Program, public gambling program, horse racing program, information processing method and information processing system

Abstract

To provide a program, public gambling program, horse racing program, information processing method, information processing system, etc. capable of providing users with an extra experience through chat.SOLUTION: There is provided a program. The program is configured to cause a computer to execute a receiving step, an acquisition step and a generation step. The receiving step is configured to be able to receive a question and a target period of the question. The acquisition step includes: when the question and the target period of the question are received, acquiring first data relating to the question on the basis of the question and a database; and when the target period of the question is later than the update date / time of the database, acquiring second data relating to the question, the second data corresponding to the target period of the question, on the basis of the question and prescribed content. The generation step includes generating an answer to the question on the basis of the question, the data, and a learned model.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a program, a program for public gambling, a program for horse racing, an information processing method, and an information processing system. [Background technology]

[0002] Patent Document 1 discloses a chatbot system.

[0003] The chatbot system will be described below. The chat model unit has a model that has been learned in advance by machine learning processing of the relationship between input data and output data when at least a video ID, which is information for identifying a video being played on the user terminal device side, and playback position information indicating the playback position of the video, are used as input data, and generated text is used as output data. When at least a video ID and playback position information are input, the chat model unit outputs generated text inferred based on the model. The client interface unit passes the video ID and playback position information obtained from the user terminal device side to the chat model unit, receives the generated text output by the chat model unit, and transmits a message including the generated text to the user terminal device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-096693 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the system disclosed in Patent Document 1 merely provides answers based on data stored in a database, and does not provide users with any additional experience through chat.

[0006] In view of the above circumstances, the present invention provides a program capable of providing users with an added experience through chat, a program for public gambling, a program for horse racing, an information processing method, an information processing system, and the like. [Means for solving the problem]

[0007] According to one aspect of the present invention, a program is provided. The program is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step. In the receiving step, a question and a target time of the question are able to be received. In the acquiring step, when the question and the target time of the question are received, first data related to the question is acquired based on the question and the database. In the acquiring step, when the target time of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time of the question is acquired based on the question and a predetermined content. In the generating step, an answer to the question is generated based on the question, the data, and the trained model.

[0008] According to this embodiment, it is possible to provide the user with an extra experience through chat. [Brief description of the drawings]

[0009] [Figure 1] 1 is a configuration diagram illustrating an information processing system 100. [Diagram 2] FIG. 2 is a block diagram showing a hardware configuration of an information processing device 200. [Diagram 3] FIG. 2 is a block diagram showing a hardware configuration of a terminal 300. [Figure 4] FIG. 2 is a block diagram showing functions realized by an information processing device 200. [Diagram 5] 2 is an activity diagram showing the flow of an information processing method executed by information processing device 200. FIG. [Figure 6] FIG. 13 is a diagram showing an initial screen corresponding to activity A105. [Figure 7] FIG. 13 shows a race selection screen corresponding to activity A110. [Figure 8] FIG. 13 shows an AI selection screen corresponding to activity A150. [Figure 9] FIG. 13 shows a question selection screen corresponding to activity A160. [Figure 10] FIG. 2 is a diagram showing an example of database contents and update dates and times. [Figure 11] FIG. 11 is a diagram showing an example of second data acquired from a news site of a newspaper company. [Figure 12] FIG. 1 is a diagram showing an outline of a flow from inputting a question to generating an answer. [Figure 13] FIG. 13 is a diagram showing an example of a display screen on the terminal 300 corresponding to activity A250. [Figure 14] FIG. 13 is a diagram showing another example of a display screen of the terminal 300 corresponding to the activity A250. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Various features shown in the following embodiments can be combined with each other.

[0011] Incidentally, the program for realizing the software appearing in this embodiment may be provided as a non-temporary computer-readable recording medium, or may be provided so as to be downloadable from an external server, or may be provided so that the program is started on an external computer and its functions are realized on a client terminal (so-called cloud computing).

[0012] In addition, in this embodiment, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, in this embodiment, various information is handled, and this information is represented, for example, by physical values ​​of signal values ​​representing voltage and current, high and low signal values ​​as a binary bit collection consisting of 0 or 1, or quantum superposition (so-called quantum bits), and communication and calculation can be performed on the circuit in the broad sense.

[0013] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. In other words, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0014] 1. Hardware Configuration In the first section, the hardware configuration of this embodiment will be described.

[0015] 1-1. Information processing system 100 FIG. 1 is a configuration diagram showing an information processing system 100. The information processing system 100 includes an information processing device 200 and a terminal 300, which are connected via a network. These components will be further described. Here, a system exemplified as the information processing system 100 is composed of one or more devices or components. Therefore, for example, even the information processing device 200 alone can become a system exemplified as the information processing system 100.

[0016] 1-2. Information processing device 200 2 is a block diagram showing a hardware configuration of the information processing device 200. The information processing device 200 has a control unit 210, a storage unit 220, and a communication unit 250, and these components are electrically connected via a communication bus 260 inside the information processing device 200. The information processing device 200 may be a server. Each component will be further described.

