Information processing device, information processing method, and information processing program
The information processing device generates summaries and calculates match rates between news article titles and texts, addressing the mismatch issue by ensuring users are aware of content alignment.
Patent Information
- Application Number
- JP2023082705
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-19
- Publication Date
- 2024-11-29
AI Technical Summary
Existing news information analysis devices fail to accurately calculate the match rate between the title and text of a news article, leading to potential mismatch between user expectations and article content.
An information processing device that generates a summary of a news article using a model like T5, calculates a match rate based on Rouge-L scores, and provides this rate along with the article title to users, ensuring alignment between title and content.
Enables users to assess the match rate between a news article's title and content, preventing disappointment from content mismatches by providing appropriate information.
Smart Images

Figure 2024166542000001_ABST
Abstract
Description
[Technical field]
[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]
[0002] The title of the news article did not always accurately express the contents of the main text of the news article. As a result, users who read the main text of the news article after checking the title of the news article sometimes felt that the news article was different from what they had expected based on the title.
[0003] For example, Patent Document 1 listed below discloses a news information analysis device that can execute identity determination for a plurality of distributed news items and improve the accuracy of identity determination. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2012-99001 A Summary of the Invention [Problem to be solved by the invention]
[0005] However, although the news information analysis device described in Patent Document 1 above can perform identity determination of news information, it cannot calculate the matching rate between the title of news information and the main text of a news article and provide appropriate information to users.
[0006] In consideration of the above-mentioned problems, the present disclosure aims to provide an information processing device, an information processing method, and an information processing program that can calculate the matching rate between the body text and title of a news article and provide appropriate information to users. [Means for solving the problem]
[0007] In order to solve the above-mentioned problems and achieve the objective, the information processing device of the present disclosure comprises a generation unit that generates a summary of a news article based on the body of the news article, a calculation unit that calculates a matching rate indicating the degree of matching between the body of the news article and the title of the news article based on the summary of the news article generated by the generation unit and the title of the news article, and a provision unit that provides various information to a user terminal, and the provision unit provides the user terminal with the matching rate calculated by the calculation unit based on the title of the news article and the news article summary, together with the title of the news article. Effect of the Invention
[0008] According to the present disclosure, it is possible to provide an information processing device, an information processing method, and an information processing program that are capable of calculating the matching rate between the body text and the title of a news article and providing appropriate information to a user. [Brief description of the drawings]
[0009] [Figure 1] FIG. 1 is a diagram illustrating a first example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of information provided to a user terminal in the information processing according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of an information processing implementation unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating a second example of information processing according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of information stored in the news article storage unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of information stored in the summary model storage unit of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of information stored in the notification information storage unit of the information processing device according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of the configuration of a user terminal according to the embodiment. [Figure 11] FIG. 11 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 12] FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, a detailed description will be given of an information processing device, an information processing method, and an information processing program according to the present disclosure (hereinafter, referred to as an "embodiment") with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present disclosure are not limited to the embodiment.
[0011] (Embodiment) 1. Information Processing According to the Embodiment 1-1. Example of information processing according to the embodiment First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Fig. 1 shows an example in which information processing according to the embodiment is executed by an information processing device 100 and a user terminal 200. Below, the information processing according to the embodiment will be described step by step.
[0012] First, the information processing device 100 generates a summary of a news article (step S1). For example, as shown in FIG. 1, the information processing device 100 generates a summary A of the news article A by inputting text data of the body of the news article A into a summary model that generates a summary. Specifically, the information processing device 100 may generate a summary of the body of the news article from the text data of the body of the news article by using an abstract summary model such as T5 (Text-to-Text Transfer Transformer). Note that a pre-trained model for Japanese may be used for T5, and a model that has been fine-tuned for a summary task by using a summary of the text and the body of the text as learning data may be used. In addition, a development environment may be prepared using Pytorch or Hugging Face.
[0013] Next, the information processing device 100 calculates a matching rate based on the news article summary and the news article title (step S2). That is, the information processing device 100 calculates a matching rate based on the news article summary generated in step S1 and the news article title. For example, as shown in FIG. 1, the information processing device 100 calculates a matching rate A based on the news article summary A and the news article title A. Specifically, the information processing device 100 calculates Rouge-L based on the news article summary and the news article title, using the following formulas (1), (2), and (3).
