Information processing system

Abstract

Provided is an information processing system that has a different configuration from conventional configurations. An information processing system (1) is provided with: an interface unit (11) that receives an input from a user (U) and presents an output to the user (U); a plurality of language models (LM1, LM2); and a processing unit (12) that causes any of the plurality of language models (LM1, LM2) to generate a response to the question inputted to the interface unit (11), and causes information indicating the language model that has generated the response to be presented together with the response to the user (U) as the output by the interface unit (11).

Description

Information Processing Systems

[0001] The following disclosure relates to an information processing system with a language model.

[0002] In recent years, various proposals have been made regarding information processing techniques using language models. For example, Patent Document 1 listed below discloses an example configuration of an information processing system that causes a language model to generate a summary sentence.

[0003] Japanese Patent Application Publication No. 2023-73095

[0004] An object of one aspect of the present disclosure is to provide an information processing system with a different configuration from conventional systems.

[0005] An information processing system according to one aspect of the present disclosure includes an interface unit that accepts input from a user and presents output to the user, a plurality of language models, and a processing unit that causes one of the plurality of language models to generate a response to a question input by the user to the interface unit, and that causes the interface unit to present the response together with information indicating the language model that generated the response as the output to the user.

[0006] According to one aspect of the present disclosure, it is possible to provide an information processing system having a configuration different from conventional ones.

[0007] 1 shows an example of the configuration of an information processing system according to embodiment 1. FIG. 2 shows an example of a method for presenting user output to a user in an interface unit according to embodiment 1. FIG. 3 is a flowchart showing an example of a processing flow in the information processing system according to embodiment 1. FIG. 4 shows an example of the configuration of an information processing system according to embodiment 2. FIG. 5 shows an example of a method for presenting user output to a user in an interface unit according to embodiment 2. FIG. 6 shows an example of language model information displayed in a language model information window according to embodiment 2. FIG. 7 is a flowchart showing an example of a processing flow in the information processing system according to embodiment 2.

[0008] [Embodiment 1] Embodiment 1 will be described below. For convenience of explanation, components having the same functions as those described in embodiment 1 will be denoted by the same reference numerals in the following embodiments, and their description will not be repeated. For simplicity, descriptions of well-known technical matters will also be omitted as appropriate. Unless otherwise specified, the components and numerical values ​​described in this disclosure are merely examples. Therefore, for example, unless otherwise specified, the positional relationship and connection relationship of the components are not limited to the examples in the figures.

[0009] FIG. 1 shows an example of the configuration of an information processing system 1 according to a first embodiment. As shown in FIG. 1, the information processing system 1 includes a terminal device 10 and a server 90. The terminal device 10 may be referred to as an edge device. As an example, the terminal device 10 may be a device owned by a user U. The server 90 may be, for example, a cloud server. In the information processing system 1, it is sufficient that the terminal device 10 and the server 90 are connected so as to be able to communicate with each other.

[0010] The terminal device 10 and the server 90 each have, for example, one or more processors and one or more memories. The processors of the terminal device 10 and the server 90 execute multiple instruction sets (programs) stored in the memories to perform the processing of each of the above-mentioned units. The processor may be any general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). Alternatively, the processor may be any dedicated processor configured, for example, by an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). For example, each unit of the terminal device 10 and the server 90 may be implemented by an independent processor.

[0011] In the example of Fig. 1, a terminal device 10 includes an interface unit 11, a processing unit 12, and a local language model LM1. The local language model LM1 in the first embodiment is a smaller language model than the remote language model LM2. Therefore, the local language model LM1 can generate a response faster than the remote language model LM2. In this specification, the response of the local language model LM1 is referred to as a local response.

[0012] In the example of Fig. 1, the server 90 includes a remote language model LM2. The remote language model LM2 in the first embodiment is a language model with a larger scale than the local language model LM1. Therefore, the remote language model LM2 can generate a more reliable response than the remote language model LM2. In this specification, the response of the remote language model LM2 is referred to as a remote response.

[0013] For example, the administrator of the information processing system 1 (or the administrator of the server 90) may update the remote language model LM2 by re-learning the remote language model LM2 as needed, thereby enabling more reliable remote responses to be presented to the user U.

[0014] In the information processing system 1, a response to a user input may be generated using at least one of the local language model LM1 and the remote language model LM2.

