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

Abstract

To provide an information processing device, an information processing method, and an information processing program that can provide effective support for content provision. [Solution] The information processing device according to the present invention comprises a reception unit, a generation unit, an estimation unit, and a provision unit. The reception unit receives the selection of a comparison target. The generation unit generates a classification result that hierarchically classifies the words constituting the search query based on the history of search queries previously entered for the comparison target. The estimation unit estimates the category name corresponding to the word. The provision unit provides content that shows the relationship between the comparison target and the category based on the category name and the classification result.

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] Conventionally, technologies for providing content, which is information on specific targets such as products and services, have become widespread. For example, Patent Document 1 discloses a technology for assisting a content provider in providing optimal content to a user based on information obtained from the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the above conventional technology, there is room for improvement in terms of providing more effective support for content provision.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of providing effective support for content provision.

Means for Solving the Problems

[0006] The information processing device according to the present invention comprises a receiving unit, a generation unit, an estimation unit, and a provision unit. The receiving unit receives the selection of a comparison target. The generation unit generates a classification result that hierarchically classifies the words constituting the search query based on the history of search queries previously entered for the comparison target. The estimation unit estimates the category name corresponding to the word. The provision unit provides content that shows the relationship between the comparison target and the category based on the category name and the classification result. [Effects of the Invention]

[0007] According to one embodiment of the system, it has the effect of providing effective support for content provision. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows the process performed by the information processing device according to the embodiment. [Figure 2] Figure 2 shows an example configuration of an information processing system equipped with an information processing device according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of user information stored in the storage unit of the information processing device according to the embodiment. [Figure 5] Figure 5 shows an example of query information stored in the memory unit of the information processing device according to the embodiment. [Figure 6] Figure 6 shows an example of model information stored in the storage unit of the information processing device according to the embodiment. [Figure 7] Figure 7 shows an example of log information acquired by the acquisition unit of the information processing device according to the embodiment. [Figure 8] Figure 8 shows an example of a system prompt input to the model of the generated AI in the information processing device according to the embodiment. [Figure 9]Figure 9 shows an example of a category name estimated by the estimation unit of the information processing device according to the embodiment. [Figure 10] Figure 10 shows an example of content created by the creation unit of the information processing apparatus according to the embodiment. [Figure 11] Figure 11 is a flowchart showing an example of information processing by the information processing device according to the embodiment. [Figure 12] Figure 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] [1. An example of information processing] First, the process performed by the information processing device according to the embodiment will be explained using Figure 1. Figure 1 is a diagram showing the process performed by the information processing device according to the embodiment.

[0011] The information processing device 1 shown in Figure 1 is an information processing device for creating content that shows the relationship between a comparison target and a category, and realizes a content provision service that provides said content.

[0012] As shown in Figure 1, the information processing device 1 accepts the selection of a comparison target, generates a classification result that hierarchically classifies the words constituting the search query based on the history of search queries previously entered for the comparison target, estimates the category name corresponding to the word, and provides content that shows the relationship between the comparison target and the category based on the category name and the classification result.

[0013] Specifically, first, user U who owns terminal device 2 uses the services provided by information processing device 4 via terminal device 2. The services provided by information processing device 4 are, for example, online sites, such as online Q&A (Question and Answer) services, online search services, online news provision services, internet bulletin board services, etc., which are online services provided by information processing device 4, but are not limited to such examples.

[0014] For example, when the service provided by information processing device 4 is an online search service, it is a search using a specific search query, but is not limited to such examples.

[0015] Here, user M who uses the content providing service makes a comparison request to information processing device 1 using terminal device 3 of user M (step S1). The comparison request is a comparison request for comparing at least two objects as comparison targets. For example, when the comparison targets are two objects of "Company A" and "Company B", the comparison request is a comparison request for comparing the two objects of "Company A" and "Company B" as comparison targets. Information processing device 1 accepts the selection of comparison targets "Company A" and "Company B" as a comparison request from terminal device 3.

[0016] Also, information processing device 4 provides log information, which is the behavior log of user U during service use, to information processing device 1 (step S2). For example, information processing device 4 provides the behavior of user U on the provided online site as log information. Specifically, information processing device 4 provides log information including browsing and search behaviors on the online site. Information processing device 1 obtains, from information processing device 4, the log information of the search queries previously input for comparison targets "Company A" and "Company B" according to the comparison request received in step S1.

