avatar video and a corresponding document are displayed in which the avatar explains, "Your total cholesterol and HDL cholesterol are fine. Please maintain them as they are." Then, an avatar video and a corresponding document are displayed in which the avatar explains, "You need to be careful about triglycerides, LDL cholesterol, and non-HDL cholesterol. In this case..."

[0084] On the other hand, when combining sentences to create a single video, multiple sentences created using LLM are combined to generate a prompt, which is then input into a generative AI model to generate an avatar video. In this case, it is necessary to obtain the video time between the two sentences and switch the document to be displayed. FIG. 13 is a diagram showing an example of combining sentences to create a single video. The example in FIG. 13 shows an example of combining two sentences to display an avatar video and a corresponding document that explains, "Your total cholesterol and HDL cholesterol levels are fine. Please maintain them as they are. Caution is required for triglycerides, LDL cholesterol, and non-HDL cholesterol. In this case..."

[0085] In the above embodiment, a medical checkup is used as an example of diagnosis, but the diagnosis is not limited to a medical checkup. For example, a diagnosis having a diagnosis result for each item, such as a road inspection or an X-ray inspection, can be applied.

[0086] Furthermore, in the above embodiment, the information processing system 10 is described as including the client terminal 12 and the server 14, but as shown in FIG. 14, a single device such as a general-purpose personal computer 50 equipped with a display unit 50H and an operation unit 50S such as a keyboard and / or a mouse may also be applied as the information processing system.

[0087] Furthermore, the various processes performed by the CPU in the above embodiments by executing software (programs) may be executed by a computer equipped with various processors other than a CPU. Examples of such processors include programmable logic devices (PLDs) (such as field-programmable gate arrays (FPGAs)) whose circuit configuration can be changed after manufacture, and dedicated electrical circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed to execute specific processes. The various processes may be executed by one of these processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

[0088] In the above embodiment, the various programs are pre-stored (installed) in the ROM 20B, but the present invention is not limited to this. The various programs may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The various programs may also be downloaded from an external information processing device or the like via a network.

[0089] The program of the present disclosure can be provided as a program product.

[0090] This includes all manner of products for providing a program. For example, program products include programs provided over a network such as the Internet, and non-transitory computer-readable recording media such as CD-ROMs and DVDs that store the programs.

[0091] Furthermore, the configuration, operation, etc. of the information processing system 10 described in the above embodiment are merely examples, and it goes without saying that they can be modified according to the circumstances within the scope of the present disclosure.

[0092] The following additional notes are provided regarding the above-described embodiments.

[0093] (Supplementary Note 1) An information processing device comprising a processor, wherein the processor acquires diagnostic information representing diagnostic results obtained by testing a plurality of items, generates a video from the diagnostic information to explain the diagnostic results for at least two or more of the items, and displays the generated video for each of the items.

[0094] (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the processor combines and displays the generated videos for each of the items, or displays the videos for each of the items in order.

[0095] (Supplementary Note 3) The information processing device according to Supplementary Note 1 or Supplementary Note 2, wherein the diagnostic result is a diagnostic result related to health.

[0096] (Supplementary Note 4) The information processing device according to any one of Supplementary Notes 1 to 3, wherein the processor generates a video in which a predetermined virtual person or creature explains the diagnosis result.

[0097] (Supplementary Note 5) The information processing device according to Supplementary Note 4, wherein the processor generates a video that explains the diagnosis result by audio.

[0098] (Supplementary Note 6) The information processing device according to Supplementary Note 4, wherein the processor changes the display of the virtual person or creature depending on the item or the diagnosis result.

[0099] (Supplementary Note 7) The information processing device according to Supplementary Note 4, wherein the processor hides the virtual person or creature depending on the item or the diagnosis result.

[0100] (Supplementary Note 8) The information processing device according to any one of Supplementary Notes 1 to 7, wherein the processor generates the video for each of the items by inputting the diagnosis result for each of the items into a generative model.

[0101] (Supplementary Note 9) The information processing device described in Supplementary Note 8, wherein the generative model is a generative AI model capable of generating data according to input data, and the processor uses the diagnostic results for each of the items to generate input information to be input to the generative AI model, and inputs the input information to the generative AI model, thereby generating the video for each of the items.

[0102] (Supplementary Note 10) The information processing device according to any one of Supplementary Notes 1 to 9, wherein the processor creates a template video corresponding to the results for each of the items in advance, and generates a video by selecting the template video corresponding to the diagnosis result.

