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

Abstract

To provide a question for deepening the understanding and interest of a user for an article.SOLUTION: An information processing device 100 comprises: an acquisition unit 121 which acquires a browsing history of articles by a user; a generation unit 122 which generates a sentence encouraging the reaction of the user for the article being browsed by the user using the browsing history of articles by the user acquired by the acquisition unit 121; and an output unit 124 which outputs the sentence encouraging the reaction of the user generated by the generation unit 122.SELECTED DRAWING: Figure 1

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 analyzing the content of comments on articles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-164417 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the prior art does not provide questions that deepen a user's understanding and interest in an article. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems and achieve the objectives, the information processing device is characterized by having an acquisition unit that acquires a user's article viewing history, a generation unit that uses the user's article viewing history acquired by the acquisition unit to generate a sentence that prompts the user to respond to the article the user is viewing, and an output unit that outputs the sentence that prompts the user to respond, generated by the generation unit. [Effects of the Invention]

[0006] According to the present invention, it is possible to provide questions that deepen a user's understanding and interest in an article. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of an information processing device according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of processing performed by the information processing apparatus according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of processing performed by the information processing apparatus according to the embodiment. [Figure 4] FIG. 4 is a flowchart illustrating an example of processing by the information processing device according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a computer that executes an information processing program. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, with reference to the drawings, 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 these embodiments. 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] Conventional technologies exist for analyzing the content of comments on news articles. However, these conventional technologies are unable to deepen users' understanding or interest in the article. For example, one of the purposes of news articles is to arouse as much interest as possible in their content, but even with the use of conventional technologies, it is not possible to encourage users to react to the article by posting comments or rating them. For this reason, it is desirable to create appropriate questions for each user that will attract users' interest in the content of the news article and deepen the discussion.

[0010] Therefore, the information processing device 100 according to this embodiment includes an acquisition unit 121 that acquires a user's article viewing history, a generation unit 122 that uses the user's article viewing history acquired by the acquisition unit 121 to generate a sentence that prompts the user to respond to the article the user is viewing, and an output unit 124 that outputs the sentence that prompts the user to respond, generated by the generation unit 122.

[0011] As a result, the information processing device 100 can deepen the user's understanding and interest in the article content by generating questions for each user using information such as the behavior history and attributes of each user.

[0012] [Configuration of information processing device] First, the configuration of the information processing device 100 will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 1, the information processing device 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that these units may be held in a distributed manner in multiple devices. The processing of these units will be described below.

[0013] 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 a telecommunication 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.

[0014] 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. Examples of information stored in the storage unit 130 include a user ID, user attributes, browsing history, article information, reaction history, data related to various machine learning algorithms, learning data for machine learning, and trained models. The browsing history includes information such as articles previously viewed by the user, articles currently being viewed by the user, the date and time the user started browsing, and the date and time the user finished browsing. The article information includes information such as the article title, headline, content, highlights (parts that attracted attention), comments, creator, ratings for the creator, ratings for the article, and posting date and time. The article information may also be information that has been analyzed using natural language processing. The reaction history includes information such as the content of comments users made on articles and ratings. The information stored in the storage unit 130 is not limited to the information described above.

[0015] 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. 1, the control unit 120 has an acquisition unit 121, a generation unit 122, a selection unit 123, and an output unit 124. Each unit of the control unit 120 will be described below.

[0016] The acquisition unit 121 acquires the browsing history of articles by the user. For example, the acquisition unit 121 acquires information about articles that the user has browsed in the past and information about articles that the user is currently browsing.

[0017] The generation unit 122 generates a sentence that prompts the user to respond to the article that the user is currently viewing, using the user's article viewing history acquired by the acquisition unit 121. For example, the generation unit 122 generates a sentence that prompts the user to comment on or rate the article that the user is currently viewing, using information about articles that the user has previously viewed and information about the article that the user is currently viewing. More specifically, the generation unit 122 acquires information about articles about pets that the user has previously viewed and information about the pet that the user is currently viewing, which are acquired by the acquisition unit 121, and generates a question that prompts the user to respond to the article that the user is currently viewing, such as "Are you sad or happy about XX?", "What is it like actually keeping XX?", "What is it great about it?", etc.

