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

Abstract

To provide new and useful information latent in a keyword group of an analysis object.SOLUTION: An information processing device comprises a clustering unit, an imparting unit, and a provision unit. The clustering unit clusters relevance of keywords, based on relevance data indicating the relevance between the keywords. The imparting unit imparts a title of each cluster clustered by the clustering unit, on the basis of the keyword belonging to the cluster. A provision unit provides contents indicating the relevance between the keywords in which the title has been imparted to each cluster by the imparting unit.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] In recent years, with the remarkable spread of the Internet, for example, technologies related to analysis using various information on the Internet have been provided. For example, a technique for extracting information related to the needs for a target based on a first keyword corresponding to the target provided by a predetermined operator and a second keyword related to the nature of the target has been proposed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology cannot provide new useful information latent in the keyword group of the analysis target. For example, the conventional technology cannot discover a new keyword group latent in the keyword group of the analysis target. Also, the conventional technology cannot promote understanding of the structure of the relevance of the keyword group of the analysis target.

[0005] The present application has been made in view of the above, and an object thereof is to provide new useful information latent in the keyword group of the analysis target.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a clustering unit, an assigning unit, and a providing unit. The clustering unit clusters the relevance of keywords based on relevance data indicating the relevance between keywords. The assigning unit assigns a title to each cluster clustered by the clustering unit based on the keywords belonging to the cluster. The providing unit provides content indicating the relevance between keywords to which titles are assigned to each cluster by the assigning unit.

Effect of the Invention

[0007] According to one aspect of the embodiment, there is an effect that new useful information latent in the keyword group to be analyzed can be provided.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing an information processing apparatus, an information processing method, and an 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 apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. Also, each embodiment can be appropriately combined within a range that does not conflict with the processing content. In addition, in the following embodiments, the same parts are denoted by the same reference numerals, and duplicate explanations are omitted.

[0010] 〔1. An Example of Information Processing〕 First, with reference to FIG. 1, an example of information processing according to the embodiment will be described. FIG. 1 is a diagram for explaining the information processing according to the embodiment.

[0011] The information processing apparatus 1 shown in FIG. 1 is an information processing apparatus that provides an online analysis service. The information processing apparatus 1 according to the present embodiment provides, as an analysis service, content indicating the relevance between various keywords used in a search. The information processing apparatus 1 is realized, for example, by one or more servers or a cloud system. User O is a user of the terminal device 2 and a user of the online service provided by the information processing apparatus 1.

[0012] As shown in FIG. 1, the information processing apparatus 1 receives an analysis request. For example, the information processing apparatus 1 receives a specification of a genre to be analyzed for the keywords used in the search (step S1). The genre is a segmentation of the state in which the keyword is used in the search or the state of the user who input the keyword. Each genre is defined with a genre name indicating what state the genre is in. For example, the information processing apparatus 1 receives an analysis request when the genre name to be analyzed is specified.

[0013] When the information processing device 1 receives an analysis request, it generates relevance data indicating the relevance between keywords (step S2). For example, the information processing device 4 stores various keywords searched on the search site by the user U operating the terminal device 2 for each genre. The information processing device 1 acquires the keywords used for the search in the specified genre from the information processing device 4. The information processing device 1 generates relevance data indicating the relevance between keywords. The relevance data stores a score indicating the relevance between keywords for each pair of relevant keywords. Hereinafter, the score indicating the relevance is also referred to as a relevance score. The relevance score between keywords is specified based on either the similarity of the input timing or the similarity of the input user U. For example, the relevance score between keywords is specified to be a higher value in the range of 0 to 1 as the similarity of the input timing or the similarity of the input user U is higher. Note that the relevance between keywords may be specified using dictionary data that stores relevant keywords for each keyword such as a thesaurus. Also, the relevance data may be generated by the information processing device 4 and transmitted to the information processing device 1.

[0014] Based on the generated relevance data, the information processing device 1 clusters the relevance of the keywords (step S3). For example, the information processing device 1 uses a generative AI (Artificial Intelligence) to cluster the relevance of the keywords.

