Information processing device, information processing method, and program

Abstract

To provide an information processing device, an information processing method, and a program that can reduce the effort required for content management. [Solution] The information processing device comprises a receiving unit that receives content, a content processing unit that assigns information identifying a physical address to the content received by the receiving unit and stores it in a content pool, and virtually classifies the content stored in the content pool, and a display control unit that causes a display unit to display the virtual classification structure of the content virtually classified by the content processing unit.

Description

[Technical Field]

[0001] This invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] The search server uses the entered keywords to retrieve documents related to those keywords from its archives as search results. The search server then provides the search results to the user's terminal device, allowing the user to view the results on their device. A technique is known for clustering search results based on their degree of similarity (see, for example, Patent Document 1). [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2005-078245 [Overview of the project] [Problems that the invention aims to solve]

[0004] Content is managed according to established management rules, but creating these rules requires a significant amount of effort. Furthermore, management rules, once established, can become outdated over time. Furthermore, when storing content, users need to configure access rights and other settings, which is time-consuming.

[0005] The object of the present invention is to provide an information processing device, an information processing method, and a program that can reduce the effort required for content management. [Means for solving the problem]

[0006] One aspect of the present invention is an information processing apparatus comprising: a receiving unit for receiving content; a content processing unit for assigning information to identify a physical address to the content received by the receiving unit, storing it in a content pool, and virtually classifying the content stored in the content pool; and a display control unit for causing a display unit to display the results of the virtual classification of the content by the content processing unit.

[0007] One aspect of the present invention is an information processing method performed by a computer, which includes receiving content, assigning information to the received content that identifies a physical address, storing the content to which the physical address has been assigned in a content pool, virtually classifying the content stored in the content pool, and displaying the results of the virtually classifying of the content on a display unit.

[0008] One aspect of the present invention is a program that enables a computer to receive content, assign information to the received content that identifies a physical address, store the content with the assigned physical address in a content pool, virtually classify the content stored in the content pool, and display the results of the virtual classification of the content on a display unit. [Effects of the Invention]

[0009] According to the present invention, the effort required for content management can be reduced. [Brief explanation of the drawing]

[0010] [Figure 1] This figure shows an example of an information processing device according to this embodiment. [Figure 2] This figure shows an example of user attribute information. [Figure 3] This figure shows an example of content metadata. [Figure 4] This figure shows an example of creator attribute information. [Figure 5]It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 6] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 7] It is a diagram illustrating an example of a classification structure setting screen. [Figure 8] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 9] It is a diagram illustrating an example of an N-dimensional vector space. [Figure 10] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 11] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 12] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 13] It is a flow diagram illustrating an example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 14] It is a flow diagram illustrating another example of an operation flow of the information processing apparatus according to the present embodiment. [Figure 15] It is a diagram illustrating an example of a content classification screen. MODE FOR CARRYING OUT THE INVENTION

[0011] Hereinafter, an information processing apparatus, an information processing method, and a program according to embodiments will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the following embodiments. In all the drawings for describing the embodiments, components having the same function are denoted by the same reference numerals, and repeated descriptions thereof are omitted. In addition, the phrase "based on XX" as used in the present application means "based at least on XX", and includes cases where it is based on another element in addition to XX. Furthermore, the phrase "based on XX" is not limited to the case of directly using XX, and also includes cases where it is based on a result obtained by performing calculation or processing on XX. "XX" is any element (for example, any information).

[0012] (Embodiment) (Information processing device) The information processing device 100 of this embodiment creates management rules for content such as documents and manages the content based on the created management rules. Figure 1 is a diagram showing an example of the information processing device 100 of this embodiment. The information processing device 100 is implemented by a device such as a personal computer, server, smartphone, tablet computer, or industrial computer.

[0013] The information processing device 100 receives content. The information processing device 100 assigns information that identifies the physical address to the received content and stores the content with the physical address identification information in the content pool. An example of information that identifies the physical address is the physical address and an ID equivalent to the physical address. The following explanation continues with the case where the physical address is applied as an example of information that identifies the physical address. The information processing device 100 virtually classifies the content stored in the content pool and displays the result of the virtual classification of the content on the display unit. An example of the result of the virtual classification of the content is a classification tree that hierarchically represents the content. The information processing device 100 also searches for content stored in the content pool based on user specifications, for example. The information processing device 100 displays the result of the content search on the display unit.

[0014] The information processing device 100 includes a user interface (UI) 10, an account registration / update processing unit 20, a reception unit 25, a content pool 30, a content processing unit 70, and a display control unit 66. The content processing unit 70 comprises a virtual content pool construction processing unit 40, a hierarchical structure generation agent 50, a pseudo-metadata search agent 62, a natural language search agent 64, and a virtual content pool 80.

[0015] UI10 comprises an account registration / update UI12, a content pool UI14, a classification display UI16, and a natural language search UI18. An example of UI10 includes a display unit. The virtual content pool construction processing unit 40 constructs the virtual content pool 80. The virtual content pool construction processing unit 40 comprises a content pool crawler 42, a metadata generation agent 44, and an LLM (Large-Scale Language Model) 4.

[0016] The virtual content pool 80 comprises a user attribute database (DB:Data Base) 81, a metadata DB 82, a usage log DB 83, a vector space generation agent 84, an embedded processing unit 85, and a content vector space storage unit 86.

[0017] The account registration / update UI12 is a user interface (UI) for user U to register and update their account. The content pool UI14 is a user interface (UI) that allows user U to view the content contained in the content pool 30 and perform predetermined actions. The classification display UI16 is a UI for classifying and displaying content. For example, a classification display UI may be created for each organization or user, and the displayed content may be made viewable based on the user's specifications. The natural language search UI18 is a user interface that receives a search prompt from the user U and performs a search based on the received search prompt.

[0018] The account registration / update processing unit 20 obtains an account registration request from the account registration / update UI 12. Based on the user identification information and other information included in the obtained account registration request, the account registration / update processing unit 20 registers user attribute information in the user attribute DB 81.

[0019] Figure 2 shows an example of user attribute information. As shown in Figure 2, an example of user attribute information includes an employee number as an example of user identification information, name, affiliation data, information indicating job title, and job type code. An example of affiliation data includes the name of the business unit, business unit, department, section, job description, and department code. Returning to Figure 1, we will continue the explanation.

[0020] After user attribute information is registered in the user attribute DB 81, the account registration / update processing unit 20, upon receiving an account update request from the account registration / update UI 12, updates the user attribute information registered in the user attribute DB 81 based on the user identification information and other data included in the received account update request.

[0021] The reception unit 25 receives content and stores the received content in the content pool 30. Here, the content may be created by the information processing device 100, or it may be created outside the information processing device 100 and input into the information processing device 100. When content is created outside the information processing device 100 and input to the information processing device 100, the content may also be transmitted to the information processing device 100 from a terminal device (not shown) connected to the information processing device 100 via a communication network. In this case, the communication unit (not shown) of the information processing device 100 receives the content transmitted by the terminal device, and the receiving unit 25 acquires the content received by the communication unit. Here, the communication network includes the internet, WAN (Wide Area Network), LAN (Local Area Network), public lines, provider equipment, dedicated lines, wireless base stations, etc. The receiving unit 25 may or may not save the received content in the content pool 30. The following explanation will continue with an example where the receiving unit 25 saves the received content in the content pool 30. The content pool 30 stores one or more content items in the information processing device 100. One or more content items can be displayed on the UI 10. The content pool 30 assigns a physical address to each of the one or more content items stored. Each of the one or more content items remains stored in the content pool 30 and is displayed on the UI 10. The content pool 30 notifies the virtual content pool construction processing unit 40 of the physical addresses assigned to the stored content items.