[0017] Next, the information processing device 1 generates a classification result that hierarchically classifies the words constituting the search query based on the history (log information) of the acquired search query (step S3). For example, suppose that the comparison targets "Company A" and "Company B" are companies that provide real estate information, and the search query is a search related to real estate. For example, when the information processing device 1 hierarchically classifies the words constituting the string as a search query, it classifies the words hierarchically by separating them with spaces between words in the string.

[0018] Specifically, let's assume that the search query history entered for the comparison target "Company A" includes the strings "land 30 tsubo", "used detached house 3LDK", and "land Chiba". For example, when the information processing device 1 hierarchically classifies the words that make up the string "land 30 tsubo" as a search query, it classifies "land" as the first-level word and "30 tsubo" as the second-level word. Other strings are similarly classified hierarchically. The method for hierarchically classifying the words that make up the search query strings will be described later in Figures 7 to 10.

[0019] Next, the information processing device 1 uses artificial intelligence (AI) to estimate the category name corresponding to the word (step S4).

[0020] Generative AI can be, for example, a text generation AI or a multimodal generation AI. A text generation AI is, for example, a large-scale language model trained to estimate and output the next token from an input sequence of tokens, such as a transformer-based model or an RNN (Recurrent Neural Network)-based model, or a hybrid model of these. A text generation AI may also be a composite system combined with an identifier for preventing misuse.

[0021] Transformer-based models include, but are not limited to, GPT (Generative Pre-trained Transformer) (registered trademark), PaLM2 (Pathways Language Model Version 2), or LLaMA (Large Language Model Meta AI). RNN-based models include, but are not limited to, RWKV (Receptance Weighted Key Value).

[0022] The generating AI is located in an external information processing device, and the information processing device 1 uses the generating AI via an API (Application Programming Interface). However, the generating AI may also be located within the information processing device 1.

[0023] A multimodal generative AI is a generative AI that can generate text or images from other sources, such as text or images. Examples of multimodal generative AIs include, but are not limited to, GPT-4o, gemini, Claude3, and CM3Leon (Chameleon Multimodal Model).

[0024] For example, the information processing device 1 uses a generative AI to estimate the category names corresponding to the words "land" and "30 tsubo" as "land" and "typical size," respectively. The method for estimating category names using the generative AI will be described later in Figures 7 to 10.

[0025] Next, the information processing device 1 creates content that shows the relationship between the comparison targets "Company A" and "Company B" and the categories, based on the category names and classification results (Step S5). Then, the information processing device 1 provides the created content to the terminal device 3 of user M who made the comparison request (Step S6).

[0026] The content presents multiple categories categorized in relation to the comparison targets, "Company A" and "Company B." For example, the multiple categories presented in the content are presented in a way that allows for identification from the highest-level category to the lowest-level category. The method for creating and presenting this content will be described later in Figures 7 to 10.

[0027] Thus, according to the information processing device 1 of this embodiment, content based on search queries of interest to user U can be provided to the terminal device 3 of user M who made the comparison request. As a result, according to the information processing device 1 of this embodiment, effective support regarding content provision can be provided to user M who uses the content provision service.Specific examples of the effects will be described later in Figures 7 to 10.

[0028] The configuration of the information processing system, which includes an information processing device 1 that performs such processing, multiple terminal devices 2, terminal device 3, and an information processing device 4, will be described in detail below.

[0029] [2. Configuration of the Information Processing System] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. As shown in Figure 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of terminal devices 2, a terminal device 3, and an information processing device 4.

[0030] Multiple terminal devices 2 are used by different users U. Terminal device 3 is a terminal device of user M, such as an employee of a company. Terminal devices 2 and 3 are, for example, notebook PCs (personal computers), desktop PCs, smartphones, tablet PCs, and wearable devices. Wearable devices are, for example, smart glasses or smartwatches, but are not limited to these examples.

[0031] The information processing device 4 provides various online services to user U. For example, the information processing device 4 provides user U with online Q&A services, online search services, online news provision services, and online bulletin board services, but is not limited to these examples.

[0032] Each of the information processing devices 1, 2, 3, and 4 is connected to each other via a network N, either by wire or wireless, enabling communication between them. Note that the information processing system 100 shown in Figure 2 may include multiple information processing devices 1, etc.

