Information processing device, information processing method, and recording medium

Abstract

An information processing device disclosed herein comprises an acquisition unit and a creation unit. The acquisition unit acquires a video of a competition that involves advancing from a start to a goal and competing for the order of arrival. The creation unit divides the course of the competition into a plurality of processing unit sections in the advancing direction, and uses the video to create explanatory text explaining the status of the competition for each processing unit section.

Description

Information processing device, information processing method, and recording medium

[0001] This disclosure relates to an information processing device, an information processing method, and a recording medium.

[0002] Related technology is disclosed in Patent Document 1. Patent Document 1 discloses a technology for creating explanatory text for video. This technology selects a time interval from among the time intervals in which events occurred in the video to be used to create a summary video. Then, this technology creates explanatory text that is superimposed on the summary video or output as audio in the summary video.

[0003] Japanese Patent Publication No. 2007-193820

[0004] One example of the purpose of this disclosure is to advance the technology used to create content.

[0005] According to one aspect of this disclosure, an information processing device is provided, which includes: an acquisition means for acquiring video footage of a competition in which participants move from a start to a finish line and compete for finishing order; and a creation means for dividing the course of the competition into a plurality of processing unit sections along the direction of travel, and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

[0006] Furthermore, according to one aspect of this disclosure, an information processing method is provided in which one or more computers acquire video footage of a competition in which participants move from a start to a finish line and compete for finishing order, divide the course of the competition into a plurality of processing unit sections along the direction of travel, and create an explanatory text describing the situation of the competition for each processing unit section using the video footage.

[0007] Furthermore, according to one aspect of this disclosure, a program is provided that causes a computer to function as an acquisition means for acquiring video footage of a competition in which participants move from a start to a finish line and compete for finishing order, and a creation means for dividing the course of the competition into a plurality of processing unit sections along the direction of travel, and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

[0008] This example of disclosure shows that it is possible to advance the technology for creating content.

[0009] Figure 1 is a diagram showing an example of a functional block diagram of an information processing device. Figure 2 is a flowchart showing an example of the processing flow of an information processing device. Figure 3 is a diagram showing an example of the hardware configuration of an information processing device. Figure 4 is a diagram illustrating an example of the process of dividing a course into multiple processing unit intervals. Figure 5 is a diagram illustrating another example of the process of dividing a course into multiple processing unit intervals.

[0010] The embodiments of this disclosure will be described below with reference to the drawings. In this disclosure, the drawings are associated with one or more embodiments. In all drawings, similar components are denoted by the same reference numerals, and their descriptions are omitted where appropriate.

[0011] <<First Embodiment>> Figure 1 is a functional block diagram showing an overview of the information processing device 10. Figure 2 is a flowchart showing an example of the processing flow executed by the information processing device 10.

[0012] As shown in Figure 1, the information processing device 10 has an acquisition unit 11 and a creation unit 12. These functional units execute the processes shown in the flowchart of Figure 2.

[0013] In S10, the acquisition unit 11 acquires video footage of a competition in which participants compete for finishing order by moving from the start to the finish line. In S11, the creation unit 12 divides the competition course into multiple processing unit sections along the direction of travel, and creates explanatory text describing the situation of the competition for each processing unit section using the video footage acquired in S10.

[0014] Incidentally, there is a service that provides customers with descriptive texts explaining the situation of a competition. These descriptive texts include, for example, commentary that explains the situation of the competition in relatively detail, and summary texts that explain the situation relatively concisely. These descriptive texts are provided in text or audio format. There is a need for technology to automatically generate such descriptive texts.

[0015] In this technology, it is necessary to devise ways to create easy-to-understand explanatory text, that is, explanatory text that allows customers to easily grasp the situation of the competition. The information processing device 10 disclosed here has a configuration that can solve this problem.

[0016] As described above, the information processing device 10 divides the course of a competition in which participants advance from the start toward the goal to compete for finishing positions into a plurality of processing unit sections along the advancing direction. Then, the information processing device 10 creates a descriptive text explaining the situation of the competition for each processing unit section. In this way, when creating a descriptive text explaining the situation of the competition for each processing unit section, a customer can grasp the situation of the competition for each processing unit section. As a result, the customer can logically and easily grasp the situation of the competition.

[0017] Further, in a competition where finishing positions are contested, it is preferable to explain the situation of the competition in chronological order. For example, by explaining the situation of the competition divided into the early stage, middle stage, final stage and the like, or divided into the first half and the second half, the customer can logically and easily grasp the flow of the competition. According to the information processing device 10 that divides the course into a plurality of processing unit sections along the advancing direction and creates a descriptive text explaining the situation of the competition for each such processing unit section, it is possible to create a descriptive text that explains the situation of the competition in chronological order.

[0018] Further, depending on the competition, there are characteristic locations on the course, and various notable events may occur at those locations. For example, in the case of a circular course such as a boat race, various events such as overtaking, making a move, collision, and operation error may occur at the corner portion where participants turn to switch their advancing direction by 180°. In the case of the information processing device 10 that divides the "course" into a plurality of processing unit sections and creates a descriptive text explaining the situation of the competition for each processing unit section, a location where a notable event may occur can be set as one processing unit section, and it becomes possible to create a descriptive text specialized for that section. According to such an information processing device 10, it is possible to create a descriptive text including an explanation of the situation at a location where a notable event may occur. That is, it is possible to suppress the inconvenience that a descriptive text without an explanation of the situation at a location where a notable event may occur is created. As a result, the customer can grasp the situation of the competition at the location on the course where a notable event may occur.

[0019] <<Second Embodiment>> <Overview> The information processing device 10 of the second embodiment embodies the configuration of the information processing device 10 of the first embodiment. Hereinafter, detailed description will be given.

[0020] <Hardware Configuration> First, an example of the hardware configuration of the information processing device 10 will be described. Each functional unit of the information processing device 10 is realized by any combination of hardware and software. Those skilled in the art will understand that there are various variations in the implementation method and the device. The software includes programs that are pre-installed at the time of shipment of the device, as well as programs downloaded from recording media such as CDs (Compact Discs) or from servers on the Internet.

