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

Abstract

To provide an information processing device capable of providing a user with more appropriate content, an information processing method, and an information processing program.SOLUTION: An information processing device comprises a selection unit and a provision unit. The selection unit selects second content provided to a user before or when the user uses first content on the basis of the user information. The provision unit provides the user with the second content selected by the selection unit or content based on the second content.SELECTED DRAWING: Figure 3

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 are known technologies for providing contents such as news articles. For example, Patent Literature 1 discloses a technology for searching and displaying articles including sentences with similar meanings to those of a specific sentence in a content as related contents. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2016 / 147624 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology has room for improvement in terms of providing more appropriate content to users. For example, in the above-mentioned conventional technology, articles including sentences with a similar meaning to the semantic content of a specific sentence are searched for as related content regardless of the user, so that there is a risk that appropriate content may not be provided for some users.

[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can provide more appropriate content to a user. [Means for solving the problem]

[0006] The information processing device of the present disclosure includes a selection unit and a provision unit. The selection unit selects second content to be provided to the user before or when the user uses the first content based on user information. The provision unit provides the user with the second content selected by the selection unit or content based on the second content. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide more appropriate content to a user. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing device according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of a content information table stored in the content information storage unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of the first content and the second content provided by the providing unit of the information processing device according to the embodiment and displayed on the terminal device. [Figure 7] FIG. 7 is a diagram showing another example of the first content and the second content provided by the providing unit of the information processing device according to the embodiment and displayed on the terminal device. [Figure 8] FIG. 8 is a flowchart illustrating an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application (hereinafter, referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0010] [1. An example of information processing] 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, which is executed by an information processing device 1.

[0011] 1, the information processing device 1 identifies a user U immediately before using a first content or a user U currently using the first content as a target user (step S1). For example, when the user U selects (for example, by clicking or tapping) a link to the first content displayed on the terminal device 2 of the user U, the information processing device 1 identifies the user U as a target user.

[0012] In addition, when a preview content of the first content (e.g., content including a headline, a thumbnail, a link, etc.) is displayed on the terminal device 2 of the user U and the first content is not yet displayed on the terminal device 2, the information processing device 1 identifies the user U as the target user.

[0013] Furthermore, when a predetermined period (e.g., several seconds) has elapsed since the first content was displayed on the terminal device 2 of the user U, the information processing device 1 identifies the user U as the target user. Furthermore, when a predetermined period or more has elapsed since the first content was displayed on the terminal device 2 of the user U, the information processing device 1 can also identify the user U as the target user.

[0014] The first content and the second content described below are content that includes text, such as article content, such as news articles, profile or resume content, etc. The article content is not limited to news articles, and may be, for example, columns, essays, interviews, product reviews, feature articles, articles about people, etc.

[0015] The profile content is content including information of a person's profile, for example, content including information of a user's profile. The resume content is, for example, but not limited to, the resume content of a user U (e.g., a target user). The first content may become the second content, and the second content may become the first content.

[0016] Next, the information processing device 1 selects the second content to be provided to the target user immediately before or when the target user uses the first content based on the information of the target user (step S2). The information of the target user is, for example, information on the target user's content usage history, information on the target user's content search history, information on the target user's attributes, etc., but is not limited to such examples.

[0017] For example, the information processing device 1 selects, as the second content, a piece of content that is related to the first content and has not been used by the target user in the past, based on the information of the target user.

[0018] Furthermore, the information processing device 1 can select, as the second content, a content related to the first content and having an older publication date than the first content. In this case, the information processing device 1 selects, as the second content, a content related to the first content, having an older publication date than the first content, and having not been used by the target user in the past, for example, based on information on the usage history of the content by the target user.

[0019] The content related to the first content is, for example, a content that shares a common topic with the first content. The content that shares a common topic with the first content is, for example, a content that includes a specific keyword or a specific phrase related to the topic, or a content that has a similar vector to the first content.

[0020] The information processing device 1 can, for example, use a topic dictionary containing keywords and phrases to extract specific keywords or phrases from the first content, and obtain content containing the extracted specific keywords or phrases as the second content from an external information providing device or an internal memory unit.

[0021] Furthermore, the information processing device 1 converts each content into a vector by natural language processing, and acquires content whose vector is similar to that of the first content as the second content from an external information providing device or an internal storage unit, etc. The content whose vector is similar to that of the first content is, for example, content whose cosine similarity is within a threshold value.