[0103] (Supplementary Note 11) The information processing device according to Supplementary Note 10, wherein the template video is a video created in advance for each group by grouping a distribution of a plurality of results for each of the items.

[0104] (Supplementary Note 12) The information processing device according to Supplementary Note 10 or Supplementary Note 11, wherein when there is no template video corresponding to the diagnosis result or when there are multiple template videos, the processor uses the diagnosis result for each item to generate input information to be input to a generative AI model capable of generating data according to input data, and inputs the input information to the generative AI model, thereby generating the video for each item.

[0105] (Supplementary Note 13) The information processing device according to any one of Supplementary Notes 1 to 12, wherein, when the diagnostic result includes an image, the processor generates, in addition to the diagnostic result, a video of an explanation related to the image.

[0106] (Supplementary Note 14) The information processing device according to any one of Supplementary Notes 1 to 13, wherein the processor displays a list of the diagnostic results and changes a display mode of the portion explained by the video to display the list.

[0107] (Supplementary Note 15) The information processing device according to any one of Supplementary Notes 1 to 14, wherein the processor generates the moving image in accordance with whether or not to generate the moving image, which is predetermined depending on the item or the diagnosis result.

[0108] (Supplementary Note 16) An information processing method including: acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items; generating a video explaining the diagnostic results for at least two or more of the items from the diagnostic information; and displaying the generated video for each of the items.

[0109] (Supplementary Note 17) An information processing program for causing a computer to execute a process including: acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items; generating a video from the diagnostic information that explains the diagnostic results for at least two or more of the items; and displaying the generated video for each of the items.

[0110] In the above, "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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

Claims

1. An information processing device comprising a processor, which acquires diagnostic information representing diagnostic results obtained by testing a plurality of items, generates a video from the diagnostic information explaining the diagnostic results for at least two or more of the items, and displays the generated video for each of the items.

2. The information processing device according to claim 1, wherein the processor combines and displays the generated videos for each of the items, or displays the videos for each of the items in order.

3. The information processing device according to claim 1, wherein the diagnostic result is a diagnostic result related to health.

4. The information processing device according to claim 1, wherein the processor generates a video in which a predetermined virtual person or creature explains the diagnosis result.

5. The information processing device according to claim 4, wherein the processor generates a video that explains the diagnosis result by audio.

6. The information processing device according to claim 4, wherein the processor changes the display of the virtual person or creature depending on the item or the diagnosis result.

7. The information processing device according to claim 4, wherein the processor hides the virtual person or creature depending on the item or the diagnosis result.

8. The information processing device according to claim 1, wherein the processor generates the video for each of the items by inputting the diagnostic results for each of the items into a generative model.

9. The information processing device described in claim 8, wherein the generative model is a generative AI model capable of generating data according to input data, and the processor uses the diagnostic results for each of the items to generate input information to be input to the generative AI model and inputs the information to the generative AI model, thereby generating the video for each of the items.

10. The information processing device according to claim 1, wherein the processor creates a template video corresponding to the results for each of the items in advance, and generates a video by selecting the template video corresponding to the diagnosis result.

11. The information processing device according to claim 10, wherein the template video is a video created in advance for each group by grouping the distribution of a plurality of results for each of the items.

12. The information processing device described in claim 10, wherein, if there is no template video corresponding to the diagnostic result or if there are multiple template videos, the processor uses the diagnostic result for each item to generate input information to be input into a generative AI model capable of generating data according to input data, and inputs the input information into the generative AI model, thereby generating the video for each item.

13. The information processing device according to claim 1, wherein, when the diagnostic result includes an image, the processor generates a video of an explanation related to the image in addition to the diagnostic result.

14. The information processing device according to claim 1, wherein the processor displays a list of the diagnostic results and changes the display mode of the portion explained by the video to display the list.

15. The information processing device according to claim 1, wherein the processor generates the video in accordance with a predetermined determination of whether or not to generate the video depending on the item or the diagnosis result.

16. An information processing method comprising: acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items; generating a video explaining the diagnostic results for at least two or more of the items from the diagnostic information; and displaying the generated video for each of the items.

17. An information processing program for causing a computer to execute a process including: acquiring diagnostic information representing diagnostic results obtained by testing a plurality of items; generating a video from the diagnostic information that explains the diagnostic results for at least two or more of the items; and displaying the generated video for each of the items.

Images