[0021] Figure 3 is a block diagram illustrating the hardware configuration of the information processing device 10. As shown in Figure 3, the information processing device 10 includes a processor 1A, memory 2A, input / output interface 3A, peripheral circuitry 4A, and bus 5A. The peripheral circuitry 4A includes various modules. The information processing device 10 does not necessarily have peripheral circuitry 4A. The information processing device 10 may also be composed of multiple physically and / or logically separated devices. In this case, each of the multiple devices may have the above hardware configuration.

[0022] The bus 5A is a data transmission path through which the processor 1A, the memory 2A, the peripheral circuit 4A, and the input / output interface 3A mutually transmit and receive data. The processor 1A is, for example, an arithmetic processing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The memory 2A is, for example, a memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The input / output interface 3A includes an interface for acquiring information from an input device, an external device, an external server, an external sensor, a camera and the like, and an interface for outputting information to an output device, an external device, an external server and the like. The input / output interface 3A also includes an interface for connecting to a communication network such as the Internet. The input device is, for example, a keyboard, a mouse, a microphone, a physical button, a touch panel or the like. The output device is, for example, a display, a projection device, a speaker, a printer, a mailer or the like. The processor 1A can issue instructions to each module and perform operations based on their operation results.

[0023] <Functional Configuration> Next, the functional configuration of the information processing apparatus 10 will be described in detail. Figure 1 is an example of a functional block diagram of the information processing apparatus 10. As illustrated, the information processing apparatus 10 includes an acquisition unit 11 and a generation unit 12.

[0024] The acquisition unit 11 acquires video of a competition in which participants advance from a start toward a goal and compete for finishing order.

[0025] The "competition in which participants advance from a start toward a goal and compete for finishing order" refers to a competition in which a plurality of competing entities move from the start toward the goal and compete for the finishing order at the goal. Examples of competing entities include, but are not limited to, humans, animals, animals ridden by humans, moving bodies ridden by humans, moving bodies remotely operated by humans, and moving bodies capable of autonomous movement. Examples of moving bodies include, but are not limited to, bicycles, motorcycles, automobiles, boats, ships, yachts, flying objects and the like.

[0026] "Video" refers to moving images of the competition. The video includes the competition equipment, the competition course, and the competition facilities. The acquisition unit 11 may acquire the video in real time processing as the competition is taking place. Alternatively, the acquisition unit 11 may acquire video recorded in the past (a few days ago, a few hours ago, a few minutes ago, etc.).

[0027] For example, the acquisition unit 11 may acquire video footage that is distributed to the general public on television or online. The video footage may include commentary from announcers and sounds from the stadium (such as the voices of spectators).

[0028] When acquiring streamed video, the acquisition unit 11 can acquire the streamed video from the receiving device that receives the streamed video. In this case, the acquisition unit 11 may acquire the video in real time processing at the time the competition is taking place.

[0029] In addition, when acquiring streamed video, the acquisition unit 11 may acquire recorded streamed video (video file) based on user operations such as uploading, sending and receiving, or reading data stored in a predetermined storage device. In this case, the acquisition unit 11 can acquire the video at any time after the competition has ended. In this case, the video acquired by the acquisition unit 11 may include index data. The index data indicates each of several target timings in the video by the elapsed time from the beginning of the video file. The target timings may include the start timing of the competition and the end timing of the competition. Such index data may be created, for example, by the user. The acquisition unit 11 may also acquire a video file in which only the competition portion is extracted and the other parts are removed. In this video file, the beginning of the video file will be the start timing of the competition. Such a video file may be created, for example, by the user.

[0030] A "user" is a person who uses the information processing device 10 to create a descriptive text describing the situation of a competition (hereinafter referred to as the "competition situation description"). The user may also be an operator of a service provider that creates and provides competition situation descriptions to customers (hereinafter referred to as the "service operator"). Alternatively, the user may be a customer who creates competition situation descriptions and enjoys them for their own benefit.

[0031] In addition, the acquisition unit 11 may acquire video footage different from the streamed video. Video footage different from the streamed video may be, for example, raw video footage used to create the streamed video. The raw video footage includes multiple videos taken by multiple cameras, each capturing the competition from start to finish. Each camera captures the competition under different shooting conditions (shooting position, zoom, etc.). For example, one camera may shoot the leading group at a relatively high magnification. Another camera may shoot the second group at a relatively high magnification. Yet another camera may shoot at a relatively low magnification so that all of the multiple competition participants are visible. Furthermore, one camera may continuously shoot at a predetermined location on the course, such as the start position, finish position, or a location where notable events are likely to occur. There may also be multiple cameras continuously shooting each of the multiple competition participants. Note that the shooting conditions of the cameras exemplified here are just examples and are not limited to these examples. The number of cameras and videos is also not limited. Each of these multiple raw videos will be at least the length of the competition from start to finish. Generally, the streamed video will be video footage created by stitching together clips extracted from such multiple raw videos. For example, at one time, video footage from the first camera is streamed, and at another time, video footage from the second camera is streamed.

[0032] The information processing device 10 is connected to a shooting system that captures multiple live video feeds via multiple cameras, and may receive video feeds from the shooting system. Alternatively, a service operator may acquire live video feeds by any means and input them into the information processing device 10.

[0033] Furthermore, when the acquisition unit 11 acquires multiple video streams (such as the streamed video streams and multiple live video streams mentioned above), it is preferable that the multiple video streams are time-synchronized with each other (for example, the start timing of each video stream is the same). In such a configuration, if a certain timing (such as the start time of a competition) can be identified based on one video stream, that result can be used in the processing of other video streams.

[0034] "Acquisition" includes at least one of the following: the device retrieving data or information stored in another device or storage medium (active acquisition), and the device inputting data or information output from another device into its own device (passive acquisition). Examples of active acquisition include making a request to another device and receiving a reply, and accessing and reading data from another device or storage medium. Examples of passive acquisition include receiving information that is delivered (or transmitted, push notification, etc.). Furthermore, acquisition may also involve selecting and acquiring data or information from among the received data or information, or selecting and receiving data or information that has been delivered.