[0015] As described above, the information processing system 1 includes the interface unit 11 and the processing unit 12. The information processing system 1 also includes a plurality of language models.

[0016] In the example of Fig. 1, the information processing system 1 includes a local language model LM1 and a remote language model LM2. The remote language model LM2 is a language model different from the local language model LM1. The local language model LM1 and the remote language model LM2 may be referred to as a first language model and a second language model, respectively. Both the local language model LM1 and the remote language model LM2 may be publicly known trained models.

[0017] The interface unit 11 accepts input from the user U. In this specification, the input from the user U is referred to as user input. The interface unit 11 includes an input device that accepts the user input. The input device is, for example, a keyboard, a touch panel, a microphone, or a camera. The interface unit 11 also presents output from the information processing system 1 to the user U. In this specification, the output from the information processing system 1 to the user U is referred to as user output. The interface unit 11 includes an output device that presents the user output. The output device is, for example, a display or a speaker. The interface unit 11 may also be referred to as an input / output unit.

[0018] In the first embodiment, a case where the user input is text data indicating a question from the user U to the information processing system 1 is mainly exemplified. As another example, the user input may be voice data. The voice data may be, for example, speech data of the user U. When the user input is voice data, the interface unit 11 may convert the voice data into text data by voice recognition processing. Alternatively, the user input may be image data. The user input may be any data that can be accepted by a language model according to one aspect of the present disclosure.

[0019] The interface unit 11 supplies the received user input to the processing unit 12 .

[0020] In the first embodiment, a response to a user input is generated by a language model. In the first embodiment, a case where the language model generates text data as a response is mainly illustrated. However, the language model according to one aspect of the present disclosure may also generate voice data or image data as a response.

[0021] The interface unit 11 acquires, via the processing unit 12, the response generated by the language model and information that can determine which language model generated the response. This information that can determine which language model generated the response is called a language model identifier. This language model identifier may be sent to the processing unit 12 by the language model that generated the response together with the response, or may be added as part of the response and sent to the processing unit 12. Alternatively, the language model identifier may be generated in the processing unit 12. The processing unit 12 sends the language model identifier and the response, or the response to which the language model identifier has been added, to the interface unit 11.

[0022] The interface unit 11 can refer to a format table that determines the format in which a response should be presented to the user U in accordance with the language model identifier, i.e., the format of the user output. This format table is recorded, for example, in a memory provided in the terminal device 10. The interface unit 11 generates a user output using the acquired language model identifier and format table, and presents it to the user U. The format will be described later.

[0023] The interface unit 11 may accept user input in any style and output a response to the user U. As an example, the interface unit 11 may accept user input in an interactive format and output a response to the user U.

[0024] The processing unit 12 selects a language model to be used to generate a response to a user input from at least one of the local language model LM1 and the remote language model LM2. The processing unit 12 makes it possible to generate a response to a user input by selectively using the local language model LM1 and the remote language model LM2.

[0025] FIG. 2 is a diagram showing an example of a method for presenting user output to a user U in the interface unit 11 according to the first embodiment. In FIG. 2, an avatar 102 and a window 103 for presenting a request (user input) from the user U and responses from each language model in text form are arranged on the display monitor 101. For example, if the user U makes a request by voice, that information is converted into text and presented in the window 103. When responses from each language model are presented by voice through a speaker (not shown), that text information can also be presented in the window 103. Note that, instead of such a window 103, only text may be displayed in an appropriate location on the screen, or multiple windows 103 may be provided. The avatar 102 need not be displayed.

[0026] Here, the format table included in the interface unit 11 will be described. The format may, for example, change the color of text characters depending on the language model identifier. More specifically, the format may specify that responses from the local language model LM1 are presented in red and responses from the remote language model LM2 are presented in blue. For example, the color of text displayed in the window 103 shown in FIG. 2 is switched as described above. The format may also be configured to change the font style or font size of text depending on the language model identifier. The format may also be configured to change the background color of the window 103 depending on the language model identifier. In this manner, changing the color, font style, font size, or background color of text is referred to as "changing the text format" in the present disclosure. The format may also be configured to display a separate window 103 for each language model.