[0015] The generative AI is, for example, a text generation AI, a multimodal AI, etc. Such a generative AI is, for example, arranged in an external information processing device and provides an API (Application Programming Interface). The information processing device 1 clusters the relevance of the keywords included in the relevance data via the API provided by the external information processing device, but is not limited to such an example. For example, the generative AI may be arranged within the information processing device 1.

[0016] Text generation AI is a language model trained, for example, to estimate and output the next token from an input token sequence, and is, for example, a transformer-based model, an RNN (Recurrent Neural Network)-based model, etc.

[0017] Transformer-based models are, for example, GPT (Generative Pre-trained Transformer), BARD (Bidirectional Auto Regressive Dialogues), etc., but are not limited to such examples. RNN-based models are, for example, RWKV (Receptance Weighted Key Value), etc., but are not limited to such examples.

[0018] Multimodal AI is a model that, for example, generates an image from text or generates text from an image, and is, for example, GPT-4V, CM3Leon (Chameleon Multimodal Model), etc., but is not limited to such examples.

[0019] Hereinafter, the case where the generative AI is GPT will be described as an example. For example, the information processing device 1 inputs information including the generated relevance data and the instruction information for instructing clustering to the generative AI as input information, and causes the generative AI to output information indicating the clustering result of clustering the relevance of the keywords included in the relevance data. The instruction information includes an instruction on how to cluster as an "element". Further, the instruction information includes an instruction on how to output the clustering result as an "output content".

[0020] For example, the information processing device 1 performs clustering on the <relevance data> part of the (data) of the first instruction information shown below by the generative AI using the text describing the data content of the relevance data as input information.

[0021] · First instruction information There is data showing the relevance of characteristic search keywords on the Internet for a specific user group as follows. (Element) · Create a network using the relevance score between search keywords, and cluster elements based on the connectivity of the network. · When starting clustering, start from the highest-scoring relevance. · For indirectly connected ones, consider up to two levels. Even if the direct keywords are not connected, if they are connected via other keywords, estimate and assign a score. · Stop clustering when the score connection becomes less than `the highest score × 0.3`. · Output the group of search keywords included in the cluster, separated by line breaks. (Output content) · Output the search keywords included in the cluster. · Output in bullet points, separating the search keywords with "\t". · Do not output elements other than bullet points. (Data) <Relevance data>

[0022] As a result, each keyword in the relevance data is clustered based on the relevance between the keywords.

[0023] The information processing apparatus 1 assigns a title to each clustered cluster based on the keywords belonging to the cluster (step S4). For example, the information processing apparatus 1 assigns a title to each cluster using a generative AI. For example, the information processing apparatus 1 inputs, as input information to the generative AI, information including the information indicating the clustering result and instruction information instructing the assignment of the title of each cluster, and causes the generative AI to output information indicating the assignment result of the title of each cluster.

[0024] For example, the information processing apparatus 1 uses the text describing the data content output in step S3 as input information and has the generated AI assign a title to the <output of step S3> part of the following second instruction information (data).

[0025] ·Second instruction information There is data below showing a group of characteristic search keywords on the Internet for a specific user group. Please give each of them a title of about 10 characters (Output content) ·Title (about 10 characters) ·Output in bullet points ·Use the symbol "·" for bullet points. ·The title should not contain "·". ·Do not output elements other than the title. ·Do not output elements other than bullet points. (Data) <Output of step S3>

[0026] As a result, each clustered cluster is assigned a title.

[0027] The information processing apparatus 1 provides content indicating the relevance between the keywords to which titles are assigned for each cluster. For example, in step S3, the information processing apparatus 1 shows the relationship between the groups of keywords grouped by clustering and provides a terminal device 2 with a network graph showing the titles for each cluster that is each group. The example shown in FIG. 1 shows a network graph 50 of the result of clustering and analyzing the keywords searched by the user U who owns a dog, with "owns a dog" specified as the genre.