[0014]
number
number
number
[0015] In formula (1), X indicates the summary of the news article text, and Y indicates the title of the news article. Furthermore, n indicates the length of the summary of the news article text, and m indicates the length of the news article title. Furthermore, LCS(X,Y) indicates the longest common subsequence of X and Y, and β is Plcs / Rlcs when ∂Flcs / ∂Rlcs=∂Flcs / ∂Plcs. Furthermore, Flcs in formula (3) is Rouge-L.
[0016] Next, the information processing device 100 calculates the matching rate by inputting Rouge-L calculated by formula (3) into the following formula (4).
[0017]
number
[0018] In formula (4), x indicates Rouge-L and score indicates the match rate. This allows the match rate to be calculated by nonlinearly transforming Rouge-L. This makes it possible to prevent bias in the match rate caused by the output of the summary model.
[0019] In this way, the information processing device 100 uses Rouge-L to calculate the matching rate based on the Longest Common Subsequence (LCS) between the summary generated by the summary model and the correct summary (in this case, the title of the news article).
[0020] Next, the information processing device 100 provides the user terminal 200 with the matching rate together with the title of the news article (step S3). For example, the information processing device 100 provides the user terminal 200 with the matching rate between the title of the news article and the summary of the text of the news article together with the title of the news article in a manner as shown in FIG. 2. FIG. 2 is a diagram showing an example of information provided to the user terminal in the information processing according to the embodiment. As shown in FIG. 2, the information processing device 100 causes the user terminal 200 to display the calculation result of the matching rate calculated in step S2 next to the title of the news article. Note that FIG. 2 shows, as an example, that the matching rate of title A is 49.2%, the matching rate of title B is 88.9%, the matching rate of title C is 67.9%, the matching rate of title D is 70.9%, the matching rate of title E is 72.5%, the matching rate of title F is 88.3%, and the matching rate of title G is 64.8%. In this way, the information processing device 100 provides the user terminal 200 with the title of the news article as well as a matching rate indicating the degree of matching between the main text of the news article and the summary of the news article.
[0021] A configuration for implementing the above-described processing of the information processing device 100 will be described with reference to FIG. 3. FIG. 3 is a diagram for explaining an example of a means for implementing the information processing according to the embodiment. As shown in FIG. 3, the information processing according to the present disclosure is implemented by a summary model that is fine-tuned to a summary task by using a summary of a sentence and the main text of the sentence as learning data for a Japanese T5 pre-learning model. A summary is generated by inputting the main text of a news article into the summary model, and a Rouge-L score is calculated based on the generated summary and the title of the news article, and a score conversion is performed on the Rouge-L score to calculate a matching rate. The calculated matching rate is then provided to the user terminal 200 together with the title of the news article.
[0022] According to this, the matching rate between the title of a news article and the summary of the text of the news article can be calculated, and the calculated matching rate can be provided to the user along with the title of the news article. Therefore, the user can view the news article after understanding the matching rate between the title of the news article and the content of the news article, and therefore can avoid disappointment when viewing a news article whose content differs from that expressed in the title of the news article. Therefore, it is possible to provide an information processing device 100 that can calculate the matching rate between the text of a news article and the title and provide appropriate information to the user.
[0023] 1-2. Other Examples of Information Processing According to the Embodiment The information processing device 100 determines notification information to be provided to the user based on the calculated matching rate, and provides the determined notification information to the user terminal 200.
[0024] This information processing will be explained step by step with reference to FIG.
[0025] First, the information processing device 100 accepts a selection of a news article by the user from the user terminal 200 (step S10). For example, the information processing device 100 may cause the user terminal 200 to display titles of a plurality of news articles and accept the selection of a news article from the user.
[0026] Next, the information processing device 100 generates a news summary (step S20). Then, the information processing device 100 calculates a matching rate based on the news article summary and the news article title (step S30). Note that step S20 is the same as step S2 described above, and therefore a description thereof will be omitted. Also, step S30 is the same as step S3 described above, and therefore a description thereof will be omitted.
