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

Abstract

To provide an information processing device and the like capable of increasing an output frequency of answers each containing one or more character strings with high reward amounts in a service using a learning model.SOLUTION: An information processing device comprises a reception unit and a learning unit. The reception unit receives: character strings for a model to be caused to learn, the model having been learnt so as to output character strings serving as answers to entered character strings; and reward amounts for increasing output frequencies of the character strings subjected to the learning. The learning unit causes the model to learn so as to increase the output frequency of the received character string subject to the learning according to the received reward amounts.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Conventionally, a technique is known in which the accuracy of a message is improved by having a model learn the evaluation results of the message provided in accordance with the purchasing behavior of the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-141302 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional technology, when information such as a user's behavioral history is input, the model is trained to output messages that satisfy the user's desire for approval for their purchasing behavior. However, it is difficult for the model to output messages that increase the output frequency of specific character strings in the responses.

[0005] The present application has been made in consideration of the above, and aims to increase the output frequency of answers containing character strings with high reward amounts in a service using a learning model. [Means for solving the problem]

[0006] The information processing device of the present application is characterized by having a string to be trained into a model that has been trained to output a string that is a response to an input string, a reception unit that receives a reward amount for learning to increase the output frequency of the trained string, and a learning unit that trains the model so as to increase the output frequency of the received trained string according to the received reward amount. [Effects of the Invention]

[0007] According to one aspect of the embodiment, in a service using a learning model, it is possible to increase the frequency with which answers containing character strings with high reward amounts are output. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is an explanatory diagram showing an overview of model learning according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a functional configuration of the terminal device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a functional configuration of the information processing device according to the embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of the learning process according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] [1. Overview of information processing method] First, an overview of an information processing method performed by an information processing device according to an embodiment will be described with reference to Fig. 1. Fig. 1 is an explanatory diagram showing an overview of model learning according to an embodiment. As shown in Fig. 1, an information processing system 1 includes a terminal device 10, a bidding terminal 50, and an information processing device 100. The terminal device 10, the bidding terminal 50, and the information processing device 100 are each connected to each other via a network N (see Fig. 2) in a wired or wireless manner so as to be able to communicate with each other. In this embodiment, the terminal device 10 cooperates with the information processing device 100.

[0011] The terminal device 10 is a smart device such as a smartphone or tablet used by a user U, and is a portable terminal device capable of communicating with any server device via a wireless communication network such as 4G (4th Generation) or LTE (Long Term Evolution). The terminal device 10 has a screen such as a liquid crystal display with a touch panel function, and accepts various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by the user U with a finger or a stylus. An operation performed on an area of ​​the screen where content is displayed may be considered an operation on the content. The terminal device 10 may be not only a smart device, but also an information processing device such as a desktop PC (Personal Computer) or a notebook PC.

[0012] The bidding terminal 50 is a terminal device through which the advertisement advertiser T makes a bid for a contract that increases the frequency of output of a specific character string in a response, which is implemented for a service that uses a learning model provided by the information processing device 100. Note that the contract is not limited to a bidding, and may be in the form of a contract for a price preset by the business operator that provides the service.

[0013] The information processing device 100 is an information processing device that works in conjunction with the terminal device 10 of each user U and provides API (Application Programming Interface) services for various applications (hereinafter referred to as apps) and various data to the terminal device 10 of each user U, and is realized by a server device, a cloud system, etc.

[0014] Furthermore, the information processing device 100 may be an information processing device that provides some kind of online web service to the terminal device 10 of each user U. For example, the information processing device 100 may provide services such as internet connection, search service, SNS (Social Networking Service), e-commerce, electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, etc. In practice, the information processing device 100 may cooperate with various servers that provide the above-mentioned web services, and may act as an intermediary for the web services or may be responsible for processing the web services.

[0015] In this embodiment, when a user U launches a chat app and asks a question to a generating AI (Artificial Intelligence), the terminal device 10 displays an answer corresponding to the question. Note that the user U may ask a question to the terminal device 10 by voice input, and the terminal device 10 may answer by speaking. Note that the chat app may be able to refer to location information, identification information, etc. of the user U. Also, an answer by the generating AI in the chat app is an example of a service using a learning model.

[0016] For example, as shown in Fig. 1, first, an advertisement advertiser T uses a bidding terminal 50 to transmit bidding information such as the category of the advertisement object, the name of the product, the remuneration amount, and the output frequency to the information processing device 100 via the network N (see Fig. 2) (step S1). Note that the output frequency may be linked to the remuneration amount, for example, so that inputting the output frequency is omitted.