[0028] In the network graph 50 shown in FIG. 1, clusters, which are groups of keywords grouped by clustering, are shown as nodes 51, and titles assigned to the clusters corresponding to each node 51 are shown. Further, in the network graph 50 shown in FIG. 1, nodes 51 of related clusters are connected by lines 52, and the relevance of the nodes 51 is shown as a network by the lines 52. The network graph 50 is configured to be able to display the network structure in detail by selecting a node 51. When a node 51 is selected in the network graph 50, if there are nodes below the selected node 51, the nodes below are displayed, and if there are no nodes below the selected node 51, the keywords grouped in the selected node 51 are displayed.

[0029] Thereby, the information processing apparatus 1 can provide the user O with new useful information latent in the keyword group to be analyzed. The user O can grasp new useful information latent in the keyword group to be analyzed. For example, the user O can discover a new keyword group latent in the keyword group by referring to the title assigned to the node 51 of the network graph 50. Further, the user O can understand the relevance structure of the keyword group to be analyzed by referring to the network graph 50.

[0030] Hereinafter, the configuration of an information processing system including the information processing apparatus 1, a plurality of terminal devices 2, a terminal device 3, and an information processing apparatus 4 that perform such processing will be described in detail.

[0031] [2. Configuration of Information Processing System 100] FIG. 2 is a diagram showing an example of the configuration of an information processing system 100 according to an embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing apparatus 1, a plurality of terminal devices 2, a terminal device 3, and an information processing apparatus 4.

[0032] The plurality of terminal devices 2 are used by different users U. The terminal device 3 is, for example, the terminal device of user O. The terminal devices 2 and 3 are, for example, notebook PCs (Personal Computers), desktop PCs, smartphones, tablet PCs, wearable devices. The wearable device is, for example, smart glasses, or a smartwatch, etc., but is not limited to such examples.

[0033] The information processing device 4 provides a search site to the user U and stores various keywords searched on the search site by genre, but is not limited to such examples. For example, the search site may be provided by another information processing device, and the information processing device 4 may obtain various keywords searched on the search site from another information processing device and store them by genre.

[0034] Each of the information processing device 1, the terminal devices 2, the terminal device 3, and the information processing device 4 is connected to be communicable with each other by wire or wirelessly via the network N. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0035] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation: the 5th generation mobile communication system).

[0036] The terminal devices 2 and 3 are connected to the network N via a mobile communication network, Bluetooth (registered trademark), short-range wireless communication such as a wireless LAN (Local Area Network), and can communicate with the information processing device 1, the information processing device 4, and the like.

[0037] [3. Configuration of Information Processing Device 1] FIG. 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.

[0038] [[3.1. Communication Unit 10]] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). And the communication unit 10 is connected to the network N either wired or wirelessly and performs information transmission and reception with various other devices. For example, the communication unit 10 performs information transmission and reception with each of the terminal device 2, the terminal device 3, and the information processing device 4 via the network N.

[0039] [[3.2. Storage Unit 11]] The storage unit 11 is realized by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical disks. The storage unit 11 stores the relevance data 20. Details of the relevance data 20 will be described later.

[0040] [[3.3. Processing Unit 12]] The processing unit 12 is a controller and is realized, for example, by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a working area.

[0041] Also, the processing unit 12 is a controller and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0042] As shown in FIG. 3, the processing unit 12 includes a reception unit 30, a generation unit 31, a clustering unit 32, an assignment unit 33, and a provision unit 34, and realizes or executes the functions and operations 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 any other configuration as long as it can perform the information processing described later.

[0043] The reception unit 30 receives various information and requests from the terminal device 2 or the terminal device 3 via the network N and the communication unit 10. For example, the reception unit 30 receives an analysis request.

[0044] For example, in response to an access from the terminal device 2 of the user O who uses the analysis service, the reception unit 30 provides the operation screen of the analysis service to the terminal device 2 and receives various inputs from the operation screen. For example, the reception unit 30 receives a designation of a genre to be analyzed for the keyword used in the search from the operation screen.