[0022] The virtual content pool construction processing unit 40 constructs the virtual content pool 80. The content pool crawler 42 receives physical addresses notified from the content pool 30. The content pool crawler 42 also checks the update status of the content in the content pool 30 and newly added content to collect (crawl) physical addresses. For example, the content pool crawler 42 polls the content in the content pool 30 to collect physical addresses by checking the update status of the content and newly added content. The metadata generation agent 44 obtains a physical address from the content pool crawler 42 and identifies the content corresponding to that physical address from the content pool 30 based on the obtained physical address. The metadata generation agent 44 generates metadata from the identified content. For example, the metadata generation agent 44 uses an LLM (Large-Scale Language Model) 4 to generate metadata from the content. The metadata generation agent 44 stores the generated metadata in the metadata DB 82, associating it with content identification information.

[0023] Figure 3 shows an example of content metadata. In Figure 3, each category is associated with attribute items, descriptions, methods for automatically extracting metadata by an AI agent, character count, number of embedding dimensions, subspaces, chunk embedding / category, etc. As shown in Figure 3, an example of content metadata includes categories such as basic information, content information, permissions and access information, and tracking and management information.

[0024] Examples of basic information include title, creator, creation date, last updater, and last update date. All of these will be vectorized. Examples of content information include version, summary, keywords, category, theme, project status, intended use, content type, content format, and number of pages. Of these, the summary, keywords, category, theme, project status, intended use, content type, and content format are the ones that will be vectorized. Permission and access information includes access rights, confidentiality levels, approvers, and approval dates. Of these, access rights and confidentiality levels are the ones that will be vectorized. Tracking and management information includes status, storage location, associated content, expiration date (lifecycle), and content ID. Of these, status, expiration date (lifecycle), and content ID are subject to vectorization. The metadata generation agent 44 may also query the user for missing information and obtain it. For example, the metadata generation agent 44 outputs information to the display control unit 66 for querying missing information. The display control unit 66 obtains the information for querying missing information from the metadata generation agent 44 and displays the information for querying missing information on the UI 10. The metadata generation agent 44 obtains the information entered by the user in response to the information for querying missing information displayed on the UI 10. This allows the metadata generation agent 44 to complete the metadata. Return to Figure 1 and continue the explanation.

[0025] The user attribute DB81 stores the user attribute information registered by the account registration / update processing unit 20. The metadata DB82 stores the metadata that the metadata generation agent 44 has stored. The usage log DB83 stores the usage logs of user U. An example of a usage log is the search history, which includes information indicating the date and time of the search, the content ID (identification information), the search user's attributes, and content metadata information. If a natural language search was performed, the search history will also include information indicating the search conditions.

[0026] The vector space generation agent 84 retrieves user attribute information from the user attribute DB 81, metadata from the metadata DB 82, and usage logs from the usage log DB 83. Based on the retrieved user attribute information, metadata, and usage logs, the vector space generation agent 84 generates an N-dimensional (N is an integer N>1) vector space as metadata representing the characteristics of the content. For example, N may be the number of attribute items to be vectorized among the metadata included in the content. The N dimensions include the creator (affiliation, employee number, name, etc.) and a summary / abstract. An example of an author is 10-dimensional, and an example of a summary / abstract is 768 × 6 dimensions (for 3,000 characters), assuming 125 characters overlap in a 500-character chunk. The vector space generation agent 84 stores the generated N-dimensional vector space in the content vector space memory unit 86.

[0027] The content vector space storage unit 86 stores the N-dimensional vector space stored by the vector space generation agent 84. The embedding processing unit 85 obtains user attribute information from the vector space generation agent 84 and embeds the content into the N-dimensional vector space stored in the content vector space storage unit 86 based on the obtained user attribute information. The vector space generation agent 84, after the embedding processing unit 85 has embedded the content into an N-dimensional vector space, derives the inter-content distances between multiple content items embedded in the N-dimensional vector space stored in the content vector space storage unit 86. Based on the derived inter-content distances, the vector space generation agent 84 generates k clusters (where k is an integer k>1) from the multiple content items. For example, the vector space generation agent 84 generates k clusters using the k-means method based on the inter-content distances.

[0028] The hierarchical structure generation agent 50 analyzes metadata for each piece of content included in the cluster generated by the vector space generation agent 84, using LLM5, for the content stored in the content vector space storage unit 86. Based on the metadata analysis results, the hierarchical structure generation agent 50 recommends the optimal folder (lowest level). The hierarchical structure generation agent 50 displays a classification display UI 16 for recommending the optimal folder on the UI 10. For example, the hierarchical structure generation agent 50 outputs classification information to the display control unit 66 in order to recommend the optimal folder. The display control unit 66 receives the classification information from the hierarchical structure generation agent 50 and displays the classification information on the UI 10. The hierarchical structure generation agent 50 then receives information entered by the user in relation to the classification information.

[0029] The natural language search agent 64 obtains user identification information and search prompts from the natural language search UI 18 and outputs them to the pseudo-metadata search agent 62. The pseudo-metadata search agent 62 obtains user identification information and search prompts from the natural language search agent 64. Based on the obtained user identification information, the pseudo-metadata search agent 62 obtains user attribute information from the user attribute DB 81. The pseudo-metadata search agent 62 generates pseudo-user attribute information using LLM6. If the pseudo-metadata search agent 62 has all the necessary pseudo-user attribute information for the search, it stores the pseudo-user attribute information and generates pseudo-metadata based on the stored pseudo-user attribute information.

[0030] The pseudo-metadata search agent 62 places pseudo-user attribute information in an N-dimensional vector space where multiple contents stored in the content vector space storage unit 86 are embedded, based on the pseudo-metadata it has generated. The pseudo-metadata search agent 62 lists a predetermined number of contents, starting with those closest to the placed pseudo-user attribute information, and derives their likelihood.

[0031] The natural language search agent 64 obtains a predetermined number of content items and information indicating the likelihood of each of those content items from the pseudo-metadata search agent 62. The natural language search agent 64 outputs the obtained predetermined number of content items and information indicating the likelihood of each of those content items to the display control unit 66. The display control unit 66 obtains a predetermined number of content items and information indicating the likelihood of each of those content items from the natural language search agent 64, and displays them on the natural language search UI 18.

[0032] In the information processing device 100, the vector space generation agent 84 may also derive the distance between contents based on the weight vector. For example, the vector space generation agent 84 generates the weights c of all attributes. i The distribution can be made equal. In this case, the vector space generation agent 84 analyzes the distribution state for each attribute and uses the following method to generate weights c iThis determines the weight c. This makes it possible to define the distance between content by averaging the variability between each attribute. i It is assumed that it follows a normal distribution (mean μ, standard deviation σ). In this case, the mean of the variance for all attributes is given by equation (1), and the weight c for attribute i is given by i σ is expressed by equation (2). i This is the standard deviation of attribute i.