[0017] Next, the information processing device 100 determines the bidding results based on the bidding information received from the multiple advertisement advertisers T, and transmits the determined bidding results to each advertisement advertiser T (step S2). The bidding results are determined as the three bidders who have won the bids in the same category, for example, in descending order of the remuneration amount.

[0018] The information processing device 100 generates sentences to be learned by the model based on the bid information of the successful bidder (step S3). For example, the information processing device 100 generates sentences such that the number of sentence variations including the character string to be learned (e.g., product name) increases as the ranking and reward amount of the bidder increases. The information processing device 100 trains the generated sentences in the model (step S4). In other words, the information processing device 100 trains the model so that the output frequency of the character string to be learned (e.g., product name) increases according to the reward amount.

[0019] Next, the terminal device 10 transmits a question from the user U to the information processing device 100 via the network N (see FIG. 2) (step S5). The information processing device 100 provides an answer to the received question based on a model trained by the generation AI (step S6). Screen 60 shows an example in which, in response to the user U's question, "Are there any recommended places nearby?", the generation AI replies, "Yes, there's a park with a great view about five minutes' walk away. It's very hot, so why not hydrate yourself? I recommend the XX drink." Here, the XX drink is a character string that advertiser T bid on in advance and trained the model, and is output frequently. In this way, in this embodiment, in a service using a learning model, it is possible to increase the output frequency of answers containing character strings with high reward amounts.

[0020] [2. Example of information processing system configuration] Next, the configuration of an information processing system 1 including a terminal device 10, a bidding terminal 50, and an information processing device 100 according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing system according to an embodiment. As shown in Fig. 2, the information processing system 1 according to an embodiment includes a terminal device 10, a bidding terminal 50, and an information processing device 100. These various devices are connected to each other via a network N so as to be able to communicate with each other via wired or wireless communication. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0021] Furthermore, the number of devices included in the information processing system 1 shown in Fig. 2 is not limited to those shown in the figure. For example, in Fig. 2, for the sake of simplicity, only one terminal device 10 and one bidding terminal 50 are shown, but this is merely an example and is not limiting, and two or more devices may be included.

[0022] The terminal device 10 is an information processing device used by a user U. For example, the terminal device 10 is a smart device such as a smartphone or a tablet terminal, a feature phone, a PC (Personal Computer), a PDA (Personal Digital Assistant), a game console with a communication function, a car navigation system, a wearable device such as a smart watch or a head-mounted display, smart glasses, a smart speaker, or the like.

[0023] In addition, the terminal device 10 can connect to the network N via a wireless communication network such as LTE, 4G, or 5G (5th Generation: 5th generation mobile communication system), or via short-range wireless communication such as Bluetooth (registered trademark) or wireless LAN, and communicate with the information processing device 100.

[0024] The bidding terminal 50 is a terminal device used by the advertisement advertiser T to make a bid for a contract in which a specific character string is output frequently in replies for a chat app (a service using a learning model) provided by the information processing device 100. Examples of the bidding terminal 50 include terminal devices such as PCs, smart devices such as smartphones and tablet terminals. The bidding terminal 50 exchanges bidding information and bidding results with the information processing device 100.

[0025] The information processing device 100 is, for example, a PC, a server device, a mainframe, a workstation, etc. The information processing device 100 may be realized by cloud computing.

[0026] [3. Example of terminal device configuration] Next, the configuration of the terminal device 10 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the functional configuration of the terminal device according to the embodiment. As shown in Fig. 3, the terminal device 10 includes a communication unit 11, a display unit 12, an operation unit 13, a positioning unit 14, a storage unit 20, and a control unit 30.

[0027] The communication unit 11 is realized by, for example, a communication module compatible with a wireless LAN or a third to fifth generation mobile communication system (3G to 5G), etc. The communication unit 11 is connected to the information processing device 100 via a network N in a wired or wireless manner.

[0028] The display unit 12 is a display device for displaying various types of information. For example, the display unit 12 is realized by a liquid crystal display, an organic EL (Electro Luminescence) display, or the like. The display unit 12 displays various screens, such as a display screen input from the control unit 30.

[0029] The operation unit 13 is an input device that accepts various operations from the user U. The operation unit 13 may be realized, for example, by a touch panel or the like as an input device, and the display device of the display unit 12 and the input device of the operation unit 13 may be integrated together. Note that the operation unit 13 may also be realized by a keyboard, a mouse, or the like as an input device. The operation unit 13 outputs the operations input by the user U to the control unit 30 as operation information.