[0022] Content vectorization can be performed using, for example, Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, Doc2Vec, Bidirectional Encoder Representations from Transformers (BERT), etc.

[0023] The information processing device 1 can also summarize each piece of content by natural language processing, convert it into vectors, and acquire, as the second content, a piece of content whose vector is similar to that of the first content.

[0024] The content can be summarized, for example, by using a generative AI (Artificial Intelligence). The generative AI includes, for example, a language model such as a transformer that is trained to estimate and output the next token from an input token string. Such a language model is in the information processing device 1 and is created independently by the operator of the information processing device 1. It is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information, such as personal information.

[0025] For example, the information processing device 1 vectorizes the first content and each piece of content used by the target user, and calculates a first vector that is a vector of the first content and a second vector that is a vector of the content used by the target user.

[0026] Then, the information processing device 1 can select, as the second content, a content whose vector is between the first vector and the second vector, from among the content that the target user has not used in the past.

[0027] In this case, the information processing device 1 can select, for example, a piece of content that is not used by the target user and has a common topic with the first content and is between the first vector and the second vector as the second content. The information processing device 1 selects, for example, a piece of content that is between the first vector and the second vector and is one of the top m pieces of content (m is an integer equal to or greater than 2) that are closest to the first vector as the second content.

[0028] Furthermore, the information processing device 1, for example, vectorizes the content published on the date immediately preceding the publication date of the first content, and calculates a third vector that is a vector of the content published on the date immediately preceding the publication date of the first content. Note that the content published on the date immediately preceding the publication date of the first content is content published during a period from the publication date of the first content until a predetermined period before, but may also be the next newest content after the first content among the contents that share a topic in common with the first content.

[0029] In this case, the information processing device 1 selects, as the second content, a content whose vector is between the first vector and the third vector among the contents that the target user has not used in the past. For example, the information processing device 1 selects, as the second content, the top m pieces of content that are between the first vector and the third vector and are closest to the first vector.

[0030] Furthermore, the information processing device 1 can select, as the second content, a content that includes a specific keyword or a specific phrase related to the topic and has a vector similar to that of the first content.

[0031] Furthermore, the information processing device 1 can also estimate the knowledge level of the target user in a field related to the first content, and select, as the second content, a content according to the estimated knowledge level.

[0032] For example, the information processing device 1 can estimate the knowledge level of the target user in a field related to the first content, based on information of the target user (for example, information on the attributes of the target user and information on the behavior history of the target user).

[0033] The information processing device 1 inputs information such as, for example, information indicating the number of views of content in the first content field, information indicating the number of searches for content in the first content field, information indicating the number of purchases of products and services in the first content field, and information on the attributes of the target user as features, and estimates the knowledge level of the target user in the field related to the first content using an estimation model that outputs the knowledge level of the target user.

[0034] In addition, the information processing device 1 can select as the second content a content related to the first content, that has not been used by the target user in the past, and that corresponds to the target user's knowledge level in the field related to the first content.

[0035] Next, the information processing device 1 provides the second content selected in step S2 or content based on the second content to the target user immediately before or when the target user uses the first content (step S3).

[0036] For example, the information processing device 1 provides the second content or content based on the second content to the target user by transmitting the second content or content based on the second content to the terminal device 2 of the target user and causing the terminal device 2 to display the second content or content based on the second content.

[0037] For example, the information processing device 1 can summarize the second content selected in step S2 and provide the summarized second content to the target user as content based on the second content.

[0038] In the example shown in Fig. 1, two second contents are displayed above a first content displayed on the display unit of the terminal device 2. Of the two contents displayed on the display unit of the terminal device 2, the second content at the top is the oldest, having been published two weeks ago, and the second content at the bottom is the next oldest, having been published one week ago. The first content is the newest content, having been published three hours ago.

[0039] The two second contents shown in Fig. 1 are contents provided by the information processing device 1 when, for example, a link of the first content is selected, and this allows the user U to deepen his / her understanding of the first content by viewing the second content before viewing the first content. In addition, the two second contents and the first content displayed on the display unit shown in Fig. 1 are arranged in chronological order, so that the user U can easily grasp the temporal relationship.

[0040] In this way, the information processing device 1 selects the second content to be provided to the user U immediately before or when the user U uses the first content, based on the information of the user U, and provides the second content or content based on the second content to the user U. This allows the information processing device 1 to use the second content or content based on the second content before or when the user U uses the first content, and can provide more appropriate content to the user U.