[0027] The format may also be set so that different icons are attached to user output depending on the language model identifier. More specifically, the character displayed in the icon may be changed, for example, so that a response based on a local language model is presented with an icon containing the letter "L" (the initial of "Local"), and a response based on a remote language model is presented with an icon containing the letter "R" (the initial of "Remote"). This icon may be displayed at the beginning of text displayed in window 103, or may be displayed outside window 103, for example, at the top. As another example of the icon, the picture (illustration) of the icon may be changed, for example, so that a human icon is attached to a response based on one language model, and a robot icon is attached to a response based on another language model.

[0028] The format may also be configured to display a user output using a different avatar 102 depending on the language model identifier. More specifically, for example, a male avatar may be displayed to present the user output in response to a response using a local language model, and a female avatar may be displayed to present the user output in response to a response using a remote language model. The avatar may be of any type, such as a human, an animal, or a robot. The avatar may also be an animated avatar. In this case, the format may be configured to cause the avatar to perform different actions (such as gestures or hand movements) depending on the language model identifier.

[0029] If the output device provided in the interface unit 11 is a speaker, the format may change the voice used for user output depending on the language model identifier. More specifically, for example, the language model may be used to change the pitch or speed of the voice. In this disclosure, changing the pitch or speed of the voice is referred to as "changing the voice characteristics."

[0030] The interface unit 11 presents the response of the language model to the user U in accordance with the above-described format, thereby presenting information indicating the language model that generated the response to the user U. In other words, it can be said that each of the above-described formats represents a method of presenting information indicating the language model that generated the response.

[0031] The method of presenting information indicating a language model in each of the above formats can be organized as follows, for example.

[0032] (1) A method for changing the presentation method of the response itself: (1-1) When presenting a response in text, the format of the text is changed according to the language model. (1-2) When presenting a response in audio, the characteristics of the audio are changed according to the language model. (1-3) When presenting a response in text or audio, at least one of the tone and / or catchphrases of the text or audio is changed according to the language model.

[0033] (2) Methods for changing what is presented along with a response (2-1) Changing the icon or avatar displayed along with a response depending on the language model (2-2) When displaying an avatar along with a response, changing the avatar's action depending on the language model

[0034] 3 is a flowchart showing an example of a processing flow in the information processing system 1. First, in step S0, the interface unit 11 accepts a user input. The interface unit 11 supplies the user input to the processing unit 12. In step S1, the processing unit 12 outputs a response generation request to the local language model LM1 based on the user input. In this way, the processing unit 12 may first select the local language model LM1 as the language model to be used to generate a response to the user input.

[0035] In step S2, the local language model LM1 generates a local response corresponding to the acquired response generation request. As an example, the local language model LM1 generates a local response corresponding to a question included in the response generation request. The local language model LM1 supplies the generated local response to the processing unit 12.

[0036] In step S3, the processing unit 12 inputs the acquired local response and the language model identifier corresponding to the local response to the interface unit 11.

[0037] However, if a local response is not supplied to the processing unit 12 even after a first predetermined time (e.g., 10 seconds) has elapsed since the processing unit 12 outputted a response generation request to the local language model LM1 in step S1, the processing unit 12 may skip the processing of step S3. If the processing of step S3 is skipped, the local response is not input to the interface unit 11. The first predetermined time, 10 seconds, is assumed to be the time from when the user U asks the information processing system 1 a question to when the user U begins to feel anxious that the information processing system 1 may not have accepted the user U's question.

[0038] The processing unit 12 may further select the remote language model LM2 as a language model to be used to generate a response to the user input. For example, in step S5 following step S2, the processing unit 12 may output a response generation request to the remote language model LM2 based on the user input. In this case, the processing unit 12 may generate the response generation request to the remote language model LM2 as information including the user input and the local response.

[0039] In step S6, the remote language model LM2 generates a remote response corresponding to the acquired response generation request. By supplying the response generation request including the local response to the remote language model LM2, the remote language model LM2 can generate a remote response based on the local response. The remote language model LM2 supplies the generated remote response to the processing unit 12.

[0040] In step S7, the processing unit 12 inputs the acquired remote response and the language model identifier corresponding to the remote response to the interface unit 11.

[0041] However, if a remote response is not supplied to the processing unit 12 even after a second predetermined time (e.g., 30 seconds) has elapsed since the processing unit 12 outputted the response generation request to the remote language model LM2 in step S5, the processing unit 12 may skip the processing of step S7. If the processing of step S7 is skipped, the remote response is not input to the interface unit 11.