[0035] The creation unit 12 divides the competition course into multiple processing unit sections along the direction of travel (i.e., from start to finish). The creation unit 12 then creates a competition situation description text that explains the situation of the competition for each processing unit section. The creation unit 12 creates the competition situation description text using the video acquired by the acquisition unit 11. The "competition situation description text" includes at least one of a commentary text that explains the situation of the competition in relatively detail and a summary text that explains the situation of the competition in relatively concise terms.

[0036] The creation unit 12 can create a description of the competition situation using artificial intelligence (AI). An example of the process for creating a description of the competition situation is described below. The creation unit 12 can perform at least one of the following processing examples 1 and 2.

[0037] "Processing Example 1: Process for Creating a Summary or Commentary Text (1)" In this example, the creation unit 12 inputs various information into the generation AI and causes the generation AI to create a description of the competition situation. The various information input into the generation AI includes the competition video acquired by the acquisition unit 11 and prompts. If the acquisition unit 11 acquires multiple videos, the creation unit 12 can input multiple videos into the generation AI. Unless otherwise specified, the information to be included in the prompts input into the generation AI can be prepared by the operator and input into the information processing device 10. Furthermore, the prompts input into the generation AI may be created by the operator and input into the information processing device 10, or they may be automatically generated by the information processing device 10 according to predetermined rules. These assumptions regarding prompts are the same below.

[0038] The creation unit 12 can include instructions in the prompts input to the generating AI to create a summary (or commentary) describing the situation of the competition for each processing unit interval.

[0039] Furthermore, the creation unit 12 can include processing unit interval information indicating the definition of a processing unit interval in the prompts input to the generated AI.

[0040] Here, we will explain the processing unit section information. First, we will explain the method of dividing the course into multiple processing unit sections. There are various ways of dividing the course, and the user can set this according to the type of competition and the content of the course, and input the setting into the information processing device 10. The number of processing unit sections can be determined by the user. The length of each processing unit section can also be determined by the user. The length of each processing unit section may be the same for all processing unit sections. Alternatively, there may be processing unit sections with different lengths. Also, there may be no overlapping portions between multiple processing unit sections. However, there may be overlapping portions between preceding and succeeding processing unit sections. Furthermore, there may be processing unit sections that overlap with other processing unit sections and processing unit sections that do not overlap with other processing unit sections.

[0041] For example, the user may divide the course into multiple processing unit sections evenly. Alternatively, the user may set each section, distinguished by its course characteristics (straight lines, curves, corners, etc.), as a single processing unit section. Furthermore, the user may set a location on the course where a notable event is likely to occur as a single processing unit section. The user may then divide the areas other than those where a notable event is likely to occur into multiple processing unit sections using any method (e.g., evenly divided, divided according to the course characteristics, etc.).

[0042] Here, we will explain specific examples of processing unit interval information that the user sets / inputs and inputs into the generating AI. The creation unit 12 can include, for example, any of the following processing unit interval information examples 1 to 3 in the prompts to be input into the generating AI. Note that these examples are merely examples and are not limited to them.

[0043] ○ Processing Unit Section Information Example 1 Figure 4 shows an example of a competition course. The example shown is a circuit course. The competitors may complete multiple laps of the circuit course, complete one lap of the circuit course, or run on a portion of the entire circuit course.

[0044] As shown in Figure 4, the circular course is a straight section C １ and C ３ And, corner section C ２ and C ４ The course can be divided into several processing unit sections. The user can divide the course into multiple processing unit sections according to the characteristics of the course. The user can then input processing unit section information indicating the settings into the information processing device 10. The creation unit 12 divides the competition course into processing unit sections for straight sections and processing unit sections for corner sections according to the user's input. The creation unit 12 can include processing unit section information of this nature in the prompts to be input to the generating AI.

[0045] Further, when a competing body laps the circuit course a plurality of times, the user can divide each of the plurality of laps into different processing unit sections. That is, the user can set the first lap and the second lap as different processing unit sections. Then, the user can input processing unit section information indicating the content to the information processing apparatus 10. The creation unit 12 divides each of the plurality of laps into different processing unit sections in accordance with the user's input. The creation unit 12 can include the processing unit section information having such content in the prompt to be input to the generative AI.

[0046] An example of the prompt to be input to the generative AI is shown below, but the present invention is not limited thereto. Note that along with the following prompt, a course layout image and a video of the competition as shown in FIG. 4 are input to the generative AI. "Divide the course from start to goal into a plurality of processing unit sections along the traveling direction, and for each processing unit section, create a live commentary text that describes the competition situation shown in the attached video. The method of dividing the processing unit sections is as follows. First, as shown in the attached course layout image, the entire circumference of the circuit course includes a straight section C １ and C ３ and a corner section C ２ and C ４ can be divided. Treat each of these sections as one processing unit section. In addition, the competing body laps the circuit course shown in the attached course layout image 3 times. Treat each lap as a separate processing unit section. M in the course layout image １ and M ２ are turn marks. Use these turn marks as a guide for the boundary between the straight section and the corner section. In addition, the position indicated by "Start / Goal" in the course layout image is the start position and the goal position."

[0047] Examples of prompts for competitions involving completing one lap of a circuit course or running a portion of the entire circuit course are as follows, but are not limited to these. Note that for all of the following prompts, a course layout image and video of the competition, as shown in Figure 4, are input to the generating AI. “Divide the course from start to finish into multiple processing unit sections along the direction of travel, and for each processing unit section, create a commentary describing the situation of the competition as shown in the attached video. The division of the processing unit sections is as follows: As shown in the attached course layout image, the entire circuit course consists of straight section C １ and C ３ And, corner section C ２ and C ４ It can be divided into sections. Please treat each of these sections as a single processing unit.

[0048] Unless otherwise specified, the information to be included in the prompts to be input to the generating AI can be prepared by the user and input into the information processing device 10 (the same applies hereinafter).