[0027] Next, the information processing device 100 determines notification information to be provided to the user based on the matching rate (step S40). For example, notification information to be provided to the user according to the matching rate is stored in the notification information storage unit 123 of the information processing device 100, which will be described later. Then, based on the matching rate calculated in step S30, the notification information associated with the matching rate may be read from the notification information storage unit 123, thereby determining the notification information to be provided to the user. Note that, for example, the notification information associated with a matching rate of 50% or less may be a message MS such as "Please note that the title of this news article has a low matching rate with the body of the news article, and therefore the title may not accurately represent the content of the body of the news article."
[0028] Next, the information processing device 100 provides the determined notification information to the user terminal 200 (step S50). For example, the information processing device 100 provides the notification information to the user terminal 200 by causing the user terminal 200 to display the above-mentioned message MS.
[0029] This makes it possible to determine notification information to be provided to a user based on the matching rate between a news article summary and the title of the news article, and to provide the determined notification information to the user terminal 200. This makes it possible to prevent a user from having excessive expectations based on a news article title with a low matching rate, and from being disappointed after reading the main text of the news article because the content differs from the title of the news article. It is therefore possible to provide an information processing device 100 that can calculate the matching rate between the main text and title of a news article and provide appropriate information to a user.
[0030] 2. Configuration of the Information Processing System Next, the configuration of the information processing system according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the information processing system according to the embodiment. As shown in Fig. 5, the information processing system 1 according to the embodiment has an information processing device 100, a user terminal 200, and a network N. Below, these configurations will be briefly described in order.
[0031] The information processing device 100 may be, for example, a personal computer (PC), a work station (WS), a computer having a server function, etc. The information processing device 100 performs processing based on information transmitted from the user terminal 200 via the network N, for example.
[0032] The user terminal 200 is an information processing device used by a user. The user terminal 200 may be, for example, an information processing device such as a smartphone, a tablet terminal, a desktop PC, a notebook PC, a mobile phone, or a PDA (Personal Digital Assistant). In the example shown in FIG. 1, the user terminal 200 is a smartphone. The information processing system 1 may include multiple user terminals 200.
[0033] The network N connects the information processing device 100 and the user terminal 200 in a wired or wireless manner so that they can communicate with each other. If the network N is wired, it may be realized by Ethernet (registered trademark) defined in IEEE802.3. If the network N is wireless, it may be realized by a wireless LAN (Local Area Network) defined in IEEE802.11.
[0034] 3. Configuration of Information Processing Device Next, the configuration of the information processing device 100 will be described with reference to FIG.
[0035] 6 is a diagram showing an example of the configuration of an information processing device according to an embodiment. As shown in FIG. 6, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit .
[0036] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC), a wireless local area network (LAN) card, etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the user terminal 200, etc.
[0037] (Regarding the storage unit 120) The storage unit 120 includes a main storage device and an external storage device. The main storage device stores programs executed by the control unit 130 or data processed by the control unit 130. The main storage device may be realized by, for example, a semiconductor memory element such as a random access memory (RAM), a read only memory (ROM), or a flash memory. The external storage device saves data processed by the control unit 130. The external storage device may be realized by, for example, a hard disk, a solid state drive (SSD), a magnetic tape, an optical disk, or the like.
[0038] 6, the storage unit 120 has a news article storage unit 121, a summary model storage unit 122, and a notification information storage unit 123. Below, these components will be described in order.
[0039] (Regarding the news article storage unit 121) The news article storage unit 121 stores information related to news articles. Here, an example of information stored in the news article storage unit 121 will be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of information stored in the news article storage unit of the information processing device according to the embodiment.
[0040] In the example shown in FIG. 7, the news article storage unit 121 stores information relating to the items "news article ID", "news article text", and "title" in association with each other.
[0041] "News article ID" is an identifier for identifying a news article stored in news article storage unit 121, and is represented by a character string, a number, or the like. "News article text" is information about the text of the news article identified by the "news article ID", and is information such as text data that represents the text of the news article. "Title" is information indicating the title of the news article identified by the "news article ID".
[0042] That is, FIG. 7 shows that the news article text of the news article identified by the news article ID "NID#1" is "ATL#1" and the title of the news article is "TLE#1."
[0043] It should be noted that the information stored in the news article memory unit 121 is not limited to information relating to the items "news article ID," "news article text," and "title," and any other information relating to a news article may be stored.