[0045] The generation unit 31 generates relevance data indicating the relevance between keywords related to the genre received by the reception unit 30. For example, the generation unit 31 acquires the keywords used for the search of the genre designated on the operation screen from the information processing device 4. The generation unit 31 generates relevance data indicating the relevance between the keywords. For example, the generation unit 31 specifies the relevance score between the keywords based on either the similarity of the input timing or the similarity of the input user U. For example, the generation unit 31 specifies the relevance score between the keywords as a higher value within the range of 0 to 1 as the similarity of the input timing or the similarity of the input user U is higher. The generation unit 31 generates relevance data in which the relevance scores between the keywords are arranged for each keyword for which the relevance is obtained. The generation unit 31 stores the generated relevance data in the storage unit as relevance data 20.

[0046] Here, an example of the relevance data 20 will be described. FIG. 4 is a diagram showing an example of the relevance data 20 according to the embodiment. The relevance data 20 has two keywords for which relevance is determined and the values of the relevance scores between the two keywords arranged side by side. For example, in FIG. 4, it is stored that the relevance score between keyword 1 and keyword 2 is 0.8. Also, it is stored that the relevance score between keyword 1 and keyword 3 is 0.6.

[0047] The clustering unit 32 clusters the relevance of the keywords based on the relevance data 20. For example, the clustering unit 32 clusters the relevance of the keywords using a generative AI. Taking the case where the generative AI is GPT as an example. For example, the clustering unit 32 inputs information including the relevance data 20 and instruction information for instructing clustering as input information to the generative AI, and causes the generative AI to output information indicating the clustering result of clustering the relevance of the keywords included in the relevance data 20. For example, the clustering unit 32 performs clustering on the generative AI using, as input information, the text describing the data content of the relevance data 20 in the <relevance data> part of the above-described first instruction information (data).

[0048] The assigning unit 33 assigns a title to each clustered cluster based on the keywords belonging to the cluster. For example, the assigning unit 33 assigns a title to each cluster using a generative AI. For example, the assigning unit 33 inputs information including the information indicating the clustering result and instruction information for instructing the assignment of the title of each cluster as input information to the generative AI, and causes the generative AI to output information indicating the assignment result of assigning the title of each cluster. For example, the assigning unit 33 performs title assignment on the generative AI using, as input information, the text describing the data content clustered by the clustering unit 32 in the <output of step S3> part of the above-described second instruction information (data).

[0049] The providing unit 34 provides content indicating the relevance between keywords with titles assigned to each cluster. For example, the providing unit 34 shows the relevance between groups of keywords grouped by clustering, and provides the terminal device 2 of the analysis requester with a screen of a network graph showing titles for each cluster, which is each group of keywords.

[0050] FIG. 5 is a diagram showing an example of a network graph 50 according to an embodiment. The example shown in FIG. 1 shows a network graph 50 which is the result of clustering and analyzing the keywords searched by the user U who is specified as "raising a dog" as a genre.

[0051] [4. Processing procedure] Next, the information processing procedure by the processing unit 12 of the information processing apparatus 1 according to the embodiment will be described. FIG. 6 is a flowchart showing an example of information processing by the processing unit 12 of the information processing apparatus 1 according to the embodiment.

[0052] As shown in FIG. 6, the processing unit 12 of the information processing apparatus 1 determines whether an analysis request has been received (step S10). For example, when the processing unit 12 receives a designation of a genre to be analyzed on the operation screen of the analysis service, it determines that an analysis request has been received.

[0053] When the processing unit 12 determines that an analysis request has been received (step S10: Yes), it generates relevance data indicating the relevance between keywords related to the received genre (step S11).

[0054] The processing unit 12 clusters the relevance of the keywords based on the relevance data 20 (step S12). For example, the processing unit 12 clusters the relevance of the keywords using a generated AI.

[0055] The processing unit 12 assigns a title to each clustered cluster based on the keywords belonging to the cluster (step S13). For example, the processing unit 12 assigns a title to each cluster using a generation AI.

