Information processing apparatus, information processing method, and information processing program

Abstract

To effectively label non-structured contents.SOLUTION: An information processing apparatus includes a generation unit, an estimation unit, and a selection unit. The generation unit generates a corresponding keyword group for each category preset as a category to be used when selecting a provision content to be provided to a user. The estimation unit estimates a category corresponding to the content on the basis of similarity between the keyword group generated by the generation unit and the content related to the web behavior of the user. The selection unit selects provision content to be provided to the user on the basis of the category estimated by the estimation unit.SELECTED DRAWING: Figure 5

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for estimating predetermined information using unstructured data, such as techniques for extracting features from unstructured data that are effective for making a predetermined prediction. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-154367 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques have not been able to effectively label unstructured content, for example.

[0005] The present application has been made in view of the above, and aims to effectively label unstructured content. [Means for solving the problem]

[0006] The information processing device according to the present application is characterized by having a generation unit that generates a corresponding group of keywords for each category that is preset as a category to be used when selecting content to be provided to a user, an estimation unit that estimates a category corresponding to the content based on the similarity between the group of keywords generated by the generation unit and content related to the user's web behavior, and a selection unit that selects content to be provided to the user based on the category estimated by the estimation unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to effectively label unstructured content. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Figure 3A] FIG. 3A is a diagram (1) showing an example of a prompt according to the embodiment. [Figure 3B] FIG. 3B is a diagram (2) showing an example of a prompt according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the configuration of a user terminal according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a category storage unit according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a category estimation result storage unit according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. [Figure 9] FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, 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 device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) [1. Information Processing System Configuration] An information processing system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the information processing system 1 includes a user terminal 10 and an information processing device 100. The user terminal 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment.

[0011] The user terminal 10 is an information processing device used by a user who performs web actions (e.g., purchasing actions, posting actions, browsing actions, etc.) on a predetermined service. The user who uses the user terminal 10 is a user to whom the provided content according to the embodiment is provided. The user terminal 10 may be any device that can realize the processing according to the embodiment. The user terminal 10 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 2 shows a case where the user terminal 10 is a smartphone.

[0012] The user terminal 10 is, for example, a smart device such as a smartphone or tablet, and is a portable terminal device capable of communicating with any server device via a wireless communication network such as 4G to 5G (Generations) or LTE (Long Term Evolution). The user terminal 10 may have a screen such as a liquid crystal display with a touch panel function, and may accept various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by a user's finger or stylus. In FIG. 2, the user terminal 10 is used by a user U1.

[0013] The information processing device 100 is an information processing device intended to effectively label unstructured content, and may be any device capable of implementing the processes described in the embodiments. For example, the information processing device 100 generates a group of keywords corresponding to each preset category, estimates a category corresponding to content related to a user's web behavior based on similarity with the generated group of keywords, and selects content to be provided to the user (hereinafter referred to as "provided content") based on the estimated category. Furthermore, for example, in order to effectively label unstructured content, the information processing device 100 performs labeling by using a generation AI to generate a group of keywords from categories, instead of inputting the unstructured content into a generation AI. The information processing device 100 may be implemented, for example, by a server device or a cloud system of an operator of a predetermined service through which users perform web behavior.

[0014] [2. An example of information processing] As an example of a conventional technology for labeling unstructured data, there is known a technology for labeling unstructured data by directly inputting the unstructured data into a generating AI. For example, there is known a technology for inputting the unstructured data together with a group of categories that are preset as categories to be used when selecting content to be provided, and then estimating which category the unstructured data belongs to from the group of categories. A technology for selecting content to be provided that is suitable for a user by performing labeling in this manner is known.

[0015] However, when using such conventional technology, since there are no restrictions on unstructured data, it is possible that the cost of using the generation AI will be high and that the response time when using the API will be slow. For example, if there are no restrictions on unstructured data, it is possible that items that do not want to be structured (e.g., information about advertising space) will be passed to the generation AI. Furthermore, for example, the more unstructured data items there are, the heavier the data volume provided to the generation AI will be, which will increase the cost burden of using the generation AI. Furthermore, it is possible that the response time will be slower because it takes time to process the number of items.

[0016] The present application has been made in view of the above, and aims to effectively label unstructured content. For example, the present application aims to effectively label content so as to reduce costs and increase response speed. The present application also aims to provide more optimal content to users.