[0044] (About the summary model storage unit 122) The summary model storage unit 122 stores information related to the summary model. An example of the information stored in the summary model storage unit 122 will now be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the information stored in the summary model storage unit of the information processing device according to the embodiment.
[0045] In the example shown in FIG. 8, the summary model storage unit 122 stores information relating to the items "model ID" and "model data" in association with each other.
[0046] "Model ID" is an identifier for identifying a model, and is represented by a character string or a number. "Model data" indicates model data of a model. A model may be a machine learning model, for example, a neural network.
[0047] 8, the model identified by the model ID "M#1" indicates the model M#1. Also, the model data "MDT#1" indicates the model data of the model M#1.
[0048] Here, when the model is a neural network, the model data "MDT#1" includes various information, such as, for example, connection information on how the nodes included in each of the multiple layers that make up the neural network are connected to each other, and connection coefficients that are multiplied by the numerical values input and output between the connected nodes.
[0049] The information stored in the summary model storage unit 122 is not limited to information relating to the items "model ID" and "model data", and any other information relating to a summary model may be stored.
[0050] (Regarding the notification information storage unit 123) The notification information storage unit 123 stores information related to notification information to be provided to a user. Here, an example of information stored in the notification information storage unit 123 will be described with reference to Fig. 9. Fig. 9 is a diagram showing an example of information stored in the notification information storage unit of the information processing device according to the embodiment.
[0051] In the example shown in FIG. 9, the notification information storage unit 123 stores information relating to the items of "notification information ID", "notification information", and "match rate" in association with each other.
[0052] The "notification information ID" is an identifier that identifies the notification information, and is represented by a character string or a number. The "notification information" indicates the content of the notification information identified by the "notification information ID", and may be, for example, text data expressing a message to the user, video data, or still image data. The "match rate" indicates the match rate value at which the notification information identified by the "notification information ID" will be provided to the user.
[0053] That is, in FIG. 9, the notification information identified by the notification information ID "NTID#1" is stored as "NTIF#1", and the matching rate for providing the notification information to the user is "SCR#1".
[0054] In addition, the information stored in the notification information storage unit 123 is not limited to information relating to the items "notification information ID," "notification information," and "match rate," and any other information related to notification information to be provided to any user may be stored.
[0055] (Regarding the control unit 130) Next, returning to Fig. 6, the control unit 130 will be described. The control unit 130 is a controller that controls the information processing device 100, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) reading out various programs stored in the storage unit 120 of the information processing device 100 and executing them using a RAM as a working area. The control unit 130 is also a controller, and may be realized, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).
[0056] 6, the control unit 130 has a receiving unit 131, a generating unit 132, a calculating unit 133, a determining unit 134, and a providing unit 135. The control unit 130 realizes these functions by reading out a program from the storage unit 120 and executing the program using the RAM as a working area, thereby realizing or executing the functions and actions of the information processing described below. These processes will be described in order below.
[0057] (Regarding the reception unit 131) The reception unit 131 receives a selection of a news article by a user from the user terminal 200. For example, the reception unit 131 may cause the user terminal 200 to display titles of multiple news articles, and receive a selection of a news article that the user wishes to view from among the multiple displayed news articles.
[0058] (Regarding the generation unit 132) The generation unit 132 generates a summary of the news article based on the body of the news article. The generation unit 132 generates a summary of the body of the news article from text data of the body of the news article by using an abstract summary model such as T5 stored in the summary model storage unit 122. A pre-trained model for Japanese may be used for T5, and a model that has been fine-tuned for a summary task by using a summary of the sentence and the body of the sentence as learning data may be used. In addition, the text data of the body of the news article input to the summary model may be that of a news article accepted by the acceptance unit 131 from a user.
[0059] (Regarding the calculation unit 133) The calculation unit 133 calculates a matching rate indicating the degree of matching between the main text of a news article and the title of the news article, based on the news article summary generated by the generation unit 132 and the title of the news article. That is, the calculation unit 133 calculates the matching rate based on the news article summary generated by the generation unit 132 and the title of the news article. Specifically, the calculation unit 133 calculates Rouge-L based on the news article summary and the news article title, using the following formulas (1), (2), and (3).