[0033]

number

number

[0034] In the information processing device 100, the vector space generation agent 84 may optimize the classification according to the creator's circumstances. For example, the vector space generation agent 84 generates the creator's attributes as M-dimensional (where M is an integer M>1) vector data. Figure 4 shows an example of creator attribute information. As shown in Figure 4, an example of creator attribute information includes an employee number as an example of creator identification information, a name, department data, information indicating job title, and a job type code. Examples of affiliation data include the name of the business unit, the name of the business division, the name of the department, the name of the section, the business content, the department code, the job title, and the job type code. For example, creator attribute information may be represented by employee number, job content, department code, information indicating the job title, and job type code.

[0035] The vector space generation agent 84 further adds the created M-dimensional vector data to generate an (M+N)-dimensional vector space as metadata representing the characteristics of the content. The vector space generation agent 84 stores the generated (M+N)-dimensional vector space in the content vector space storage unit 86. Returning to Figure 1, the explanation continues.

[0036] The embedding processing unit 85 embeds the content into the (N+M)-dimensional vector space stored in the content vector space storage unit 86. Here, the vector space generation agent 84 may create attributes of the creator, such as relationships between organizations (departments) and hierarchical relationships within departments. For example, the vector space generation agent 84 may use a graph neural network (GNN) to create relationships between organizations (departments) and hierarchical relationships within departments. By specifying the creator's attributes and cutting a cross-section of an N-dimensional space along the specified creator's attributes, it is possible to generate subclassifications of the classification. This method makes it possible to display the most suitable classification for an organization or individual.

[0037] In the information processing device 100, the vector space generation agent 84 may acquire management rules. The vector space generation agent 84 quantifies the acquired management rules and generates an R-dimensional vector space (where R is an integer R > 1). For example, management rules may include confidentiality levels, access rights, compliance requirements, lifecycle settings, etc. The management rules may be set by user U. The vector space generation agent 84 further adds the created R-dimensional vector data to generate an (R+M+N)-dimensional vector space as metadata representing the characteristics of the content. The vector space generation agent 84 stores the generated (R+M+N)-dimensional vector space in the content vector space storage unit 86.

[0038] The embedding processing unit 85 embeds the content into the (R+N+M) dimension vector space stored in the content vector space storage unit 86. The embedding processing unit 85 acquires an image with content embedded in a (R+N+M)-dimensional vector space and outputs it to the display control unit 66. The display control unit 66 acquires the image with content embedded in a (R+N+M)-dimensional vector space from the embedding processing unit 85 and displays it on the UI 10. This makes it possible to visualize the distribution state in (R+N+M) dimensions, i.e., within a (R,N,M) vector space.

[0039] In the information processing device 100, the vector space generation agent 84 may optimize classification according to the time attribute. For example, the vector space generation agent 84 creates the time attribute as T-dimensional (T is an integer T>1) vector data. An example of a time attribute is a two-dimensional (attribute, time) attribute that specifies the creation date or expiration date and the time indicating the corresponding date and time. The vector space generation agent 84 further adds the created T-dimensional vector data to generate a (T+R+M+N)-dimensional vector space as metadata representing the characteristics of the content. The vector space generation agent 84 stores the generated (T+R+M+N)-dimensional vector space in the content vector space storage unit 86. The embedding processing unit 85 embeds the content into a (T+R+N+M) dimension vector space stored in the content vector space storage unit 86.

[0040] In the information processing device 100, the vector space generation agent 84 may create user attributes as U-dimensional vector data (where U is an integer U > 1). Since Figure 4 can be applied to user attributes, a detailed explanation is omitted. The vector space generation agent 84 further adds the created U-dimensional vector data to generate a (U + T + R + M + N)-dimensional vector space as metadata representing the characteristics of the content. The vector space generation agent 84 stores the generated (U + T + R + M + N)-dimensional vector space in the content vector space storage unit 86.

[0041] The embedding processing unit 85 embeds the content that user U has searched so far into a (U+T+R+N+M) dimension vector space stored in the content vector space storage unit 86. The vector space generation agent 84 calculates the distance between the content and specific content included in the search history. The pseudo-metadata search agent 62 retrieves search results based on the distance calculated by the vector space generation agent 84. For example, the pseudo-metadata search agent 62 may prioritize retrieving search results starting with those with the shortest distance.

[0042] Here, the vector space generation agent 84 may calculate the distance not only to specific content included in the search history, but also to all content included in the search history or to content included in the same classification. The pseudo-metadata search agent 62 may have a first trained model that derives content features based on one or more content combinations included in the content search results. The pseudo-metadata search agent 62 creates information for presenting the derived content features and outputs it to the display control unit 66. The display control unit 66 displays the information for presenting the content features from the pseudo-metadata search agent 62 on the UI 10.

[0043] The first trained model is created by machine learning the relationship between one or more content combinations included in the search results and the content features derived from those combinations. For example, the first trained model is created by machine learning with one or more content combinations included in the search results as explanatory variables and the content features derived from those combinations as the dependent variable.

[0044] Furthermore, the pseudo-metadata search agent 62 may have a second trained model that derives questions for narrowing down the content based on the characteristics of the derived content. The pseudo-metadata search agent 62 creates questions for narrowing down the derived content and outputs them to the display control unit 66. The display control unit 66 displays the questions for narrowing down the content from the pseudo-metadata search agent 62 on the UI 10. The second pre-trained model is created by machine learning the relationship between content features and the questions used to narrow down content based on those features. For example, the second pre-trained model is created by machine learning with content features as explanatory variables and the questions used to narrow down content based on those features as the dependent variable. This allows for the creation of information that presents the characteristics of the content to the user based on the search results, and enables the creation of questions to narrow down the most suitable content. Based on the answers, more relevant content can be presented.

[0045] In the information processing device 100, the embedding processing unit 85 may embed the content into a (T+R+N+M) dimension vector space stored in the content vector space storage unit 86, and present nearby content as similar documents to the user. Furthermore, the vector space generation agent 84 may present the reciprocal of the distance between contents as the similarity score to the user. In this case, if there is content with a distance of zero between contents, the vector space generation agent 84 creates information to notify the user U that there is a high possibility of it being a duplicate document and outputs it to the display control unit 66. The display control unit 66 may display the information from the vector space generation agent 84 indicating a high possibility of it being a duplicate document on the UI 10.

[0046] The vector space generation agent 84 may generate a (R+N)-dimensional vector space, a (T+N)-dimensional vector space, a (U+N)-dimensional vector space, a (T+M+N)-dimensional vector space, or a (U+M+N)-dimensional vector space as metadata representing the features of the content. In other words, the vector space generation agent 84 can generate a vector space of any combination of T, R, M, and U plus N.

[0047] In the embodiment described above, the functions of the information processing device 100 may be implemented in a distributed manner by multiple devices. In this case, the multiple devices that implement the functions of the information processing device 100 in a distributed manner may be configured to be directly connected to perform information input and output, or they may be configured to be connected via a communication network to send and receive information. Furthermore, among the multiple devices that implement the functions of the information processing device 100 in a distributed manner, there may be a mix of directly connected devices and devices connected via a network. All or part of the account registration / update processing unit 20, reception unit 25, content pool crawler 42, metadata generation agent 44, hierarchical structure generation agent 50, pseudo-metadata search agent 62, natural language search agent 64, display control unit 66, vector space generation agent 84, and embedded processing unit 85 are functional units (hereinafter referred to as software functional units) realized by a processor such as a CPU (Central Processing Unit) executing a program stored in a memory unit (not shown).