[0049] ○Example 2 of Processing Unit Section Information In Example 1 of Processing Unit Section Information, the creation unit 12 treated a corner section where a notable event could occur as a single processing unit section. In Example 2 of Processing Unit Section Information, the creation unit 12 divides a single corner section into multiple processing unit sections. By doing so, the generating AI can create a competition situation description that explains the situation of the corner section where a notable event could occur in more detail.

[0050] Figure 5 shows an example of a competition course. The example shown is a circuit course. Competitors may complete multiple laps of the circuit course, complete one lap of the circuit course, or run only a portion of the entire circuit course.

[0051] As shown in Figure 5, the circular course is a straight section C １ and C ３ And, corner entry section C ２－１ and C ４－１ And, turn section C ２－２ and C ４－２ And, corner outside section C ２－３ and C ４－３ It can be divided into and .

[0052] Corner entry section C ２－１ and C ４－１ This is the section where the competitor begins preparing to turn. For example, the competitor is in corner section C. ２－１ and C ４－１ In this context, the car moves to the inside lane, steers to change its attitude and direction, and adjusts the throttle to decelerate.

[0053] Turn section C ２－２ and C ４－２ This is the section where the competition vehicle turns and changes direction by 180 degrees.

[0054] Corner outside section C ２－３ and C ４－３ This is the section where the racing car completes a turn, accelerates again, and enters a straight section.

[0055] The following is an example of a prompt to be input to the generating AI, but it is not limited to this. Note that for all of the following prompts, the course layout image and competition video shown in Figure 5 will be input to the generating AI. "Divide the course from start to finish into multiple processing unit sections along the direction of travel, and for each processing unit section, create a commentary describing the situation of the competition as shown in the attached video. The method of dividing the processing unit sections is as follows. First, as shown in the attached course layout image, the entire circumference of the loop course is a straight section C １ and C ３ And, corner entry section C ２－１ and C ４－１ And, turn section C ２－２ and C ４－２ And, corner outside section C ２－３ and C ４－３ It can be divided into and . Treat each of these sections as a single processing unit section. Corner-in section C ２－１ and C ４－１ This is the section where the competitor begins preparing to turn. For example, the competitor is in corner section C. ２－１ and C ４－１ In this section, you move to the inside lane, steer to change attitude and direction, adjust the throttle to decelerate. Turn section C２－２ and C ４－２ This is the section where the racing car turns and changes direction by 180 degrees. Corner Out Section C ２－３ and C ４－３ This is the section where the race car completes a turn, accelerates again, and enters a straight section. The race car will complete three laps of the circuit shown in the attached course layout image. Each lap should be treated as a separate processing unit section. M1 and M2 in the course layout image are turn markers. Use these turn markers as a guide for the boundary between the corner-in section and the turn section, and between the corner-out section and the turn section. L1 and L2 in the course layout image are safety wave dampers. Use the ends of these safety wave dampers as a guide for the boundary between the straight section and the corner-in section. The position indicated as "Start / Goal" in the course layout image is both the start and finish position.

[0056] ○Example of processing unit section information 3 In this example, the competition involves completing multiple laps of the circuit course. The creation unit 12 then divides each of the multiple laps into a different processing unit section. Note that the creation unit 12 does not divide the entire circuit of the course into multiple processing unit sections.

[0057] Examples of prompts in this case are as follows, but are not limited to these. Note that for all of the following prompts, a course layout image and video of the competition as shown in Figure 4 are input to the generating AI. "Divide the course from start to finish into multiple processing unit sections along the direction of travel, and for each processing unit section, create a commentary describing the situation of the competition as shown in the attached video. The method of dividing the processing unit sections is as follows: The competitors will complete three laps of the circuit course shown in the attached course layout image. Each lap should be one processing unit section." The creation unit 12 can create a competition situation description (summary or commentary) by processing as described above, for example. Note that the creation unit 12 may also perform at least one of the following improvements 1 to 9 in the process of creating the competition situation description (summary or commentary) as described above.

[0058] ○Innovation 1: Various noteworthy events such as overtaking, maneuvers, collisions, and operational errors can occur in corner sections. Therefore, the creation unit 12 may have the generating AI create a race situation description that explains the conditions in the corner section in more detail. In this case, the creation unit 12 can include such an instruction in the prompts that it inputs to the generating AI.

[0059] An example of the instruction to be included in the prompt in this case is as follows, but is not limited to this: "Corner section C shown in the attached course layout image" ２ and C ４ In this section, various noteworthy events such as overtaking, maneuvers, collisions, and operational errors may occur. Corner section C ２ and C ４ In the corresponding processing unit interval, please describe the details of such notable events.

[0060] ○Improvement 2 The creation unit 12 may include information in the prompts it inputs to the generating AI that enables the generating AI to distinguish processing unit intervals more accurately. For example, the creation unit 12 can distinguish multiple processing unit intervals based on at least one of the following: facilities in the stadium, the position of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes. The creation unit 12 may include instructions in the prompts it inputs to the generating AI that distinguish multiple processing unit intervals based on at least one of the following: facilities in the stadium, the position of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes.

[0061] An example of instructions to include in the prompt in this case is as follows, but is not limited to this: "In the process of identifying the processing unit section in which the competition body exists, refer to at least one of the following as appropriate: the equipment in the competition field, the position of the competition body participating in the competition, the orientation of the competition body, and the posture of the competition body. M in the attached course layout image" １ and M ２This is a turn mark. Use this turn mark as a guideline for the boundary between the straight section and the corner section. Use the comparison result between this boundary and the position of the competition vehicle to identify the processing unit section in which the competition vehicle is located. Also, the orientation of the competition vehicle hardly changes in the straight section, but it changes significantly when entering the turn section from the straight section. Use this change in the orientation of the competition vehicle as a reference to detect changes in the processing unit section in which the competition vehicle is located. Furthermore, when entering the turn section from the straight section, the occupant of the competition vehicle begins to shift their weight in preparation for the turn, and their posture changes. Use this change in the posture of the occupant of the competition vehicle as a reference to detect changes in the processing unit section in which the competition vehicle is located.