[0018] Furthermore, the generation unit 122 generates sentences that prompt a user's response from the user's article viewing history using a model that has learned the relationship between articles and sentences that prompt a user's response. For example, the generation unit 122 generates sentences that prompt the user to comment or rate the article that the user is viewing using a model that has learned the relationship between articles that have been analyzed by natural language processing and user comments and ratings.

[0019] For example, the generation unit 122 uses a learning model that takes as input information about articles that the user has previously viewed and information about the article that the user is currently viewing, and outputs sentences that prompt the user to respond to the article that the user is currently viewing, thereby generating sentences that prompt the user to respond to the article that the user is currently viewing.

[0020] Here, when generating a sentence, the generation unit 122 uses a model that has been trained to output a response sentence corresponding to the input sentence. For example, this model is stored in a server that processes information and has been independently created by a business (Yahoo). Note that it is desirable to train the input information so that it will not be used as a new response, thereby keeping the input information, such as personal information, confidential.

[0021] Furthermore, the generation unit 122 generates a sentence that prompts a user's response by further using the user's attributes. For example, the generation unit 122 generates a sentence that prompts the user to leave a comment or an evaluation by further using the user's attributes such as the user's age, sex, hometown, place of residence, family structure, occupation, hobbies, preferences, and inclinations. More specifically, the generation unit 122 uses information on the user's age and hometown to generate a question that prompts the user to leave a comment, such as "How do you feel as someone of the XX generation?" or "What do you think as a resident of XX prefecture?"

[0022] At this time, the generation unit 122 may change the expression of the sentence that prompts the user's response in accordance with the user's attributes. For example, if the user's age is less than a predetermined value, the generation unit 122 generates a sentence that prompts the user's response using easier and more understandable expressions. Note that the user's attributes used to change the expression of the sentence that prompts the user's response are not limited to age, and the generation unit 122 may use information included in the user's attributes as appropriate.

[0023] Furthermore, the user attributes used by the generation unit 122 when generating a sentence that prompts a user response may be user attributes stored in the storage unit 130, or may be user attributes selected by the selection unit 123 described below.

[0024] Furthermore, the generation unit 122 generates a sentence that prompts the user to make a response, further using the user's response history. For example, the generation unit 122 generates a sentence that prompts the user to make a comment or evaluation, further using the user's response history, such as the user's past comment content and article evaluation. More specifically, the generation unit 122 generates a question that prompts the user to make a comment, such as "What do you think about XX?", using information on the user's past comment, such as "I experienced XX, and it was..."

[0025] Furthermore, for example, the generation unit 122 generates a question that prompts the user to make a comment, using information on whether or not the user has made a comment in the past, for the sentence generated by the generation unit 122. For example, the generation unit 122 may generate a sentence that prompts the user to make a comment or rate, using a model that has undergone reinforcement learning using information on whether or not the user has made a comment in the past.

[0026] The selection unit 123 selects a user attribute. For example, the selection unit 123 selects a user attribute by accepting an operation by a user, an external device, an external system, or the like. For example, the selection unit 123 selects a user attribute by accepting an operation by a user of a slider, a pull-down menu, a radio button, a check box, or the like. More specifically, the selection unit 123 accepts a slider operation from the user to select a user attribute (age) and change the user attribute from "30s" to "40s." Furthermore, for example, the selection unit 123 accepts a pull-down menu operation from the user to select a user attribute (place of origin) and change the user attribute from "Hokkaido" to "Aomori Prefecture."

[0027] The output unit 124 outputs the sentence that prompts the user to respond, which is generated by the generation unit 122. For example, the output unit 124 displays the sentence that prompts the user to leave a comment or rating, which is generated by the generation unit 122, together with the content of the article. Furthermore, for example, the output unit 124 displays the sentence that prompts the user to leave a comment or rating, which is generated by the generation unit 122, on a page different from the page on which the content of the article is displayed.