[0042] In general, it is considered that the time required to obtain a remote response from the remote language model LM2 is longer than the time required to obtain a local response from the local language model LM1. For this reason, it is considered that a longer waiting time when using the remote language model LM2 than when using the local language model LM1 is acceptable to the user U. Therefore, the second predetermined time (e.g., 30 seconds) may be set to be longer than the first predetermined time (e.g., 10 seconds).

[0043] In step S9, the interface unit 11 may determine which response to present to the user U based on whether a local response and / or a remote response has been input to the interface unit 11 after a predetermined time has elapsed. The start point of the predetermined time may be, for example, the time when step S0, step S1, or step S5 is executed.

[0044] For example, if only a local response is input to the interface unit 11, the process proceeds to step S8-a. In step S8-a, the interface unit 11 refers to the format table and reads out a format (e.g., "make text characters red") corresponding to the language model identifier corresponding to the local language model LM1. The interface unit 11 then formats the language model response in a format conforming to the read format to generate a user output (e.g., generate text data with red characters), and presents the user output to the user U.

[0045] If the local response and the remote response are input to the interface unit 11, the process proceeds to step S8-b. In step S8-b, the interface unit 11 first performs the same process as in step S8-a to format the language model response into a format corresponding to the language model identifier corresponding to the local language model LM1, and presents the generated user output (e.g., text data in red characters) to the user U. Next, the interface unit 11 references the format table and reads out a format corresponding to the language model identifier corresponding to the remote language model LM2 (e.g., "make the text characters blue"). The interface unit 11 then formats the language model response into a format corresponding to the read format, generates a user output (e.g., generates text data in blue characters), and further presents the user output to the user U.

[0046] If only the remote response is input to the interface unit 11, the process proceeds to step S8-c. In step S8-c, the interface unit 11 performs the same process as the latter half of step S8-b, and formats the language model response into a format that conforms to the language model identifier corresponding to the remote language model LM2, and generates a user output (e.g., text data in blue characters), which is then presented to the user U.

[0047] If neither the remote response nor the remote response has been input to the interface unit 11, the process proceeds to step S8-d. In the example of FIG. 3, in step S8-d, the interface unit 11 does not present any response to the user U. As another example, in step S8-d, the interface unit 11 may present text such as "No response was obtained" to the user U.

[0048] As another example, the determination process of step S9 may be executed by the processing unit 12. In this case, the processing unit 12 does not perform the processes of steps S3 and S7, and after the determination process of step S9, supplies the response determined to be presented to the user together with the language model identifier for that response to the interface unit 11. The interface unit 11 performs the same process as above with reference to the language model identifier, and presents the user output to the user U.

[0049] As another example, the processing of each step S8-a to S8-d may be executed by the processing unit 12. In this case, the processing unit 12 may have a format table instead of the interface unit 11, and may format the response from the language model into a format corresponding to the language model identifier that generated the response, output the format to the interface unit 11, and the interface unit 11 may present the format to the user U.

[0050] 3, if the process proceeds to step S8-d as a result of the determination process of step S9, no response is presented to the user U by the interface unit 11. Therefore, in order to avoid proceeding to step S8-d as much as possible, the processing unit 12 may wait in step S3 until a local response is provided from the local language model LM1. The processing unit 12 may wait in step S7 until a remote response is provided from the remote language model LM2.

[0051] According to the information processing system 1 of the first embodiment, when responses based on multiple language models are presented to the user U, it is possible to clearly show the user U which language model is providing the response. To explain further, language models may have different characteristics (e.g., different areas of expertise) due to differences in their structures or the data used for learning. In such a situation, by showing the user U which language model is providing the response, as in the information processing system 1 of the first embodiment, the user can know whether the response is based on a language model that specializes in the field of the user's question, for example, and can easily determine the reliability of the response.

[0052] In the first embodiment, an example in which text is displayed as a method of presentation to the user U has been described, but the presentation method may also be audio. In that case, the format settings provided in the interface unit 11 may change the audio characteristics of the conversation, such as the pitch, speech speed, and sound effects (pop motion), depending on the language model identifier.