[0030] The positioning unit 14 receives signals from a satellite positioning system. The positioning unit 14 receives signals from global navigation satellite systems such as GPS (Global Positioning System), GLONASS (Global Navigation Satellite System), and Galileo as satellite positioning systems and performs positioning. When the positioning unit 14 is requested to perform positioning by the control unit 30, it performs positioning and outputs the positioning result as position information based on a geodetic system such as the World Geodetic System (WGS) 84. When the positioning unit 14 is requested by the control unit 30 to continue positioning continuously, it performs positioning continuously and continues to output the position information until it is requested to stop by the control unit 30. The positioning unit 14 may also receive signals from a regional navigation satellite system such as a quasi-zenith satellite system as a satellite positioning system. The positioning unit 14 may also perform positioning using autonomous navigation using a gyro sensor or an acceleration sensor, or using a wireless LAN or a base station of a third- to fifth-generation mobile communication system.

[0031] The storage unit 20 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 20 stores, for example, identification information of the user U. The storage unit 20 also stores information (programs and data) used for processing by the control unit 30.

[0032] The control unit 30 is a controller, and is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like, executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the terminal device 10 using a storage area such as a RAM as a working area. In the example shown in FIG. 3, the control unit 30 has a reception unit 31 and a display control unit 32.

[0033] The reception unit 31 starts acquiring location information from the positioning unit 14 when the chat app is started by the user U or automatically starts in the background. When a question is input by the user U, the reception unit 31 accepts the question. The reception unit 31 may accept the question by voice input from the user U using a microphone (not shown). The reception unit 31 transmits the accepted question to the information processing device 100 via the communication unit 11 and the network N. The reception unit 31 may transmit identification information of the user U together with the question to the information processing device 100. In this case, it is assumed that the identification information of the user U is stored in advance in the storage unit 20.

[0034] When the chat app is launched by the user U or automatically launched in the background, the display control unit 32 displays an answer to the question received from the information processing device 100 via the network N and the communication unit 11. The display control unit 32 may output the answer as audio from a speaker (not shown).

[0035] [4. Configuration example of information processing device] Next, the functional configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the functional configuration of the information processing device according to the embodiment. As shown in Fig. 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0036] The communication unit 110 is realized by, for example, a network interface card (NIC), etc. The communication unit 110 is connected to the terminal device 10 and the bidding terminal 50 via the network N by wire or wirelessly.

[0037] The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4 , the storage unit 120 includes a bid information storage unit 121 and a model storage unit 122.

[0038] The bidding information storage unit 121 stores bidding information received from multiple advertisement advertisers T. The bidding information includes the category of the advertising object, the name of the product, the remuneration amount, the output frequency, etc. The bidding information storage unit 121 also stores the ranking of the successful bidders in association with the bidding information.

[0039] The model storage unit 122 stores a model that has been trained to output a character string that is a response to an input character string in order to provide a predetermined service. Examples of the model include a Generative Pre-trained Transformer (GPT), a Transformer, and an attention model. In other words, the model is a machine learning model that performs natural language processing. For example, a plurality of models for various services such as navigation, weather forecasts, news, various inquiries, and catalog information for home appliances may be used.

[0040] The control unit 130 is a controller, and is realized by, for example, a CPU, an MPU, an ASIC, an FPGA, or the like, executing various programs (corresponding to examples of information processing programs) stored in a storage device inside the information processing device 100 using a storage area such as a RAM as a work area. In the example shown in FIG. 4, the control unit 130 has a receiving unit 131, a generating unit 132, a learning unit 133, and a providing unit 134.

[0041] The receiving unit 131 receives bidding information from each bidding terminal 50 of multiple advertisement advertisers T via the network N and the communication unit 110. The bidding information includes a character string to be learned by the model and a reward amount for learning to increase the output frequency of the character string to be learned. For example, the character string to be learned may be the name of a product, and the receiving unit 131 may receive the product name as the character string to be learned for each category to which the product belongs. Furthermore, the receiving unit 131 may receive designation of a model to be learned from among multiple models stored in the model storage unit 122. The receiving unit 131 may also receive designation information of one or more of the attributes of a user U (a user) to whom an answer character string is to be output and a usage situation of the user U.

[0042] The reception unit 131 determines bidding results based on the received bidding information of multiple advertisement advertisers T. For example, the reception unit 131 determines three bidders in the same category in descending order of remuneration amount as the successful bidders. Alternatively, for example, the reception unit 131 may determine the advertisement advertiser T with the highest remuneration amount as the successful bidder in the same category. The reception unit 131 transmits the determined bidding results to each advertisement advertiser T via the communication unit 110 and the network N. The reception unit 131 also stores bidding information corresponding to the bidding results in the bidding information storage unit 121. The reception unit 131 also stores various information received from the successful bidders as bidding information in the bidding information storage unit 121. The reception unit 131 outputs the bidding results to the generation unit 132.