[0028] [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. 2 and Fig. 3. Fig. 2 and Fig. 3 are diagrams illustrating an example of processing performed by the information processing device 100 according to the embodiment. First, Fig. 2(1) is a schematic diagram showing a user's article browsing history. For example, articles A to E shown in Fig. 2(1) are articles that the user has previously browsed, and article F is an article that the user is currently browsing. Here, for example, the acquisition unit 121 acquires information on articles A to E that the user has previously browsed and article F that the user is currently browsing.

[0029] 2(2) is a schematic diagram showing an output screen of the generated sentences that prompt the user's reaction. For example, first, the generation unit 122 uses, as input, article information (A to E) about pets that the user has previously viewed and article information (F) about the pet that the user is currently viewing, and a learning model that outputs sentences that prompt the user's reaction to the article that the user is currently viewing, to generate sentences such as "Are you sad or happy about XX?", "How is it actually keeping XX?", and "What's so great about it?" as sentences that prompt the user's reaction to the article (F) about the pet that the user is currently viewing.

[0030] Then, the output unit 124 displays the generated sentence as shown in Fig. 2(2). At this time, the output unit 124 may display the generated sentence together with the content of the article, or may display it on a page different from the content of the article.

[0031] Next, Fig. 3(1) is a schematic diagram showing a change of a user attribute. For example, as shown in Fig. 3(1), the selection unit 123 accepts a pull-down operation from the user, selects a user attribute (place of origin), and changes the user attribute from "Hokkaido" to "Aomori Prefecture." Note that a slider, pull-down, radio button, check box, etc. for selecting a user attribute may be displayed together with the text generated by the generation unit 122.

[0032] Next, the generation unit 122 uses the changed user attributes to generate a question that prompts the user to comment, such as "As a resident of Aomori prefecture, what do you think about XX?" Then, the output unit 124 displays the generated sentence again, as shown in FIG. 2(2).

[0033] 〔flowchart〕 Next, the flow of processing by the information processing device 100 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of the flow of processing according to this embodiment.

[0034] First, the acquisition unit 121 acquires the browsing history of articles by the user (step S101). For example, the acquisition unit 121 acquires information about articles that the user has browsed in the past and information about articles that the user is currently browsing.

[0035] Next, the generation unit 122 generates a sentence that prompts the user to respond to the article that the user is currently viewing, using the user's article viewing history acquired by the acquisition unit 121 (step S102). For example, the generation unit 122 generates a sentence that prompts the user to comment or rate the article that the user is currently viewing, using information about articles that the user has previously viewed and information about the article that the user is currently viewing. Furthermore, for example, the generation unit 122 further uses user attributes to create a sentence that prompts the user to comment or rate the article.

[0036] Then, the output unit 124 outputs the sentence generated by the generation unit 122 to prompt the user's reaction (step S103). For example, the output unit 124 displays the sentence generated by the generation unit 122 to prompt the user to leave a comment or rating together with the content of the article.

[0037] Thereafter, the selection unit 123 determines whether or not a user attribute has been selected by the user or the like (step S104). Here, for example, if the selection unit 123 determines that a user attribute has been selected by the user or the like (step S104 "YES"), the selection unit 123 accepts an operation by the user or the like and selects a user attribute (step S105). Thereafter, the processing of step S102 is performed again. On the other hand, if the selection unit 123 determines that a user attribute has not been selected (step S104 "NO"), the information processing device 100 ends the processing.

[0038] 〔effect〕 The information processing device 100 according to the embodiment includes an acquisition unit 121 that acquires a user's article viewing history, a generation unit 122 that uses the user's article viewing history acquired by the acquisition unit 121 to generate a sentence that prompts the user to respond to the article the user is viewing, and an output unit 124 that outputs the sentence that prompts the user to respond, generated by the generation unit 122.

[0039] As a result, the information processing device 100 can generate and output sentences that prompt the user's reaction to the article that the user is viewing based on the information of the user's viewing history, and can provide questions that deepen the user's understanding and interest in the article.