[0033] Network N includes, for example, WANs (Wide Area Networks) such as the Internet, and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th Generation Mobile Communication System).

[0034] Terminal devices 2 and 3 can connect to network N via short-range wireless communication such as a mobile communication network, Bluetooth®, or Wi-Fi (Local Area Network), and communicate with information processing device 1, information processing device 4, and the like.

[0035] Next, with reference to Figure 3, an example configuration of the information processing device 1 will be described.

[0036] [3. Configuration of Information Processing Device 1] Figure 3 shows an example of the configuration of an information processing device 1 according to an embodiment. As shown in Figure 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0037] [3.1. Communications Section 10] The communication unit 10 is implemented, for example, by a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to the network N by wire or wireless connection and transmits and receives information with various other devices. For example, the communication unit 10 transmits and receives information with terminal device 2, terminal device 3, and information processing device 4 via the network N.

[0038] [3.2. Storage section 11] The memory unit 11 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs.

[0039] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in the memory device inside the information processing device 1, using RAM or the like as a working area.

[0040] Furthermore, the processing unit 12 is a controller, and may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or GPGPU (General Purpose Graphic Processing Unit).

[0041] As shown in Figure 3, the processing unit 12 includes a receiving unit 31, an acquisition unit 32, a generation unit 33, an estimation unit 34, a creation unit 35, and a provision unit 36, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in Figure 3, and other configurations are also acceptable as long as they perform the information processing described later.

[0042] Furthermore, as shown in Figure 3, the storage unit 11 stores user information 41, query information 42, and model information 43.

[0043] Figure 4 shows an example of user information 41 stored in the storage unit 11 of the information processing device 1 according to this embodiment. User information 41 is information about user U. As shown in Figure 4, user information 41 includes items such as "user ID," "attribute information," and "behavioral history."

[0044] "User ID" is identification information that identifies the user. "Attribute Information" is information about the user's attributes. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral History" is information about the user's behavioral history, such as search behavior.

[0045] Figure 5 shows an example of query information 42 stored in the storage unit 11 of the information processing device 1 according to the embodiment. The query information 42 is information about search queries previously entered by user U. As shown in Figure 5, the query information 42 includes items such as "query ID", "query content", "input date and time", and "user ID".

[0046] The "Query ID" is the identifier that identifies each search query. The "Query Content" is the word (string) that constitutes the search query. The "Input Date and Time" is the date and time the search query was entered. The "User ID" is the information of the user U who entered the search query; for example, the User ID from User Information 41 above is entered here.

[0047] Figure 6 shows an example of model information 43 stored in the storage unit 11 of the information processing device 1 according to the embodiment. The model information 43 is information that includes a model of a generative AI used by the processing unit 12 to estimate category names and create content. As shown in Figure 6, the model information 43 includes items such as "model ID", "output content", and "model parameters".

[0048] The "Model ID" is identification information that identifies each model. The "Output Content" is information that indicates what the model outputs, and details will be described later in Figures 7 to 10. The "Model Parameters" are weight values ​​used in the neural network and deep learning algorithms that make up the model.

[0049] Next, we will describe the functions of the processing unit 12 of the information processing device 1 (reception unit 31, acquisition unit 32, generation unit 33, estimation unit 34, creation unit 35, and provision unit 36).

[0050] [3.3.1. Reception Department 31] The reception unit 31 receives the selection of comparison targets as a comparison request from the terminal device 3. For example, suppose user M, who uses the content provision service, uses user M's terminal device 3 to make a comparison request to the information processing device 1 to compare two targets, "Company A" and "Company B". For example, suppose that the comparison targets "Company A" and "Company B" are companies that provide real estate information.

[0051] [3.3.2. Acquisition part 32] The acquisition unit 32 acquires various types of information. For example, in response to a comparison request, the acquisition unit 32 acquires log information of previously entered search queries for the comparison targets "Company A" and "Company B" from the information processing device 4.

[0052] Figure 7 shows an example of log information acquired by the acquisition unit 32 of the information processing device 1 according to the embodiment.