[0048] Furthermore, all or part of these functional units may be implemented by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), or FPGA (Field-Programmable Gate Array), or by a combination of software functional units and hardware.

[0049] The operation of the information processing device 100 will be explained below with reference to Figures 5 to 15. Figure 5 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. The process by which the information processing device 100 stores content will be explained with reference to Figures 1 and 5. (Step S1-1) The information processing device 100 performs the login process. For example, user U enters user identification information and a password on the initial screen (not shown) displayed on the UI 10. The information processing device 100 performs the login process based on the entered user identification information and password.

[0050] (Step S2-1) The information processing device 100 creates content. For example, user U creates content using the information processing device 100. Content may also be input to the information processing device 100 from an external device. For example, content may be transmitted to the information processing device 100 from a terminal device (not shown) connected to the information processing device 100 via a communication network. In this case, the information processing device 100 receives and acquires the content transmitted by the terminal device. (Step S3-1) The content pool UI14 detects when the "Save As" button (not shown) is pressed.

[0051] (Step S4-1) The reception unit 25 receives content and saves the received content to the content pool 30. (Step S5-1) The content pool 30 notifies the content pool crawler 42 of the physical addresses assigned to the stored content. (Step S6-1) The content pool crawler 42 accepts the physical address notified by the content pool 30.

[0052] (Step S7-1) The metadata generation agent 44 obtains a physical address from the content pool crawler 42. Based on the obtained physical address, the metadata generation agent 44 identifies the content corresponding to the physical address from the content stored in the content pool 30. The metadata generation agent 44 generates metadata from the identified content. The metadata generation agent 44 stores the generated metadata in the metadata DB 82, associating it with content identification information.

[0053] (Step S8-1) The hierarchical structure generation agent 50 analyzes metadata for each piece of content included in the cluster generated by the vector space generation agent 84, for the content stored in the content vector space storage unit 86. Based on the metadata analysis results, the hierarchical structure generation agent 50 recommends the optimal folder (lowest level). The hierarchical structure generation agent 50 displays a classification display UI 16 for recommending the optimal folder on the UI 10.

[0054] (Step S9-1) The hierarchical structure generation agent 50 determines whether or not user U has performed an action to respond to a recommendation on the classification display UI 16. (Step S10-1) If the hierarchical structure generation agent 50 determines that user U has not taken any action to respond to the recommendation on the classification display UI 16, it displays the classification display UI 16 on UI 10 to recommend the next most suitable folder. Proceed to step S9-1. (Step S11-1) When the hierarchical structure generation agent 50 determines that user U has responded to a recommendation on the classification display UI 16, it opens the recommended folder on the classification display UI 16 and displays the file name of the corresponding content.

[0055] In the operation flow of the information processing device 100 shown in Figure 5, the following processing may be performed. For example, in step S6-1, the content pool crawler 42 may accept physical addresses notified by any means, not limited to physical addresses notified by the content pool 30. Furthermore, in step S7-1, if the metadata generation agent 44 finds any missing information in the metadata generated from the identified content, it may ask user U questions to fill in the gaps. This allows the metadata generation agent 44 to complete the metadata.

[0056] Figure 6 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. The process by which the information processing device 100 generates a hierarchical structure of classification will be explained with reference to Figures 1 and 6. (Step S1-2) The hierarchical structure generation agent 50 starts a classification setting program. An example of the classification setting program is included in the hierarchical structure generation agent 50. (Step S2-2) The hierarchical structure generation agent 50 displays all folders in the content pool 30.

[0057] (Step S3-2) The hierarchical structure generation agent 50 detects that user U has selected a folder to be classified and pressed the "Execute" button (not shown). (Step S4-2) The hierarchical structure generation agent 50 displays the "Classification Structure Settings Screen" based on the pressed "Execute" button.

[0058] Figure 7 shows an example of the classification structure settings screen. As shown in Figure 7, in this example of the classification structure settings screen, the total number of content items to be classified is M, the maximum number of levels is m, the average number of content items in the lowest level folder is n1, the number of folders in the lowest level (number of classifications) is k1 (=[M / n1]+1), and the number of folders in any i-th level below the lowest level is n. iand the number of folders k included in the i-th layer i can be set. Among these, the total number of contents to be classified M, the number of folders n1 in the lowermost layer, and the number n of folders included in the i-th layer i are set by the information processing apparatus 100. The user U can set the maximum number of layers m, the average number of contents n1 included in the lowermost layer folders, and the number k of folders included in any i-th layer above the lowermost layer i by the user U.

[0059] If a large classification (l folders) and middle classification (m folders) are set, the middle classification folders are created as follows. The average number of folders included in the folder one level upper is n2. The average number of folders is input on the UI 10. In this case, the number of classifications is calculated by equation (4). k2=[k1 / n2]+1 (4) A middle classification folder is generated by dividing the final centroids (k centroids) of the lowermost folders obtained by the k-means method into k2 centroids using the k-means method. The user U sets the number of layers m of the hierarchical structure in advance, and the process ends when the number of layers reaches m.

[0060] The user U refers to the classification structure setting screen, and inputs the number n of folders included in each layer i i (the number of contents n1 for the lowermost layer) and the maximum number of layers m. The hierarchical structure generation agent 50 sets the number n of folders included in each layer i input by the user U i (the number of contents n1 for the lowermost layer) and the maximum number of layers m. Returning to FIG. 6, the description will be continued.

[0061] (Step S5-2) The hierarchical structure generation agent 50 sets the layer i to 1. (Step S6-2) The hierarchical structure generation agent 50 calculates the number of folders included in the i-th folder from the lowermost layer by the following equation (5). k i =[ki-1 / n i ]+1 (5) However, k0 = M (total number of content items).

[0062] (Step S7-2) The hierarchical structure generation agent 50 determines whether or not level i is level m. If the hierarchical structure generation agent 50 determines that level i is level m, it considers the hierarchical structure of the classification to be complete. (Step S8-2) If the hierarchical structure generation agent 50 determines that each hierarchical level i is not m, it sets i to i+1 and proceeds to step S6-2.

[0063] In the information processing device 100, the hierarchical structure generation agent 50 may be configured to automatically improve the hierarchical structure. Specifically, the hierarchical structure generation agent 50 may reconfigure the folders when the distance between the centroids of the lowest-level folders falls below the threshold initially set. Alternatively, the hierarchical structure generation agent 50 may reconfigure the folders when the number of contents of the lowest-level folders exceeds the initially set range of the initially set value of n1. The hierarchical structure generation agent 50 may also reconfigure the folders based on the number of views. This configuration allows you to reconfigure folders when the initially set hierarchical structure is no longer optimal due to increases or decreases in the stored content.

[0064] Figure 8 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. Referring to Figures 1 and 8, the process by which the information processing device 100 starts generating the optimal folder (lowest level) will be described. Here, as an example, the case in which the vector space generation agent 84 generates an N-dimensional vector space will be described. (Steps S1-3) The vector space generation agent 84 collects data for all files to be classified from the user attribute DB 81, metadata DB 82, and usage log DB 83.

[0065] (Step S2-3) The vector space generation agent 84 generates an N-dimensional vector space based on the acquired user attribute information, metadata, and usage logs. The vector space generation agent 84 stores the generated N-dimensional vector space in the content vector space storage unit 86. The embedding processing unit 85 obtains content identification information and metadata from the vector space generation agent 84, and embeds the content into the N-dimensional vector space stored in the content vector space storage unit 86 based on the obtained content identification information and metadata.