[0017] The control unit 210 performs processing and control of the overall operation related to the information processing device 200. The control unit 210 is, for example, a central processing unit (CPU) not shown. The control unit 210 realizes various functions related to the information processing device 200 by reading out a predetermined program stored in the storage unit 220. That is, information processing by software stored in the storage unit 220 can be specifically realized by the control unit 210, which is an example of hardware, and executed as each functional unit included in the control unit 210. These will be further described in Section 2. Note that the control unit 210 is not limited to being single, and may be implemented to have multiple control units 210 for each function. Also, a combination of these may be used.

[0018] The storage unit 220 stores various information necessary for information processing of the information processing device 200. This can be implemented, for example, as a storage device such as a solid state drive (SSD) that stores various programs related to the information processing device 200 executed by the control unit 210, or as a memory such as a random access memory (RAM) that stores temporarily required information (arguments, arrays, etc.) related to the calculation of the program. Also, it may be a combination of these.

[0019] The communication unit 250 is preferably a wired communication means such as USB, IEEE1394, Thunderbolt (registered trademark), wired LAN network communication, etc., but may also include wireless LAN network communication, mobile communication such as 5G / LTE / 3G, Bluetooth (registered trademark) communication, etc. as necessary. In other words, it is more preferable to implement it as a collection of multiple communication means. In other words, the information processing device 200 communicates various information with the terminal 300 via the communication unit 250 and the network.

[0020] 1-3. Terminal 300 3 is a block diagram showing a hardware configuration of the terminal 300. The terminal 300 has a control unit 310, a storage unit 320, a display unit 330, an input unit 340, and a communication unit 350, and these components are electrically connected inside the terminal 300 via a communication bus 360. The terminal 300 may be a smartphone, a tablet terminal, a notebook computer, a desktop computer, or the like. The explanation of the control unit 310, the storage unit 320, and the communication unit 350 is omitted because it is substantially the same as the explanation of the control unit 210, the storage unit 220, and the communication unit 250 in the information processing device 200.

[0021] The display unit 330 may be included in the housing of the terminal 300 or may be externally attached. The display unit 330 displays a screen of a graphical user interface (GUI) that can be operated by a user. This is preferably implemented by using display devices such as a CRT display, a liquid crystal display, an organic EL display, and a plasma display depending on the type of the terminal 300. In the following, the display unit 330 will be described as being included in the housing of the terminal 300.

[0022] The input unit 340 may be included in the housing of the terminal 300, or may be externally attached. For example, the input unit 340 may be implemented as a touch panel integrated with the display unit 330. If it is a touch panel, the user can input a tap operation, a swipe operation, or the like. Of course, a switch button, a mouse, a QWERT keyboard, or the like may be adopted instead of the touch panel. That is, the input unit 340 accepts an operation input made by the user. The input is transferred to the control unit 310 via the communication bus 360 as a command signal. Then, the control unit 310 can execute a predetermined control or calculation as necessary.

[0023] 2. Functional configuration The functional configuration of this embodiment will be described in Section 2. As described above, information processing by software stored in the storage unit 220 is specifically realized by the control unit 210, which is an example of hardware, and can be executed as each functional unit included in the control unit 210.

[0024] 4 is a block diagram showing functions realized by the information processing device 200. As described above, the information processing device 200 (information processing system) includes a control unit 210. Specifically, the information processing device 200 (control unit 210) is configured to execute each step of the program of this embodiment. The information processing device 200 (control unit 210) includes a reception unit 211, an acquisition unit 212, and a generation unit 213 corresponding to each step of the program of this embodiment. Here, the program of this embodiment is configured to cause a computer such as the information processing device 200 to execute a reception step, an acquisition step, and a generation step.

[0025] The receiving unit 211 is configured to receive various pieces of information. The receiving unit 211 is configured to execute a receiving step. For example, the receiving unit 211 is configured to be able to receive a question and a target time period for the question.

[0026] The acquiring unit 212 is configured to acquire various information. The acquiring unit 212 is configured to execute an acquiring step. For example, when a question and a target time period of the question are accepted, the acquiring unit 212 acquires first data related to the question based on the question and the database. Also, when the target time period of the question is newer than the update date and time of the database, the acquiring unit 212 acquires second data related to the question and corresponding to the target time period of the question based on the question and a predetermined content.

[0027] The generating unit 213 is configured to generate various information. The generating unit 213 is configured to execute a generating step. For example, the generating unit 213 generates an answer to a question based on the question, data (at least one of the first data and the second data), and a trained model.

[0028] 3. Overview of information processing method In the third section, the flow of information processing by the information processing device 200 described above will be explained.

[0029] The program is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step. In the receiving step, the program is configured to be able to accept a question and a target time period of the question. In the acquiring step, when the question and the target time period of the question are accepted, first data related to the question is acquired based on the question and the database. In the acquiring step, when the target time period of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time period of the question is acquired based on the question and a predetermined content. In the generating step, an answer to the question is generated based on the question, the data, and the trained model.

[0030] Preferably, the predetermined content is a predetermined website. In the obtaining step, the second data is obtained from the predetermined website.