[0053] As shown in Figure 7, for example, let's assume that the comparison targets "Company A" and "Company B" are companies that provide real estate information, and the search queries are related to real estate. For example, let's assume that the acquisition unit 32 acquires the strings "land 30 tsubo", "used detached house 3LDK", and "land Chiba" as the history (log information) of search queries entered in the past for comparison target "Company A". For example, let's assume that the acquisition unit 32 acquires the strings "used detached house 5LDK", "land 50 tsubo", "custom-built house", and "used detached house" as the history (log information) of search queries entered in the past for comparison target "Company B".

[0054] [3.3.3. Generation unit 33] The generation unit 33 generates classification results that hierarchically classify the words that make up the search queries based on the history (log information) of search queries previously entered for the comparison targets "Company A" and "Company B".

[0055] For example, when the generation unit 33 hierarchically classifies the words that make up a string as a search query, it classifies the words hierarchically by separating them with spaces between words in the string. The method for hierarchically classifying the words that make up the string of a search query will be explained in detail with reference to Figure 7.

[0056] In the example shown in Figure 7, the search query history entered in the past for the comparison target "Company A" includes the strings "land 30 tsubo", "used detached house 3LDK", and "land Chiba". For example, when the generation unit 33 hierarchically classifies the words that make up the string "land 30 tsubo" in the search query for the comparison target "Company A", it classifies "land" as the first-level word and "30 tsubo" as the second-level word. For example, when the generation unit 33 hierarchically classifies the words that make up the string "used detached house 3LDK" in the search query for the comparison target "Company A", it classifies "used detached house" as the first-level word and "3LDK" as the second-level word. For example, when the generation unit 33 hierarchically classifies the words that make up the string "land Chiba" in the search query for the comparison target "Company A", it classifies "land" as the first-level word and "Chiba" as the second-level word.

[0057] Furthermore, in the example shown in Figure 7, the history of search queries previously entered for the comparison target "Company B" includes the strings "used detached house 5LDK", "land 50 tsubo", "custom-built house", and "used detached house". For example, when the generation unit 33 hierarchically classifies the words that make up the string "used detached house 5LDK" in the search query for the comparison target "Company B", it classifies "used detached house" as the first-level word and "5LDK" as the second-level word. For example, when the generation unit 33 hierarchically classifies the words that make up the string "land 50 tsubo" in the search query for the comparison target "Company B", it classifies "land" as the first-level word and "50 tsubo" as the second-level word. For example, when the generation unit 33 hierarchically classifies the words that make up the string "custom-built house" in the search query for the comparison target "Company B", it classifies "custom-built house" as the first-level word and, since there are no words for the second level or beyond, it classifies "null". For example, when the generation unit 33 hierarchically classifies the words that make up the string "used detached house" in the search query for the comparison target "Company B", it classifies "used detached house" as the first layer word, and since there are no words in the second layer or beyond, it classifies "null".

[0058] [3.3.4. Estimation section 34] The estimation unit 34 uses a generation AI to estimate the category name corresponding to a word. Here, the reception unit 31 has previously received instruction information indicating the conditions instructed by the user, and the estimation unit 34 inputs the instruction information received by the reception unit 31 into the generation AI. For example, the instruction information received by the reception unit 31 is information about a search query related to real estate. In this case, the estimation unit 34 creates a system prompt containing the information about the search query related to real estate and inputs it into the model of the generation AI.

[0059] Figure 8 shows an example of a system prompt input to the model of the generated AI in the information processing device 1 according to the embodiment.

[0060] In the system prompt shown in Figure 8, for example, if the word "apple" is input to the generating AI, the instruction information instructs the generating AI to generate (output) "fruit" as the category name corresponding to the word "apple". For example, if the word "cucumber" is input to the generating AI, the instruction information instructs the generating AI to generate "vegetables" as the category name corresponding to the word "cucumber". For example, if the word "renovation" is input to the generating AI, the instruction information instructs the generating AI to generate "lifestyle" as the category name corresponding to the word "renovation". For example, if the word "orange" is input to the generating AI, the instruction information instructs the generating AI to generate "fruit" as the category name corresponding to the word "orange".

[0061] In the system prompt shown in Figure 8, for example, if the word "muscular macho" is input to the generation AI, the instruction information instructs the generation AI to generate "unknown" instead of using "null" or similar, because there is no category name corresponding to the word "muscular macho".

[0062] Furthermore, in the system prompt shown in Figure 8, for example, the generation AI is instructed by the instruction information to assign categories only to real estate-related items. For example, it is mandatory (a must) that the generation AI generate (output) the following real estate-related categories: "rental," "newly built condominium," "used condominium," "used detached house," "newly built detached house," "custom-built house," "land," and "place name."