[0066] (Step S3-3) The vector space generation agent 84 extracts k1 points from an N-dimensional space. For example, the vector space generation agent 84 may extract k1 points from an N-dimensional space according to a predetermined rule, or it may extract them randomly. (Step S4-3) The vector space generation agent 84 calculates the content-to-content distance between each content and the k1 extracted points. For example, the vector space generation agent 84 calculates the content-to-content distance according to the definition of content-to-content distance shown in equation (6).

[0067]

number

[0068] The vector space generation agent 84 identifies points among those extracted in step S3-3 that are closest in distance from other content, and collects content close to these identified points to generate k1 clusters.

[0069] (Step S5-3) The vector space generation agent 84 calculates the centroid point in each cluster based on the distance between contents. (Step S6-3) The vector space generation agent 84 calculates the distance of all content to k1 centroid points and moves content that is close to a centroid point in a different cluster than the one it belongs to to the cluster that is closer.

[0070] (Step S7-3) The vector space generation agent 84 moved N pieces of content between clusters. T Determine whether the value is 0 or not. N is the number of contents moved between clusters. T If = 0, the creation of the optimal folder is completed. Number of contents moved between clusters N T If the result is not equal to 0, proceed to step S6-3.

[0071] Figure 9 shows an example of an N-dimensional vector space. As shown in Figure 9, content is embedded in this example of an N-dimensional vector space. Furthermore, Figure 9 shows clusters C1 to C6 and the centroids COG1 of cluster C1 to COG6 of cluster C6.

[0072] Figure 10 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. Referring to Figures 1 and 10, the process by which the information processing device 100 starts generating the optimal folder (upper layer) will be explained. Here, as an example, the case in which the vector space generation agent 84 generates an N-dimensional vector space will be explained. (Steps S1-4) The vector space generation agent 84 extracts k2 points from the k1 centroids of the cluster directly below it. For example, the vector space generation agent 84 may extract k2 points from the k1 centroids of the cluster directly below it according to a predetermined rule, or it may extract them randomly. (Step S2-4) The vector space generation agent 84 measures the distance between the extracted k2 points and the centroid points of the lower clusters, and generates k2 clusters using the k-means method.

[0073] (Step S3-4) The vector space generation agent 84 calculates the centroid point in each cluster based on the distance between contents. (Step S4-4) The vector space generation agent 84 calculates the distance to k2 centroid points for all folders and moves folders that are close to the centroid points of a different cluster than the one they belong to to that nearby cluster.

[0074] (Step S5-4) The vector space generation agent 84 moved N pieces of content between clusters. T Determine whether the value is 0 or not. N is the number of contents moved between clusters. T If = 0, the creation of the optimal top-level folder is completed. Number of contents moved between clusters N T If the result is not equal to 0, proceed to step S4-4.

[0075] Figure 11 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. The process by which the information processing device 100 performs natural language search will be explained with reference to Figures 1 and 11. Here, as an example, we will explain the case where user U is logged in and the vector space generation agent 84 is generating a (T+R+M+N) dimension vector space.

[0076] (Steps S1-5) The natural language search UI 18 receives a search prompt entered by user U. The natural language search agent 64 obtains the search prompt received by the natural language search UI 18 and the logged-in user's identification information. Based on the obtained user identification information, the natural language search agent 64 obtains user attribute information from the user attribute DB 81. The natural language search agent 64 creates a prompt creation request that includes the user identification information and user attribute information and outputs it to the pseudo-metadata search agent 62.

[0077] (Step S2-5) The pseudo-metadata search agent 62 obtains a prompt creation request from the natural language search agent 64. The pseudo-metadata search agent 62 obtains user identification information and user attribute information included in the obtained prompt creation request, and creates a prompt using LLM6 based on the obtained user attribute information. LLM6 includes a model that has been trained for pseudo-metadata generation. (Steps S3-5) The pseudo-metadata search agent 62 uses LLM6 to check whether the user attribute information necessary for the search is available. LLM6 includes pre-trained functions that check the availability of the user attribute information necessary for the search and list the required user attribute information. For example, the pseudo-metadata search agent 62 outputs information to the display control unit 66 for querying missing user attribute information. The display control unit 66 receives the information for querying missing user attribute information from the pseudo-metadata search agent 62 and displays the information for querying missing user attribute information on the UI 10. The pseudo-metadata search agent 62 then receives the information entered by user U in response to the information for querying missing user attribute information displayed on the UI 10.

[0078] (Steps S4-5) The pseudo-metadata search agent 62 determines whether the user attribute information necessary for the search is available. (Step S5-5) The pseudo-metadata search agent 62 requests additional information from user U if it determines that the user attribute information necessary for the search is not available. For example, the pseudo-metadata search agent 62 may request additional information via chat. After that, the process proceeds to step S1-5.

[0079] (Step S6-5) The pseudo-metadata search agent 62, when it determines that it has all the necessary user attribute information for a search, stores pseudo-user attribute information and generates pseudo-metadata based on the stored pseudo-user attribute information. (Step S7-5) The pseudo-metadata search agent 62 places the generated pseudo-metadata into a (T+R+M+N)-dimensional vector space in which multiple contents stored in the content vector space storage unit 86 are embedded, based on the pseudo-metadata it generates.

[0080] (Step S8-5) The pseudo-metadata search agent 62 lists a predetermined number of content items, starting with those closest to the placed pseudo-metadata, and derives their likelihood. When P is the coordinate of a point in the content vector space generated by the pseudo-metadata, the likelihood L of content X can be expressed, for example, by equation (7). L(x) = α(1 / D(P,X)) (7) In equation (7), α is an arbitrary constant used to adjust the value. According to equation (7), the closer (smaller) the distance D, the larger the likelihood L becomes.

[0081] The natural language search agent 64 obtains a predetermined number of content items and information indicating the likelihood of each of those content items from the pseudo-metadata search agent 62. The natural language search agent 64 outputs the obtained predetermined number of content items and information indicating the likelihood of each of those content items to the display control unit 66. The display control unit 66 obtains the predetermined number of content items and information indicating the likelihood of each of those content items from the natural language search agent 64 and displays them on the UI 10.

[0082] Figure 12 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. Referring to Figures 1 and 12, other processes performed by the information processing device 100 for natural language search will be described. Here, as an example, we will describe the case where user U is logged in and the vector space generation agent 84 is generating a (T+R+M+N) dimension vector space.

[0083] (Steps S1-6) The natural language search UI 18 receives a search prompt entered by user U. The natural language search agent 64 obtains the search prompt received by the natural language search UI 18 and the logged-in user's identification information. Based on the obtained user identification information, the natural language search agent 64 obtains user attribute information from the user attribute DB 81. The natural language search agent 64 creates a prompt creation request that includes the user identification information and user attribute information and outputs it to the pseudo-metadata search agent 62.

[0084] (Step S2-6) The pseudo-metadata search agent 62 obtains a prompt creation request from the natural language search agent 64. The pseudo-metadata search agent 62 obtains user identification information and user attribute information included in the obtained prompt creation request, and creates a prompt using LLM6 based on the obtained user attribute information. LLM6 includes a model that has been trained for pseudo-metadata generation.