[0031] The program is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step. In the receiving step, a question can be accepted. In the acquiring step, when a question is accepted, first data related to the question is acquired based on the question and the database. In the generating step, an answer to the question is generated based on the question, the data, and the trained model. The trained model is fine-tuned to adjust the tendency of the answer.

[0032] Preferably, the receiving step is configured to be capable of receiving a selection of the trained model, and the generating step is configured to generate an answer using the selected trained model.

[0033] Preferably, the receiving step is configured to be able to receive a question and a target time period of the question. In the acquiring step, when the question and the target time period of the question are accepted, first data is acquired based on the question and the database. In the acquiring step, when the target time period of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time period of the question is acquired based on the question and the predetermined content. In the generating step, an answer to the question is generated based on the question, the data, and the trained model. The trained model is fine-tuned to adjust the tendency of the answer.

[0034] The public gambling program is configured to cause a computer to execute a reception step, an acquisition step, and a generation step. In the reception step, the type of race to be questioned can be received. In the reception step, when the type of race is received, the program is configured to be able to receive a question about the race. In the acquisition step, when the question is received, first data is acquired based on the question and the database. In the acquisition step, when the date and time of the race is newer than the update date and time of the database, second data related to the question and corresponding to the date and time of the race is acquired based on the question and the predetermined content. In the generation step, an answer to the question is generated based on the question, the data, and the trained model. The trained model is fine-tuned to adjust the tendency of the answer.

[0035] Preferably, the trained model is tuned based on how betting tickets are purchased.

[0036] The horse racing program is configured to cause a computer to execute each step of the public gambling program.

[0037] The information processing method includes steps of a program.

[0038] The information processing system includes a control unit configured to execute each step of the program.

[0039] 4. Details of data processing method In the fourth section, the flow of the information processing method of the information processing device 200 described above will be described. This information processing method includes each step of the program of this embodiment. This information processing method includes a reception step, an acquisition step, and a generation step. In the reception step, a question and a target time of the question can be received. In the acquisition step, when the question and the target time of the question are received, first data related to the question is acquired based on the question and the database. In the acquisition step, when the target time of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time of the question is acquired based on the question and a predetermined content. In the generation step, an answer to the question is generated based on the question, data, and a trained model.

[0040] FIG. 5 is an activity diagram showing the flow of an information processing method executed by the information processing device 200. The following description will be given along with each activity shown in FIG. 5. The program of this embodiment will be described as a horse racing program. The horse racing program functions as a chat application (hereinafter simply referred to as a "chat application") for horse racing with AI (Artificial Intelligence, which corresponds to the learned model in the claims). The AI ​​of this embodiment may be a large language model (LLM), and may be a generative AI in particular. The horse racing program is executed by communication between the information processing device 200 and the terminal 300. The information processing device 200 accesses a database or LLM server (not shown) and generates an answer by the AI ​​in the chat application executed by the terminal 300. According to this aspect, it is possible to enjoy a horse racing game with the AI. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0041] First, the control unit 310 in the terminal 300 starts the chat application (activity A105). In the activity A105, for example, the following two-stage information processing is executed. (1) The control unit 310 reads out the chat application from the storage unit 320. (2) The control unit 310 causes the display unit 330 to display the initial screen of the chat application.

[0042] 6 is a diagram showing an initial screen corresponding to the activity A 105. On the screen 331, in addition to the title of the application, a start button 411, a setting button 412, and an end button 413 are displayed.

[0043] The start button 411 is a button for starting a chat with the AI. When the start button 411 is tapped, it transitions to the screen 332.

[0044] The setting button 412 is a button for making various settings. When the setting button 412 is tapped, it transitions to a setting screen (not shown). On this setting screen, for example, user registration, setting of a user icon, etc. are possible.

[0045] The end button 413 is a button for ending the chat application. When the end button 413 is tapped, the chat application is ended.

[0046] Returning to the explanation of FIG. 5, the control unit 310 in the terminal 300 then selects the type of race the user wishes to play against the wall (activity A110). In activity A110, for example, the following three-stage information processing is executed. (1) The input unit 340 accepts a selection operation from the user. (2) The control unit 310 acquires the result of acceptance by the input unit 340 via the communication bus 360. (3) The control unit 310 stores the acquired information on the type of race in the memory unit 320.

[0047] 7 is a diagram showing a race selection screen corresponding to activity A 110. On the screen 332, a calendar 421, an area 422, an area 423, and an OK button 424 are displayed.

[0048] Calendar 421 is a calendar for selecting the date of the race. In calendar 421, the date of the race is selected by tapping the date. Here, December 24, 2023 is selected.

[0049] A list of racecourses is displayed in area 422. In area 422, the racecourse where the race is held can be selected by tapping on the name of the racecourse. In this example, Nakayama Racecourse is selected.

[0050] Area 423 displays a list of races to be held at the racecourse selected in area 422 on the date selected in calendar 421. In area 423, the races displayed can be switched by performing a swipe operation. In area 423, the type of race can be selected by tapping the race name. Here, the Arima Kinen is selected.

[0051] The OK button 424 is a button for transitioning to the next screen after completing settings in the calendar 421, the area 422, and the area 423. The OK button 424 transitions to the screen 333 when tapped.