[0056] The processing unit 12 provides content indicating the relevance between the keywords with titles assigned to each cluster (step S14). For example, the processing unit 12 shows the relationship between the groups of keywords grouped by clustering, and provides the terminal device 2 of the analysis requester with a screen of a network graph showing the titles of each cluster, which are the respective groups.

[0057] When the processing in step S14 is completed, or when it is determined that no analysis request has been received (step S10: No), the processing unit 12 determines whether the operation end timing has arrived (step S15). The processing unit 12 determines that the operation end timing has arrived, for example, when the power of the information processing apparatus 1 is turned off.

[0058] When it is determined that the operation end timing has not arrived (step S15: No), the processing unit 12 transfers the processing to step S10, and when it is determined that the operation end timing has arrived (step S15: Yes), the processing shown in FIG. 6 is terminated.

[0059] 〔5. Modification Example〕 In the above-described embodiment, the case of clustering keywords based on the relevance between keywords has been described as an example. However, it is not limited to this. For example, in the above embodiment, the user may be able to specify the axis of categorization. Also, in the above embodiment, the user may be able to specify the number of hierarchical levels to consider the indirect connection between keywords. For example, the reception unit 30 receives the specification of the genre as the axis of categorization and the number of hierarchical levels to consider the indirect connection between keywords from the operation screen. The clustering unit 32 clusters the keywords in the relevance data 20 considering the indirect connection between the keywords at the specified number of hierarchical levels with the specified axis of categorization. For example, instead of the first instruction information described above, the clustering unit 32 inputs the text describing the data content of the relevance data 20 into the <relevance data> part of the following third instruction information (data) as input information and performs clustering by the generated AI. In <genre input by user> of (element), the genre specified by the user as the axis of categorization is set. Also, in (element) <n>Set the numerical value of the number of hierarchical levels that consider the indirect connection between keywords.

[0060] · Third instruction information There is data below showing the relevance of characteristic search keywords on the Internet for a specific user group. (Element) · Create a network using the relevance score between search keywords and cluster elements based on the connection of the network. · Consider the general <genre input by the user> and reflect it in the score. · Consider the proximity in natural language and reflect it in the score · When starting clustering, start from the highest-scoring relevance. · Indirect connection is <n>Consider up to the hierarchy Even if the direct keywords are not connected, if they are connected via other keywords, estimate and assign a score · Stop clustering when the connection of scores becomes less than `highest score × 0.3` · Output the search keyword groups included in the cluster, separated by line breaks (Output content) · Output the search keywords included in the cluster · Output in bullet points, separating the search keywords with "\t" · Do not output elements other than bullet points (Data) <Relevance data>

[0061] As a result, the clustering unit 32 can cluster the keywords in the relevance data 20 with respect to the genre specified by the user as the axis. Also, the clustering unit 32 can cluster the keywords in the relevance data 20 with respect to the genre specified by the user as the axis.

[0062] In addition, in the above-described embodiment, for each keyword, a feature score indicating the characteristics and tendencies of the keyword may be set, and the keywords may be clustered taking into account the feature scores as well. The generation unit 31 generates feature data storing a feature score indicating the characteristics of a keyword for each keyword. The feature score may be any score as long as it indicates features such as the characteristics and tendencies of the keyword. For example, the generation unit 31 generates feature data in which the value is set as the feature score as 0 (male) to 1 (female) based on the ratio of male and female of the gender of the user who input the keyword for each keyword. Note that the feature data may be generated by the information processing apparatus 4 and transmitted to the information processing apparatus 1. The clustering unit 32 clusters the keywords in the relevance data 20 taking into account the features of the keywords as well. For example, instead of the first instruction information described above, the clustering unit 32 describes the data content of the relevance data 20 in the <relevance data> portion of the following fourth instruction information (data), and describes the data content of the feature data in the <feature data> portion of (characteristic data of search keyword), and performs clustering by the generation AI using the text as input information.

