Information processing apparatus, information processing method, and information processing program
The information processing device addresses the lack of effective language proficiency improvement by assessing user utterances and providing tailored feedback through a natural language processing model, enhancing language skills.
Patent Information
- Application Number
- JP2023082857
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-19
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Conventional natural language processing technologies do not provide adequate services for improving language proficiency, particularly in non-native languages, by providing targeted feedback on user utterances.
An information processing device that includes a reception section to receive user utterances, an estimation section to assess language proficiency, and a provision section to provide targeted responses based on a natural language processing model, which outputs feedback on language errors and appropriate responses tailored to the user's proficiency level.
Enhances language proficiency by providing personalized feedback and responses, thereby improving language skills effectively.
Smart Images

Figure 2024166641000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]
[0002] 2. Description of the Related Art Conventionally, for example, a technique has been disclosed in which a response is made to a sentence uttered by a user using a natural language processing model (see, for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Patent No. 7216863 Summary of the Invention [Problem to be solved by the invention]
[0004] However, the prior art leaves room for further improvement in terms of providing better services.
[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can provide better services. [Means for solving the problem]
[0006] The information processing device according to the present application includes a reception unit, an estimation unit, an acquisition unit, and a provision unit. The reception unit receives an utterance in a predetermined language from a user. The estimation unit estimates the user's proficiency level in the predetermined language based on the received utterance. The acquisition unit inputs utterance information indicating the utterance and request text requesting a response according to the proficiency level to a model that outputs a response text that is a response to input information, and acquires the response text indicating the response output from the model. The provision unit provides the user with content based on the acquired response text. Effect of the Invention
[0007] According to one aspect of the embodiment, an effect is achieved in that better service can be provided. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a diagram showing a process executed by an information processing device according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of user information. [Diagram 5] FIG. 5 is a diagram illustrating an example of model information. [Figure 6] FIG. 6 is a diagram illustrating an example of topic information. [Figure 7] FIG. 7 is a flowchart showing the processing procedure executed by the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application 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 the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.
[0010] (Embodiment) First, a process executed by an information processing device according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing a process executed by an information processing device according to an embodiment. Fig. 1 shows an operation example of an information processing system S including an information processing device 1 according to an embodiment.
[0011] 1, an information processing system S according to an embodiment includes an information processing device 1 and a user terminal 100. A user who uses the user terminal 100 uses a service provided by the information processing device 1 for the purpose of improving language skills in a predetermined language. In the following, a case where the predetermined language is a language other than the native language (e.g., English, etc.) is taken as an example, but the predetermined language may be the native language.
[0012] In FIG. 1, an information processing system S according to an embodiment receives an utterance in a predetermined language from a user, estimates the user's proficiency level in the predetermined language based on the received utterance, inputs utterance information indicating the utterance and a request text requesting a response according to the proficiency level into a model, and provides the user with content based on a response text indicating the response output from the model. The model is a natural language processing model that is trained to output a response text that is a response to input information (text, voice, image, etc.). This model is in an information processing device 1 that processes information, and is independently created by a business entity that manages the information processing device 1. It is preferable that the input information is trained so that it is not used as a new answer, thereby concealing the input information such as personal information.
[0013] First, the information processing device 1 accepts a language designation and a topic from the user terminal 100 (step S1). For example, the information processing device 1 displays a list of languages that can be designated, and accepts a language designation by a user's operation on the list. The information processing device 1 also displays a list of topics that can be designated, and accepts a topic designation by a user's operation on the list. A topic is a specific object (a product, a service, a current event, etc.), a specific situation (the role of a hotel guest or employee, the role of a person asking how to get to a destination or the role of a person being asked, etc.), etc. A current event is, for example, a news article, etc.
[0014] Next, the information processing device 1 sets the specified language and topic (step S2). For example, the information processing device 1 sets the language (e.g., English) and topic (e.g., the role of a restaurant employee) selected by the user in the list.
[0015] Next, the information processing device 1 accepts speech in the user's designated language from the user terminal 100 (step S3). Specifically, the information processing device 1 accepts the user's speech collected by a microphone (not shown) of the user terminal 100.
[0016] Next, the information processing device 1 converts the received utterance (voice) into text in the specified language (step S4). For example, the information processing device 1 converts the voice into text using a conversion application that converts voice into text.