[0017] In the following embodiment, a category is estimated for unstructured data. However, when providing unstructured data to a generation AI and having it directly estimate a category, both the cost and processing time can be excessive depending on the amount of unstructured data. For this reason, in the following embodiment, a group of categories is provided to the generation AI to generate a group of keywords related to the unstructured data. Then, by taking into account the similarity between the group of keywords and the unstructured data, it is no longer necessary to provide large amounts of data such as unstructured data to the generation AI, enabling high-speed labeling with low API costs.

[0018] In the following embodiments, an example of provided content will be described in which the provided content is an advertisement. The provided content does not have to be limited to advertisements. In the following embodiments, the category group is preset and remains constant regardless of the unstructured data. The categories included in the category group are used when selecting provided content. In the following embodiments, an example of unstructured data will be described in which the unstructured data is a news article or a product purchase / view page. The unstructured data does not have to be limited to these examples. For example, the unstructured data may be a Q&A or review page. The unstructured data may also be data from a provider of provided content such as advertisements. For example, in the case of advertisements, the unstructured data may be advertising submission data. In other words, instead of targeting category estimation for content that provides provided content such as advertisements, the target of category estimation may be targeting provided content such as advertisements submitted by advertisers. The advertising submission data may be, for example, advertisement copy, catch phrases, or audio text for video data. This makes it possible to assign a common category not only to the content that provides provided content such as advertisements, but also to the provided content itself. Therefore, it can be expected that content selection will become easier.

[0019] FIG. 2 is a diagram illustrating an example of information processing in an information processing system according to an embodiment. The information processing device 100 acquires a category group M1 (step S101). Then, the information processing device 100 provides the category group M1 to a generation AI to generate a group of keywords associated with each piece of unstructured data (step S102). For example, the information processing device 100 generates a group of keywords associated with each piece of unstructured data for each of categories K1, K2, and so on included in the category group M1. For example, in the case of categories K1 and K2, the information processing device 100 generates one or more keywords for category K1 as keywords associated with each piece of unstructured data, and generates one or more keywords for category K2 as keywords associated with each piece of unstructured data. Note that the number of keywords generated from a category need not be particularly limited and may differ for each category included in the category group M1.

[0020] In this way, the information processing device 100 generates a keyword group for each category included in the category group M1. Furthermore, in order to generate a keyword group related to the target unstructured data for each category, the information processing device 100 generates a keyword group for each combination of a category and unstructured data.

[0021] An example of generating a keyword group will be described below. For example, if the unstructured data is a news article and the category K1 is "news, information media / news enthusiasts / technology (IT)," the information processing device 100 generates a keyword group such as "AI, blockchain, smartphone, software update, cybersecurity, data leak, cloud computing, IoT, big data, tech industry, innovation, digital transformation."

[0022] On the other hand, if the unstructured data is a purchase / view product page and the category K1 is "news, information media / news lovers / technology (IT)", the information processing device 100 generates a group of keywords such as "smart watch, tablet, laptop, earphones, e-book reader, gaming keyboard, wireless mouse, external hard drive, VR headset, smart home device, programming-related books".

[0023] Furthermore, for example, if the unstructured data is a news article and category K2 is "sports, fitness / sports enthusiasts / soccer / overseas soccer," the information processing device 100 generates a group of keywords such as "World Cup, UEFA Champions League, Premier League, La Liga, Serie A, Bundesliga, transfer market, goal collection, highlights, player interviews, soccer tactics, fan dive."

[0024] On the other hand, if the unstructured data is a purchase / view product page and category K2 is "sports, fitness / sports enthusiasts / soccer / overseas soccer," the information processing device 100 generates a group of keywords such as "soccer ball, soccer cleats, replica uniform, training wear, goalkeeper gloves, fitness band, protein, soccer tactical manual, fitness mat, soccer ticket (overseas league), sports drink."

[0025] Furthermore, for example, if the unstructured data is a news article and category K3 is "travel / travel lover / family trip," the information processing device 100 generates a group of keywords such as "theme park, hot spring trip, camping, domestic resort, overseas resort, travel guide, travel plan, tourist spot, hotel reservation, travel insurance, package tour, travel goods."