[0085] (Steps S3-6) The pseudo-metadata search agent 62 uses LLM6 to check whether the user attribute information necessary for the search is available. LLM6 includes pre-trained functions that check the availability of the user attribute information necessary for the search and list the required user attribute information. For example, the pseudo-metadata search agent 62 outputs information to the display control unit 66 for querying missing user attribute information. The display control unit 66 receives the information for querying missing user attribute information from the pseudo-metadata search agent 62 and displays the information for querying missing user attribute information on the UI 10. The pseudo-metadata search agent 62 then receives the information entered by user U in response to the information for querying missing user attribute information displayed on the UI 10.

[0086] (Steps S4-6) The pseudo-metadata search agent 62 excludes dimensions relating to attributes that have not yet been generated from the search space if attribute generation is not complete. (Steps S5-6) The pseudo-metadata search agent 62 stores user attribute information after excluding dimensions relating to attributes that have not been generated in steps S4-6 from the search space, or after attribute generation is completed in step S3-6, and generates pseudo-metadata based on the stored user attribute information.

[0087] (Step S6-6) The pseudo-metadata search agent 62 places the generated pseudo-metadata into a (T+R+M+N)-dimensional vector space in which multiple contents stored in the content vector space storage unit 86 are embedded, based on the pseudo-metadata it has generated. The pseudo-metadata search agent 62 generates a subspace containing only the dimensions in which attribute data exists, and searches this space.

[0088] (Step S7-6) The pseudo-metadata search agent 62 lists a predetermined number of content items, starting with those closest to the placed pseudo-metadata, and derives their likelihood. The natural language search agent 64 obtains a predetermined number of content items and information indicating the likelihood of each of those content items from the pseudo-metadata search agent 62. The natural language search agent 64 outputs the obtained predetermined number of content items and information indicating the likelihood of each of those content items to the display control unit 66. The display control unit 66 obtains a predetermined number of content items and information indicating the likelihood of each of those content items from the natural language search agent 64 and displays them on the UI 10.

[0089] Figure 13 is a flowchart showing an example of the operation flow of the information processing device 100 in this embodiment. Referring to Figures 1 and 13, the process by which the information processing device 100 displays the optimal classification for user U will be described. Here, as an example, the case in which the vector space generation agent 84 generates a (T+R+M+N) dimension vector space will be described. (Steps S1-7) The information processing device 100 performs the login process. For example, user U enters user identification information and a password on the initial screen (not shown) displayed on the UI 10. The information processing device 100 performs the login process based on the entered user identification information and password.

[0090] (Step S2-7) The display control unit 66 displays the classification creation screen on the UI 10. The classification creation screen includes a display for selecting whether to target content created by the user (user U), content created by others other than user U, or all content.

[0091] First, let's explain what happens when user U chooses to target content they have created. (Step S3-7-1) The vector space generation agent 84 creates a subspace in a (T+R+M+N) dimension vector space in which multiple contents stored in the content vector space memory unit 86 are embedded, by fixing the creator attribute, which is M-dimensional vector data, to itself. (Step S4-7-1) The hierarchical structure generation agent 50 creates and completes the classification on this subspace.

[0092] Next, we will explain what happens when user U chooses to target content created by others. (Step S3-7-2) The vector space generation agent 84 creates a subspace in a (T+R+M+N) dimension vector space in which multiple contents stored in the content vector space memory unit 86 are embedded, by fixing the creator attribute, which is an M-dimensional vector data, to something other than itself (someone other than itself).

[0093] (Step S4-7-2) The hierarchical structure generation agent 50 creates a classification on this subspace. (Step S5-7-2) The hierarchical structure generation agent 50 leaves the lowest-level folder containing previously viewed content as is, and creates a category called "Other" for all other folders, moving them under this category, and then completes the process. By classifying content with a viewing frequency below a pre-set threshold into "Other," the hierarchical structure generation agent 50 can improve visibility.

[0094] Next, we will explain what happens when user U chooses to include all content. (Step S3-7-3) The vector space generation agent 84 creates and completes classification in a (T+R+M+N) dimension vector space in which multiple contents stored in the content vector space memory unit 86 are embedded.

[0095] In the information processing device 100, the vector space generation agent 84 may use LLM to extract creator attributes that are similar to the user attributes of the user themselves. The vector space generation agent 84 may also create a classification based on a subset of the content vector space based on the extracted creator attributes.

[0096] Figure 14 is a flowchart showing another example of the operation flow of the information processing device 100 in this embodiment. Referring to Figures 1 and 14, the process by which the information processing device 100 displays the optimal classification for user U will be described. Here, as an example, the case in which the vector space generation agent 84 generates a (T+R+M+N) dimension vector space will be described. (Steps S1-8) The information processing device 100 performs the login process. For example, user U enters user identification information and a password on the initial screen (not shown) displayed on the UI 10. The information processing device 100 performs the login process based on the entered user identification information and password.

[0097] (Step S2-8) The natural language search UI18 accepts the conditions for creating classifications that are entered as prompts on the Chat input screen of LLM (not illustrated). The natural language search agent 64 obtains user identification information and conditions for classification creation entered as prompts from the natural language search UI 18 and outputs them to the pseudo-metadata search agent 62. The pseudo-metadata search agent 62 obtains user identification information and classification creation conditions entered as prompts from the natural language search agent 64. The pseudo-metadata search agent 62 outputs the obtained user identification information and prompts to the LLM (not shown). The LLM (not shown) obtains the user identification information and prompts from the pseudo-metadata search agent 62, refers to the (T+R+M+N) dimension vector space in which multiple contents stored in the content vector space storage unit 86 are embedded, and creates a content subspace that matches the conditions of user U.

[0098] (Steps S3-8) The vector space generation agent 84 creates and completes a classification in the content subspace that matches the conditions for user U created by LLM (not shown). Figure 15 shows an example of a content classification screen. As shown in Figure 15, the example content classification screen includes a section for displaying major categories and a section for displaying subcategories. Furthermore, the example content classification screen includes an update button (UPBU).

[0099] The section displaying major categories shows one or more folders. In the example shown in Figure 15, the folders "AAA", "BBB", "CCC", ..., "XXX", ..., and "KKK" are displayed. The section displaying subcategories shows one or more folders that are included in the folder specified by user U, from among the one or more folders displayed in the section displaying major categories. In the example shown in Figure 15, the folders "PPP", "QQQ", "RRR", ..., "SSS", and "TTT" that are included in the "XXX" folder are displayed. Furthermore, when the update button UPBU is pressed, the maximum number of levels m that can be set by user U in the classification structure settings screen shown in Figure 7, the average number of contents n1 in the lowest level folder, and the number of folders k in the i-th level from the lowest level are displayed. i This will allow for corrections.

[0100] <Example Configuration> As an example configuration, the information processing device comprises a receiving unit that receives content, a content processing unit that assigns information identifying a physical address to the content received by the receiving unit, stores it in a content pool, virtually classifies the content stored in the content pool, and a display control unit that causes the content processing unit to display the results of the virtual classification of the content on a display unit. By configuring it in this way, the information processing device can display the results of a virtual classification of the content stored in the content pool on the display unit. This reduces the effort required for content management.

[0101] As one example configuration, the content processing unit searches for content stored in the content pool, and the display control unit causes the content processing unit to display the search results on the display unit. By configuring it in this way, the information processing device can display content stored in the content pool on the display unit. For example, a virtual classification display UI may be created and displayed for each organization or user. When a user specifies content on the virtual classification display UI, the information processing device can display the specified content on the display unit. This reduces the effort required for content management. Here, instead of a physical address, or along with a physical address, a URI (Uniform Resource Identifier) ​​may be specified so that the content corresponding to the specified URI is displayed on the display unit.