[0017] Next, the information processing device 1 estimates the user's proficiency level for the specified language from the spoken voice and the text in the specified language (spoken text) (step S5). Specifically, the information processing device 1 estimates the proficiency level by comparing the pronunciation and intonation of words based on the spoken voice with the pronunciation and intonation of a standard (for example, a native speaker). The information processing device 1 also estimates the proficiency level by comparing the grammar and words used in a sentence based on the spoken text with the grammar and words used of a standard (for example, a native speaker). The proficiency level may be an overall proficiency level in the entire utterance (entire voice and text), or it may be a proficiency level for each ability element such as speaking, grammar ability, and vocabulary ability, or a proficiency level in a set topic.
[0018] Next, the information processing device 1 inputs an evaluation request according to the proficiency level, a response request to the utterance, and the utterance text into the model to obtain the output of the model (step S6). The evaluation request is a request to point out a linguistic error in the utterance. The information processing device 1 determines the content to be pointed out based on the proficiency level, and inputs text indicating the evaluation request requesting the pointing out of the determined content into the model. For example, the information processing device 1 determines the content to be pointed out as a capability element whose proficiency level is less than a predetermined value. In addition, in the case of the above-mentioned overall proficiency level, the information processing device 1 determines the content to be pointed out as a content (sentence or capability element) that has a higher contribution to the decrease in the proficiency level in the entire utterance. In addition, the response request is a request for a response to the utterance. The information processing device 1 inputs text indicating a response request into the model based on the topic and the utterance. For example, when the set topic is the role of a restaurant employee, the information processing device 1 inputs text such as "Response to XX as a restaurant employee" into the model. Note that the above "XX" is the user's utterance text. Furthermore, the information processing device 1 may request an evaluation not only for pointing out linguistic errors, but also for linguistic evaluation of the spoken voice and spoken text (speaking, grammatical ability, vocabulary, appropriateness of use in a topic).
[0019] In addition, when the received utterance is not directed to the user terminal 100 (the role in the set topic) but to another user (a person playing a different role in the topic), the information processing device 1 inputs only the evaluation request of the evaluation request and the answer request into the model.
[0020] Next, the information processing device 1 converts the text (answer text and evaluation text or only the evaluation text) that is the output of the model into speech (step S7) and provides it to the user terminal 100 (step S8). For example, the information processing device 1 converts the speech so as to obtain a language feature specified by the user (American English, British English, native speaker, non-native speaker, gender, etc.). The information processing device 1 may convert only the answer text out of the answer text (output in response to an answer request) and the evaluation text (output in response to an evaluation request) and provide the evaluation text in text format. In addition, when the evaluation text points out a linguistic error, if the amount of points out is large (above a threshold), the information processing device 1 may adjust the amount of points out to be provided to the user. For example, when the amount of points out is large, the information processing device 1 provides the user with a predetermined ratio (for example, 50%) of the amount of points out. In addition, the information processing device 1 may determine the amount of points out to be provided based on a conversation history with the user. For example, the information processing device 1 provides more points of criticism when the conversation has reached a certain point (for example, when a word that ends a conversation such as "thank you" or "I understand"), and provides less points of criticism when the conversation is in progress. This makes it possible to point out errors without interrupting the flow of the conversation with the user.
[0021] In this way, the information processing device 1 according to the embodiment can contribute to improving the user's language proficiency level by providing a response (answer or evaluation) according to the user's language proficiency level. In other words, the information processing device 1 according to the embodiment can provide better services.
[0022] Next, a configuration example of an information processing system S according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of an information processing system S according to an embodiment. As shown in Fig. 2, in the information processing system S according to an embodiment, an information processing device 1 and a user terminal 100 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a Wide Area Network (WAN), or a Local Area Network (LAN).
[0023] The information processing device 1 is a server device that executes an information processing method according to the embodiment. The information processing device 1 receives an utterance in a predetermined language from a user, estimates the user's proficiency level in the predetermined language based on the received utterance, inputs utterance information indicating the utterance and a request text requesting a response according to the proficiency level to a model, and provides the user with content based on the response text indicating the response output from the model.