[0062] ○Innovation 3 If the video acquired by the acquisition unit 11 is a streamed video, commentary audio may be attached to the video. When video with commentary audio is input to the generation AI, the creation unit 12 may instruct the generation AI to use the commentary audio to create a summary or commentary text. For example, the creation unit 12 may include instructions in the prompts input to the generation AI to create a summary text by summarizing the commentary audio for each processing unit section. Alternatively, the creation unit 12 may include instructions in the prompts input to the generation AI to create commentary text by appropriately using the content of the commentary audio for each processing unit section.

[0063] ○Improvement 4 The creation unit 12 can instruct the generating AI to analyze the video and create a summary or commentary for each processing unit section. For example, the creation unit 12 can include instructions in the prompts input to the generating AI to analyze the video and create a summary (or commentary) for each processing unit section.

[0064] ○Improvement 5 The creation unit 12 may include information that identifies multiple sports figures in the video from one another in the prompts it inputs to the generating AI. Multiple sports figures may be assigned different colors or numbers to each other. For example, the equipment (clothing, bibs, helmets, hats, etc.) of each of the multiple sports figures may be assigned different colors or numbers to each other. In this case, the creation unit 12 can identify the multiple sports figures included in the video from one another based on at least one of the colors and numbers assigned to each of the multiple sports figures.

[0065] The following is an example of a prompt that may be used in this example, but is not limited to this: "Identify multiple competitors based on the color of their helmets and clothing, and the number assigned to their boats. The colors and numbers of each competitor are as follows: 1. White, Tokyo Taro 2. Black, Kyoto Jiro 3. Red, Kanagawa Kenji 4. Blue, Chiba Koji 5. Yellow, Saitama Makoto 6. Green, Osaka Shinsuke"

[0066] ○Ingenuity 6 The creation unit 12 may include instructions in the prompts it inputs to the generating AI that specify what to include in the summary or commentary. For example, the creation unit 12 may include instructions in the prompts it inputs to the generating AI that instruct the AI ​​to include at least one of the following in the summary or commentary: - Explanation of the rankings of multiple sports - Explanation of changes in the rankings of multiple sports - Explanation of predetermined movements for each of the multiple sports - Explanation of notable scenes

[0067] "The predetermined movements for each of the multiple competition bodies" are, for example, capsizing, falling, falling off a horse, etc., but are not limited to these. The creation unit 12 can include the definition of the predetermined movements in the prompts that it inputs to the generating AI.

[0068] A "highlight scene" is a scene in the competition that deserves attention. The creation unit 12 can include criteria for identifying highlight scenes through image analysis or audio analysis in the prompts input to the generating AI. These criteria are defined using the state of the athletes in the video, the content of the commentary accompanying the streamed video, etc.

[0069] Here, we will explain the criteria for identifying scenes of interest. For example, the creation unit 12 can detect scenes of interest from the video based on at least one of the following: The creation unit 12 can include instructions for detecting scenes of interest from the video based on at least one of the following in the prompts input to the generating AI: - Changes in the rankings of multiple competitions participating in the competition - The movements of each of the multiple competitions - Words and expressions contained in the commentary audio accompanying the video - The emotions of the speaker (announcer, etc.) estimated based on the commentary audio accompanying the video

[0070] The criteria for determining a scene of note may include, for example, the timing of changes in the rankings of multiple sports and the surrounding period (for example, a few seconds before and after; the same applies hereinafter).

[0071] Furthermore, the criteria for determining a scene of interest may include the timing and surrounding area when a competitor performs a predetermined movement. In this case, the definition of the predetermined movement can be included in the prompt input to the generating AI. The predetermined movement may be, for example, capsizing, falling, or falling off a horse, but is not limited to these.

[0072] Furthermore, the criteria for determining a scene of interest may also include the timing and surrounding content of the appearance of specific words and expressions in the commentary audio. In this case, the definitions of these specific words and expressions can be included in the prompts input to the generating AI. Examples of these specific words and expressions include, but are not limited to, "went in," "made a move," and "made a move." By defining words and expressions specific to each sport, it becomes possible to identify scenes of interest specific to each sport. In addition, each announcer has their own speaking style. That is, each announcer may have different catchphrases and frequently used expressions. By defining words and expressions that announcers in the video being processed tend to use in scenes of interest, as specific words and expressions, it is expected that the accuracy of identifying scenes of interest will improve.

[0073] Furthermore, the criteria for determining a scene of interest may also include the timing and surrounding content of the commentator's (announcer, etc.) emotions when they are experiencing a predetermined emotion. In this case, the definition of the predetermined emotion can be included in the prompt input to the generating AI. The predetermined emotion here could be, for example, excitement or passion, but is not limited to these. In this example, the generating AI can analyze the commentary audio and estimate the speaker's emotions.

[0074] ○Innovation 7 The creation unit 12 can cause the generating AI to create a summary or commentary for each processing unit section based on different criteria for each processing unit section. In this case, the creation unit 12 can include the criteria for creating the summary or commentary for each processing unit section in the prompts input to the generating AI. For example, these criteria may define that in a "relatively early stage (initial stage) processing unit section of the course," the AI ​​should create an explanatory text describing the situation of all the participating athletes, or the situation of the athlete of interest. Also, these criteria may define that in a "relatively late stage (final stage) processing unit section of the course," the AI ​​should create an explanatory text describing the situation of the leading group.

[0075] When adopting the above example of creation criteria, the creation unit 12 may include an instruction in the prompt input to the generating AI to designate at least one of the multiple competitions as the competition to be highlighted. This prompt explicitly indicates the competition to be highlighted. The creation unit 12 may also designate a competition specified by the user as the competition to be highlighted. In addition, the creation unit 12 may designate a competition as the competition to be highlighted if its popularity ranking, as indicated by the odds of each competition obtained from a predetermined server, is above a predetermined rank. Note that the creation criteria exemplified here are just examples and are not limited thereto.