[0041] The configuration of an information processing system including the information processing device 1 and terminal device 2 that perform such processing will be described in detail below.

[0042] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, an information processing system 100 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0043] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, a smart glass or a smart watch, but is not limited to such examples.

[0044] The information processing device 1 and the terminal device 2 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG.

[0045] The network N includes, for example, a Wide Area Network (WAN) such as the Internet and mobile communication networks such as Long Term Evolution (LTE), 4th Generation (4G), and 5th Generation (5G: fifth generation mobile communication system).

[0046] The terminal device 2 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0047] 3. Configuration of information processing device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0048] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 via the network N.

[0049] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20 and a content information storage unit 21.

[0050] 3.2.1. User information storage unit 20 The user information storage unit 20 stores various pieces of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 of the information processing device 1 according to the embodiment.

[0051] 4, the user information table stored in the user information storage unit 20 includes information items such as "User ID (Identifier)," "Attribute Information," and "History Information." The "User ID" is an identifier for identifying a user U, and is information assigned to each user U.

[0052] The "attribute information" is attribute information indicating attributes of the user U associated with the "user ID." The attributes of the user U are, for example, demographic attributes, psychographic attributes, etc. The demographic attributes are demographic attributes, and include a plurality of attribute items such as age, sex, occupation, place of residence, annual income, and family structure.

[0053] The psychographic attributes are psychological attributes, and include, for example, a plurality of attribute items related to lifestyle, values, interests, etc. For example, each of the plurality of attribute items in the psychographic attributes is an object of interest of the user U, such as a car, clothes, travel, games, camping, motorcycle, train, home appliance, or computer.

[0054] The "history information" includes information on the behavior history of the user U associated with the "user ID." The behavior history of the user U includes, for example, information on the behavior history of the user U in the online service. The behavior history information of the user U in the online service includes, for example, search history information, browsing history information, delivery history information, and transaction history information in the online service of the user U.

[0055] The search history information of the user U includes, for example, information on the search history of content by the user U in a web search service. The browsing history information of the user U includes, for example, information on the browsing history of content by the user U in an online service. The delivery history information includes information on the delivery history of content delivered to the terminal device 2 of the user U. The transaction history information includes information on the transaction history of products by the user U in an online service.

[0056] [3.2.2. Content information storage unit 21] The content information storage unit 21 stores various pieces of information related to content. Fig. 5 is a diagram showing an example of a content information table stored in the content information storage unit 21 of the information processing device 1 according to the embodiment.

[0057] 5, the content information table stored in the content information storage unit 21 includes information items such as "content ID" and "content." The "content ID" is an identifier that identifies the content, and is information that is assigned to the content.

[0058] "Content" is content associated with a "Content ID", for example, content including text, such as article content, which is content such as news articles, profile content, resume content, etc. Article content is not limited to news articles, and may be content such as columns, essays, interviews, product reviews, feature articles, and articles about people.

[0059] The profile content is content including information of a person's profile, for example, content including information of a user's profile. The resume content is, for example, but not limited to, the resume content of a user U (e.g., a target user). The first content may become the second content, and the second content may become the first content.

[0060] In addition, although not shown, the content information table stored in the content information storage unit 21 also includes information indicating, for example, the knowledge level of the user U who is able to understand the content associated with the "content ID."

[0061] [3.3. Processing section 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 1 using a RAM as a working area.

[0062] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0063] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, an identification unit 32, an estimation unit 33, a vectorization unit 34, a selection unit 35, a summary unit 36, and a provision unit 37, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

[0064] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device or a terminal device 2 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0065] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or the terminal device 2, etc., via the communication unit 10, and adds the acquired user information to a user information table in the user information storage unit 20. In addition, the acquisition unit 30 acquires content from an external information processing device, etc., via the communication unit 10, and adds the acquired content to a content information table in the content information storage unit 21.

[0066] The acquisition unit 30 also acquires various information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information about the user U, from the user information storage unit 20 or the like. The user information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the above-mentioned attribute information and history information. Furthermore, when a content request is accepted by the acceptance unit 31 or the like, the acquisition unit 30 acquires the content from the content information storage unit 21 or the like.

[0067] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information. For example, the reception unit 31 receives a content request transmitted from the terminal device 2. Such a content request includes information that identifies the content.

[0068] By accepting the content request, the acceptance unit 31 can detect that a link to the content displayed on the terminal device 2 of the user U has been selected by the user U (for example, by a click operation or a tap operation).