[0024] In addition, the information processing device 1 is an information processing device that cooperates with the user terminal 100 and provides the user terminal 100 with API (Application Programming Interface) services for various applications (hereinafter, apps), etc., as well as various data, and is realized by a server device, a cloud system, etc.
[0025] The information processing device 1 may be an information processing device that provides some kind of Web service online to the user terminal 100. For example, the information processing device 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route search, route guidance, line information, operation information, weather forecasts, and applications as Web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned Web services and act as an intermediary for the Web services or be responsible for processing the Web services.
[0026] The user terminal 100 is a terminal device used by a user who wishes to improve his / her language skills in a predetermined language. The user terminal 100 may be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, a tablet PC, an AR (Augmented Reality) terminal, or a VR (Virtual Reality) terminal. The user terminal 100 transmits various types of information to the information processing device 1 or the like, and receives information provided by the information processing device 1 or the like.
[0027] Next, a configuration example of the information processing device 1 will be described with reference to FIG.
[0028] Fig. 3 is a diagram showing an example of the configuration of an information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a reception unit 31, an estimation unit 32, an acquisition unit 33, and a provision unit 34. The storage unit 4 stores user information 41, model information 42, and topic information 43.
[0029] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a network by wire or wirelessly.
[0030] The control unit 3 is a controller, and is realized by, for example, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a working area. The control unit 3 is also a controller, and may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).
[0031] The storage unit 4 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.
[0032] User information 41 is information related to a user. Fig. 4 is a diagram showing an example of the user information 41. As shown in Fig. 4, the user information 41 includes items such as "user ID", "attribute information", and "purchase history".
[0033] "User ID" is identification information for identifying a user. "Attribute information" is information related to the attributes of a user. The attribute information includes, for example, psychographic attributes and demographic attributes. "Proficiency level" is information indicating the user's proficiency level in a specified language, and is information estimated by the estimation unit 32 described later.
[0034] The model information 42 is information related to a natural language processing model. Fig. 5 is a diagram showing an example of the model information 42. As shown in Fig. 5, the model information 42 includes items such as "model ID" and "model information".
[0035] The "model ID" is identification information for identifying a model. The "model information" is information related to the model, and includes, for example, functions. Note that a dedicated model may be generated for each topic and each user.
[0036] Topic information 43 is information related to a topic. Fig. 6 is a diagram showing an example of topic information 43. As shown in Fig. 6, topic information 43 includes items such as "topic ID" and "topic information".
[0037] "Topic ID" is identification information for identifying a topic. "Topic information" is information related to a topic, and includes, for example, settings that match the topic. Details of topic information will be described later.
[0038] Next, each function (reception unit 31, estimation unit 32, acquisition unit 33, and provision unit 34) of the control unit 3 of the information processing device 1 will be described.
[0039] The reception unit 31 receives various information. The reception unit 31 receives language designation and topic from the user terminal 100. For example, the reception unit 31 displays a list of languages that can be designated, and receives language designation by a user's operation on the list. The reception unit 31 also displays a list of topics that can be designated, and receives topic designation by a user's operation on the list. Topics are specific targets (products, services, current events, etc.), specific situations (roles of hotel guests or employees, roles of people asking for directions to a destination, roles of people being asked, etc.), etc.
[0040] The reception unit 31 sets the specified language and topic. For example, the reception unit 31 sets the language (e.g., English, Spanish, French, German, Italian, Chinese, Korean, etc.) and topic (e.g., the role of a restaurant employee) selected by the user in the above-mentioned list.
[0041] The receiving unit 31 receives speech in a specified language of the user from the user terminal 100. Specifically, the information processing device 1 receives the user's speech collected by a microphone (not shown) of the user terminal 100.
[0042] The estimation unit 32 estimates the user's proficiency level in the specified language based on the received utterance. The estimation unit 32 converts the received utterance (voice) into text in the specified language. For example, the estimation unit 32 converts the voice into text using a conversion application that converts voice into text.