[0052] Returning to the explanation of FIG. 5, the control unit 310 in the terminal 300 then transmits information relating to the type of race (Arima Kinen to be held on December 24, 2023) (hereinafter also simply referred to as "Arima Kinen") to the information processing device 200 (activity A120). The information relating to the Arima Kinen is information that limits the information processing executed in the subsequent activities to the scope of the Arima Kinen, for example, the date and time of the Arima Kinen. In activity A120, for example, the following two-stage information processing is executed. (1) The control unit 310 reads out information relating to the Arima Kinen from the storage unit 320. (2) The control unit 310 transmits information relating to the Arima Kinen to the information processing device 200 via the communication unit 350.

[0053] Next, the control unit 210 in the information processing device 200 receives information related to the Arima Kinen transmitted from the information processing device 200 (activity A130). In other words, this is a step, and the reception step is configured to be able to receive the type of race to be asked about. In activity A130, for example, the following two-stage information processing is executed. (1) The communication unit 250 receives information related to the Arima Kinen transmitted from the terminal 300. (2) The control unit 210 stores the received information related to the Arima Kinen in the memory unit 220.

[0054] Next, the control unit 310 in the terminal 300 selects the type of AI to be used as a balloting opponent (activity A150). In other words, in the reception step, the selection of a trained model can be received. Here, the trained model is fine-tuned to adjust the tendency of answers to questions. More specifically, the trained model is adjusted based on the way of buying a betting ticket (voting ticket). Therefore, the user can select the type of AI based on the desired balloting content. In the activity A150, for example, the following three-stage information processing is executed. (1) The input unit 340 receives a selection operation from the user. (2) The control unit 310 acquires the acceptance result by the input unit 340 via the communication bus 360. (3) The control unit 310 stores the acquired information on the type of AI in the storage unit 320. According to this embodiment, the user can enjoy balloting according to the way of buying a betting ticket. Also, according to this embodiment, the user can have a conversation with the AI ​​according to his / her preferences.

[0055] 8 is a diagram showing an AI selection screen corresponding to activity A 150. On the screen 333, an area 431, an area 432, and an OK button 433 are displayed.

[0056] Selectable AIs are displayed in area 431. The user can select a desired AI by checking a checkbox corresponding to the AI. Here, the balanced AI is selected from among the conservative, balanced, and adventurous types.

[0057] Area 432 displays the answering tendencies of each AI displayed in area 431. The user can consider which AI to select based on the contents displayed in area 432. Here, the answering tendency (personality) of the Conscientious type is displayed as "Tends to focus on favorites and rivals. Says he wants to experience the joy of hitting the mark." The answering tendency (personality) of the Balanced type is displayed as "Tends to consider both the hit rate and the return rate, and buys betting tickets flexibly." The answering tendency (personality) of the Adventurous type is displayed as "Tends to aim for longshots. His favorite phrase is to increase the return rate."

[0058] The OK button 433 is a button for transitioning to the next screen after completing the settings in the area 431. The OK button 433 transitions to the screen 334 when tapped.

[0059] Returning to the explanation of Fig. 5, the control unit 310 in the terminal 300 then accepts a question from the user (activity A160). In activity A160, for example, the following three-stage information processing is executed. (1) The input unit 340 accepts an input operation from the user. (2) The control unit 310 acquires a result of the acceptance by the input unit 340 via the communication bus 360. (3) The control unit 310 stores information related to the acquired question in the memory unit 320.

[0060] 9 is a diagram showing a question selection screen corresponding to activity A 160. On the screen 334, an area 441 and an area 442 are displayed.

[0061] The category of each question is displayed in area 441. The user can tap a menu button displayed in area 442 to display details of a question corresponding to the category on screen 334. When a specific question is selected, control unit 310 transitions to screen 336.

[0062] Area 443 is an area for inputting a question. The user may ask a standard question shown on screen 334, or may input a free-form question in area 443. Here, it is assumed that the question "What is the recommended way to buy a betting ticket for this race?" has been selected in the "Horse Racing Predictions and Strategies" category in area 441.

[0063] Next, the control unit 310 in the terminal 300 transmits information relating to the acquired question to the information processing device 200 (activity A170). In this case, the acquired information relating to the question is "What is the recommended way to buy a betting ticket for this race?" In activity A170, for example, the following two-stage information processing is executed. (1) The control unit 310 reads out the acquired information relating to the question from the memory unit 320. (2) The control unit 310 transmits the acquired information relating to the question to the information processing device 200 via the communication unit 350.

[0064] Next, the control unit 210 in the information processing device 200 receives information related to the question sent from the terminal 300 (activity A180). In other words, in the reception step, when the type of race is received, a question related to the race can be received. In activity A180, for example, the following two-stage information processing is executed. (1) The communication unit 250 receives information related to the question sent from the terminal 300. (2) The control unit 210 stores the received information related to the question in the memory unit 220.