[0069] Furthermore, the reception unit 31 receives display information transmitted from the terminal device 2. The display information is, for example, information indicating that content is being displayed on the terminal device 2, and includes information identifying the content that has started to be displayed on the terminal device 2 (including, for example, a content ID), and information indicating the elapsed time since the content was displayed on the terminal device 2.

[0070] The display information may be transmitted from the terminal device 2 at the timing when the display of the content is started on the terminal device 2. By receiving the display information, the reception unit 31 can detect the content being displayed on the terminal device 2, the elapsed time since the content was displayed, and the like.

[0071] The content specified by the content request or the display information is, for example, a first content or a second content. The first content is a content that triggers the provision of the second content. The first content may become the second content, and the second content may become the first content.

[0072] [3.3.3. Specification part 32] The identification unit 32 identifies a user U immediately before using the first content or a user U currently using the first content as a target user.

[0073] For example, when the user U selects (for example, by clicking or tapping) a link of the first content displayed on the terminal device 2 of the user U, the identification unit 32 identifies the user U as a target user.

[0074] In addition, when a preview content of the first content (e.g., content including a headline, a thumbnail, a link, etc.) is displayed on the terminal device 2 of the user U and the first content is not yet displayed on the terminal device 2, the identification unit 32 identifies the user U as the target user.

[0075] Furthermore, when a predetermined period (e.g., several seconds) has elapsed since the first content was displayed on the terminal device 2 of the user U, the identification unit 32 identifies the user U as the target user. Furthermore, when a predetermined period or more has elapsed since the first content was displayed on the terminal device 2 of the user U, the identification unit 32 can also identify the user U as the target user.

[0076] [3.3.4. Estimation part 33] The estimation unit 33 estimates the knowledge level of the target user in the field related to the first content identified by the identification unit 32. The knowledge levels are, for example, three levels of beginner level (amateur level), intermediate level, and advanced level (expert level), but are not limited to such an example, and may be two levels or four or more levels.

[0077] For example, the estimation unit 33 can estimate the knowledge level of the target user in a field related to the first content based on information of the target user identified by the identification unit 32 (e.g., information on the attributes of the target user and information on the behavioral history of the target user).

[0078] The estimation unit 33 inputs, as features, information such as information indicating the number of views of contents in the field of the first content, information indicating the number of searches for contents in the field of the first content, information indicating the number of purchases of products and services in the field of the first content, and information on the attributes of the target user, and estimates the knowledge level of the target user in the field related to the first content using an estimation model that outputs the knowledge level of the target user. Note that the information input as the features is not limited to the above examples.

[0079] The estimation model may be, for example, a linear regression model, a Gradient Boosting Decision Tree (GBDT), or Recurrent Neural Networks (RNNs) such as a Long Short-Term Memory (LSTM) or a Gated Recurrent Unit (GRU), but is not limited to such examples.

[0080] A field is, for example, a content category. For example, if the content is news article content, the field may be politics, economics, society, international affairs, science and technology, sports, entertainment, etc., but is not limited to such examples and may be a further subdivided category or a category classified using a different classification method.

[0081] [3.3.5. Vectorization Unit 34] The vectorization unit 34 vectorizes each piece of content to obtain a vector for each piece of content. The vectorization of the content can be performed using, for example, TF-ID, Word2Vec, Doc2Vec, BERT, or the like.

[0082] For example, the vectorization unit 34 vectorizes the first content to obtain a first vector that is a vector of the first content. Also, the vectorization unit 34 vectorizes the content used by the target user to obtain a second vector that is a vector of the content used by the target user.

[0083] Moreover, the vectorization unit 34 vectorizes the content related to the first content and having a publication date immediately before the publication date of the first content to obtain a third vector, which is a vector of the content related to the first content and having a publication date immediately before the publication date of the first content. Note that the content having a publication date immediately before the publication date of the first content is content published during a period from the publication date of the first content until a predetermined period before, but may also be the next newest content after the first content among the contents that share a topic in common with the first content.

[0084] The vectorizer 34 can also vectorize the content summarized by the summarizer 36 to obtain a vector for each piece of content.

[0085] [3.3.6. Selection unit 35] The selection unit 35 selects the second content to be provided to the target user immediately before or at the time of the target user's use of the first content, based on the information of the target user identified by the identification unit 32. The information of the target user is, for example, information acquired by the acquisition unit 30, and is, for example, information on the target user's content use history, information on the target user's content search history, information on the target user's attributes, etc., but is not limited to such examples.