[0043] The estimation unit 32 estimates the user's proficiency level for the specified language from the spoken voice and the text in the specified language (spoken text). Specifically, the estimation unit 32 estimates the proficiency level by comparing the pronunciation and intonation of words based on the spoken voice with the pronunciation and intonation of a standard (for example, a native speaker). The information processing device 1 also estimates the proficiency level by comparing the grammar and words used in a sentence based on the spoken text with the grammar and words used of a standard (for example, a native speaker). The proficiency level may be a comprehensive proficiency level in the entire utterance (entire voice and text), or may be a proficiency level for each ability element such as speaking, grammar ability, and vocabulary ability, or a proficiency level in a set topic.
[0044] The acquisition unit 33 inputs speech information (speech voice and speech text) indicating an utterance and request text (evaluation request text and answer request text) requesting a response according to a proficiency level to a model that outputs a response text that is a response to the input information, and acquires a response text indicating a response output from the model. The acquisition unit 33 inputs an evaluation request according to a proficiency level, an answer request to the utterance, and the utterance text to the model, thereby acquiring an output of the model. The evaluation request is a request to point out a linguistic error in the utterance. The information processing device 1 determines the content to be pointed out based on the proficiency level, and inputs text indicating an evaluation request requesting the pointing out of the determined content to the model. For example, the acquisition unit 33 determines the content to point out an ability element whose proficiency level is less than a predetermined value. In addition, in the case of the above-mentioned overall proficiency level, the acquisition unit 33 determines the content to point out a content (sentence or ability element) that has a higher contribution to a decrease in the proficiency level in the entire utterance. In addition, the answer request is a request for an answer to the utterance. The acquisition unit 33 inputs text indicating a response request based on the topic and the speech to the model. For example, when the set topic is the role of a restaurant employee, the information processing device 1 inputs text such as "Response to XX as a restaurant employee" to the model. Note that the above "XX" is the user's speech text. The acquisition unit 33 may also request an evaluation of the speech voice and the speech text (speaking, grammar ability, vocabulary, appropriateness of use in the topic) without being limited to an evaluation request for pointing out a linguistic error.
[0045] In addition, when the received utterance is not directed to the user terminal 100 (the role in the set topic) but to another user (a person playing a different role in the topic), the acquisition unit 33 inputs only the evaluation request of the evaluation request and the answer request into the model.
[0046] The providing unit 34 converts the text (answer text and evaluation text or only the evaluation text) that is the output of the model into voice and provides it to the user terminal 100. For example, the providing unit 34 converts the voice so as to obtain a language feature specified by the user (American English, British English, native speaker, non-native speaker, gender, etc.). The providing unit 34 may convert only the answer text out of the answer text (output in response to an answer request) and the evaluation text (output in response to an evaluation request) and provide the evaluation text in text format. In addition, when the evaluation text points out a linguistic error, if the amount of the points is large (above a threshold), the providing unit 34 may adjust the amount to be provided to the user. For example, when the amount of the points is large, the providing unit 34 provides the user with a predetermined ratio (for example, 50%) of the amount of points to be provided. In addition, the providing unit 34 may determine the amount of points to be provided based on a conversation history with the user. For example, the providing unit 34 provides more indications when the conversation has reached a certain point (for example, when a word that ends a conversation such as "thank you" or "I understand"), and provides less indications when the conversation is in progress. This makes it possible to provide indications of errors without interrupting the flow of the conversation with the user.
[0047] Next, a processing procedure of the processing executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the processing procedure of the processing executed by the information processing device 1 according to the embodiment.
[0048] As shown in FIG. 7, the control unit 3 first accepts a language designation and a topic from the user terminal 100 (step S101).
[0049] Next, the control unit 3 accepts an utterance in the specified language from the user terminal 100 (step S102).
[0050] Next, the control unit 3 converts the spoken voice into text (step S103).
[0051] Next, the control unit 3 estimates the user's proficiency level in the predetermined language based on the spoken voice and the spoken text (step S104).
[0052] Next, the control unit 3 inputs the evaluation request, the answer request, and the spoken text to the model, thereby acquiring the output of the model (step S105).
[0053] Next, the control unit 3 converts the output of the model into voice (step S106), provides it to the user terminal 100 (step S107), and ends the process.
[0054] 〔others〕 In addition, among the processes described in the above embodiments, some of the processes described as being performed automatically can be performed manually. Alternatively, all or some of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.
[0055] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.
[0056] 3 may be held in a storage server or the like instead of being held by each device. In this case, each device obtains various pieces of information by accessing the storage server.