[0060]
number
number
number
[0061] In formula (1), X indicates the summary of the news article text, and Y indicates the title of the news article. Furthermore, n indicates the length of the summary of the news article text, and m indicates the length of the news article title. Furthermore, LCS(X,Y) indicates the longest common subsequence of X and Y, and β is Plcs / Rlcs when ∂Flcs / ∂Rlcs=∂Flcs / ∂Plcs. Furthermore, Flcs in formula (3) is Rouge-L.
[0062] Next, the calculation unit 133 inputs Rouge-L calculated by equation (3) into the following equation (4) to calculate the matching rate.
[0063]
number
[0064] In the formula (4), x represents Rouge-L, and score represents the matching rate.
[0065] In this way, the calculation unit 133 uses Rouge-L to calculate the matching rate based on the longest common subsequence between the summary generated by the summary model and the correct summary (in this case, the title of the news article). In other words, the calculation unit 133 calculates the matching rate between the summary of a news article and the title of the news article based on the longest common subsequence between the summary of a news article and the title of the news article.
[0066] (Regarding the determination unit 134) The determination unit 134 determines the notification information to be provided to the user based on the matching rate calculated by the calculation unit 133. For example, the notification information to be provided to the user is stored in the notification information storage unit 123 according to the matching rate. Then, the determination unit 134 may determine the notification information to be provided to the user by reading the notification information associated with the matching rate calculated by the generation unit 132 from the notification information storage unit 123. Note that, for example, the notification information associated with a matching rate of 50% or less may be a message such as "Please note that the title of this news article has a low matching rate with the body of the news article, and therefore the title may not accurately represent the content of the body of the news article."
[0067] (About the provider 135) The providing unit 135 provides various types of information to the user terminal 200. Below, a specific example of the information that the providing unit 135 provides to the user terminal 200 will be described.
[0068] For example, the providing unit 135 provides the user terminal 200 with the matching rate calculated by the calculation unit 133 based on the title of the news article and the summary of the news article, together with the title of the news article. For example, the providing unit 135 provides the user terminal 200 with the matching rate between the title of the news article and the summary of the main text of the news article, together with the title of the news article, in a manner as shown in Fig. 3. As shown in Fig. 3, the providing unit 135 causes the user terminal 200 to display the calculation result of the matching rate calculated by the calculation unit 133 next to the title of the news article. In this way, the providing unit 135 provides the user terminal 200 with the matching rate indicating the degree of matching between the main text of the news article and the summary of the news article, together with the title of the news article.
[0069] Furthermore, the providing unit 135 provides the notification information determined by the determining unit 134 to the user terminal 200. For example, when the notification information determined by the determining unit 134 is a message, the providing unit 135 provides the message to the user terminal 200 by causing the user terminal 200 to display the message.
[0070] [4. User terminal configuration] Next, the configuration of the user terminal 200 according to the embodiment will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the configuration of the user terminal according to the embodiment. As shown in Fig. 10, the user terminal 200 has a communication unit 210, an input unit 220, an output unit 230, and a control unit 240.
[0071] The communication unit 210 is realized by, for example, a NIC, a wireless LAN card, etc. The communication unit 210 is connected to a network N by wire or wirelessly, and transmits and receives various information to and from the information processing device 100 via the network N.
[0072] Various types of operation information are input to the input unit 220 by the user. For example, the input unit 220 may receive various operations from the user via a display surface (e.g., the output unit 230) using a touch panel. The input unit 220 may also receive various operations from buttons provided on the user terminal 200, or a keyboard or mouse connected to the user terminal 200.
[0073] The output unit 230 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. In other words, when the input unit 220 of the user terminal 200 is a touch panel, the output unit 230, which is a display screen, receives input from the user and outputs the input to the user. The output unit 230 may also be a speaker, and may output sound from the speaker.
[0074] The control unit 240 is realized, for example, by a CPU, an MPU, or the like executing various programs stored in the user terminal 200 using a RAM as a working area. The control unit 240 may also be realized, for example, by an integrated circuit such as an ASIC or an FPGA.
[0075] As shown in FIG. 10, the control unit 240 includes a receiving unit 241 and a providing unit 242.
[0076] The accepting unit 241 accepts various operations from the user. For example, the accepting unit 241 may cause the output unit 230 to display titles of multiple news articles and accept a selection of a news article from the user.
