Information processing device, information processing method, and information processing program
The information processing device efficiently identifies and summarizes relevant articles in response to user queries, addressing the limitations of conventional systems by providing accurate and interactive information delivery.
Patent Information
- Application Number
- JP2023081819
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-17
- Publication Date
- 2024-11-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Conventional information processing techniques fail to efficiently provide users with the desired information, often requiring users to read summaries that lack necessary details and necessitate additional searches for clarification, which can be burdensome and prone to biased content.
An information processing device that acquires user input sentences, identifies relevant articles through natural language processing and machine learning, generates summaries of those articles, and outputs them to the user, utilizing a trained model to ensure relevance and accuracy.
Efficiently provides users with desired information by identifying and summarizing relevant articles, addressing user queries interactively and reducing the need for additional searches, while ensuring the accuracy and reliability of the provided content.
Smart Images

Figure 2024165541000001_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] Conventionally, there exists a technique for generating summary information of an article. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2019-053558 A Summary of the Invention [Problem to be solved by the invention]
[0004] However, the conventional techniques are unable to efficiently provide the information desired by the user. [Means for solving the problem]
[0005] In order to solve the above-mentioned problems and achieve the objective, an information processing device is characterized in having an acquisition unit that acquires a sentence input by a user on an application, an identification unit that identifies an article related to the sentence acquired by the acquisition unit, a generation unit that generates a summary of the article identified by the identification unit as a response to the sentence acquired by the acquisition unit, and an output unit that outputs information about the article identified by the identification unit and the summary generated by the generation unit on the application. Effect of the Invention
[0006] According to the present invention, it is possible to efficiently provide information desired by a user. [Brief description of the drawings]
[0007] [Figure 1]FIG. 1 is a diagram illustrating an overview of an information processing device according to an embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of processing performed by the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating an example of processing by the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a computer that executes an information processing program. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0008] Hereinafter, with reference to the drawings, an embodiment of an information processing device, an information processing method, and an information processing program according to the present application will be described in detail. Note that the present invention is not limited to the embodiment. In addition, in the description of the drawings, the same parts are denoted by the same reference numerals, and duplicated explanations will be omitted.
[0009] [Introduction] First, an overview of an information processing device 100 will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an overview of the information processing device.
[0010] Conventionally, there are technologies that summarize the contents of articles such as news to reduce the burden on users in collecting information. However, conventional technologies cannot efficiently provide the information desired by users. For example, summaries in conventional technologies merely summarize the main points of a text, and do not necessarily summarize the information required by the user. Furthermore, if a user does not have sufficient background knowledge, it is difficult to accurately understand the contents of the summary without reading the original article and related articles before the summary.
[0011] Furthermore, to resolve any questions that arise while reading summaries or articles, users must search for and view additional articles, which places a heavy burden on users. In addition, users must themselves determine whether the content of an article is biased, which is difficult to avoid.
[0012] Therefore, the information processing device 100 according to the present embodiment performs the following process. First, the information processing device 100 acquires a sentence such as "Tell me about the achievements of XX player" input on an application such as a talk application running on a terminal device, for example, as shown in FIG. 1(1). Next, the information processing device 100 identifies an article corresponding to the acquired sentence. Next, the information processing device 100 generates a summary of the identified article as a response to the acquired sentence. Then, as shown in FIG. 1(2), for example, the information processing device 100 outputs the title of the identified article (including URL information) "XX hits a home run in two consecutive at-bats!!", "XX and XX double steal!", and the summary of the generated article "Information regarding the recent achievements of XX player is as follows. · In the XX vs. XX game held on XX / XX, XX player hit a home run in two consecutive at-bats, contributing to the victory with XX number of at-bats, XX hits, and XX RBIs. · In the XX vs. XX game held on XX / XX, XX player and XX player successfully performed a double steal." on the application and provides it to the user.
[0013] This enables the information processing device 100 to acquire information desired by the user in an interactive manner, and efficiently provide the information desired by the user.
[0014] [Configuration of information processing device] Next, the configuration of the information processing device 100 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 2, the information processing device 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that each of these units may be held in a distributed manner in a plurality of devices. The processing of each of these units will be described below.
[0015] The communication unit 110 is realized by a NIC (Network Interface Card) or the like, and enables communication between an external device and the control unit 120 via an electric communication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 enables communication between the external device and the control unit 120.