[0063] As a result, if the comparison targets "Company A" and "Company B" are companies that provide real estate information, and the search query is related to real estate, the estimation unit 34 inputs the words that make up the search query as input information to the generating AI, and has the generating AI generate category names corresponding to the words, thereby estimating real estate-related category names.

[0064] Figure 9 shows an example of a category name estimated by the estimation unit 34 of the information processing device 1 according to this embodiment.

[0065] For example, as described above, the generation unit 33 hierarchically classifies the words that make up the search query string "land 30 tsubo" for the comparison target "Company A" into a first-layer word "land" and a second-layer word "30 tsubo". In this case, the estimation unit 34 inputs the words "land" and "30 tsubo" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "land" as the category name corresponding to the first-layer word "land", and estimates "typical size" as the category name corresponding to the second-layer word "30 tsubo".

[0066] For example, as described above, the generation unit 33 hierarchically classifies the words "used detached house" (first layer) and "5ldk" (second layer) as words that make up the search query string "used detached house 5ldk" for the comparison target "Company B". In this case, the estimation unit 34 inputs the words "used detached house" and "5ldk" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "used detached house" as the category name corresponding to the first layer word "used detached house", and estimates "spacious" as the category name corresponding to the second layer word "5ldk".

[0067] For example, as described above, the generation unit 33 hierarchically classifies the words "used detached house" (first layer) and "3LDK" (second layer) as words that make up the search query string "used detached house 3LDK" for the comparison target "Company A". In this case, the estimation unit 34 inputs the words "used detached house" and "3LDK" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "used detached house" as the category name corresponding to the first layer word "used detached house", and estimates "typical size" as the category name corresponding to the second layer word "3LDK".

[0068] For example, as described above, the generation unit 33 hierarchically classifies the words that make up the search query string "land 50 tsubo" for the comparison target "Company B" into a first-layer word "land" and a second-layer word "50 tsubo". In this case, the estimation unit 34 inputs the words "land" and "50 tsubo" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "land" as the category name corresponding to the first-layer word "land", and estimates "spacious" as the category name corresponding to the second-layer word "50 tsubo".

[0069] For example, as described above, the generation unit 33 hierarchically classifies the words "land" (first layer) and "Chiba" (second layer) as words that make up the search query string "land Chiba" for the comparison target "Company A". In this case, the estimation unit 34 inputs the words "land" and "Chiba" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "land" as the category name corresponding to the first layer word "land", and estimates "place name" for the category name corresponding to the second layer word "Chiba".

[0070] For example, as described above, the generation unit 33 hierarchically classifies the words that make up the search query string "custom-built homes" for the comparison target "Company B" into a first-layer word "custom-built homes" and a second-layer word "null". In this case, the estimation unit 34 inputs the words "custom-built homes" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "custom-built homes" as the category name corresponding to the first-layer word "custom-built homes". Here, the category name corresponding to the second-layer word "null" is left as "null".

[0071] For example, as described above, the generation unit 33 hierarchically classifies the words that make up the search query string "used detached house" for the comparison target "Company B" into a first-layer word "used detached house" and a second-layer word "null". In this case, the estimation unit 34 inputs the words "used detached house" that make up the search query as input information to the generation AI, and estimates real estate-related category names by having the generation AI generate category names corresponding to the words. In the example shown in Figure 9, the estimation unit 34 uses the generation AI to estimate "used detached house" as the category name corresponding to the first-layer word "used detached house". Here, the category name corresponding to the second-layer word "null" is left as "null".

[0072] [3.3.5. Creation Section 35] The creation unit 35 creates content that shows the relationship between the comparison targets "Company A" and "Company B" and the categories, based on the category names and classification results.

[0073] Figure 10 shows an example of content created by the creation unit 35 of the information processing device 1 according to this embodiment.

[0074] The content displays multiple categories categorized in relation to the comparison targets, "Company A" and "Company B." For example, the content displays multiple categories categorized in relation to comparison target "Company A," such as "Land," "Typical Size," and "Place Name," and multiple categories categorized in relation to comparison target "Company B," such as "Used Detached House," "Custom-Built House," and "Spacious."