[0086] For example, the selection unit 35 selects, as the second content, a piece of content that is related to the first content and has not been used by the target user in the past, based on information about the content usage history of the target user.

[0087] The selection unit 35 can also select, as the second content, a content related to the first content and having an older publication date than the first content. In this case, the selection unit 35 selects, as the second content, a content related to the first content, having an older publication date than the first content, and having not been used by the target user in the past, for example, based on information on the content usage history by the target user.

[0088] The selection unit 35 can also treat content that the target user has used in the past but has not used for a predetermined period of time or more as content that the target user has not used in the past.

[0089] The content related to the first content is, for example, content that shares a common topic (such as a topic or subject) with the first content. The content that shares a common topic with the first content is, for example, content that includes a specific keyword or phrase related to the topic, or content that has a similar vector to the first content.

[0090] The selection unit 35 can, for example, use a topic dictionary containing keywords and phrases to extract specific keywords or phrases from the first content, and obtain content containing the extracted specific keywords or phrases as the second content from an external information providing device, etc.

[0091] The selection unit 35 also acquires, as the second content, a content whose vector obtained by the vectorization unit 34 is similar to that of the first content from an external information providing device or the like. The content whose vector is similar to that of the first content is, for example, a content whose cosine similarity is within a threshold value. The vectorization of the content can be performed using, for example, TF-IDF, Word2Vec, Doc2Vec, BERT, or the like.

[0092] In addition, for example, when each content summarized by the summarization unit 36 ​​is vectorized by the vectorization unit 34, the selection unit 35 can also acquire content having a similar vector of the summary obtained by the vectorization unit 34 as the second content.

[0093] In addition, the selection unit 35 can select as the second content, from among the content that the target user has not used in the past, the content whose vector obtained by vectorization by the vectorization unit 34 is between the first vector and the second vector.

[0094] In this case, the selection unit 35 can select, for example, as the second content, content that is not used by the target user, has a common topic with the first content, and is between the first vector and the second vector.

[0095] The selection unit 35 selects, for example, top m pieces (m is an integer of 2 or more) of content that are between the first vector and the second vector and are closest to the first vector as the second content.

[0096] Furthermore, the selection unit 35 selects, as the second content, a content whose vector obtained by vectorization by the vectorization unit 34 is between the first vector and the third vector, among the contents not used by the target user in the past. For example, the selection unit 35 selects, as the second content, the top m pieces of content that are between the first vector and the third vector and are closest to the first vector.

[0097] The selection unit 35 can also select, as the second content, a content that includes a specific keyword or a specific phrase related to the topic and has a vector similar to that of the first content.

[0098] The selection unit 35 can also select, as the second content, content according to the knowledge level estimated by the estimation unit 33. For example, the selection unit 35 selects, as the second content, content associated with information of the same knowledge level as the knowledge level estimated by the estimation unit 33. The information of the knowledge level associated with the content is acquired by the acquisition unit 30 from the content information storage unit 21, for example.

[0099] The selection unit 35 can also estimate the knowledge level corresponding to the content by using an estimation model (e.g., a language model such as a transformer) that estimates the knowledge level corresponding to the content. The selection unit 35 compares the estimated knowledge level with the knowledge level estimated by the estimation unit 33, and selects the content according to the knowledge level estimated by the estimation unit 33. The estimation of the knowledge level corresponding to the content may be performed by the estimation unit 33.

[0100] In addition, for example, when there is no content associated with information of a knowledge level identical to the knowledge level estimated by the estimation unit 33, the selection unit 35 selects as the second content a content associated with information of a lower knowledge level than the knowledge level estimated by the estimation unit 33 or a content associated with information of a knowledge level closest to the knowledge level estimated by the estimation unit 33.

[0101] In addition, the selection unit 35 can select as the second content a content related to the first content, that has not been used by the target user in the past, and that corresponds to the target user's knowledge level in the field related to the first content.

[0102] [3.3.7. Summary Section 36] The summarization unit 36 ​​summarizes each piece of content by natural language processing. The summarization of the content can be performed using, for example, generative AI.

[0103] The generative AI includes, for example, a language model such as a transformer that is trained to estimate and output the next token from an input token sequence. Such a language model is in the information processing device 1 and is created independently by the operator of the information processing device 1. It is preferable that the input information is trained so as not to be used as a new answer, thereby concealing the input information, such as personal information.