[0026] On the other hand, if the unstructured data is a purchase / view product page and category K3 is "travel / travel lover / family trip," the information processing device 100 generates a group of keywords such as "suitcase, travel guidebook, action camera, travel pouch, neck pillow, kids' travel game, portable charger, folding umbrella, sunscreen, beach sandals, family room reservation service."

[0027] Furthermore, for example, if the unstructured data is a news article and category K4 is "media, entertainment / television enthusiasts / domestic dramas," the information processing device 100 generates a group of keywords such as "romance drama, mystery, suspense, comedy, family drama, human drama, reality show, drama special, new season, cast announcement, drama filming location, viewership ratings."

[0028] On the other hand, if the unstructured data is a purchase / viewing product page and category K4 is "media, entertainment / television lovers / domestic dramas," the information processing device 100 generates a group of keywords such as "DVD box set, soundtrack CD, official goods, novelized books, posters, original T-shirts, drama script collections, character figures, making-of books, online viewing subscriptions, drama location tour tickets."

[0029] Furthermore, for example, if the unstructured data is a news article and category K5 is "apparel, accessories / women's fashion," the information processing device 100 generates a group of keywords such as "trendy outfits, fashion shows, brand collaborations, new items, sale information, street fashion, accessory trends, bag collections, new shoes, fashion magazines, styling tips, online shopping."

[0030] On the other hand, if the unstructured data is a purchase / view product page and category K5 is "apparel, accessories / women's fashion," the information processing device 100 generates a group of keywords such as "dress, handbag, accessory set, high heels, scarf, sunglasses, leggings, jacket, blouse, denim pants, fashion magazine."

[0031] Here, the prompt input to the generation AI will be described. In step S102, the information processing device 100 provides the category group M1 to the generation AI to generate a group of keywords associated with each piece of unstructured data. At this time, a prompt is provided to the generation AI along with the category group M1 to generate the keyword group. The prompt is a prompt that instructs the generation AI to generate a group of keywords for each category included in the category group M1. The prompt is also a prompt generated in accordance with the unstructured data, and is a prompt that instructs the generation AI to generate a group of keywords associated with each piece of unstructured data.

[0032] 3A and 3B are diagrams showing examples of prompts according to an embodiment. FIG. 3A is a prompt when the unstructured data is a news article, and FIG. 3B is a prompt when the unstructured data is a product page for purchase or viewing. The information processing device 100 identifies a category of the unstructured data and provides a prompt according to the identified category to the generation AI to generate a group of keywords related to the unstructured data.

[0033] The information processing device 100 also acquires unstructured data D1 (step S103). The unstructured data D1 is content related to the web behavior of the user U1. In this case, the information processing device 100 acquires information related to the web behavior of the user U1 (step S12) in accordance with the web behavior of the user U1 (step S11), thereby acquiring the unstructured data D1, which is the corresponding unstructured data.

[0034] Then, the information processing device 100 calculates the similarity between the keyword group for each category and the unstructured data D1 (step S104). For example, the information processing device 100 may calculate the similarity based on whether or not a predetermined keyword is included in the unstructured data D1, or may calculate the similarity for the entire keyword group. In the latter case, for example, the information processing device 100 may calculate the similarity between information obtained by vectorizing character strings included in the unstructured data D1 at word boundaries and information obtained by vectorizing each keyword in the keyword group. For example, the information processing device 100 may calculate the overall average of the similarities.

[0035] Then, the information processing device 100 estimates a category based on the calculated similarity (step S105). Specifically, the information processing device 100 estimates a category corresponding to the unstructured data D1 by selecting a keyword group that has the highest similarity to the unstructured data D1. More specifically, the information processing device 100 selects a keyword group that has the highest similarity to the unstructured data D1 from among the keyword groups generated for each category included in the category group M1 (keyword groups corresponding to each category).

[0036] At this time, the information processing device 100 estimates a category corresponding to the unstructured data D1 by selecting a keyword group that has the highest similarity to the unstructured data D1. That is, the information processing device 100 estimates a category corresponding to the unstructured data for each piece of unstructured data by selecting a keyword group for each piece of unstructured data.

[0037] In this way, the information processing device 100 estimates a user category suitable for the user by estimating a category corresponding to content related to the user's web behavior based on the similarity with the content related to the user's web behavior (corresponding to unstructured data D1).