[0016] The storage unit 130 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The information stored in the storage unit 130 includes, for example, a user ID, a user attribute, a browsing history, a sentence input on an application, article information, data related to various machine learning algorithms, learning data for machine learning, and a learned model. Here, the article information includes various information such as the title, headline, content, highlights (parts that attracted attention), comments, creator, evaluation of the creator, evaluation of the article, and posting date and time. The article information may also be information that has been analyzed by natural language processing. Note that the information stored in the storage unit 130 is not limited to the above-mentioned.
[0017] The control unit 120 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in Fig. 2, the control unit 120 has an acquisition unit 121, an identification unit 122, a generation unit 123, and an output unit 124. Each unit of the control unit 120 will be described below.
[0018] The acquisition unit 121 acquires a sentence input by a user on an application. For example, the acquisition unit 121 acquires a sentence such as a question or a request input by a user on an application used for communication. More specifically, the acquisition unit 121 acquires a sentence such as "Please tell me about the achievements of XX player" input by a user on a chat application. Note that the sentence acquired by the acquisition unit 121 may be something like an everyday conversation, in addition to a question or a request.
[0019] The identification unit 122 identifies an article related to the sentence acquired by the acquisition unit 121. For example, the identification unit 122 identifies an article related to the content of a sentence such as a question or a request acquired by the acquisition unit 121. More specifically, first, the identification unit 122 analyzes the sentence acquired by the acquisition unit 121 by natural language processing such as morphological analysis, grammatical analysis, semantic analysis, and context analysis.
[0020] Thereafter, the identification unit 122 receives the analyzed sentence as an input, and uses the analyzed sentence and information on each analyzed article stored in the storage unit 130 to use a learning model that outputs articles that are highly relevant to the sentence acquired by the acquisition unit 121, thereby identifying articles that are highly relevant to the sentence acquired by the acquisition unit 121. Note that for the natural language processing and learning model used in the process of identifying articles that are highly relevant to the sentence acquired by the acquisition unit 121, conventional technologies according to the purpose can be used.
[0021] Furthermore, the identification unit 122 identifies an article related to an article previously identified and a sentence acquired by the acquisition unit 121. For example, the identification unit 122 identifies an article related to information of an article previously identified and currently being viewed by the user and a sentence of a question or request acquired by the acquisition unit 121. More specifically, the identification unit 122 analyzes the sentence acquired by the acquisition unit 121 by natural language processing, and uses information of the analyzed sentence and information of an article previously identified and currently being viewed by the user as input, and identifies an article highly related to the sentence acquired by the acquisition unit 121 by using information of the article currently being viewed by the user, the analyzed sentence, and information of each analyzed article, and using a learning model that outputs an article highly related to the sentence acquired by the acquisition unit 121.
[0022] Also, for example, the identification unit 122 identifies articles related to information of articles identified in the past and viewed by the user and text of a question or request acquired by the acquisition unit 121. More specifically, the identification unit 122 analyzes the text acquired by the acquisition unit 121 by natural language processing, and uses information of the analyzed text and information of articles identified in the past and viewed by the user as input, and identifies articles highly related to the text acquired by the acquisition unit 121 by using information of the articles viewed by the user, the analyzed text, and information of each analyzed article, and using a learning model that outputs articles highly related to the text acquired by the acquisition unit 121.
[0023] Furthermore, the identification unit 122 identifies articles related to the text, using the text acquired by the acquisition unit 121 and the reactions to the article. For example, the identification unit 122 identifies articles highly related to the text acquired by the acquisition unit 121, using the content of the text, such as a question or request, acquired by the acquisition unit 121, and information, such as the evaluation of an article provider for each article stored in the storage unit 130 and the evaluation of the article.
[0024] More specifically, the identification unit 122 analyzes the sentence acquired by the acquisition unit 121 using natural language processing, and uses as input information on the analyzed sentence, information on the creator of each article, and information on reactions to the article such as evaluations of the creator and evaluations of the article, and uses the analyzed sentence, information on reactions to the article, and information on each analyzed article to identify articles that are highly relevant to the sentence acquired by the acquisition unit 121 by using a learning model that outputs articles that are highly relevant to the sentence acquired by the acquisition unit 121.
[0025] Furthermore, the identification unit 122 identifies articles related to the text, using the text acquired by the acquisition unit 121 and the content of comments on the article. For example, the identification unit 122 identifies articles highly related to the text, using the content of the text, such as a question or request, acquired by the acquisition unit 121, and the content of the highlighted parts of the article stored in the storage unit 130 and the content of the comments on the highlighted parts.