[0063] · Fourth instruction information There is data showing the relevance of characteristic search keywords on the Internet for a specific user group below. (Element) · Create a network using the relevance score between search keywords, and cluster the elements based on the connection of the network. · Reflect the tendency of the characteristic score for each search keyword in the score when performing clustering. · When starting clustering, start from the relevance with the highest score. · Indirect connections are considered up to two levels. Even if the direct keywords are not connected, if they are connected via other keywords, estimate and assign a score. · Stop clustering when the connection of the scores becomes less than `the highest score × 0.3`. · Output the group of search keywords included in the cluster in line breaks. (Output content) ·Output the search keywords included in the cluster ·Output in bullet points and separate the search keywords with "\t" ·Do not output elements other than bullet points (Data) <Relevance data> (Characteristic data of search keywords) <Feature data>

[0064] Thus, the clustering unit 32 can cluster the keywords in the relevance data 20 in consideration of the feature scores of the keywords.

[0065] Also, in the above embodiment, the clustering unit 32 may cluster the keywords in the relevance data 20 in multiple layers. For example, instead of the first instruction information described above, the clustering unit 32 inputs, as input information to the generation AI, data in which the data content of the relevance data 20 is described in the <Relevance data> part of the (Data) of the fifth instruction information shown below, and performs clustering. In the (Element) of the fifth instruction information <n>Set the numerical value of the maximum number of keywords to group into clusters.

[0066] · Fifth instruction information The following is data showing the relevance of characteristic search keywords on the Internet for a specific user group. (Element) · Create a network using the relevance score between search keywords, and cluster elements based on the connection of the network. · When starting clustering, start from the highest-scoring relevance. · Consider up to two levels for indirect connections. Even if the direct keywords are not connected, if they are connected through other keywords, estimate and assign a score. · The maximum number of clusters <n>up to <n>Repeat the aggregation based on the connection of the process until it becomes less than or equal to the specified number. - Output the search keyword groups included in the cluster, separated by line breaks. (Output content) - Output the search keywords included in the cluster. - Output in bullet points, separating the search keywords with "\t". - Do not output elements other than bullet points. (Data) <Relevance data>

[0067] As a result, the clustering unit 32 can cluster the keywords of the relevance data 20 in multiple layers based on the relevance between the keywords.

[0068] FIG. 7 is a diagram showing an example of a multi-layer clustered network graph 50 according to the embodiment. When a node 51 is selected in the network graph 50, if there are lower-level nodes for the selected node 51, the lower-level nodes are displayed, and if there are no lower-level nodes for the selected node 51, the keywords grouped for the selected node 51 are displayed. The network graph 50 enables detailed display of the network structure by selecting the node 51. When a node 51 is selected in the network graph 50, if there are lower-level nodes for the selected node 51, the lower-level nodes are displayed, and if there are no lower-level nodes for the selected node 51, the keywords grouped for the selected node 51 are displayed. The example shown in FIG. 7 shows the changes when the node 51 of "travel" is selected. When the node 51 of "travel" is selected with the lower-level node 51 not displayed, the lower-level node 51 of the node 51 of "travel" is displayed. Also, when the node 51 of "travel" is selected with the lower-level node 51 not shown, the lower-level node 51 becomes not displayed.

[0069] In addition, in the above-described embodiment, the clustering unit 32 may cluster the relevance of keywords without using a generation AI. Also, the assigning unit 33 may assign a title to each cluster without using a generation AI. For example, the clustering unit 32 executes processing of the content indicated in text for the (elements) of the first and third to fifth instruction information with respect to the relevance data 20 to cluster the keywords. For example, when there is a relevance through other keywords between keywords that have no direct relevance in the relevance data 20, the clustering unit 32 estimates a score indicating an indirect relevance and clusters them. For example, in FIG. 4, when there is no relevance score between keyword 2 and keyword 3, the clustering unit 32 estimates the relevance score between keyword 2 and keyword 3 from the relevance score between keyword 1 and keyword 2 and the relevance score between keyword 1 and keyword 3. For example, the clustering unit 32 estimates a value obtained by multiplying the relevance score between keyword 1 and keyword 2 and the relevance score between keyword 1 and keyword 3 as the relevance score between keyword 2 and keyword 3. Then, the clustering unit 32 performs keyword clustering from the relevance with the highest relevance score for each, and stops clustering when the highest relevance score becomes less than 0.3 times. The assigning unit 33 identifies, for each of the clustered clusters, synonyms and equivalent words of the keywords grouped in the cluster using, for example, dictionary data storing keywords relevant to each keyword such as a thesaurus, and assigns the most overlapping synonyms and equivalent words as the title of the cluster.