[0065] Next, the control unit 210 in the information processing device 200 acquires first data related to the question (activity A190). The method of acquiring data related to the question from the database in activity A190 may be, for example, RAG (Retrieval Augmented Generation). In other words, in the acquisition step, when a question about a race is accepted, first data related to the question is acquired based on the question and the database. The first data may be data related to the question "How should I buy a betting ticket for this race?", and may be, for example, the track record of each horse participating in the Arima Kinen. In activity A190, for example, the following four-stage information processing is executed. (1) The control unit 210 reads information related to the question (question "How should I buy a betting ticket for this race?") from the storage unit 220. (2) The control unit 210 accesses the database via the communication unit 250. (3) The control unit 210 acquires the track record (first data) of each horse participating in the Arima Kinen from the database. (4) The control unit 210 causes the storage unit 220 to store the first data.

[0066] Next, the control unit 210 in the information processing device 200 compares the update date and time of the database with the date and time of the race (activity A200). If the control unit 210 determines that the update date and time of the race is newer (YES in activity A200), it proceeds to processing activity A210. If the control unit 210 determines that the update date and time of the database is newer (NO in activity A200), it proceeds to processing activity A220. In activity A200, for example, the following three stages of information processing are executed. (1) The control unit 210 reads out the received information about the Arima Kinen (here, the date and time of the Arima Kinen) from the storage unit 220. (2) The control unit 210 accesses the database via the communication unit 250. (3) The control unit 210 compares the update date and time of the database with the date and time of the Arima Kinen, and proceeds to the next activity.

[0067] FIG. 10 is a diagram showing an example of the contents of the database and the update date and time. Various information is stored in the database, and in this case, information on races held in 2023 is shown. The database also stores information on the update date and time, which is 20:30 on September 22, 2023. Since the Arima Kinen will be held on December 24 in 2023, in this embodiment, the date and time of the Arima Kinen (the date and time of the race) is newer than the update date and time of the database.

[0068] Returning to the description of FIG. 5, the control unit 210 in the information processing device 200 subsequently acquires second data related to the question "How should I buy a betting ticket for this race?" and corresponding to the date and time of the Arima Kinen (activity A210). In other words, in the acquisition step, if the date and time of the race is newer than the update date and time of the database, the second data related to the question and corresponding to the date and time of the race is acquired from the specified website based on the question and the specified website. The specified website may be any site that handles horse racing information, and may be, for example, the site of the Japan Racing Association (JRA) or a news site of a newspaper company. The second data here may be the starting order of each horse in the Arima Kinen. In the activity A210, for example, the following four-stage information processing is executed. (1) The control unit 210 reads out information related to the question from the storage unit 220. (2) The control unit 210 accesses the news site of the newspaper company (the specified website) via the communication unit 250. (3) The control unit 210 acquires data on the starting positions of each horse in the Arima Kinen (second data). (4) The control unit 210 stores the data on the starting positions of each horse in the Arima Kinen in the storage unit 220. According to this embodiment, data can be efficiently acquired from a website that carries the latest information.

[0069] 11 is a diagram showing an example of the second data acquired from a news site of a newspaper company. Here, the gate number, horse number, horse name, sex and age, weight, jockey, etc. of each horse in the Arima Kinen to be held on December 24, 2023 are shown.

[0070] Returning to the explanation of FIG. 5, the control unit 210 in the information processing device 200 generates an answer to the question "How should I buy a betting ticket for this race?" (activity A220). The method of generating an answer in activity A220 may be, for example, RAG. In other words, in the generation step, an answer to the question "How should I buy a betting ticket for this race (Arima Kinen)?" is generated based on the data and the selected trained model. The data in the claims indicates at least one of the first data and the second data. In activity A220, for example, the following four-stage information processing is executed. (1) The control unit 210 reads out the first data and the second data from the storage unit 220. (2) The control unit 210 reads out the selected AI. (3) The control unit 210 inputs the question, the first data, and the second data to the AI, and causes it to generate an answer. (4) The control unit 210 stores the generated answer in the storage unit 220.

[0071] FIG. 12 is a diagram showing an outline of the flow from inputting a question to generating an answer. Here, it is assumed that the race to be queried is set to "Arima Kinen in 2023." First, it is assumed that the question is input as "Which horse is likely to win?". In response to this question, information regarding the newly announced starting positions of the horses is integrated. This integrated information and the past race results of each horse are input to an AI whose answering tendencies have been fine-tuned, and the AI ​​generates the answer "Justin Palace is likely to win."

[0072] Returning to the explanation of Fig. 5, the control unit 210 in the information processing device 200 then transmits the generated answer to the terminal 300 (activity A230). In activity A230, for example, the following two-stage information processing is executed. (1) The control unit 210 reads out the generated answer from the storage unit 220. (2) The control unit 210 transmits the answer to the terminal 300 via the communication unit 250.

[0073] Next, the control unit 310 in the terminal 300 receives the response transmitted from the information processing device 200 (activity A240). In activity A240, for example, the following two-stage information processing is executed. (1) The communication unit 350 receives the response transmitted from the information processing device 200. (2) The control unit 310 stores the received response in the storage unit 320.