[0026] More specifically, the identification unit 122 analyzes the sentence acquired by the acquisition unit 121 using natural language processing, and uses as input information on the analyzed sentence and information on comments on the article, such as the highlighted parts of the article and the content of the comments on the highlighted parts, to identify articles that are highly relevant to the acquired sentence by using a learning model that outputs articles that are highly relevant to the acquired sentence using the analyzed sentence, information on the comments on the article, and information on each analyzed article.
[0027] Furthermore, the identification unit 122 identifies an article related to the text by using the text acquired by the acquisition unit 121 and attribute information of the user. The identification unit 122 identifies related articles by using attribute information of the user, such as the user's age, sex, birthplace, residence, family structure, occupation, hobbies, preferences, and inclinations, in addition to the content of the text, such as a question or request, acquired by the acquisition unit 121.
[0028] More specifically, the identification unit 122 analyzes the sentence acquired by the acquisition unit 121 using natural language processing, and uses information on the analyzed sentence and user attribute information such as the user's age, gender, place of origin, place of residence, family structure, occupation, hobbies, preferences, and inclinations as input, and identifies articles that are highly relevant to the acquired sentence by using a learning model that outputs articles that are highly relevant to the acquired sentence using the analyzed sentence, the user attribute information, and information on each analyzed article.
[0029] The generation unit 123 generates a summary of the article identified by the identification unit 122 as a response to the sentence acquired by the acquisition unit 121. For example, the generation unit 123 generates a summary of the article identified by the identification unit 122 as a response to the sentence acquired by the acquisition unit 121 using a model that receives the sentence acquired by the acquisition unit 121 and information on the article identified by the identification unit 122 as input and outputs a summary of the article.
[0030] Here, when generating an article summary, the generation unit 123 uses a model that has been trained to output a response sentence corresponding to an input sentence. For example, this model is in a server that processes information, and is created independently by a business (Yahoo). It is preferable that the input information is trained so that it is not used as a new response, thereby concealing the input information, such as personal information.
[0031] The output unit 124 outputs, to an application, information on the article identified by the identification unit 122 and the summary generated by the generation unit 123. For example, the output unit 124 outputs, to an application used by a user for communication, the title of the article identified by the identification unit 122 (including URL information) and the summary generated by the generation unit 123.
[0032] [Processing performed by information processing device] Next, an example of processing performed by the information processing device 100 according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram for explaining an example of processing performed by the information processing device 100 according to the embodiment. First, Fig. 3(1) is an example in which a user inputs a sentence on an application used for communication. At this time, for example, the acquisition unit 121 acquires a sentence such as a request or question, such as "Tell me about the achievements of XX player", input by the user on the application.
[0033] 3(2) is an example that illustrates a schematic diagram of article information stored in the storage unit 130. For example, the identification unit 122 performs natural language processing such as morphological analysis on the text information acquired by the acquisition unit 121, and uses the analyzed text as an input to compare the information on the analyzed text with the information on each article that has been analyzed and stored in the storage unit 130, thereby identifying articles related to the text acquired by the acquisition unit 121 using a model that outputs articles that are highly related to the text acquired by the acquisition unit 121. For example, the identification unit 122 identifies article B and article E as articles related to the text acquired by the acquisition unit 121, "Tell me about the achievements of XX player."
[0034] Here, the identification unit 122 may further identify an article using information on an article previously identified or an article currently being viewed. For example, the identification unit 122 identifies an article about "raccoons living in the city" from information on an animal article previously identified and a sentence such as "Please tell me about raccoons." For example, the identification unit 122 identifies an article about "raccoon dance" from information on a baseball article previously identified and currently being viewed and a sentence such as "Please tell me about raccoons."
[0035] Furthermore, the identification unit 122 may further identify articles using reactions to the articles. For example, when the acquisition unit 121 acquires a sentence such as "I want highly reliable information about the XX virus," the identification unit 122 uses information on reactions to the articles, such as information on the creators of the articles, evaluations of the creators, and evaluations of the articles, to identify articles that include highly reliable information from among articles related to the XX virus.
[0036] Furthermore, the identification unit 122 may further identify an article using comments on the article. For example, when the acquisition unit 121 acquires a sentence such as "I want to know what other people think about the XX incident," the identification unit 122 uses information such as the highlight portion included in each article and the comments on the highlight portion to identify articles that include various opinions of other users among the articles related to the XX incident.
[0037] Furthermore, the identification unit 122 may further identify an article by using a user attribute. For example, when the acquisition unit 121 acquires a sentence such as "What is XX?", the identification unit 122 identifies, from among articles highly related to XX, an article that has a large number of views, comments, etc., from users who have attribute information in common with the user who input the sentence.