[0070] 〔6. Hardware Configuration〕 The information processing apparatus 1 according to the above-described embodiment is realized by a computer 80 having a configuration as shown in FIG. 8, for example. FIG. 8 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing apparatus 1 according to the embodiment. The computer 80 includes a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an 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.

[0071] The CPU 81 operates based on programs stored in the ROM 83 or the HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, and programs dependent on the hardware of the computer 80.

[0072] The HDD 84 stores programs executed by the CPU 81 and data used by such programs. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and sends data generated by the CPU 81 to other devices via the network N.

[0073] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. Further, the CPU 81 outputs data generated via the input / output interface 86 to the output devices.

[0074] The media interface 87 reads a program or data stored in the recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads such a 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 Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory, etc.

[0075] For example, when the computer 80 functions as the information processing apparatus 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing the program loaded onto the RAM 82. Further, the data in the storage unit 11 is stored in the HDD 84. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88. As another example, these programs may be acquired from other devices via the network N.

[0076] 〔7. Others〕 Among the respective processes described in the above embodiment, all or part of the processes described as being automatically performed can also be performed manually, or all or part of the processes described as being performed manually can be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0077] Also, each component of each illustrated device is a functional concept, and it is not necessarily physically configured as shown in the figure. That is, the specific form of the dispersion and integration of each device is not limited to that shown in the figure, and all or part of it can be functionally or physically dispersed and integrated in any unit according to various loads, usage situations, etc.

[0078] For example, the above-described information processing apparatus 1 may be implemented by a terminal device and a server computer, or may be implemented by a plurality of server computers. Further, depending on the function, the configuration can be flexibly changed, such as by calling an external platform or the like using an API or network computing.

[0079] In addition, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not conflict.

[0080] [8. Effects] As described above, the information processing apparatus 1 according to the embodiment includes a clustering unit 32, an assigning unit 33, and a providing unit 34. The clustering unit 32 clusters the relevance of keywords based on the relevance data 20 indicating the relevance between keywords. The assigning unit 33 assigns a title to each cluster clustered by the clustering unit 32 based on the keywords belonging to the cluster. The providing unit 34 provides content indicating the relevance between the keywords to which titles are assigned to each cluster by the assigning unit 33. Thereby, the information processing apparatus 1 can provide new useful information latent in the keyword group to be analyzed. For example, the information processing apparatus 1 can assist in discovering a new keyword group latent in the keyword group to be analyzed. Further, the information processing apparatus 1 can promote understanding of the relevance structure of the keyword group to be analyzed.

[0081] In addition, the information processing apparatus 1 according to the embodiment further includes a reception unit 30 and a generation unit 31. The reception unit 30 receives a genre designation. The generation unit 31 generates relevance data 20 indicating the relevance between keywords related to the genre received by the reception unit 30. The clustering unit 32 clusters the relevance of keywords based on the relevance data 20 generated by the generation unit 31. Thereby, the information processing apparatus 1 can provide new useful information latent in the keyword group of the designated genre.

[0082] In addition, the clustering unit 32 clusters the relevance of keywords using a generative AI. The assigning unit 33 assigns a title to each cluster using a generative AI. As a result, since the information processing apparatus 1 can cluster and assign a title to each cluster using a generative AI, it can provide new useful information latent in the keyword group to be analyzed.