[0043] When the bidding results are input from the receiving unit 131, the generating unit 132 refers to the bid information storage unit 121 and generates sentences such that, for example, the higher the ranking and reward amount of the bidder, the greater the number of sentence variations including the character string to be learned (product name). Also, for example, the generating unit 132 may refer to the bid information storage unit 121 and generate sentences such that the character string to be learned (product name) with the highest reward amount within the same category is output with a higher frequency. Also, for example, the generating unit 132 may refer to the bid information storage unit 121 and generate sentences including the character string to be learned (product name) according to the specified information. The generating unit 132 outputs the generated sentences to the learning unit 133.

[0044] When the learning unit 133 receives the sentences generated by the generation unit 132, it refers to the model storage unit 122 and uses the generated sentences to train the model. For example, the learning unit 133 trains the model using multiple variations of sentences generated so that the output frequency of the string to be trained (product name) increases according to the reward amount. For example, the learning unit 133 may train the model using sentences generated so that the number of sentence variations including the string to be trained (product name) increases as the ranking of the bidder and the reward amount increase. Note that the more variations of the sentences, the higher the output frequency of the string to be trained (product name) in more situations. For example, the learning unit 133 may train the model using sentences generated so that the string to be trained (product name) with the highest reward amount increases within the same category. Note that, when the receiving unit 131 receives the designation of models to be trained, the learning unit 133 may train the model using sentences generated for each of the designated models. For example, the learning unit 133 may train the model using sentences generated so as to include the string to be trained (product name) according to the designated information. That is, the learning unit 133 may learn the model using sentences that include the character string to be learned (the name of the product) and correspond to the attribute or situation. The learning unit 133 updates the model in the model storage unit 122 based on the learning result.

[0045] The providing unit 134 acquires a question accepted in the chat app of the terminal device 10 of the user U (consumer) via the network N and the communication unit 110. The providing unit 134 refers to the model storage unit 122 and inputs the question into the model. The providing unit 134 transmits an answer to the question output from the model to the terminal device 10 of the user U (consumer) via the communication unit 110 and the network N. The chat app of the terminal device 10 provides the answer to the received question to the user U (consumer). That is, the providing unit 134 provides an answer to the received question based on a model that has been trained by the generation AI.

[0046] [5. Processing Procedure] Next, a processing procedure by the information processing device 100 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of a learning process according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 130 of the information processing device 100 every time a bid (contract) is made.

[0047] The reception unit 131 of the information processing device 100 receives bidding information from each bidding terminal 50 of a plurality of advertisement advertisers T (step S101). The reception unit 131 determines bidding results based on the received bidding information of the plurality of advertisement advertisers T and transmits the results to each advertisement advertiser T (step S102). The reception unit 131 outputs the bidding results to the generation unit 132.

[0048] When the bidding results are input from the receiving unit 131, the generating unit 132 refers to the bidding information storage unit 121 and generates a sentence based on the bidding information including the bidding results (step S103). The generating unit 132 outputs the generated sentence to the learning unit 133.

[0049] When the sentence generated by the generation unit 132 is input, the learning unit 133 refers to the model storage unit 122 and performs model learning using the generated sentence (step S104). In this way, in a service using a learning model, it is possible to increase the output frequency of answers that include character strings with high reward amounts.

[0050] [6. Modifications] The information processing device 100 described above may be implemented in various different forms other than the above embodiment, and therefore, modifications of the embodiment will be described below.

[0051] In the above embodiment, some or all of the processing performed by the information processing device 100 may actually be performed by the terminal device 10. For example, the processing may be completed in a stand-alone manner (by the terminal device 10 alone). In this case, the terminal device 10 is assumed to have the functions of the information processing device 100 in the above embodiment. Furthermore, in the above embodiment, the terminal device 10 cooperates with the information processing device 100, and therefore, from the perspective of the user U, it appears that the processing of the information processing device 100 is also being performed by the terminal device 10. In other words, from another perspective, it can be said that the terminal device 10 is equipped with the information processing device 100.

[0052] In the above embodiment, the input and output of the generation AI are described as questions and answers in a chat app, but are not limited thereto. For example, the input and output of the generation AI may be a combination such as a search query and search results in a search engine.