[0074] Next, the control unit 310 in the terminal 300 causes the display unit 330 to display the received answer (activity A250). In activity A250, for example, the following two-stage information processing is executed. (1) The control unit 310 reads out the information of the received answer from the storage unit 320. (2) The control unit 310 causes the display unit 330 to display the answer.

[0075] 13 is a diagram showing an example of a display screen on the terminal 300 corresponding to the activity A250. An area 461, an icon 462, an icon 463, an icon 464, and an icon 465 are displayed on the screen 336. On the screen 336, the question target is set to "Arima Kinen to be held in 2023."

[0076] Area 461 is an area for inputting a question. The user may ask a standard question shown on screen 334, or may input a free-form question in area 461. Here, the question corresponding to icon 462 indicates the standard question shown on screen 334, and the question corresponding to icon 464 indicates the free-form question input in area 461.

[0077] An icon 462 indicates a user. It is assumed that the user has asked, "What is the recommended way to buy a betting ticket for this race?"

[0078] Icon 463 is an icon that represents the AI. The AI ​​generated the answer, "It seems that Justin Palace is the most popular horse in this race. So, how about betting on Justin Palace and including horses with a small difference in body weight."

[0079] Icon 464 is an icon representing a user. It is assumed that the user, upon receiving the above response from the AI, asks, "I like jockey Yutaka Take, so I want to base my bet on Dodeuce. What do you think?"

[0080] Icon 465 is an icon that represents an AI. The AI ​​has generated the answer, "Doudeuce has won against Equinox, and is considered to be a horse with great potential. He is likely to run well with jockey Yutaka Take. I think he is a good choice."

[0081] 14 is a diagram showing another example of a display screen of the terminal 300 corresponding to activity A250. An icon 451, an icon 452, and an area 453 are displayed on the display unit 335. Here, it is assumed that a standard question has been selected on the screen 334.

[0082] An icon 451 indicates a user. It is assumed that the user has asked, "Please tell me the meaning of the predicted mark."

[0083] Icon 452 is an icon showing the AI. It is assumed that the AI ​​has generated the following answer: "◎: Favourite. This is given to the horse that is thought to have the highest possibility of winning the race. ○: Contender. This is given to the horse that is thought to be the second strongest in the race. ▲: Longshot. This is given to a horse that is not very popular but is thought to have the potential to win the favourite or contender. △: Lower ranking. This is given to a horse that is thought to have the potential to come in second or third."

[0084] Area 453, like area 461, is an area for inputting a question.

[0085] 5, the control unit 310 in the terminal 300 may move to activity A160 after activity A250. In this case, the control unit 310 and the control unit 210 in the information processing device 200 may repeatedly execute the processes of activities A160 to A250.

[0086] According to this embodiment, it is possible to provide accurate information even on topics that are not reflected in the database. It is also possible to provide a conversation with a personalized AI. This makes it possible to provide users with an experience that is extra special through chat. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0087] Although the embodiment of the present invention has been described above, the present invention is not limited to this, and can be modified as appropriate without departing from the technical concept of the invention.

[0088] 5. Variations In Section 5, a modification of this embodiment will be described.

[0089] The control unit 210 performs writing (storing) and reading processes for various data and information in the storage unit 220, but is not limited to this, and may execute information processing for each activity using, for example, a register or cache memory in the control unit 210. The same applies to the control unit 310.

[0090] In the present embodiment, the second data is obtained by scraping a website. However, the second data is not particularly limited as long as it is content. For example, the second data may be obtained by scraping a social networking service (SNS).

[0091] In this embodiment, a horse racing program has been described as an example, but the present invention is not limited to this, and may be a public gambling program. The public gambling program may be a bicycle racing program, a boat racing program, or an auto racing program. According to this aspect, it is possible to enjoy playing public gambling. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0092] In activity A190, not only one database but also multiple databases may be accessed to acquire data related to the question from each database. A method for acquiring data related to the question from a database in activity A190 may be, for example, RAG. In other words, in the acquisition step, when a question and a target time period of the question are accepted, multiple first data are acquired from multiple databases, and in the generation step, an answer to the question is generated using the acquired multiple first data. According to such an embodiment, a more substantial answer can be provided to the user by acquiring qualitative information and quantitative information required for answer generation from different databases.

[0093] When the contact information (email address, phone number, etc.) of the second user is received from the terminal of the first user, the second user may be allowed to participate in a chat between the first user and the AI. In other words, in the receiving step, a question from the first user and a target time period of the question from the first user may be received, in the receiving step, the contact information of the second user may be received from the terminal of the first user, in the linking step, when the contact information of the second user is received, the information of the first user is linked to the information of the second user, in the receiving step, the question from the second user may be further received, and in the generating step, the generated answer is transmitted to the terminal of the first user and the terminal of the second user. The linking step may be executed by a linking unit (not shown). According to such an embodiment, when the second user is registered by the first user, the second user may be allowed to participate in a conversation between the first user and the AI.

[0094] Furthermore, the program of this embodiment is not limited to a program for public gambling, and may be provided as a program for purposes other than public gambling.

[0095] In the present embodiment, an example of a suitable information processing method has been described, but the present invention is not limited to this, and the following information processing methods (1) to (3) may also be used.