[0075] [3.3.6.Providing Department 36] The provisioning unit 36 ​​provides the content created by the creation unit 35 to the terminal device 3 of user M who made the comparison request.

[0076] The multiple categories presented in the content are shown in a way that allows for identification from the highest-level category to the lower-level categories. For example, for comparison target "Company A," the multiple categories presented in the content are shown in a way that allows for identification from the highest-level category "Land" to the lower-level categories "Typical Size" and "Place Name." Similarly, for comparison target "Company B," the multiple categories presented are shown in a way that allows for identification from the highest-level category "Used Detached House" and "Custom-Built House" to the lower-level category "Spacious." For example, the multiple categories presented in the content are shown in a way that allows for identification from the highest-level category to the lower-level categories, such as by using color coding or diagonal lines for each category.

[0077] For example, content is presented with multiple categories as nodes and the connections between those categories as edges. In the example shown in Figure 10, the content is presented with multiple categories "land," "typical size," "place name," "used detached house," "custom-built house," and "spacious" as nodes, and the connections between those categories as edges.

[0078] Specifically, among the multiple categories "Land," "Average Size," "Place Name," "Used House," "Custom-Built House," and "Spacious," the edges connecting the first category and the second category (the category following the first category) are represented by arrows pointing from the first category to the second category. Here, the first category is presented with the category name corresponding to the first word entered in the search query, and the second category is presented with the category name corresponding to the next word entered in the search query.

[0079] For example, the edge connecting the first category "Land" and the second category, which is the next category after the first category "Land," is represented by an arrow pointing in the direction from the first category "Land" to the second category "General size," "Place name," and "Wide." In other words, the first category "Land" and the second category "General size," "Place name," and "Wide" are presented in a way that makes them distinguishable by the arrow.

[0080] For example, the edge connecting the first category "Used Detached House" and the second category "Average Size" and "Spacious" (which are the categories following the first category "Used Detached House") is represented by an arrow pointing from the first category "Used Detached House" to the second category "Average Size" and "Spacious". In other words, the first category "Used Detached House" and the second category "Average Size" and "Spacious" are presented in a way that makes them distinguishable by the arrow.

[0081] Regarding the first category, "Custom-Built Homes," there is no category immediately following it, so no arrow indicating the direction from the first category, "Custom-Built Homes," to the next category is shown.

[0082] Thus, according to the information processing device 1 of this embodiment, for example, if the comparison targets "Company A" and "Company B" are companies that provide real estate information, content based on search queries that user U is interested in regarding real estate can be provided to the terminal device 3 of user M who made the comparison request.

[0083] For example, in the information processing device 1 according to the embodiment, when comparing "Company A" and "Company B," the user U tends to be more interested in "Company B" the larger the area and layout of the property. Therefore, as a content provision service, it is possible to suggest to "Company A" that there are weaknesses in properties with large areas and layouts. As a result, in the information processing device 1 according to the embodiment, companies providing real estate information can provide user U with information on properties that are of more interest to them. In other words, according to the information processing device 1 according to the embodiment, effective support regarding content provision can be provided to user M who uses the content provision service.

[0084] [4. Processing Procedure] Next, the procedure for information processing by the processing unit 12 of the information processing device 1 according to the embodiment (corresponding to an example of an information processing method) will be described. Figure 11 is a flowchart showing the processing procedure of the processing performed by the processing unit 12 of the information processing device according to the embodiment.

[0085] As shown in Figure 11, the processing unit 12 first receives a selection of comparison targets from the terminal device 3 as a comparison request from the user M of the terminal device 3 (step S101).

[0086] In this case, the processing unit 12 obtains the history (log information) of search queries previously entered for the comparison target from the information processing device 4 (step S102).

[0087] Next, the processing unit 12 generates a classification result that hierarchically classifies the words constituting the search query based on the history of the acquired search query (step S103).

[0088] Next, the processing unit 12 uses the generation AI to estimate the category name corresponding to the word (step S104).

[0089] Next, the processing unit 12 creates content that shows the relationship between the comparison target and the category based on the category name and the classification result (step S105).

[0090] Then, the processing unit 12 provides the created content (step S106) and terminates the process.

[0091] [5. Variations] In the embodiments described above, we used as an example the case where the comparison targets "Company A" and "Company B" are companies that provide real estate information, and the search queries are related to real estate. However, we are not limited to this.