[0038] The information processing device 100 then selects content to be provided to the user based on the user category estimated for the user (step S106). Specifically, the information processing device 100 selects content to be provided to the user based on the category estimated as a category corresponding to content related to the user's web behavior. The information processing device 100 selects content to be provided to the user for each user. For example, if the content last viewed by the user contains many of the generated keywords such as "AI, blockchain, ...", the information processing device 100 estimates that the category corresponding to the content is category K1 "news, information media / news lover / technology (IT)". Furthermore, for example, if the content last viewed by the user contains many of the generated keywords such as "World Cup, UEFA Champions League," the information processing device 100 estimates that the category corresponding to the content is category K2 "sports, fitness / sports lover / soccer / overseas soccer". The information processing device 100 then estimates the user category from the estimated categories. For example, when the estimated category is category K1, the information processing device 100 estimates a user category such as "a user who frequently reads news articles" from category K1. Furthermore, when the estimated category is category K2, the information processing device 100 estimates a user category such as "a user who likes sports" from category K2. Then, the information processing device 100 selects provided content such as advertisements corresponding to the user category.

[0039] Then, the information processing device 100 provides the provided content to the corresponding user (step S107). The information processing device 100 provides the provided content selected for each user to the corresponding user.

[0040] In the above embodiment, the information processing device 100 generates a group of keywords with general names, such as "laptop computer" and "soccer ball," from a category. However, the keywords may not be limited to general names. For example, the generated keyword group may include keywords such as product names. For example, keywords such as product names, such as "XX product of the XX brand," may be included. In this way, the information processing device 100 may generate a keyword group including keywords that are not general names, such as product names, from a category. Furthermore, for example, the generated keyword group may include keywords that take seasonality into consideration. For example, the prompt shown in FIG. 3A or 3B may include an instruction such as, "Please consider that it is now June and that summer is coming." In such a case, the information processing device 100 generates a keyword group including keywords that take seasonality into consideration. As a specific example, if the unstructured data is a product page for purchase or viewing, the category is "apparel, accessories / women's fashion," and the prompt does not include an instruction to take seasonality into consideration, the information processing device 100 generates a keyword group such as "dress, handbag, accessory set, high heels, scarf, sunglasses, leggings, jacket, blouse, denim pants, fashion magazine" without considering seasonality. On the other hand, if the unstructured data is a product page for purchase or viewing, the category is "apparel, accessories / women's fashion," and the prompt includes an instruction to take seasonality into consideration, the information processing device 100 generates a keyword group such as "sandals, beach hat, sunglasses, bikini, summer handbag, shorts, tank top, summer scarf, beach cover-up, anklet, summer cardigan" with considering seasonality.

[0041] [3. User terminal configuration] Next, the configuration of the user terminal 10 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the user terminal 10 according to the embodiment. As shown in Fig. 4, the user terminal 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0042] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100, etc., via the predetermined network N.

[0043] (Input section 12) The input unit 12 accepts various operations from a user. In FIG. 2, the input unit 12 accepts various operations from a user U1. For example, the input unit 12 may accept various operations from a user via a display screen using a touch panel function. The input unit 12 may also accept various operations from buttons provided on the user terminal 10 or a keyboard or mouse connected to the user terminal 10.

[0044] (Output section 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information transmitted from the information processing device 100. For example, the output unit 13 displays provided content such as advertisements.

[0045] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the user terminal 10 using a RAM (Random Access Memory) as a work area. For example, these various programs include application programs installed in the user terminal 10. For example, these various programs include application programs that display information transmitted from the information processing device 100. The control unit 14 is also realized by an integrated circuit, such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0046] As shown in FIG. 4, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0047] (Receiving unit 141) The receiving unit 141 receives, for example, information transmitted from the information processing device 100. For example, the receiving unit 141 receives provided content. Furthermore, for example, the receiving unit 141 receives control information for displaying the provided content.

[0048] (Transmitter 142) The transmission unit 142 transmits information to, for example, the information processing device 100. For example, the transmission unit 142 transmits information related to the user's web behavior. For example, the transmission unit 142 transmits information related to the user's purchasing behavior, posting behavior, or browsing behavior on a predetermined service.

[0049] 4. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 5, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may also have an input unit (e.g., a keyboard or a mouse) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display) that displays various information.

[0050] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the user terminal 10 etc. via the network N.

[0051] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 5 , the storage unit 120 includes a category storage unit 121 and a category estimation result storage unit 122.