[0096] (1) In the reception step, a question and a target time of the question can be received. In the acquisition step, when the question and the target time of the question are received, first data is acquired based on the question and the database. In the acquisition step, when the target time of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time of the question is acquired based on the question and the predetermined content. In the generation step, an answer to the question is generated based on the question, data, and a trained model. The trained model is fine-tuned to adjust the tendency of the answer. According to this embodiment, it is possible to provide accurate information even for topics not reflected in the database, and to provide a conversation with a characterized AI. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0097] (2) In the reception step, a question and a target time period of the question can be received. In the acquisition step, when the question and the target time period of the question are received, first data related to the question is acquired based on the question and the database. In the acquisition step, when the target time period of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time period of the question is acquired based on the question and the predetermined content. In the generation step, an answer to the question is generated based on the question, the data, and the trained model. According to this embodiment, it is possible to provide accurate information even for topics not reflected in the database. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0098] (3) In the reception step, the system is configured to be able to receive a question. In the acquisition step, when a question is received, first data related to the question is acquired based on the question and the database. In the generation step, an answer to the question is generated based on the question, the data, and the trained model. The trained model is fine-tuned to adjust the tendency of the answer. According to this embodiment, it is possible to provide a conversation with a characterized AI. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0099] 6.Other It may be provided in any of the following ways:

[0100] (1) A program configured to cause a computer to execute a receiving step, an acquiring step, and a generating step, wherein the receiving step is configured to be able to accept a question and a target time period of the question, and the acquiring step, when the question and the target time period of the question are accepted, acquires first data related to the question based on the question and a database, and when the target time period of the question is newer than the update date and time of the database, acquires second data related to the question, the second data corresponding to the target time period of the question, based on the question and a specified content, and the generating step generates an answer to the question based on the question, the data, and a trained model.

[0101] According to this embodiment, it is possible to provide accurate information even on topics that are not reflected in the database. Also, because of the simple configuration, the saved resources can be used for other core functions.

[0102] (2) The program according to (1) above, wherein the specified content is a specified website, and the acquiring step acquires the second data from the specified website.

[0103] According to this embodiment, data can be efficiently acquired from websites that contain the latest information.

[0104] (3) A program configured to cause a computer to execute a receiving step, an acquiring step, and a generating step, wherein the receiving step is configured to accept a question, and when the question is accepted, the acquiring step acquires first data related to the question based on the question and a database, and the generating step generates an answer to the question based on the question, the data, and a trained model, and the trained model is fine-tuned to adjust the tendency of the answer.

[0105] According to this embodiment, it is possible to provide a conversation with a personalized AI. Also, because of the simple configuration, the saved resources can be used for other core functions.

[0106] (4) A program according to (3) above, wherein the receiving step is configured to receive a selection of the trained model, and the generating step generates the answer using the selected trained model.

[0107] According to this embodiment, it is possible to provide a conversation with an AI that meets the user's preferences.

[0108] (5) A program according to any one of (1) to (4) above, wherein the receiving step is configured to be able to receive the question and a target time period of the question, and the acquiring step, when the question and the target time period of the question are received, acquires the first data based on the question and the database, and when the target time period of the question is newer than an update date and time of the database, acquires second data related to the question and corresponding to the target time period of the question based on the question and a specified content, and the generating step generates an answer to the question based on the question, the data, and the trained model, and the trained model is fine-tuned to adjust the tendency of the answers.

[0109] According to this embodiment, it is possible to provide accurate information even on topics that are not reflected in the database, and to provide conversations with a personalized AI.

[0110] (6) A program according to any one of (1) to (5) above, wherein in the acquisition step, when the question and the target time period of the question are accepted, a plurality of the first data are acquired from a plurality of databases, and in the generation step, the plurality of first data are further used to generate the answer.

[0111] According to this aspect, the qualitative information and the quantitative information required for generating an answer are obtained from different databases, so that a more substantial answer can be provided to the user.

[0112] (7) A program according to any one of (1) to (6) above, further configured to cause a computer to execute a linking step, wherein the receiving step is configured to be capable of receiving a question from a first user and a target time period of the question from the first user, the receiving step is configured to be capable of receiving contact information of a second user from the terminal of the first user, the linking step links information of the second user to information of the first user when the contact information of the second user is received, the receiving step is configured to further receive a question from the second user, and the generating step is configured to send the generated answer to the terminal of the first user and the terminal of the second user.

[0113] According to this aspect, when the second user is registered by the first user, the second user can be allowed to participate in a conversation between the first user and the AI.

[0114] (8) A program for public gambling, the program being configured to cause a computer to execute a reception step, an acquisition step, and a generation step, the reception step being configured to be capable of accepting a type of race to be asked about, the reception step being configured to be capable of accepting a question about the race if the type of race is accepted, the acquisition step being configured to acquire first data related to the question based on the question and a database if the question is accepted, the acquisition step being configured to acquire second data related to the question, the second data corresponding to the date and time of the race, based on the question and a specified content if the date and time of the race is newer than the update date and time of the database, the generation step being configured to generate an answer to the question based on the question, the data, and a trained model, the trained model being fine-tuned to adjust the tendency of the answers.