[0104] For example, the summarizing unit 36 ​​summarizes each piece of content that is a candidate for the second content, in order for the selection unit 35 to select the second content. In addition, the summarizing unit 36 ​​summarizes the second content selected by the selection unit 35.

[0105] The summarization unit 36 ​​can perform summarization according to the knowledge level of the target user estimated by the estimation unit 33, for example. For example, the summarization unit 36 ​​can perform summarization according to the knowledge level of the target user estimated by the estimation unit 33 by additionally inputting information according to the knowledge level of the target user estimated by the estimation unit 33 to the generative AI.

[0106] For example, the summarization unit 36 ​​can input input information including the string information "Please summarize the content in a way that even people with little knowledge of the topic of the following content can understand" and content information to the generative AI, thereby causing the generative AI to output a summary result that corresponds to the knowledge level of the target user.

[0107] Furthermore, when the content includes images and audio, the summarization unit 36 ​​can summarize the images and audio in addition to summarizing the text included in the content. The summarization of images and audio is performed using generative AI. The generative AI can, for example, extract important information from the images and audio included in the content and output the extracted information as language.

[0108] [3.3.8.Providing Department 37] The providing unit 37 provides various information to the user U. For example, when a content request is accepted by the accepting unit 31, the providing unit 37 transmits the content specified in the content request to the terminal device 2 that sent the content request via the communication unit 10. When the content request is accepted by the accepting unit 31, the content specified in the content request is acquired by the acquiring unit 30.

[0109] In addition, for example, when the second content is selected by the selection unit 35, the provision unit 37 provides the second content or content based on the second content to the target user by transmitting the second content or content based on the second content to the terminal device 2 of the target user.

[0110] The providing unit 37 can provide the second content summarized by the summarizing unit 36 ​​to the target user as content based on the second content, for example. The second content summarized by the summarizing unit 36 ​​is an example of a summary result of the summarizing unit 36.

[0111] In addition, the providing unit 37 can also determine whether or not to provide the second content summarized by the summarizing unit 36 ​​to the target user as content based on the second content, for example, based on the knowledge level of the target user estimated by the estimation unit 33.

[0112] For example, if the knowledge level of the target user estimated by the estimation unit 33 is below or equal to a threshold, the provision unit 37 decides to provide the second content that is not summarized by the summarization unit 36 ​​to the target user, and if not, decides to provide the second content summarized by the summarization unit 36 ​​to the target user as content based on the second content.

[0113] Fig. 6 is a diagram showing an example of a first content and a second content provided by the providing unit 37 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. As shown in Fig. 6, a first content 51 and second contents 52a and 52b are displayed in a display area 50 of the terminal device 2.

[0114] The second contents 52a, 52b are contents provided by the information processing device 1, for example, when a link to the first content 51 is selected. This allows the user U to deepen his / her understanding of the first content 51 by viewing the second contents 52a, 52b before viewing the first content 51.

[0115] Furthermore, since the second contents 52a and 52b and the first content 51 are arranged in chronological order in the display area 50 of the terminal device 2, the user U can easily grasp the time relationship.

[0116] 7 is a diagram showing another example of the first content and the second content provided by the providing unit 37 of the information processing device 1 according to the embodiment and displayed on the terminal device 2. In the example shown in FIG. 7, the second contents 52a and 52b are superimposed on the first content 51.

[0117] In this case, too, by viewing the second contents 52a and 52b, the user U can deepen his / her understanding of the first content 51. Furthermore, after the user U has finished viewing the second contents 52a and 52b or when viewing the second contents 52a and 52b is no longer necessary, the user U can erase the second contents 52a and 52b from the display area 50 by performing a swipe operation or the like on the second contents 52a and 52b.

[0118] In the examples shown in FIGS. 6 and 7, the second contents 52a and 52b are displayed in a scrollable manner, but this is not limited to the example, and the second contents 52a and 52b may be displayed in their entirety in the display area 50.

[0119] In the above example, the second content is displayed so that the user U can use the second content before using the first content, but the present invention is not limited to such an example. For example, when the user U performs an operation (e.g., a double-click operation or a double-tap operation) on the first content after the user U starts using (e.g., viewing) the first content, the providing unit 37 can transmit the second content to the terminal device 2 and display it on the terminal device 2.

[0120] In addition, in the examples shown in Figures 6 and 7, examples have been described in which the first content and the second content are mainly article content, but the first content and the second content may also be profile content, resume content, etc.