[0076] ○Ingenuity 8 The creation unit 12 may choose not to include certain words or expressions in the audio accompanying the video in the summary or commentary. The creation unit 12 may include instructions in the prompts input to the generation AI to exclude certain words and expressions from the summary or commentary. In this case, the creation unit 12 may include definitions of words and expressions to be excluded from the summary or commentary in the prompts input to the generation AI. Such words and expressions are, for example, words and expressions directed at local people, such as "Please do not throw away your betting slips," and are not related to the situation of the competition, but are not limited to these.

[0077] ○Innovation 9 The creation unit 12 can create commentary text that presents background information for each of the multiple sports teams that have been prepared in advance. That is, the creation unit 12 may include background information for each of the multiple sports teams in the commentary text. In this case, the creation unit 12 can include background information for each of the multiple sports teams in the prompts that it inputs to the generation AI. The creation unit 12 can also include instructions in the prompts that it inputs to the generation AI to include background information for each of the multiple sports teams in the commentary text. Background information may include, but is not limited to, past competition records, hobbies, family structure, upbringing, and enthusiasm for the current competition.

[0078] "Processing Example 2: Process for creating a summary or commentary (2)" In this processing example, the creation unit 12 receives a designation from the user to designate at least one of the multiple sports participating in the competition as the sports to be watched. For example, the user can designate the sports they are supporting (e.g., the sports for which they have bought boat race or horse racing tickets) as the sports to be watched.

[0079] The creation unit 12 creates a summary or commentary describing the status of the featured sport for each processing unit interval. The creation unit 12 can create a summary or commentary describing the status of the featured sport for each processing unit interval using the same process as the process (1) for creating a summary or commentary.

[0080] Furthermore, the creation unit 12 may include an instruction in the prompts input to the generating AI to designate at least one of the multiple competitions as the competition of interest. The competition to be designated as the competition of interest is explicitly stated in the prompts. The creation unit 12 may also include an instruction in the prompts input to the generating AI to create a summary text (or commentary) describing the status of the competition of interest for each processing unit interval. For example, the creation unit 12 may include an instruction in the prompts input to the generating AI to create a summary text (or commentary) describing the ranking of the competition of interest, the movements of the competition of interest, etc., for each processing unit interval.

[0081] The creation unit 12 can output a competition situation description created by, for example, the process described above. The creation unit 12 may output the competition situation description via an output device such as a display or speaker provided by the information processing device 10. Alternatively, the creation unit 12 may send the competition situation description to a client terminal and have the client terminal output the competition situation description. The creation unit 12 may display the text data representing the competition situation description on a display provided by the information processing device 10 or on the display of the client terminal. Alternatively, the creation unit 12 may output the text data representing the competition situation description as audio using predetermined text-to-speech software. The creation unit 12 can achieve this audio output via a speaker provided by the information processing device 10 or on the speaker of the client terminal.

[0082] Generative AI is a concept that includes large language models (LLMs). Generative AI can also incorporate image analysis models. It interprets prompts input in natural language, generates responses to those prompts based on pre-trained data, and outputs responses expressed in natural language. Furthermore, it can accept inputs such as images along with prompts, interpret the content of the input images, and generate responses reflecting the interpretation. Generative AI can also generate and output images. Such a generative AI can be implemented, for example, by a neural network. A neural network contains multiple artificial neurons, each with synapses connecting them. Each synapse has a weight. When such a neural network receives input, it performs calculations using the weights associated with each synapse and outputs an output corresponding to the input. The model representing the connection relationships between neurons and synapses is stored in memory, for example, in software form. Alternatively, the model may be implemented as a dedicated circuit. Similarly, the weights of each synapse are also stored in memory in software form. Furthermore, a dedicated circuit may be implemented to represent the weights. Note that when constructing a generative AI using multiple models, it is not necessarily required that all models be stored in the same memory. A wide variety of neural network models exist. Generative AI can be realized by employing and substituting various models such as Transformers, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs).

[0083] Other configurations of the information processing device 10 in the second embodiment can be the same as those of the information processing device 10 in the first embodiment.

[0084] <Effects and Effects> The information processing device 10 of the second embodiment can achieve the same effects and effects as the information processing device 10 of the first embodiment.

[0085] Furthermore, the information processing device 10 can create a summary or commentary using the characteristic processing described above. With such an information processing device 10, it is possible to create a commentary that clearly shows the situation of the competition.

[0086] Furthermore, the information processing device 10 can identify multiple sports in the video based on at least one of the color and number assigned to each of the multiple sports. With such an information processing device 10, multiple sports in the video can be identified with high accuracy. Then, by using the identification result, a description of the sports situation can be created that accurately explains the state of the sports.

[0087] Furthermore, the information processing device 10 can detect noteworthy scenes from the video using the characteristic processing described above, and create a description of the competition situation that includes explanations about the detected noteworthy scenes. With such an information processing device 10, it is possible to create a high-quality description of the competition situation that includes content about noteworthy scenes.

[0088] Furthermore, the information processing device 10 can create a competition situation description that explains the rankings of multiple competitions. With such an information processing device 10, it is possible to create a competition situation description that explains the situation (ranking) that the user wants to know.

[0089] Furthermore, the information processing device 10 can create a description of the competition situation that explains the background information of multiple competitions. With such an information processing device 10, it is possible to create a description of the competition situation that explains the information the user wants to know.

[0090] Furthermore, the information processing device 10 can create a competition situation description that explains the status of a particular competition selected by the user from among multiple competitions. Users who are supporting a specific competition among multiple competitions want to know the status of the competition they are supporting. However, the commentary accompanying the streamed video is aimed at the majority of people, so it provides a general overview of the competition rather than a description of the status of a specific competition. As a result, there may be little or no explanation of the competition that the user is supporting. By creating a competition situation description that focuses on a specific competition, as the information processing device 10 does, it is possible to create a competition situation description that explains the information each user wants to know.

[0091] <Examples> The following describes examples of the information processing device 10 of this embodiment, but the system is not limited to these examples.

[0092] "Example 1" In Example 1, after the competition ends, the service operator inputs the video of the competition into the information processing device 10 and creates a competition situation description. The service operator provides the created competition situation description to the customer via a web page, application, predetermined content provision platform, etc.