[0077] The providing unit 242 provides various information to the user. For example, the providing unit 242 causes the output unit 230 to display the title of a news article provided by the providing unit 135 of the information processing device 100, together with the title of the news article and a matching rate based on the summary of the news article. The providing unit 242 also causes the output unit 230 to display notification information provided by the providing unit 135 of the information processing device 100.
[0078] [5. Information processing flow] Next, the procedure of information processing according to the embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing an example of information processing according to the embodiment. Below, the procedure of information processing according to the embodiment will be described with reference to the flowchart shown in Fig. 11.
[0079] First, the information processing device 100 accepts a selection of a news article by a user from the user terminal 200 (step S101). Next, the information processing device 100 generates a summary of the news article (step S102). Then, the information processing device 100 calculates a match rate based on the summary of the news article and the title of the news article (step S103). Then, the information processing device 100 determines notification information to be provided to the user based on the match rate (step S104). Then, the information processing device 100 provides the determined notification information to the user terminal 200 (step S105).
[0080] This makes it possible to determine notification information to be provided to a user based on the matching rate between a news article summary and the title of the news article, and to provide the determined notification information to the user terminal 200. This makes it possible to prevent a user from having excessive expectations based on a news article title with a low matching rate, and from being disappointed after reading the body of the news article because the content differs from the title of the news article. It is therefore possible to provide an information processing method and information processing program that can calculate the matching rate between the body and title of a news article and provide appropriate information to a user.
[0081] [6. Hardware Configuration] Moreover, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in Fig. 12, for example. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. 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.
[0082] 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 that stores data used by the arithmetic device 1030 for various calculations and various databases, and is realized by a ROM (Read Only Memory), a HDD (Hard Disk Drive), a flash memory, or the like.
[0083] 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.
[0084] 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.
[0085] 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.
[0086] 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.
[0087] For example, when the computer 1000 functions as the information processing device 100, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 130 of the information processing device 100 by executing a program loaded onto the primary storage device 1040.
[0088] 7. Composition and Effects The information processing device 100 of the present disclosure includes a generation unit 132 that generates a summary of a news article based on the body of the news article, a calculation unit 133 that calculates a matching rate indicating the degree of matching between the body of the news article and the title of the news article based on the summary of the news article generated by the generation unit 132 and the title of the news article, and a provision unit 135 that provides various information to a user terminal 200, and the provision unit 135 provides the user terminal 200 with the matching rate calculated by the calculation unit 133 based on the title of the news article and the summary of the news article, together with the title of the news article.
[0089] According to this configuration, the matching rate between the title of a news article and the summary of the text of the news article can be calculated, and the calculated matching rate can be provided to the user along with the title of the news article. Therefore, the user can view the news article after understanding the matching rate between the title of the news article and the content of the news article, and therefore can avoid disappointment when viewing a news article whose content differs from that expressed in the title of the news article. Therefore, it is possible to provide an information processing device 100 that can calculate the matching rate between the text of a news article and the title and provide appropriate information to the user.
[0090] The information processing device 100 according to the present disclosure further includes a determination unit 134 that determines notification information to be provided to the user based on the matching rate calculated by the calculation unit 133, and the provision unit 135 provides the notification information determined by the determination unit 134 to the user terminal 200.
[0091] According to this configuration, notification information to be provided to a user can be determined based on the matching rate between the summary of a news article and the title of the news article, and the determined notification information can be provided to the user terminal 200. This can prevent a user from having excessive expectations based on the title of a news article with a low matching rate, and from being disappointed after reading the main text of the news article because the content differs from the title of the news article. It is therefore possible to provide an information processing device 100 that can calculate the matching rate between the main text and the title of a news article and provide appropriate information to a user.
[0092] The calculation unit 133 of the information processing device 100 according to the present disclosure calculates the matching rate between the summary of a news article and the title of the news article, based on the longest common subsequence between the summary of the news article and the title of the news article.
[0093] According to this configuration, it is possible to calculate the matching rate between the summary of a news article and the title of the news article based on the longest common subsequence. Therefore, it is possible to provide an information processing device 100 that can appropriately calculate the matching rate between the body text and the title of a news article and provide appropriate information to a user.