[0038] The additional elements used to identify the above-mentioned articles can be combined according to the purpose. For example, when the acquisition unit 121 acquires a sentence such as "Please tell me about reliable information about the XX virus and what people of the same age are worried about," the identification unit 122 uses information about the creator of each article, reactions to the article such as evaluations of the creator and evaluations of the article, comments on the article such as the highlights of each article and comments on the highlights, and user information such as age to identify articles that include reliable information among articles about the XX virus and articles that have many comments posted by users of the same age on the articles about the XX virus.
[0039] 4(3) is an example that diagrammatically illustrates information on an article summarized by the generation unit 123. The generation unit 123 generates a summary of the article identified by the identification unit 122 as an answer to the sentence acquired by the acquisition unit 121. For example, the generation unit 123 inputs the sentence acquired by the acquisition unit 121 and information on the article identified by the identification unit 122 into a trained large-scale language model that is independently created by a business entity (Yahoo), thereby obtaining a result that summarizes the information on the article identified by the identification unit 122 to be an answer to the sentence acquired by the acquisition unit 121.
[0040] For example, the generation unit 123 inputs the sentence "Tell us about player XX's achievements" acquired by the acquisition unit 121, information about the article "XX hits home runs in two consecutive at-bats!!" identified by the identification unit 122, and information about the article "XX and XX perform a double steal!", and generates information such as "Information about player XX's recent achievements is as follows: - In the XX vs. XX game held on XX / XX, player XX hit home runs in two consecutive at-bats, contributing to the victory with XX at-bats, XX hits, and XX RBIs. - In the XX vs. XX game held on XX / XX, player XX and player XX successfully performed a double steal."
[0041] Here, the generation unit 123 may generate a summary using not only the contents of the article but also each element included in the information of the article. For example, the generation unit 123 can generate a summary using the contents of comments added to the highlighted parts of the article.
[0042] 4(4) shows an example in which a summary and an article title (including URL information) are output on an application used for communication by the output unit 124. When the user further inputs a question, request, or other text in response to the output result by the output unit 124, the information processing device 100 repeats the above-mentioned process again.
[0043] 〔flowchart〕 Next, a flow of processing by the information processing device 100 will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of a flow of processing according to this embodiment.
[0044] First, the acquisition unit 121 acquires a sentence input by a user on an application (step S101). For example, the acquisition unit 121 acquires a sentence such as a question or a request input by a user on an application used for communication.
[0045] Next, the identifying unit 122 identifies an article related to the text acquired by the acquiring unit 121 (step S102). For example, the identifying unit 122 identifies an article related to the content of the text, such as a question or a request, acquired by the acquiring unit 121.
[0046] Then, the generation unit 123 generates a summary of the article identified by the identification unit 122 as a response to the sentence acquired by the acquisition unit 121 (step S103). For example, the generation unit 123 generates a summary of the article identified by the identification unit 122 as a response to the sentence acquired by the acquisition unit 121 using a model that receives the sentence acquired by the acquisition unit 121 and information on the article identified by the identification unit 122 as input and outputs a summary of the article.
[0047] Then, the output unit 124 outputs the information of the article identified by the identification unit 122 and the summary generated by the generation unit 123 to an application (step S104). For example, the output unit 124 outputs the information of the article identified by the identification unit 122 and the summary generated by the generation unit 123 to an application used by the user for communication.
[0048] After that, the acquisition unit 121 judges whether or not the user has input text on the application (step S105). If the acquisition unit 121 judges that the user has input text on the application (step S105 "YES"), the process returns to step S101 and executes the process again. On the other hand, if the acquisition unit 121 judges that the user has not input text on the application (step S105 "NO"), the information processing device 100 ends the process.
[0049] 〔effect〕 Thus, the information processing device 100 according to the embodiment has an acquisition unit 121 that acquires a sentence input by a user on an application, an identification unit 122 that identifies an article related to the sentence acquired by the acquisition unit 121, a generation unit 123 that generates a summary of the article identified by the identification unit 122 as a response to the sentence acquired by the acquisition unit 121, and an output unit 124 that outputs information on the article identified by the identification unit 122 and the summary generated by the generation unit 123 on the application.
[0050] As a result, the information processing device 100 can efficiently provide the information that the user is looking for by identifying articles related to the sentence that the user has entered on the application and summarizing the contents of the identified articles to provide an answer to the sentence.
[0051] Furthermore, in the information processing device 100 according to the embodiment, the identification unit 122 identifies an article related to a previously identified article and a sentence acquired by the acquisition unit 121. As a result, the information processing device 100 can efficiently provide information desired by a user by identifying an article related to a sentence input by a user on an application and an article identified in the past and summarizing the identified article content as an answer to the sentence.