[0093] For example, on a webpage, application, or designated content delivery platform, a description of the competition situation is provided, linked to each of multiple competitions. The customer accesses the webpage, application, or designated content delivery platform using their own device. The customer then selects the competition situation description for the desired competition and views the content.

[0094] "Example 2" In Example 2, after the competition ends, the service operator inputs the video of the competition into the information processing device 10. The service operator provides a service to create a description of the competition situation via a web page, application, predetermined content provision platform, etc.

[0095] For example, multiple sports are displayed for selection on a web page, application, or designated content delivery platform. The customer accesses the web page, application, or designated content delivery platform using their own terminal. The customer then selects their desired sport. The information processing device 10 creates a description of the selected sport's situation and transmits it to the customer's terminal device.

[0096] In addition, the customer may select a desired competition and also designate at least one of the participating competitions as a competition of interest. In this example, the information processing device 10 creates a competition status description that explains the status of the designated competition of interest and transmits it to the customer's terminal device.

[0097] "Example 3" In Example 3, the information processing device 10 generates a description of the competition situation in real time while the competition is taking place. The information processing device 10 then provides the generated description of the competition situation to the customer in real time.

[0098] The service operator provides a service that generates competition status descriptions in real time while the competition is taking place, via web pages, applications, designated content delivery platforms, etc.

[0099] For example, multiple competitions are displayed for selection on a web page, application, or designated content delivery platform before or during a competition. The customer accesses the web page, application, or designated content delivery platform using their own terminal. The customer then selects their desired competition. The information processing device 10 generates a description of the competition situation for the selected competition in real time and transmits it to the customer's terminal device in real time.

[0100] In addition, the customer may select a desired competition and also designate at least one of the participating competitions as a competition of interest. In this example, the information processing device 10 generates a competition status description in real time that explains the status of the designated competition of interest and transmits it to the customer's terminal device in real time.

[0101] In this example, the information processing device 10 acquires video footage recording the competition in real time. For example, the information processing device 10 can acquire video footage via streaming or other means.

[0102] <<Modifications>> Below, modifications applicable to the first and second embodiments are described. In these modifications, the same effects and advantages as those of the first and second embodiments are achieved.

[0103] <Modification 1> In some cases, the competition equipment is displayed to the audience before the competition. Examples include the start display and lap display in boat racing, and the display of racehorses in the paddock in horse racing. The information processing device 10 may acquire video footage of such displays and create a description of the competition situation from the video footage.

[0104] In boat races, the starting and lap demonstrations involve the same movements as during the actual race. Therefore, the information processing device 10 can generate a description of the race situation from the demonstration video in the same manner as described above.

[0105] In horse racing, when racehorses are displayed in the paddock, multiple racehorses slowly circle the paddock. The information processing device 10 can divide this circular course into multiple processing unit sections and create an explanatory text for each processing unit section. The method of dividing the processing unit sections is the same as in the above embodiment. The information processing device 10 may also create an explanatory text describing the state of each racehorse for each processing unit section. For example, the information processing device 10 may determine the state of each racehorse from the video and create an explanatory text describing the state of each racehorse. The state of each racehorse is defined in advance, for example, as calm, excited, etc. For example, the information processing device 10 can include the definition of each state in the prompts input to the generating AI. For example, a calm state may be defined as walking slowly, ears pointing forward, neck relaxed, etc. An excited state may be defined as shaking its head violently, moving around restlessly, ears flattened back (alert / dissatisfied), tail wagging frequently, etc.

[0106] <Modification 2> Among sports announcers, there are some famous announcers who use distinctive catchphrases and expressions. The information processing device 10 may transcribe the commentary of such famous announcers and create a summary of the famous announcer's commentary (a description of the competition situation) for each processing unit section. With such an information processing device 10, it is possible to create characteristic descriptions of the competition situation from the commentary of famous announcers.

[0107] <Modification 3> The information processing device 10 can retrieve posts related to the competition from social networking service (SNS) posts and create a competition situation description including the retrieved posts. For example, the information processing device 10 can input the retrieved posts into a generating AI and have it create a competition situation description including the content of those posts. The information processing device 10 may also include examples of how to use the posts in the prompts it inputs to the generating AI. Examples of use may be, for example, "Here are some SNS posts. ○○○."

[0108] The information processing device 10 may, for example, retrieve posts containing predetermined keywords or hashtags from posts made before and after the competition (e.g., several minutes to several hours before and after) and during the competition. Examples of keywords and hashtags include the name of the competition, the name of the competition body, etc., but are not limited to these.

[0109] Although this disclosure has been described above with reference to embodiments, this disclosure is not limited to the embodiments described above. Various modifications to the structure and details of this disclosure are possible, which can be understood by those skilled in the art within the scope of this disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0110] Furthermore, the flowchart used in the above explanation shows multiple steps (processes) in sequence. However, the execution order of the steps performed in each embodiment is not limited to the order in which they are described. In each embodiment, the order of the illustrated steps can be changed to the extent that it does not impede the content.