[0102] As an example configuration, the content processing unit further comprises: a content pool crawler that receives information identifying the physical address assigned to content stored in the content pool; a metadata generation unit that obtains the physical address from the content pool, obtains information identifying the content from the content pool based on the obtained physical address, and generates metadata based on the information identifying the content; a vector space generation unit that generates an N-dimensional vector space (where N is an integer N>1); and an embedding processing unit that embeds the content into the N-dimensional vector space generated by the vector space generation unit based on the metadata. The vector space generation unit generates k clusters (where k is an integer k>1) from multiple contents embedded in the N-dimensional vector space (where N is an integer N>1). By configuring it in this way, the information processing device can generate an N-dimensional vector space as metadata representing the characteristics of the content. Furthermore, the information processing device can generate k clusters from multiple content items embedded in the generated N-dimensional vector space. Since multiple content items can be classified into k clusters, the effort required for content management can be reduced.

[0103] As one example configuration, the vector space generation unit derives the inter-content distances between multiple contents embedded in an N-dimensional vector space, and generates k clusters from the multiple contents based on the derived inter-content distances. By configuring it in this way, the information processing device can generate k clusters based on the inter-content distances between multiple contents embedded in an N-dimensional vector space. Since multiple contents can be classified into k clusters, the effort required for content management can be reduced.

[0104] As one example configuration, the vector space generation unit derives the distance between content items based on the weight vector. By configuring it in this way, the information processing device can derive the distance between content items based on the weight vector, allowing it to average out the variability between each attribute to derive the distance between content items, or to increase the weight of attributes whose influence on the distance between content items you want to increase.

[0105] As one example configuration, the content processing unit further comprises a hierarchical structure generation unit that generates a hierarchical structure based on the distance between the centroids of each of the k clusters. By configuring it in this way, the information processing device can classify content based on the distance between the centroids of each of the k clusters, thereby reducing the effort required for content management.

[0106] As one example configuration, the vector space generation unit creates M-dimensional (where M is an integer > 1) vector data representing the attributes of the content creator, generates an M-dimensional vector space, and the embedding unit embeds the content into the N+M-dimensional vector space. By configuring it in this way, the information processing device can create M-dimensional vector data representing the attributes of the content creator and generate an N+M-dimensional vector space. Furthermore, the information processing device can generate multiple clusters based on the inter-content distances between multiple content items embedded in the generated N+N-dimensional vector space. Since multiple content items can be classified into multiple clusters, the effort required for content management can be reduced.

[0107] As an example configuration, the vector space generation unit creates R-dimensional (where R is an integer R>1) vector data based on management rules and generates an R-dimensional vector space. The embedding unit embeds the content into the N+M+R-dimensional vector space. By configuring it in this way, the information processing device can create R-dimensional vector data based on management rules and generate an N+M+R-dimensional vector space. Furthermore, the information processing device can generate multiple clusters based on the inter-content distances between multiple contents embedded in the generated N+N+R-dimensional vector space. Since multiple contents can be classified into multiple clusters, the effort required for content management can be reduced.

[0108] As an example configuration, the vector space generation unit creates T-dimensional (T is an integer where T>1) vector data representing the time axis and attributes, and generates a T-dimensional vector space. The embedding unit embeds the content into the N+M+R+T-dimensional vector space. By configuring it in this way, the information processing device can create T-dimensional vector data representing the time axis and attributes, and generate an N+M+R+T-dimensional vector space. Furthermore, the information processing device can generate multiple clusters based on the inter-content distances between multiple contents embedded in the generated N+M+R+T-dimensional vector space. Since multiple contents can be classified into multiple clusters, the effort required for content management can be reduced.

[0109] As one example configuration, the vector space generation unit creates U-dimensional vector data (where U is an integer U>1) representing user attributes and generates a U-dimensional vector space, while the embedding processing unit embeds the content into the U+N+M+R+T-dimensional vector space. By configuring it in this way, the information processing device can create U-dimensional vector data representing user attributes and generate a U+N+M+R+T-dimensional vector space. Furthermore, the information processing device can generate multiple clusters based on the inter-content distances between multiple contents embedded in the generated U+N+M+R+T-dimensional vector space. Since multiple contents can be classified into multiple clusters, the effort required for content management can be reduced.

[0110] As an example configuration, the content processing unit further includes a pseudo-metadata search unit that generates pseudo-metadata based on search prompts and user attributes, and searches for content based on the created pseudo-metadata, while the display control unit causes the content searched by the pseudo-metadata search unit to be displayed on the display unit. By configuring it in this way, the information processing device can generate pseudo-metadata based on search prompts and user attributes, and search for content based on the generated pseudo-metadata.

[0111] As one example configuration, the vector space generation unit derives the similarity between content based on the distance between content, and the display control unit causes the display unit to display the similarity derived by the vector space generation unit. By configuring it in this way, the information processing device can inform the user of the degree of similarity between a given piece of content and similar pieces of content by notifying them of the degree of similarity. Here, cosine similarity, Manhattan distance, Mahalanobis distance, perceptual distance, tree distance, etc., can also be applied as the distance between pieces of content.

[0112] As one example configuration, the vector space generation unit derives the distance between multiple content items based on the content search results obtained by the pseudo-metadata search unit. By configuring the system in this way, the information processing device can generate k clusters based on the search results for content and the distances between multiple content items. Since multiple content items can be classified into k clusters, the effort required for content management can be reduced. Here, the method for classifying multiple content items into k clusters is independent of how the distance is defined. In addition to the k-nearest neighbors method, other clustering methods can also be applied.

[0113] As one example configuration, the hierarchical structure generation unit analyzes metadata for the content contained in each of the k clusters and, based on the metadata analysis results, creates information indicating classification for recommending folders. By configuring it in this way, the information processing device can analyze metadata for the content contained in each of the k clusters, and based on the results of the metadata analysis, it can create information indicating classifications for recommending folders.

[0114] As one example configuration, if the metadata generation unit generates metadata based on the content and there is missing information, it creates information to query for the missing information, retrieves the information entered in response to the created query information, and completes the metadata. By configuring it in this way, the information processing device can query user U for missing metadata, and then generate a vector space based on the metadata obtained through the query.

[0115] As one example configuration, the hierarchical structure generation unit generates a hierarchical structure based on the maximum number of levels, the average number of contents in the lowest-level folder, and the number of folders in any level below the lowest level. By configuring it in this way, the information processing device can generate a hierarchical structure based on the maximum number of levels set by user U, the average number of contents in the lowest-level folder, and the number of folders in any level below the lowest level.

[0116] As one example configuration, the pseudo-metadata search unit derives content characteristics based on the search results for the content, and the display control unit causes the display unit to display information indicating the content characteristics derived by the pseudo-metadata search unit. By configuring it in this way, the information processing device can derive the characteristics of the content based on the search results and display them on the display unit, thereby allowing the user U to recognize the characteristics of the content.

[0117] As one example configuration, the pseudo-metadata search unit derives a query to narrow down the content based on the characteristics of the derived content, and the display control unit causes the display unit to display information indicating the query for narrowing down the content derived by the pseudo-metadata search unit. By configuring it in this way, the information processing device can derive questions to narrow down the content based on the characteristics of the content and display them on the display unit, so that the optimal content can be selected based on the answers to the questions.