[0052] Furthermore, when the user has additional questions or requests regarding the generated summary, the information processing device 100 identifies related articles again and summarizes the contents of the identified articles to provide answers to the text, thereby resolving questions that arise while the user is reading the summary and efficiently providing the user with the information they are looking for.
[0053] Furthermore, in the information processing device 100 according to the embodiment, the identification unit 122 identifies an article related to the sentence, using the sentence and the reaction to the article acquired by the acquisition unit 121. As a result, the information processing device 100 identifies an article related to a sentence input by a user on an application, using the reaction to the article, and summarizes the content of the identified article as an answer to the sentence, thereby making it possible to efficiently provide information desired by the user.
[0054] Furthermore, in the information processing device 100 according to the embodiment, the identification unit 122 identifies an article related to the sentence, using the sentence acquired by the acquisition unit 121 and the content of the comment on the article. As a result, the information processing device 100 identifies an article related to a sentence input by a user on an application, using the content of the comment on the article, and summarizes the identified article content as an answer to the sentence, thereby making it possible to efficiently provide information desired by the user.
[0055] Furthermore, in the information processing device 100 according to the embodiment, the identification unit 122 identifies an article related to the sentence, using the sentence acquired by the acquisition unit 121 and the user's attribute information. As a result, the information processing device 100 identifies an article related to the sentence input by the user on the application, using the user's attribute information, and summarizes the identified article content to provide an answer to the sentence, thereby efficiently providing information desired by the user.
[0056] 〔program〕 Moreover, the information processing device 100 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 6. The information processing device 100 will be described below as an example. Fig. 6 is a hardware configuration diagram showing an example of a computer that executes an information processing program. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.
[0057] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.
[0058] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.
[0059] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs data generated via the input / output interface 1600 to the output devices.
[0060] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.
[0061] For example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1200 to realize the function of the control unit 120. In addition, the HDD 1400 stores each piece of data in the storage device of the information processing device 100. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from another device via a predetermined communication network.
[0062] 〔others〕 Although various embodiments have been described in detail herein with reference to the drawings, these embodiments are examples and are not intended to limit the present invention to these embodiments.
[0063] Furthermore, the above-mentioned "module (-er suffix, -or suffix)" can be read as a unit, a means, a circuit, etc. For example, a communication module, a control module, and a storage module can be read as a communication unit, a control unit, and a storage unit, respectively. [Explanation of symbols]
[0064] 100 Information processing device 110 Communications Department 120 Control section 121 Acquisition Department 122 Specific part 123 Generation part 124 Output section 130 Storage section
Claims
1. An acquisition unit that acquires a sentence input by a user on an application; an identification unit that identifies an article related to the text acquired by the acquisition unit; a generation unit that generates a summary of the article identified by the identification unit as a response to the sentence acquired by the acquisition unit; an output unit that outputs information on the article identified by the identification unit and the summary generated by the generation unit onto the application; 13. An information processing device comprising:
2. The identification unit is Identifying an article related to the previously identified article and the text acquired by the acquisition unit 2. The information processing apparatus according to claim 1,
3. The identification unit is Using the sentence acquired by the acquisition unit and the reaction to the article, an article related to the sentence is identified.
2. The information processing apparatus according to claim 1,
4. The identification unit is Using the text acquired by the acquisition unit and the contents of comments on the article, an article related to the text is identified.
2. The information processing apparatus according to claim 1,
5. The identification unit is Using the sentence acquired by the acquisition unit and attribute information of the user, an article related to the sentence is identified.
2. The information processing apparatus according to claim 1,
6. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring a sentence input by a user on an application; a step of identifying an article related to the text acquired by the acquisition step; a generating step of generating a summary of the article identified by the identifying step as a response to the sentence acquired by the acquiring step; an output step of outputting, on the application, information on the article identified in the identification step and the summary generated in the generation step; 13. An information processing method comprising:
7. An acquisition step of acquiring a sentence input by a user on an application; a step of identifying an article related to the sentence acquired by the acquisition step; a generating step of generating a summary of the article identified by the identifying step as a response to the sentence acquired by the acquiring step; an output step of outputting, on the application, information on the article identified in the identification step and the summary generated in the generation step; An information processing program characterized by causing a computer to execute the above.
Citation Information
Patent Citations
History information retrieval apparatus
JP2010061508A
Learning device, learning method, learning program, first model, and second model
JP2019053558A