[0111] Some or all of the above embodiments may also be described as follows, but are not limited to the following: 1. An information processing device having: an acquisition means for acquiring video footage of a competition in which participants proceed from a start to a finish line and compete for finishing order; and a creation means for dividing the course of the competition into a plurality of processing unit sections along the direction of travel, and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage. 2. The information processing device according to 1, wherein the course of the competition is a circuit course that is completed in multiple laps, and the creation means divides each of the multiple laps into different processing unit sections. 3. The information processing device according to 2, wherein the creation means divides the course of the competition into processing unit sections of straight sections and processing unit sections of corner sections. 4. The information processing device according to 3, wherein the creation means divides the processing unit section of the corner section into a plurality of processing unit sections of corner-in sections, turn sections, and corner-out sections. 5. 1. The information processing device according to any one of 1 to 4, wherein the creation means distinguishes the processing unit intervals based on at least one of the following: the facilities in the stadium, the positions of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes. 6. The information processing device according to any one of 1 to 5, wherein the creation means detects a scene of interest from the video and creates an explanatory text describing the scene of interest based on at least one of the following: changes in the rankings of multiple athletes participating in the competition, the movements of each of the multiple athletes, the words and expressions included in the commentary accompanying the video, and the emotions of the speaker estimated based on the commentary. 7. The information processing device according to any one of 1 to 6, wherein the creation means creates an explanatory text describing the situation of the entire group of athletes participating in the competition, or the situation of a particular athlete, in the processing unit intervals at a relatively early stage in the course, and creates an explanatory text describing the situation of the leading group of athletes in the processing unit intervals at a relatively late stage in the course.9. An information processing method comprising: one or more computers acquiring video footage of a competition in which participants advance from a start to a finish line and compete for finishing order; dividing the course of the competition into multiple processing unit sections along the direction of travel; and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage. 10. A program that causes a computer to function as an acquisition means for acquiring video footage of a competition in which participants advance from a start to a finish line and compete for finishing order; and a creation means for dividing the course of the competition into multiple processing unit sections along the direction of travel; and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

[0112] Some or all of the appendices 2 to 8, which are dependent on the information processing device described in appendice 1 above, may also be dependent on the information processing method in appendice 9 and the program in appendice 10 in the same dependent relationship as between appendice 1 and appendices 2 to 8. Furthermore, within the scope of not departing from each of the embodiments described above, some or all of the configurations described as appendices can be realized in various hardware, software, various recording means for recording software, or systems.

[0113] This application claims priority based on Japanese Patent Application No. 2025-067593, filed on 16 April 2025, and incorporates all of its disclosures herein.

[0114] 10 Information processing device 11 Acquisition unit 12 Creation unit 1A Processor 2A Memory 3A Input / Output I / F 4A Peripheral circuit 5A Bus

Claims

1. An information processing device comprising: an acquisition means for acquiring video footage of a competition in which participants proceed from a start to a finish line and compete for finishing order; and a creation means for dividing the course of the competition into a plurality of processing unit sections along the direction of travel, and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

2. The information processing apparatus according to claim 1, wherein the course for the competition is a circuit course that is completed in multiple laps, and the creation means divides each of the multiple laps into different processing unit sections.

3. The information processing apparatus according to claim 2, wherein the creation means divides the course of the competition into processing unit sections of straight sections and processing unit sections of corner sections.

4. The information processing apparatus according to claim 3, wherein the creation means divides the processing unit section of the corner section into a plurality of processing unit sections: a corner-in section, a turn section, and a corner-out section.

5. The information processing apparatus according to any one of claims 1 to 4, wherein the creation means distinguishes the processing unit interval based on at least one of the facilities in the stadium, the position of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes.

6. The information processing apparatus according to any one of claims 1 to 5, wherein the creation means detects a scene of interest from the video and creates an explanatory text describing the scene of interest, based on at least one of the following: changes in the ranking of multiple competitions participating in the competition, the movements of each of the multiple competitions, words and expressions included in the commentary accompanying the video, and the emotions of the speaker estimated based on the commentary.

7. The information processing apparatus according to any one of claims 1 to 6, wherein the creation means creates the explanatory text according to different criteria for each processing unit interval.

8. The information processing apparatus according to claim 7, wherein the creation means creates the descriptive text describing the situation of the entire group of participating athletes or the situation of a particular athlete in the relatively early processing unit section of the course, and creates the descriptive text describing the situation of the leading group of athletes in the relatively late processing unit section of the course.

9. An information processing method comprising: one or more computers acquiring video footage of a competition in which participants move from a start to a finish line and compete for finishing order; dividing the course of the competition into multiple processing unit sections along the direction of movement; and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

10. The information processing method according to claim 9, wherein the course for the competition is a circuit course that is completed in multiple laps, and one or more computers divide each of the multiple laps into different processing unit sections.

11. The information processing method according to claim 10, wherein one or more computers divide the course of the competition into processing unit sections of straight sections and processing unit sections of corner sections.

12. The information processing method according to claim 11, wherein one or more computers divide the processing unit section of the corner section into a plurality of processing unit sections: a corner-in section, a turn section, and a corner-out section.

13. The information processing method according to any one of claims 9 to 12, wherein one or more computers distinguish the processing unit intervals based on at least one of the following: the facilities in the stadium, the positions of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes.

14. The information processing method according to any one of claims 9 to 13, wherein one or more computers detect a scene of interest from the video based on at least one of the following: changes in the rankings of multiple competitions participating in the competition, the movements of each of the multiple competitions, words and expressions included in the commentary accompanying the video, and the emotions of the speaker estimated based on the commentary, and create the explanatory text describing the scene of interest.

15. A recording medium that stores a program that causes a computer to function as an acquisition means for acquiring video footage of a competition in which participants move from a start to a finish line and compete for finishing order, and a creation means for dividing the course of the competition into multiple processing unit sections along the direction of movement, and creating an explanatory text describing the situation of the competition for each processing unit section using the video footage.

16. The recording medium according to claim 15, wherein the course for the competition is a circuit course that is completed in multiple laps, and the creation means divides each of the multiple laps into different processing unit sections.

17. The recording medium according to claim 16, wherein the creation means divides the course of the competition into processing unit sections of straight sections and processing unit sections of corner sections.

18. The recording medium according to claim 17, wherein the creation means divides the processing unit section of the corner section into a plurality of processing unit sections: a corner-in section, a turn section, and a corner-out section.

19. The recording medium according to any one of claims 15 to 18, wherein the production means distinguishes the processing unit interval based on at least one of the facilities in the stadium, the position of the athletes participating in the competition, the orientation of the athletes, and the posture of the athletes.

20. The recording medium according to any one of claims 15 to 19, wherein the creation means detects a scene of interest from the video and creates an explanatory text describing the scene of interest based on at least one of the following: changes in the ranking of multiple competitions participating in the competition, the movements of each of the multiple competitions, words and expressions included in the commentary accompanying the video, and the emotions of the speaker estimated based on the commentary.

Images