[0092] For example, the comparison target may be a landing page, domain, or business operator, and the information processing device 1 may hierarchically classify the words that make up the search query based on the history (log information) of search queries previously entered for the comparison target.

[0093] For example, the comparison target may be user attributes, individual users, user personas, etc., and the information processing device 1 may hierarchically classify the words that make up the search query based on the history (log information) of search queries previously entered for the comparison target.

[0094] For example, the comparison target may be any other comparison target besides those mentioned above, and the information processing device 1 may hierarchically classify the words that make up the search query based on the history (log information) of search queries previously entered for that comparison target.

[0095] Furthermore, in the above-described embodiment, the information processing device 1 was given the example of classifying the words constituting the search query hierarchically in two stages, such as first-layer words and second-layer words. However, it is not limited to this, and the words constituting the search query can be classified in three or more stages. That is, in the above-described embodiment, the example was given of two categories, but the categories can be divided into three or more.

[0096] For example, in the embodiment described above, the information processing device 1 used a generation AI to estimate "place name" as the category name corresponding to the word "Chiba," but it is not limited to this, and for example, terms such as "Kanto" or "Tokyo metropolitan area" may also be estimated as category names.

[0097] Furthermore, in the embodiments described above, the content that the information processing device 1 provides to the terminal device 3 of user M who made the comparison request is, in the example shown in Figure 10, content showing the relationship between the comparison targets "Company A" and "Company B" and the categories, presented with multiple categories as nodes and the connections between those categories as edges. However, the invention is not limited to this.

[0098] For example, content showing the relationship between comparison targets "Company A" and "Company B" and categories can be presented in a graph format, where multiple categories are arranged on a graph. Various graph formats are acceptable, such as bar graphs, line graphs, and dual-axis graphs.

[0099] [6. Hardware Configuration] The information processing device 1 according to the above embodiment is implemented by a computer 80 having the configuration shown in Figure 12, for example. Figure 12 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, RAM 82, ROM (Read Only Memory) 83, HDD (Hard Disk Drive) 84, communication interface (I / F) 85, input / output interface (I / F) 86, and media interface (I / F) 87.

[0100] The CPU 81 operates based on programs stored in the ROM 83 or HDD 84, and controls various parts. The ROM 83 stores the boot program executed by the CPU 81 when the computer 80 starts up, as well as programs that depend on the computer 80's hardware.

[0101] HDD84 stores programs executed by CPU81 and data used by such programs. The communication interface85 receives data from other devices via network N (see Figure 2) and sends it to CPU81, and transmits the data generated by CPU81 to other devices via network N.

[0102] The CPU 81 controls output devices such as displays and printers, and input devices such as keyboards or mice, via the input / output interface 86. The CPU 81 acquires data from input devices via the input / output interface 86. The CPU 81 also outputs data it has generated to output devices via the input / output interface 86.

[0103] 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 the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 can be, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or 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.

[0104] For example, when the computer 80 functions as an information processing device 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing a program loaded on the RAM 82. The HDD 84 stores data from the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88, but as another example, these programs may be obtained from other devices via a network N.

[0105] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0106] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0107] For example, the information processing device 1 described above may be implemented using a terminal device and a server computer, or using multiple server computers. Furthermore, depending on the function, it may be implemented by calling external platforms via APIs or network computing, allowing for flexible configuration changes.

[0108] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0109] [8. Effects] As described above, the information processing device 1 according to the embodiment comprises a reception unit 31, a generation unit 33, an estimation unit 34, and a provision unit 36. The reception unit 31 accepts the selection of a comparison target. The generation unit 33 generates a classification result that hierarchically classifies the words constituting the search query based on the history of search queries previously entered for the comparison target. The estimation unit 34 estimates the category name corresponding to the word. The provision unit 36 ​​provides content that shows the relationship between the comparison target and the category based on the category name and the classification result. For example, according to the information processing device 1 according to the embodiment, if the comparison target is a company that provides real estate information, content based on search queries that user U is interested in regarding real estate can be provided to the terminal device 3 of user M who made the comparison request. As a result, the company providing real estate information can provide user U with information on properties that are of more interest to them. In this way, the information processing device 1 according to the embodiment can provide effective support regarding content provision.