[0053] [7. Effects] As described above, information processing device 100 according to the present application includes a receiving unit 131 that receives a string to be trained into a model that has been trained to output a string that will be an answer to an input string, a reward amount for learning to increase the output frequency of the trained string, and a learning unit 133 that trains the model to increase the output frequency of the received trained string according to the received reward amount. As a result, in a service that uses a trained model, it is possible to increase the output frequency of answers that include strings with a high reward amount.

[0054] [8. Hardware Configuration] The information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in Fig. 6, for example. The information processing device 100 will be described below as an example. Fig. 6 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output I / F (Interface) 1060, an input I / F 1070, and a network I / F 1080 are connected via a bus 1090.

[0055] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The arithmetic device 1030 is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

[0056] The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), a flash memory, or the like. The secondary storage device 1050 may be an internal storage device or an external storage device. The secondary storage device 1050 may also be a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), a NAS (Network Attached Storage), a file server, or the like.

[0057] The output I / F 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a display, projector, printer, etc., and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input I / F 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, keypad, button, scanner, etc., and is realized by USB, etc.

[0058] Furthermore, the output I / F 1060 and the input I / F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, the output device 1010 and the input device 1020 may be wireless devices.

[0059] The output device 1010 and the input device 1020 may be integrated into one device, such as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated into one device as an input / output I / F.

[0060] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0061] The network I / F 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0062] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output I / F 1060 and the input I / F 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0063] For example, when the computer 1000 functions as the information processing device 100, the arithmetic unit 1030 of the computer 1000 executes a program loaded onto the primary storage device 1040 to realize the functions of the control unit 130. The arithmetic unit 1030 of the computer 1000 may also load a program acquired from another device via the network I / F 1080 onto the primary storage device 1040 and execute the loaded program. The arithmetic unit 1030 of the computer 1000 may also cooperate with the other device via the network I / F 1080 to call and use the functions and data of a program from another program of the other device.

[0064] [9. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0065] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0066] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0067] For example, the information processing device 100 described above may be realized by multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0068] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0069] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a reception section can be read as a reception means or a reception circuit. [Explanation of symbols]

[0070] 1. Information Processing Systems 10 Terminal Equipment 50 Bidding Terminals 100 Information processing device 110 Communications Department 120 Storage section 121 Bidding information storage unit 122 Model Memory Unit 130 Control Unit 131 Reception 132 Generation part 133 Learning Department 134 Provision Department

Claims

1. a receiving unit that receives, for a model that is trained to increase the output frequency of answers that include a character string with a high reward amount, a character string to be trained into the model and the reward amount for training to increase the output frequency of answers that include the character string to be trained; a learning unit that trains the model using sentences generated so that the number of variations of sentences including the received character string to be trained increases as the received reward amount increases; An information processing device comprising:

2. The character string to be learned is a product name, the receiving unit receives, for each category to which the product belongs, a name of the product as the character string to be learned; 2. The information processing apparatus according to claim 1, wherein:

3. the receiving unit receives the category, the product name, and the remuneration amount from each of a plurality of bidders; the learning unit causes the model to learn using sentences generated in such a way that the number of variations of sentences including the name of the accepted product increases as the remuneration amount increases within the category; 3. The information processing apparatus according to claim 2, wherein:

4. the learning unit causes the model to learn using sentences generated so as to increase the number of sentence variations including the name of the product with the highest remuneration amount within the category; 4. The information processing apparatus according to claim 3,

5. the receiving unit receives the character string to be learned and the reward amount from each of a plurality of bidders; a generation unit that generates sentences such that the number of variations of sentences including the received character string to be learned increases as the ranking of the bidder and the reward amount increase; the learning unit learns the model using each generated sentence.

2. The information processing apparatus according to claim 1, wherein:

6. the receiving unit receives one or more pieces of specified information from among an attribute of a user of an output destination to which the character string serving as the answer is to be output and a usage situation of the user; Further, a generation unit that generates a sentence that includes the character string to be learned and corresponds to the received specified information, the learning unit learns the model using each generated sentence.

2. The information processing apparatus according to claim 1, wherein:

7. receiving, for a model that is trained to increase the output frequency of answers that include a character string with a high reward amount, the character string to be trained by the model and the reward amount for training to increase the output frequency of answers that include the character string to be trained; The model is trained using sentences generated such that the number of variations of sentences including the received character string to be trained increases as the received reward amount increases. An information processing method characterized in that the processing is executed by a computer.

8. receiving, for a model that is trained to increase the output frequency of answers that include a character string with a high reward amount, the character string to be trained by the model and the reward amount for training to increase the output frequency of answers that include the character string to be trained; The model is trained using sentences generated such that the number of variations of sentences including the received character string to be trained increases as the received reward amount increases. An information processing program that causes a computer to execute a process.

Images