[0052] The category storage unit 121 stores information about categories that are preset as categories to be used when selecting provided content. FIG. 6 shows an example of the category storage unit 121 according to the embodiment. The information stored in the category storage unit 121 is used, for example, to generate a group of keywords to be compared for similarity with content related to the user's web behavior. As shown in FIG. 6, the category storage unit 121 has items such as "category ID" and "category."

[0053] "Category ID" indicates identification information for identifying a category. "Category" indicates a category.

[0054] The category estimation result storage unit 122 stores the category estimation result. Here, FIG. 7 shows an example of the category estimation result storage unit 122 according to the embodiment. The information stored in the category estimation result storage unit 122 is used, for example, to select content to be provided. As shown in FIG. 7, the category estimation result storage unit 122 has items such as "user ID," "unstructured data ID," and "category."

[0055] "User ID" indicates identification information for identifying a user. "Unstructured Data ID" indicates identification information for identifying unstructured data. "Category" indicates the category inferred for the unstructured data.

[0056] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a CPU or an MPU executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0057] 5, the control unit 130 has an acquisition unit 131, a generation unit 132, an estimation unit 133, a selection unit 134, and a provision unit 135, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be any other configuration as long as it performs the information processing described below.

[0058] (Acquisition part 131) The acquiring unit 131 acquires various pieces of information from the storage unit 120. The acquiring unit 131 also stores the acquired various pieces of information in the storage unit 120.

[0059] The acquisition unit 131 acquires various pieces of information from an external information processing device. The acquisition unit 131 acquires various pieces of information from other information processing devices such as the user terminal 10.

[0060] The acquisition unit 131 acquires, for example, information about categories that are set in advance as categories used when selecting content to be provided. The acquisition unit 131 also acquires information about content related to the user's web behavior.

[0061] (Generation unit 132) The generation unit 132 generates a corresponding keyword group for each category preset as a category used when selecting provided content, for example. For example, the generation unit 132 generates a keyword group for each combination of a category preset as a category used when selecting provided content and content related to the user's web behavior. For example, the generation unit 132 generates a corresponding keyword group by providing the generation AI with a category preset as a category used when selecting provided content and a prompt generated according to the content related to the user's web behavior. For example, the generation unit 132 generates a corresponding keyword group by providing the generation AI with a prompt instructing the generation AI to generate a keyword group from a category preset as a category used when selecting provided content. In this case, for example, the generation unit 132 generates a prompt according to content related to the user's web behavior and provides the generated prompt to the generation AI to generate a corresponding keyword group.

[0062] (Estimation part 133) The estimation unit 133 estimates a category corresponding to content related to the user's web behavior based on, for example, the similarity between the keyword group generated by the generation unit 132 and content related to the user's web behavior. For example, the estimation unit 133 estimates a category corresponding to content related to the user's web behavior based on the similarity between information obtained by vectorizing each keyword in the keyword group generated by the generation unit 132 and information obtained by vectorizing character strings included in content related to the user's web behavior using word separators. For example, the estimation unit 133 estimates a category corresponding to content related to the user's web behavior by selecting a keyword group that has a high similarity to the content related to the user's web behavior. In this case, for example, the estimation unit 133 calculates the similarity between the keyword group generated by the generation unit 132 and content related to the user's web behavior, and estimates a category corresponding to content related to the user's web behavior based on the calculated similarity. Note that, for example, the estimation unit 133 may perform category estimation based on an overall average of similarities. The estimation unit 133 also estimates a user category by, for example, estimating a category corresponding to content related to the user's web behavior. For example, the estimation unit 133 estimates a user category that indicates the user's interests and concerns.

[0063] (Selection unit 134) The selection unit 134 selects content to be provided to the user, for example, based on the category estimated by the estimation unit 133. For example, the selection unit 134 selects content to be provided to the user, based on the user category estimated by the estimation unit 133.

[0064] (Provider 135) The providing unit 135 provides the provided content selected by the selecting unit 134, for example.

[0065] [5. Information Processing Flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the procedure of information processing by the information processing system according to the embodiment.

[0066] As shown in FIG. 8, the information processing device 100 acquires a group of categories that are preset as categories to be used when selecting provided content (step S201). The information processing device 100 generates a group of keywords for each of the acquired group of categories (step S202). The information processing device 100 estimates a category corresponding to content related to the user's web behavior based on similarity with the generated group of keywords (step S203). The information processing device 100 selects provided content corresponding to the estimated category (step S204). The information processing device 100 provides the selected provided content (step S205).