[0121] The profile content is, for example, content including information showing a profile of a specific person, but may also be content including information showing a profile of the user U. When creating a first content including information showing his / her own profile, the user U can refer to a second content including information showing the profile of another person. In this case, the use of the first content is viewing or creating a profile, but is not limited to such an example.

[0122] In addition, when the user U selects a portion of the information indicating the profile, the providing unit 37 can transmit a second content, in which the portion selected by the user U is the first content, to the terminal device 2 and cause it to be displayed.

[0123] Furthermore, the resume content is, for example, content including information showing a resume of a specific person, but may also be content including information showing the resume of user U. When creating a first content including information showing his / her own resume, user U can refer to a second content including information showing another person's resume. In this case, the use of the first content is viewing or creating a resume, but is not limited to such an example.

[0124] Furthermore, when the user U selects a portion of the information indicating the resume, the providing unit 37 can transmit a second content, in which the portion selected by the user U is the first content, to the terminal device 2 to display it.

[0125] 4. Processing Procedure Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 8 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0126] 8, the processing unit 12 of the information processing device 1 determines whether or not the target user has been identified (step S20). When the processing unit 12 determines that the target user has been identified (step S20: Yes), the processing unit 12 selects second content to be provided to the target user immediately before or when the target user uses the first content (step S21). Then, the processing unit 12 provides the second content selected in step S21 or content based on the second content (step S22).

[0127] When the processing of step S22 is completed, or when it is determined that the target user has not been specified (step S20: No), the processing unit 12 determines whether or not the content request has been accepted (step S23). When it is determined that the content request has been accepted (step S23: Yes), the processing unit 12 provides the content corresponding to the content request to the user U of the terminal device 2 that has sent the content request by transmitting the content corresponding to the content request to the terminal device 2 that has sent the content request (step S24).

[0128] When the process of step S24 is completed or when it is determined that the content request has not been received (step S23: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S25). The processing unit 12 determines that the operation end timing has arrived when, for example, the power supply of the information processing device 1 is turned off.

[0129] If the processing unit 12 determines that the operation end time has not arrived (step S25: No), it transitions to step S20, and if the processing unit 12 determines that the operation end time has arrived (step S25: Yes), it terminates the processing shown in FIG. 8.

[0130] 5. Modifications In the above example, the first content has been described as indicating the entire article content, but the first content may be a part of the article content.

[0131] In addition, for example, for a user U whose frequency of use of the provided second content is equal to or greater than a threshold, the providing unit 37 can transmit the second content to the terminal device 2 and display it on the terminal device 2 before transmitting the first content to the terminal device 2 and displaying it on the terminal device 2, and when the user U has finished using the second content, can transmit the first content to the terminal device 2 and display it on the terminal device 2.

[0132] Furthermore, for example, when the first content is on a topic similar to content that the user U has used in the past, the providing unit 37 may not provide the second content or may reduce the number of second contents to be provided.

[0133] In addition, when the first content is content created by a generative AI, the providing unit 37 can also provide content created by a writer as the second content. In addition, when the first content is content created by a writer, the providing unit 37 can also provide content created by a generative AI as the second content.

[0134] In addition, if the display area 50 in which the first content is displayed includes an input box in which the user U inputs a search keyword and a search button, the providing unit 37 can also transmit the second content to the terminal device 2 and display it on the terminal device 2 when the user U taps the input box or moves the cursor.

[0135] Some or all of the functions of the information processing device 1 described above can also be functions of the terminal device 2. For example, when the terminal device 2 has some of the functions of the information processing device 1 described above, the information processing device is configured by the information processing device 1 and the terminal device 2. Also, when the terminal device 2 has all of the functions of the information processing device 1 described above, the information processing device is configured by the terminal device 2.

[0136] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 80 having a configuration as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, a HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0137] The CPU 81 operates and controls each part based on a program stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, and programs that depend on the hardware of the computer 80.

[0138] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0139] The CPU 81 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 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs data generated via the input / output interface 86 to the output devices.

[0140] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

[0141] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82 to realize the function of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, these programs may be obtained from another device via the network N.

[0142] [7. Other] In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0143] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0144] For example, the above-mentioned information processing device 1 may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0145] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0146] 8. Effects As described above, the information processing device 1 according to the embodiment includes a selection unit 35 that selects second content to be provided to the user U immediately before or when the user U uses the first content based on information about the user U, and a provision unit 37 that provides the user U with the second content or content based on the second content selected by the selection unit 35. This allows the information processing device 1 to provide more appropriate content to the user U.