[0083] In addition, the relevance data 20 is data that stores a score indicating the relevance between keywords for each pair of relevant keywords. As a result, the information processing apparatus 1 can cluster the relevance between keywords from the relevance data 20 and provide new useful information latent in the keyword group to be analyzed.

[0084] In addition, when there is an indirect relevance between keywords that have no direct relevance in the relevance data 20 via other keywords, the clustering unit 32 estimates a score indicating the indirect relevance and performs clustering. As a result, the information processing apparatus 1 can take into account the indirect relevance between keywords and provide new useful information latent in the keyword group to be analyzed.

[0085] In addition, the generation unit 31 generates relevance data 20 indicating the relevance between keywords based on any one of the similarity searched simultaneously, the similarity of the input timing, and the similarity of the input user. As a result, the information processing apparatus 1 can provide new useful information latent in the keyword group to be analyzed based on the relevance between keywords of any one of the similarity searched simultaneously, the similarity of the input timing, and the similarity of the input user.

[0086] In addition, the providing unit 34 provides, as content, a network graph showing clusters as nodes and showing the titles assigned to the clusters corresponding to the respective nodes. As a result, the information processing apparatus 1 can provide new useful information latent in the keyword group to be analyzed by the network graph.

[0087] As described above, the embodiments of the present application have been described in detail with reference to the drawings. However, this is an example, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0088] Also, the "section (section, module, unit)" described above can be read as "means", "circuit", etc. For example, the acquisition section can be read as an acquisition means or an acquisition circuit.

Description of Reference Numerals

[0089] 1,4 Information processing apparatus 2,3 Terminal device 10 Communication section 11 Storage section 12 Processing section 20 Relevance data 30 Reception section 31 Generation section 32 Clustering section 33 Assignment section 34 Provision section 100 Information processing system N Network< / n> < / n> < / n> < / n> < / n>

Claims

1. A clustering unit that clusters the relevance of the keywords based on relevance data indicating the relevance between the keywords; An assigning unit that assigns a title to each cluster clustered by the clustering unit based on the keywords belonging to the cluster; A providing unit that provides content indicating the relevance between the keywords to which titles have been assigned to each cluster by the assigning unit; An information processing apparatus, characterized by comprising the above.

2. A receiving unit that receives a genre specification; A generating unit that generates relevance data indicating the relevance between keywords related to the genre received by the receiving unit; further comprising, The clustering unit clusters the relevance of the keywords based on the relevance data generated by the generating unit The information processing apparatus according to claim 1.

3. The clustering unit clusters the relevance of the keywords using a generative AI (Artificial Intelligence); The assigning unit assigns a title to each cluster using a generative AI The information processing apparatus according to claim 1.

4. The relevance data is data that stores a score indicating the relevance between keywords for each pair of relevant keywords The information processing apparatus according to claim 1.

5. When there is an indirect relevance between keywords that have no direct relevance in the relevance data via other keywords, the clustering unit estimates a score indicating the indirect relevance and clusters them The information processing apparatus according to claim 4.

6. The generating unit generates relevance data indicating the relevance between keywords based on any one of the similarity of simultaneous searches, the similarity of input timing, and the similarity of the input users The information processing apparatus according to claim 2.

7. The providing unit provides, as the content, a network graph showing clusters as nodes and titles assigned to the clusters corresponding to each node The information processing apparatus according to claim 1.

8. An information processing method executed by a computer, comprising: A clustering step of clustering the relevance of the keywords based on relevance data indicating the relevance between the keywords; An assigning step of assigning a title to each clustered cluster based on the keywords belonging to the cluster; A providing step of providing content indicating the relevance between keywords to which titles are assigned to each cluster; An information processing method characterized by including the above.

9. A clustering procedure for clustering the relevance of the keywords based on relevance data indicating the relevance between the keywords; An assigning procedure for assigning titles to each of the clustered clusters based on the keywords belonging to the clusters; A providing procedure for providing content indicating the relevance between the keywords to which titles are assigned to each cluster; An information processing program characterized by causing a computer to execute the above.

Images