[0110] Furthermore, the estimation unit 34 inputs the words constituting the search query as input information to the generation AI, and estimates the category name by causing the generation AI to generate a category name corresponding to the words. As a result, the information processing device 1 according to this embodiment can provide effective support for content provision.

[0111] Furthermore, the reception unit 31 pre-receives instruction information indicating the conditions instructed by the user, and the estimation unit 34 inputs the instruction information into the generation AI, inputs the words constituting the search query as input information into the generation AI, and estimates the category name by causing the generation AI to generate the category name corresponding to the words. As a result, the information processing device 1 according to the embodiment can provide effective support for content provision.

[0112] Furthermore, the content presents multiple categories classified in relation to the comparison target, and these multiple categories are presented in a way that allows identification from the highest-level category to the lowest-level category. This enables the information processing device 1 according to the embodiment to provide effective support for content provision.

[0113] Furthermore, the content is presented with multiple categories as nodes and the connections between those categories as edges. This allows the information processing device 1 according to this embodiment to provide effective support for content delivery.

[0114] Furthermore, among the multiple categories, the edges connecting the first category and the second category, which is the next category after the first category, are represented by arrows pointing in the direction from the first category to the second category. This allows the information processing device 1 according to the embodiment to provide effective support for content provision.

[0115] Furthermore, the first category is presented using the category name corresponding to the first word entered among the words that make up the search query, and the second category is presented using the category name corresponding to the next word entered among the words that make up the search query. This allows the information processing device 1 according to the embodiment to provide effective support for content provision.

[0116] Although embodiments of the present application have been described in detail based on the drawings, these are illustrative examples, and the present invention can be implemented in various other forms, including those described in the disclosure section of the invention, based on the knowledge of those skilled in the art.

[0117] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0118] 1,4 Information Processing Devices 2,3 Terminal devices 10 Communications Department 11 Storage section 12 Processing Units 31 Reception Department 32 Acquisition Department 33 Generation part 34 Estimation part 35 Creation Section 36 Providing Department 41 User information 42 Query Information 43 Model Information 100 Information Processing Systems N Network

Claims

1. A reception desk that accepts the selection of comparison targets, A generation unit generates classification results that hierarchically classify the words constituting the search query based on the history of search queries previously entered for the comparison target, An estimation unit that estimates the category name corresponding to the aforementioned word, A providing unit that provides content showing the relationship between the comparison target and the category based on the category name and the classification result, An information processing device equipped with the following features.

2. The estimation unit inputs the words constituting the search query as input information to the generating AI, and estimates the category name by causing the generating AI to generate a category name corresponding to the words. The information processing apparatus according to claim 1.

3. The reception unit receives instruction information indicating the conditions instructed by the user as a system prompt. The estimation unit inputs the instruction information into the generating AI and inputs the words constituting the search query into the generating AI as input information. The information processing apparatus according to claim 2.

4. The aforementioned content shows multiple categories classified in relation to the comparison target, The aforementioned multiple categories are presented in a way that allows for identification from the highest-level category to the lowest-level category. The information processing apparatus according to any one of claims 1 to 3.

5. The aforementioned content is presented with the multiple categories as nodes and the connections between those categories as edges. The information processing apparatus according to claim 4.

6. Among the aforementioned multiple categories, the edge connecting the first category and the second category, which is the category following the first category, is indicated by an arrow pointing in the direction from the first category to the second category. The information processing apparatus according to claim 5.

7. The first category is presented with the category name corresponding to the first word entered among the words constituting the search query, and the second category is presented with the category name corresponding to the next word entered among the words constituting the search query. The information processing apparatus according to claim 6.

8. A method of information processing performed by a computer, A reception process for accepting the selection of comparison targets, A generation process that generates classification results by hierarchically classifying the words constituting the search query based on the history of search queries previously entered for the comparison target, An estimation step for estimating the category name corresponding to the aforementioned word, A provision step of providing content that shows the relationship between the comparison target and the category based on the category name and the classification result, Information processing methods including

9. The procedure for accepting the selection of comparison targets, A generation procedure that generates classification results by hierarchically classifying the words constituting the search query based on the history of search queries previously entered for the comparison target, An estimation procedure for estimating the category name corresponding to the aforementioned word, A provision procedure for providing content that shows the relationship between the comparison target and the category based on the category name and the classification result, An information processing program that causes a computer to execute something.

Images