[0147] Moreover, the selection unit 35 selects, as the second content, a content that is related to the first content and that the user U has not used in the past.

[0148] Furthermore, the selection unit 35 selects, as the second content, a piece of content that is related to the first content and has an older publication date than the first content. This enables the information processing device 1 to provide the user U with more appropriate content.

[0149] Furthermore, the selection unit 35 selects, as the second content, a piece of content related to the first content and having a common topic, thereby enabling the information processing device 1 to provide the user U with more appropriate content.

[0150] The information processing device 1 also includes a vectorization unit 34 that vectorizes the first content and the content used by the user U to obtain a first vector that is a vector of the first content and a second vector that is a vector of the content used by the user U, and the selection unit 35 selects, as the second content, a content that has not been used by the user U in the past and whose vector obtained by the vectorization by the vectorization unit 34 is between the first vector and the second vector. This allows the information processing device 1 to provide more appropriate content to the user U.

[0151] The information processing device 1 also includes a vectorization unit 34 that vectorizes the first content and content related to the first content and having a publication date immediately before the publication date of the first content to obtain a first vector that is a vector of the first content and a third vector that is a vector of content related to the first content and having a publication date immediately before the publication date of the first content, and the selection unit 35 selects, as the second content, a content whose vector obtained by vectorization by the vectorization unit 34 is between the first vector and the third vector, from among the contents that the user U has not used in the past. This allows the information processing device 1 to provide more appropriate content to the user U.

[0152] The information processing device 1 also includes a summarizing unit 36 ​​that summarizes the second content selected by the selecting unit 35, and the providing unit 37 provides the summary result by the summarizing unit 36 ​​to the user U as content based on the second content. This allows the information processing device 1 to provide more appropriate content to the user U.

[0153] Moreover, the information processing device 1 includes an estimation unit 33 that estimates a knowledge level of the user U in a field related to the first content, and a selection unit 35 selects, as the second content, a content according to the knowledge level estimated by the estimation unit 33. This allows the information processing device 1 to provide the user U with more appropriate content.

[0154] 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.

[0155] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0156] 1. Information processing device 2 Terminal Equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Content information storage unit 30 Acquisition Department 31 Reception 32 Specific part 33 Estimation part 34 Vectorization Department 35 Selection section 36 Summary 37 Providing Department 100 Information Processing Systems N Network

Claims

1. a selection unit that selects a second content to be provided to the user before or when the user uses a first content based on user information; a providing unit that provides the second content or content based on the second content selected by the selecting unit to the user.

23. An information processing apparatus comprising:

2. The selection unit is Selecting, as the second content, a content related to the first content and not used by the user in the past.

2. The information processing apparatus according to claim 1,

3. The selection unit is Selecting, as the second content, a content that is related to the first content and has a publication date older than that of the first content.

3. The information processing apparatus according to claim 2.

4. The selection unit is Selecting, as the second content, content having a common topic as content related to the first content.

4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

5. a vectorization unit that vectorizes the first content and the content used by the user to obtain a first vector that is a vector of the first content and a second vector that is a vector of the content used by the user; The selection unit is Among the contents that the user has not used in the past, a content whose vector obtained by the vectorization unit is between the first vector and the second vector is selected as the second content.

4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

6. a vectorization unit that vectorizes the first content and a content related to the first content and having a publication date immediately before the publication date of the first content to obtain a first vector that is a vector of the first content and a third vector that is a vector of a content related to the first content and having a publication date immediately before the publication date of the first content, The selection unit is Among the contents that the user has not used in the past, a content whose vector obtained by the vectorization unit is between the first vector and the third vector is selected as the second content.

4. The information processing apparatus according to claim 2, wherein the information processing apparatus is a computer.

7. a summary unit that summarizes the second content selected by the selection unit, The providing unit is The summary result by the summarization unit is provided to the user as content based on the second content.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

8. an estimation unit that estimates a knowledge level of the user in a field related to the first content, The selection unit is selecting, as the second content, a content corresponding to the knowledge level estimated by the estimation unit; 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

9. 1. A computer-implemented information processing method, comprising: a selection step of selecting second content to be provided to the user before or when the user uses the first content based on user information; a providing step of providing the second content or content based on the second content selected by the selection step to the user.

23. An information processing method comprising:

10. a selection step of selecting second content to be provided to the user before or when the user uses the first content based on user information; a providing step of providing, to the user, the second content or content based on the second content selected by the selection step.

2. An information processing program comprising:

Images