[0040] Furthermore, in the information processing device 100 according to the embodiment, the generation unit 122 generates sentences that prompt a user's response from the user's article browsing history using a model that has learned the relationship between articles and sentences that prompt a user's response. As a result, by using the learning model, the information processing device 100 can generate and output sentences that prompt a user's response to the article that the user is browsing based on information about the user's browsing history, and can provide questions that deepen the user's understanding and interest in the article.

[0041] Furthermore, in the information processing device 100 according to the embodiment, the generation unit 122 further generates a sentence that prompts a user's response by using the user's attributes. As a result, the information processing device 100 can generate and output a sentence that prompts the user's response to the article that the user is viewing, based on the information on the user's browsing history and the user's attributes, and can provide a question that deepens the user's understanding and interest in the article.

[0042] Furthermore, in the information processing device 100 according to the embodiment, the generation unit 122 further generates a sentence that prompts a user's reaction using the user's reaction history. As a result, the information processing device 100 can generate and output a sentence that prompts the user's reaction to the article that the user is viewing, based on the information on the user's browsing history and the user's reaction history, and can provide a question that deepens the user's understanding and interest in the article.

[0043] Moreover, the information processing device 100 according to the embodiment further includes a selection unit 123 that selects a user attribute, and the generation unit 122 generates a sentence that prompts a user's response by using the user attribute selected by the selection unit 123. As a result, the information processing device 100 can generate and output a sentence that prompts a user's response to an article that the user is viewing, based on information about the user's browsing history and the selected user attribute, and can provide a question that deepens the user's understanding of and interest in the article.

[0044] 〔program〕 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. 5. The following description will be given taking the information processing device 100 as an example. Fig. 5 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, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0045] The CPU 1100 operates and controls each unit based on programs 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 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0046] 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.

[0047] 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 generated data to the output devices via the input / output interface 1600.

[0048] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. 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.

[0049] For example, when the computer 1000 functions as the information processing device 100, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 120. The HDD 1400 also stores various 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, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0050] 〔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.

[0051] Furthermore, the above-mentioned "module (-er suffix, -or suffix)" can be read as a unit, means, 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]

[0052] 100 Information processing device 110 Communications Department 120 control section 121 Acquisition Department 122 Generation part 123 Selection Section 124 Output section 130 Storage section

Claims

1. an acquisition unit that acquires a user's article browsing history; a generation unit that inputs article information previously viewed by the user and article information currently being viewed by the user, which are included in the user's article viewing history acquired by the acquisition unit, into a learning model that uses the article information previously viewed by the user and the article information currently being viewed by the user as input and outputs sentences that prompt the user to respond to the article currently being viewed by the user, and generates sentences that prompt the user to respond to the article currently being viewed by the user related to the input information; an output unit that outputs the sentence that prompts a response from the user and that is generated by the generation unit; An information processing device comprising:

2. 1. A computer-implemented information processing method, comprising: an acquisition step of acquiring a user's article browsing history; a generation process of inputting article information previously viewed by the user and article information currently being viewed by the user, which are included in the user's article viewing history acquired by the acquisition process, into a learning model that uses the article information previously viewed by the user and the article information currently being viewed by the user as input and outputs a sentence that prompts the user to respond to the article currently being viewed by the user, thereby generating a sentence that prompts the user to respond to the article currently being viewed by the user related to the input information; an output step of outputting the sentence that prompts a response from the user, which is generated by the generation step; An information processing method comprising:

3. an acquisition step of acquiring a user's article browsing history; a generation step of inputting article information previously viewed by the user and article information currently being viewed by the user, which are included in the user's article viewing history acquired by the acquisition step, into a learning model that uses the article information previously viewed by the user and the article information currently being viewed by the user as input and outputs a sentence that prompts the user to respond to the article currently being viewed by the user, thereby generating a sentence that prompts the user to respond to the article currently being viewed by the user related to the input information; an output step of outputting the sentence that prompts a response from the user, which is generated by the generation step; An information processing program characterized by causing a computer to execute the above.

Images