[0115] According to this embodiment, it is possible to enjoy playing against the wall in public gambling. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0116] (9) A program for public gambling as described in (8) above, wherein the trained model is adjusted based on how betting tickets are purchased.

[0117] According to this embodiment, players can enjoy playing ball against a wall depending on how they purchase their ballots.

[0118] (10) A horse racing program configured to cause the computer to execute each step of the public gambling program described in (8) or (9) above.

[0119] According to this embodiment, it is possible to enjoy horse racing by hitting the wall. In addition, because of the simple configuration, the saved resources can be used for other core functions.

[0120] (11) An information processing method comprising the steps of the program according to any one of (1) to (7) above.

[0121] According to such an embodiment, it is possible to provide the user with an extra experience through chat. Also, due to the simple configuration, the saved resources can be used for other core functions.

[0122] (12) An information processing system comprising a control unit, the control unit being configured to execute each step of the program described in any one of (1) to (7) above.

[0123] According to such an embodiment, it is possible to provide the user with an extra experience through chat. Also, due to the simple configuration, the saved resources can be used for other core functions. Of course, this is not the case. [Explanation of symbols]

[0124] 100: Information processing systems 200: Information processing device 210: Control section 211: Reception 212: Acquisition Department 213 :Generation part 220: Storage section 250: Communications Department 260: Communication bus 300: Terminal 310: Control section 320: Storage section 330: Display section 331: Screen 332: Screen 333: Screen 334: Screen 335: Display section 336: Screen 340: Input section 350: Communications Department 360: Communication bus 411: Start button 412: Setting button 413: Exit button 421: Calendar 422: area 423: area 424: OK button 431 :Area 432: area 433: OK button 441 :Area 442 :Area 443 :Area 451: Icon 452: Icon 453 :Area 461 :Area 462: Icon 463: Icon 464: Icon 465: Icon

Claims

1. A program, The method is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step, The receiving step is configured to receive a question and a target time period of the question, In the acquiring step, when the question and the target time period of the question are accepted, first data related to the question are acquired based on the question and a database; In the acquiring step, when the target time period of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time period of the question is acquired based on the question and a predetermined content; In the generating step, an answer to the question is generated based on the question, the data, and a trained model. program.

2. The program according to claim 1, the predetermined content is a predetermined website, In the acquiring step, the second data is acquired from the predetermined website. program.

3. A program, The method is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step, The receiving step is configured to be able to receive a question, In the acquiring step, when the question is accepted, first data related to the question is acquired based on the question and a database; In the generating step, an answer to the question is generated based on the question, the data, and a trained model; The trained model is fine-tuned to adjust for the tendency of the answer. program.

4. The program according to claim 3, The receiving step is configured to receive a selection of the trained model, In the generating step, the answer is generated using the selected trained model. program.

5. The program according to claim 1, The receiving step is configured to receive the question and a target time period of the question, In the acquiring step, when the question and the target time period of the question are accepted, the first data is acquired based on the question and the database; In the acquiring step, when the target time period of the question is newer than the update date and time of the database, second data related to the question and corresponding to the target time period of the question is acquired based on the question and a predetermined content; In the generating step, an answer to the question is generated based on the question, the data, and the trained model; The trained model is fine-tuned to adjust for the tendency of the answer. program.

6. The program according to claim 1, In the acquiring step, when the question and the target time period of the question are accepted, a plurality of first data are acquired from a plurality of databases; In the generating step, the answer is generated by further using the plurality of first data. program.

7. The program according to claim 1, The method is further configured to cause the computer to perform a linking step, The receiving step is configured to receive a question from a first user and a target time period of the question from the first user, The receiving step is configured to receive contact information of a second user from a terminal of the first user, In the linking step, when the contact information of the second user is accepted, information of the first user is linked to information of the second user; The receiving step is configured to further receive a question from the second user, In the generating step, the generated answer is transmitted to a terminal of the first user and a terminal of the second user. program.

8. 1. A public gambling program comprising: The method is configured to cause a computer to execute a receiving step, an acquiring step, and a generating step, The receiving step is configured to receive a type of race to be inquired about, the receiving step is configured to receive a question about the race when the type of the race is received, In the acquiring step, when the question is accepted, first data related to the question is acquired based on the question and a database; In the acquisition step, if the date and time of the race is newer than the update date and time of the database, second data related to the question and corresponding to the date and time of the race is acquired based on the question and a predetermined content; In the generating step, an answer to the question is generated based on the question, the data, and a trained model; The trained model is fine-tuned to adjust for the tendency of the answer. Public gambling programs.

9. 9. The public gambling program according to claim 8, The trained model is adjusted based on how to buy voting tickets. Public gambling programs.

10. 1. A horse racing program comprising: The computer is configured to execute each step of the public gambling program according to claim 8 or 9. Horse racing program.

11. 1. An information processing method, comprising: The program comprises the steps of any one of claims 1 to 7. Information processing methods.

12. An information processing system, A control unit is provided, The control unit is configured to execute each step of the program according to any one of claims 1 to 7. Information processing system.

Images