[0053] Furthermore, the format settings provided by the interface unit 11 are not limited to changing the design of avatars and icons according to the language model identifier, but may also change the tone of voice, catchphrases, pronunciation, language, etc., or may set a speaking avatar for each language model and display multiple avatars simultaneously to switch between conversation actions such as lip-syncing and gestures. As long as the user U can see which language model is currently responding, any method is acceptable. Furthermore, these technologies may be combined. Note that several variations of these avatars and text presentation methods may be stored in the interface unit, allowing the user U to switch between them at will.

[0054] Although the information processing system 1 according to the first embodiment includes a local language model LM1 and a remote language model LM2, the scope of application of the present disclosure is not limited to this. The information processing system according to the present disclosure may include multiple language models, regardless of whether the language models exist locally or remotely as defined in the present disclosure.

[0055] Furthermore, although the interface unit 11 and the processing unit 12 according to the first embodiment have been described as separate processing units, they may be integrated and exist within the information processing system 1. Furthermore, the processing described in the first embodiment as being executed by the interface unit 11 may be executed by the processing unit 12, and conversely, the processing described as being executed by the processing unit 12 may be executed by the interface unit 11.

[0056] [Embodiment 2] In embodiment 2, a case will be described in which a user U intentionally selects which language model to ask a question to. In this case, there is a possibility that the accuracy of the answer will be improved compared to when the language model is selected on the information processing system side. In order for the user U to specify a language model, it is necessary to present the user U with options such as the skills of each language model.

[0057] Fig. 4 shows an example of the configuration of an information processing system 2 in embodiment 2. Unlike the information processing system 1, the information processing system 2 further includes a management unit 121 in the processing unit 12. The example in Fig. 4 shows a case where the server 90 has two types of remote language models, which are remote language model aLM2a and remote language model bLM2b.

[0058] The management unit 121 stores information about each language model, such as skills indicating areas of expertise such as summarization and translation, knowledge indicating areas such as natural science, social science, computer science, law, and medicine, response speed performance related to response time, and cost information such as usage fees and communication costs for the language model. This information may be stored in the management unit 121 as initial values, or may be stored in each language model and the information temporarily stored in the management unit 121. In the latter case, the information may be added or changed as needed. Such information about each language model is also referred to as "feature information" of the language model. The management unit 121 also stores information about how to present this information to the user U. This information is referred to as display format information. This display format information may be changed based on instructions from the user U, or may be stored in each language model and the information temporarily stored in the management unit 121. In the latter case, the information may be added or changed as needed.

[0059] FIG. 5 is a diagram showing an example of a method for presenting user output to the user U in the interface unit 11 according to the second embodiment. A language model information window 104 is additionally arranged in the upper right corner of FIG. 2 . Language model information can be displayed in this language model information window 104. For example, as shown in FIG. 6 , the nickname, possessed skills, retained knowledge, response speed, and cost of each language model may be displayed. Of course, other information may be displayed, and the name of the language model may be displayed instead of the nickname. However, since the name of the language model may be difficult for the user U to pronounce when actually calling out to the information processing system 2 (more specifically, for example, the avatar 102 displayed on the display monitor 101), there is no problem in allowing the user U to arbitrarily set or change a nickname that is easy for the user U to call the information processing system 2 (more specifically, for example, the avatar 102 displayed on the display monitor 101). Note that instead of this language model information window 104, text alone may be displayed in an appropriate location on the screen, or multiple language model information windows 104 may be arranged.

[0060] 7 is a flowchart showing an example of the flow of processing in the information processing system 2. Explanation of the steps described in the first embodiment will be omitted.

[0061] 7 is a flowchart showing the initial state when the language model information window 104 in FIG. 5 is not displayed. In step S0a, the interface unit 11 accepts user input. This user input includes information indicating that the user U wants to check language model information, such as "What are your areas of expertise?" The interface unit 11 supplies the user input to the processing unit 12. If the processing unit 12 determines that presentation of language model information is requested, in step S11, the processing unit 12 sends skill information and display format information required to present the information of each language model stored in the management unit 121 to the interface unit 11, and the interface unit 11 displays the skill information in the language model information window 104 in the specified display format.

[0062] Thereafter, in step S12, a request such as "Switch to A" or "A, tell me about **" is accepted from the user U, and in step S13 the processing unit 12 issues a response request to the language model specified by the user U. In step 14, the specified language model generates a response and sends it to the processing unit 12. In step 15, the processing unit 12 outputs the response from the specified language model and the language model identifier corresponding to the language model that generated the response to the interface unit 11.