[0057] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 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 IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.
[0058] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050 and programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, 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), a HDD (Hard Disk Drive), a flash memory, or the like.
[0059] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by a USB, for example.
[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. The input device 1020 may also be an external storage medium such as a USB memory.
[0061] The network IF 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 IF 1060 and the input IF 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 1, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 3 by executing a program loaded onto the primary storage device 1040.
[0064] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes a reception unit 31, an estimation unit 32, an acquisition unit 33, and a provision unit 34. The reception unit 31 receives a user's utterance in a predetermined language. The estimation unit 32 estimates the user's proficiency level in the predetermined language based on the received utterance. The acquisition unit 33 inputs utterance information indicating the utterance and a request text requesting a response according to the proficiency level to a model that outputs a response text that is a response to the input information, and acquires the response text indicating the response output from the model. The provision unit 34 provides the user with content based on the acquired response text. With such a configuration, it is possible to provide better services.
[0065] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.
[0066] 〔others〕 In addition, 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 by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.
[0067] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.
[0068] Furthermore, the processes described in the above-described embodiments can be appropriately combined as long as the process contents are not contradictory.
[0069] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, the control unit 3 can be read as control means or a control circuit. [Explanation of symbols]
[0070] 1. Information processing device 2. Communications Department 3. Control Unit 4 Storage section 31 Reception 32 Estimation part 33 Acquisition Department 34 Providing Department 41 User Information 42 Model Information 43 Topic Information 100 user terminals S Information Processing System
Claims
1. a reception unit that receives an utterance in a predetermined language from a user; an estimation unit that estimates a proficiency level of the user in the predetermined language based on the received utterance; an acquisition unit that inputs utterance information indicating the utterance and a request text requesting a response according to the proficiency level to a model that outputs a response text that is a response to the input information, and acquires the response text indicating the response output from the model; a providing unit that provides content based on the acquired response text to the user; An information processing device comprising:
2. The acquisition unit is A request text is input, the request text requesting an answer to the utterance as the response, and the response text indicating the answer is obtained. The information processing device according to claim 1 .
3. The acquisition unit is inputting a request text requesting an evaluation of language ability in the utterance as the response, and obtaining the response text indicating the evaluation; The information processing device according to claim 1 .
4. The acquisition unit is A request text is input, which requests an evaluation on a specified ability element among a plurality of ability elements constituting the language ability as the response, and the response text indicating the evaluation is obtained. The information processing device according to claim 3 .
5. The request text for the evaluation may include: A text requesting the correction of a linguistic error in the utterance. The information processing device according to claim 3 .
6. The providing unit is When providing content related to the suggestions output from the model, the amount of suggestions provided is changed depending on the content of the conversation with the user. The information processing device according to claim 5 .
7. The estimation unit is The proficiency level is estimated for each ability element of the predetermined language. The information processing device according to claim 1 .
8. The providing unit is Providing audio content by converting the response text into voice The information processing device according to claim 1 .
9. The providing unit is Converting speech based on linguistic features specified by the user The information processing device according to claim 8.
10. 1. A computer-implemented information processing method, comprising: a receiving step of receiving an utterance in a predetermined language from a user; an estimation step of estimating a proficiency level of the user in the predetermined language based on the received utterance; an acquisition step of inputting utterance information indicating the utterance and a request text requesting a response according to the proficiency level into a model that outputs a response text that is a response to the input information, and acquiring a response text indicating the response output from the model; providing content based on the acquired response text to the user; An information processing method comprising:
11. a receiving step of receiving an utterance in a predetermined language from a user; an estimation step of estimating a proficiency level of the user in the predetermined language based on the received utterance; an acquisition step of inputting utterance information indicating the utterance and a request text requesting a response according to the proficiency level into a model that outputs a response text that is a response to the input information, and acquiring a response text indicating the response output from the model; providing content based on the acquired response text to the user; An information processing program that causes a computer to execute the above.
Citation Information
Patent Citations
Online interactive voice recognition system and voice recognizing method
JP2002157113A
Automatic evaluating device of uttered voice and computer program
JP2006084966A
Partial translation device
JP2007286925A
Foreign language learning device and dialogue system
JP2013512461A
Summary generation device and method and program
JP2014044539A