[0067] [6. Effects] As described above, the information processing device 100 according to the embodiment includes the generation unit 132, the estimation unit 133, and the selection unit 134. The generation unit 132 generates a group of keywords corresponding to each category that is preset as a category used when selecting content to be provided to a user. The estimation unit 133 estimates a category corresponding to content based on the similarity between the group of keywords generated by the generation unit 132 and content related to the user's web behavior. The selection unit 134 selects content to be provided to the user based on the category estimated by the estimation unit 133.

[0068] As a result, the information processing apparatus 100 according to the embodiment can effectively estimate the user category, for example, and provide content suited to the user.

[0069] Furthermore, the generating unit 132 generates a group of keywords for each combination of a category and a content.

[0070] This enables the information processing apparatus 100 according to the embodiment to more effectively estimate a user category by using, for example, a group of keywords as a comparison target.

[0071] Furthermore, the generation unit 132 generates a keyword group by providing the generation AI with a category and a prompt that is generated according to the content and instructs the generation AI to generate a keyword group from the category.

[0072] As a result, the information processing device 100 according to the embodiment can, for example, generate a group of keywords from a category according to content, thereby enabling more effective estimation of a user category by using the group of keywords as a comparison target.

[0073] Furthermore, the estimation unit 133 estimates the category based on the similarity between information obtained by vectorizing character strings included in the content at word boundaries and information obtained by vectorizing each keyword in the keyword group.

[0074] As a result, the information processing apparatus 100 according to the embodiment can determine the similarity across the entire keyword group, for example, and therefore can more effectively estimate the user category.

[0075] Furthermore, the web behavior is a purchasing behavior, a posting behavior, or a browsing behavior.

[0076] As a result, the information processing apparatus 100 according to the embodiment can provide content that is highly relevant to the user's interests and concerns, for example.

[0077] [7. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0078] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0079] The HDD 1400 stores programs executed by the CPU 1100, data used by these programs, etc. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0080] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0081] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0082] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0083] [8. 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 using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0084] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0085] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0086] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0087] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0088] 1. Information Processing Systems 10 User terminal 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information processing device 110 Communications Department 120 Storage section 121 Category Memory 122 Category estimation result memory unit 130 Control Unit 131 Acquisition Department 132 Generation part 133 Estimation Department 134 Selection Section 135 Provision Department 141 Receiving unit 142 Transmitter N Network

Claims

1. a generating unit that generates a group of keywords corresponding to each of categories that are preset as categories used when selecting content to be provided to a user; an estimation unit that estimates a category corresponding to the content based on a similarity between the keyword group generated by the generation unit and the content related to the user's web behavior; a selection unit that selects content to be provided to the user based on the category estimated by the estimation unit; An information processing device comprising:

2. The generation unit The keyword group is generated for each combination of the category and the content.

2. The information processing apparatus according to claim 1, wherein:

3. The generation unit The category and a prompt generated according to the content, the prompt instructing the AI ​​to generate a keyword group from the category, are provided to the AI ​​to generate the keyword group.

3. The information processing apparatus according to claim 2, wherein:

4. The estimation unit The category is estimated based on the similarity between information obtained by vectorizing character strings included in the content by word segmentation and information obtained by vectorizing each keyword in the keyword group.

2. The information processing apparatus according to claim 1, wherein:

5. The web behavior is a purchasing behavior, a posting behavior, or a browsing behavior.

2. The information processing apparatus according to claim 1, wherein:

6. A computer-implemented information processing method, comprising: a generating step of generating a group of keywords corresponding to each of categories previously set as categories used when selecting content to be provided to a user; an estimation step of estimating a category corresponding to the content based on a similarity between the keyword group generated by the generation step and the content related to the user's web behavior; a selection step of selecting content to be provided to the user based on the category estimated by the estimation step; An information processing method comprising:

7. a generation step of generating a group of keywords corresponding to each category that is preset as a category used when selecting content to be provided to a user; an estimation step of estimating a category corresponding to the content based on a similarity between the keyword group generated by the generation step and the content related to the user's web behavior; a selection step of selecting content to be provided to the user based on the category estimated by the estimation step; An information processing program characterized by causing a computer to execute the above.

Images