[0118] As one example configuration, the pseudo-metadata search unit creates information to query for missing information if there is missing information in the user attributes. By configuring it in this way, the information processing device can query user attributes that are missing from user U, and then search for content based on the user attributes obtained through the query.

[0119] Although embodiments of the present invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments, and design modifications and the like are also included within the scope of the gist of the present invention. Alternatively, a computer program for realizing the functions of the information processing device 100 described above may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be loaded into a computer system and executed. The term "computer system" here may include hardware such as an operating system and peripheral devices.

[0120] Furthermore, "computer-readable recording media" refers to writable non-volatile memory such as flexible disks, magneto-optical disks, ROMs, and flash memory, portable media such as DVDs (Digital Versatile Disks), and storage devices such as hard disks built into computer systems.

[0121] Furthermore, "computer-readable recording media" also includes volatile memory (such as DRAM (Dynamic Random Access Memory)) within computer systems that act as servers or clients when programs are transmitted via networks such as the Internet or communication lines such as telephone lines, which retain programs for a certain period of time.

[0122] Furthermore, the above program may be transmitted from a computer system that stores the program in a memory device or the like to another computer system via a transmission medium or by transmission waves within the transmission medium. Here, the "transmission medium" used to transmit the program refers to a medium that has the function of transmitting information, such as a network (communication network) like the Internet or a communication line (communication line) like a telephone line.

[0123] Furthermore, the above program may be intended to implement some of the functions described above. It may also be a so-called differential file (differential program) that can implement the aforementioned functions in combination with programs already recorded in the computer system. [Explanation of Symbols]

[0124] 100…Information processing device, 10…UI, 12…Account registration / update UI, 14…Content pool UI, 16…Classification display UI, 18…Natural text search UI, 20…Account registration / update processing unit, 30…Content pool, 40…Virtual content pool construction processing unit, 42…Content pool crawler, 44…Metadata generation agent, 50…Hierarchical structure generation agent, 62…Pseudo-metadata search agent, 64…Natural text search agent, 66…Display control unit, 80…Virtual content pool, 81…User attribute DB, 82…Metadata DB, 83…Usage log DB, 84…Vector space generation agent, 85…Embedding processing unit, 86…Content vector space storage unit

Claims

1. The reception desk that accepts content, The reception unit assigns information to identify the physical address to the content it receives, stores it in a content pool, and the content processing unit virtually classifies the content stored in the content pool. The content processing unit virtually classifies the content and the resulting display control unit displays this classification on the display unit. An information processing device equipped with the following features.

2. The content processing unit searches for content stored in the content pool, The information processing apparatus according to claim 1, wherein the display control unit causes the content processing unit to display the results of the content search on the display unit.

3. The aforementioned content processing unit, A content pool crawler that receives information identifying the physical addresses assigned to the content stored in the aforementioned content pool, A metadata generation unit obtains information identifying a physical address from the content pool crawler, obtains content from the content pool based on the obtained information identifying a physical address, and generates metadata based on the obtained content. A vector space generator that generates an N-dimensional (where N is an integer N > 1) vector space, An embedding processing unit that embeds content based on metadata into the N-dimensional vector space generated by the vector space generation unit, Furthermore, The vector space generation unit generates k clusters (where k is an integer k > 1) from multiple contents embedded in an N-dimensional vector space (where N is an integer N > 1). The information processing apparatus according to claim 2.

4. The information processing apparatus according to claim 3, wherein the vector space generation unit derives the inter-content distances between a plurality of contents embedded in an N-dimensional vector space, and generates k clusters from the plurality of contents based on the derived inter-content distances.

5. The information processing apparatus according to claim 4, wherein the vector space generation unit derives the distance between contents based on the weight vector.

6. The aforementioned content processing unit, A hierarchical structure generation unit generates a hierarchical structure based on the distance between the centroids of each of the k clusters. The information processing apparatus according to claim 3, further comprising:

7. The vector space generation unit creates M-dimensional (where M is an integer M > 1) vector data representing the attributes of the content creator, and generates an M-dimensional vector space. The information processing apparatus according to claim 3, wherein the embedding processing unit embeds the content into an N+M dimensional vector space.

8. The vector space generation unit creates R-dimensional (where R is an integer R > 1) vector data based on management rules, and generates an R-dimensional vector space. The information processing apparatus according to claim 7, wherein the embedding processing unit embeds the content into an N+M+R dimension vector space.

9. The vector space generation unit creates T-dimensional vector data (where T is an integer T > 1) representing the time axis and attributes, and generates a T-dimensional vector space. The information processing apparatus according to claim 8, wherein the embedding processing unit embeds the content into an N+M+R+T dimension vector space.

10. The vector space generation unit creates U-dimensional vector data (where U is an integer U > 1) representing user attributes, and generates a U-dimensional vector space. The information processing apparatus according to claim 9, wherein the embedding processing unit embeds the content into a U+N+M+R+T dimension vector space.

11. The aforementioned content processing unit, A pseudo-metadata search unit that generates pseudo-metadata based on search prompts and user attributes, and searches for content based on the created pseudo-metadata. Furthermore, The information processing apparatus according to claim 3, wherein the display control unit causes the display unit to display the content retrieved by the pseudo-metadata search unit.

12. The vector space generation unit derives the similarity between content based on the distance between content, The information processing apparatus according to claim 4, wherein the display control unit causes the display unit to display the similarity derived by the vector space generation unit.

13. The information processing apparatus according to claim 11, wherein the vector space generation unit derives the distance between multiple contents based on the search results of the pseudo-metadata search unit.

14. The information processing apparatus according to claim 6, wherein the hierarchical structure generation unit analyzes metadata for the content contained in each of the k clusters and creates classification information for recommending folders based on the metadata analysis results.

15. The information processing apparatus according to claim 3, wherein the metadata generation unit, if there is missing information in the metadata generated based on the content, creates information for querying for the missing information, retrieves the information input to the created query information, and completes the metadata.

16. The information processing apparatus according to claim 6, wherein the hierarchical structure generation unit generates a hierarchical structure based on the maximum number of levels, the average number of contents in the lowest level folder, and the number of folders in any level below the lowest level.

17. The aforementioned pseudo-metadata search unit derives the characteristics of the content based on the search results for the content, The information processing apparatus according to claim 11, wherein the display control unit causes the display unit to display information indicating the characteristics of the content derived by the pseudo-metadata search unit.

18. The aforementioned pseudo-metadata search unit derives questions to narrow down the content based on the characteristics of the derived content, The information processing apparatus according to claim 17, wherein the display control unit causes the display unit to display information indicating a question for narrowing down the content derived by the pseudo-metadata search unit.

19. The information processing apparatus according to claim 11, wherein the pseudo-metadata search unit creates information for querying for missing information if there is missing information in the user attributes.

20. A method of information processing performed by a computer, We accept content, The received content is given information that identifies the physical address, The content to which the aforementioned physical address has been assigned is stored in the content pool. The content stored in the aforementioned content pool is virtually classified, The results of virtually classifying the content are displayed on the display unit. Information processing methods.

21. On the computer, We accept content, The received content is given information that identifies the physical address, The content to which the aforementioned physical address has been assigned is stored in the content pool. The content stored in the aforementioned content pool is virtually classified, The results of virtually classifying the content are displayed on the display unit. program.

Images