[0063] In step S16, the interface unit 11 selects a process for generating a user output based on the language model identifier. If the language model identifier indicates the local language model LM1, the interface unit 11 proceeds to step S17-a, if the language model identifier indicates the remote language model aLM2a, the interface unit 11 proceeds to step S17-b, and if the language model identifier indicates the remote language model bLM2b, the interface unit 11 proceeds to step S17-c.

[0064] Here, the format table provided in the interface unit 11 according to the second embodiment is assumed to be in a format in which responses from the local language model LM1 are presented in red text, responses from the remote language model aLM2a are presented in blue text, and responses from the remote language model bLM2b are presented in green text.

[0065] When the process proceeds to step S17-a, the interface unit 11 refers to the format table and reads out a format corresponding to the language model identifier corresponding to the local language model LM1. The interface unit 11 then formats the response of the language model in a format conforming to the read format to generate a user output (generates text data in red characters), and presents the user output to the user U.

[0066] When the process proceeds to step S17-b, the interface unit 11 refers to the format table and reads out a format corresponding to the language model identifier corresponding to the remote language model aLM2a. The interface unit 11 then formats the response of the language model in a format conforming to the read format to generate a user output (generates text data in blue characters), and presents the user output to the user U.

[0067] When the process proceeds to step S17-c, the interface unit 11 refers to the format table and reads out a format corresponding to the language model identifier corresponding to the remote language model bLM2b. The interface unit 11 then formats the response of the language model in a format conforming to the read format to generate a user output (generates text data in green characters), and presents the user output to the user U.

[0068] The information processing system 2 according to the second embodiment makes it easier for the user U to select which language model to get a response from, and similar to the information processing system 1 according to the first embodiment, it is possible to clearly show the user U which language model is providing the response.

[0069] It goes without saying that if the language model information window 104 is already displayed, steps S0 and S11 can be omitted.

[0070] Also, although an example has been given in which the language model to be used is specified by voice, it is of course also possible to do this by text input, and in the case of a monitor with a touch panel function, there is no problem in switching by touching the desired language model on the language model information window 104, or by touching an avatar or icon.

[0071] [Additional Notes] One aspect of the present disclosure is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of one aspect of the present disclosure. Furthermore, new technical features can be formed by combining the technical means disclosed in each embodiment.

[0072] 1, 2 Information processing system 10 Terminal device 11 Interface unit 12 Processing unit 90 Server 101 Display monitor 102 Avatar 103 Window 104 Language model information window 121 Management unit LM1 Local language model LM2 Remote language model LM2a Remote language model a LM2b Remote language model b U User

Claims

1. An information processing system comprising: an interface unit that accepts input from a user and presents output to the user; a plurality of language models; and a processing unit that causes one of the plurality of language models to generate a response to a question input into the interface unit by the user, and that causes the interface unit to present the response together with information indicating the language model that generated the response as the output to the user.

2. The information processing system of claim 1, wherein the information is presented by formatting the text that presents the output in accordance with the language model that generated the response.

3. The information processing system of claim 1, wherein the information is presented by modifying characteristics of the speech that presents the output in accordance with the language model that generated the response.

4. The information processing system of claim 1, wherein the information is presented by modifying at least one of the tone and diction of the text or voice presenting the output according to the language model that generated the response.

5. The information processing system of claim 1, wherein the information is presented by changing an icon or avatar displayed with the response depending on the language model that generated the response.

6. The information processing system according to claim 1, wherein the information is presented by changing the action of an avatar displayed together with the response according to the language model that generated the response.

7. An information processing system according to any one of claims 1 to 6, further comprising a memory storing a table relating to a method for presenting the information corresponding to each of the plurality of language models, wherein the processing unit selects the method for presenting the information from the table according to the language model that generated the response, and causes the interface unit to present the information to the user according to the selected method.

8. The information processing system according to claim 1, wherein the processing unit causes the interface unit to present feature information of each of the plurality of language models to the user, and allows the user to select from which language model a response is to be obtained.

9. An information processing method comprising: a step of causing one of a plurality of language models to generate a response to a question input by a user to an interface unit; and a step of presenting to the user, via the interface unit, information indicating the language model that generated the response together with the response.

Images