[0094] The information processing method of the present disclosure includes the steps of generating a summary of a news article based on the body of the news article, calculating a matching rate indicating the degree of matching between the body of the news article and the title of the news article based on the generated summary of the news article and the title of the news article, and providing various information to a user terminal 200, in which in the providing step, the matching rate calculated in the calculating step based on the title of the news article and the news article summary is provided to the user terminal 200 together with the title of the news article.
[0095] According to this configuration, the matching rate between the title of a news article and the summary of the text of the news article can be calculated, and the calculated matching rate can be provided to the user along with the title of the news article. Therefore, the user can view the news article after understanding the matching rate between the title of the news article and the content of the news article, and can avoid being disappointed by viewing a news article whose content differs from that expressed in the title of the news article. Therefore, it is possible to provide an information processing method that calculates the matching rate between the text of a news article and the title, and can provide appropriate information to the user.
[0096] The information processing program of the present disclosure includes a step of generating a summary of a news article based on the body of the news article, a step of calculating a matching rate indicating the degree of matching between the body of the news article and the title of the news article based on the generated summary of the news article and the title of the news article, and a step of providing various information to a user terminal, and in the providing step, the computer is caused to provide to the user terminal 200 the matching rate calculated in the calculating step based on the title of the news article and the news article summary, together with the title of the news article.
[0097] According to this configuration, the matching rate between the title of a news article and the summary of the text of the news article can be calculated, and the calculated matching rate can be provided to the user along with the title of the news article. Therefore, the user can view the news article after understanding the matching rate between the title of the news article and the content of the news article, and can avoid being disappointed by viewing a news article whose content differs from that expressed in the title of the news article. Therefore, it is possible to provide an information processing program that can calculate the matching rate between the text of a news article and the title, and provide appropriate information to the user.
[0098] The above describes the embodiment of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include 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.
[0099] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, the reception unit 131 can be read as reception means or reception circuit. [Explanation of symbols]
[0100] 1. Information Processing Systems 100 Information processing device 110 Communications Department 120 Storage section 121 News Article Memory Section 122 Summary Model Storage Unit 123 Notification information storage unit 130 Control section 131 Reception 132 Generation part 133 Calculation section 134 Decision Section 135 Provision Department 200 User terminals 210 Communications Department 220 Input section 230 Output section 240 Control Unit 241 Reception 242 Provision Department N Network
Claims
1. a generator for generating a summary of the news article based on the text of the news article; a calculation unit that calculates a matching rate indicating a degree of matching between a body of a news article and a title of the news article based on the summary of the news article generated by the generation unit and the title of the news article; A providing unit that provides various information to a user terminal, The providing unit provides the user terminal with the title of the news article, together with the title of the news article and the matching rate calculated by the calculating unit based on the title of the news article and a summary of the news article. Information processing device.
2. a determination unit that determines notification information to be provided to a user based on the match rate calculated by the calculation unit, The providing unit provides the notification information determined by the determining unit to a user terminal. The information processing device according to claim 1 .
3. The calculation unit calculates a matching rate between a summary of a news article and a title of the news article based on a longest common subsequence between the summary of the news article and the title of the news article.
3. The information processing device according to claim 1 or 2.
4. generating a summary of the news article based on a body of the news article; A step of calculating a match rate indicating a degree of match between the body of the news article and the title of the news article based on the generated summary of the news article and the title of the news article; Providing various information to a user terminal; In the providing step, the matching rate calculated in the calculating step is provided to a user terminal based on the title of the news article and a summary of the news article together with the title of the news article. An information processing method comprising:
5. generating a summary of the news article based on a body of the news article; A step of calculating a match rate indicating a degree of match between the body of the news article and the title of the news article based on the generated summary of the news article and the title of the news article; Providing various information to a user terminal; In the providing step, the matching rate calculated in the calculating step is provided to a user terminal based on the title of the news article and a summary of the news article together with the title of the news article; An information processing program that causes a computer to execute the following.
Citation Information
Patent Citations
News information analysis apparatus
JP2012099001A
Cited By
Information processing device, information processing method, and information processing program
JP2026124099A
Information processing device, information processing method, and information processing program
JP2026154737A
Information processing device, information processing method, and program
JP2026174137A
