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

Abstract

We deliver search-direction ads to users who visit the ad page via search. [Solution] The information processing device according to the present invention is characterized by comprising: a prediction unit that predicts the probability of a search using a trained model; a distribution control unit that delivers search-guided advertisements to users who are expected to perform a search based on the predicted probability of a search; an estimation unit that estimates the search keywords used in searches performed as a result of the search-guided advertisements; a determination unit that determines whether a search was performed using the estimated search keywords among the searches performed by users to whom the search-guided advertisements were delivered; and a learning unit that trains a model on user-related information about the user, advertising-related information about the search-guided advertisements, and search-related information about whether a search was performed and the search keywords.

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] There is disclosed a technique for predicting the conversion rate of advertisement content when the advertisement content is distributed on a distribution surface using a prediction model that predicts the conversion rate of advertisement content when input information including advertisement information, user information, and distribution surface information is input (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the above conventional technology has a problem that it is not possible to grasp users who did not directly reach conversion from the advertisement but reached conversion by another means later.

[0005] The present application has been made in view of the above, and an object thereof is to distribute search-inducing advertisements to users who visit the advertisement page via search.

Means for Solving the Problems

[0006] The information processing device according to the present invention is characterized by comprising: a prediction unit that predicts the probability of a search using a trained model; a distribution control unit that delivers search-guided advertisements to users who are expected to perform a search based on the predicted probability of a search; an estimation unit that estimates the search keywords used in searches performed as a result of the search-guided advertisements; a determination unit that determines whether a search performed by a user to whom the search-guided advertisements were delivered uses the estimated search keywords; and a learning unit that trains the model on user-related information about the user, advertising-related information about the search-guided advertisements, and search-related information about whether a search was performed and the search keywords. [Effects of the Invention]

[0007] According to one embodiment, search-direction advertisements can be delivered to users who visit the advertisement page via search. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is an explanatory diagram showing an overview of the information processing system according to the embodiment. [Figure 2] Figure 2 is an explanatory diagram illustrating the concept of search guidance. [Figure 3] Figure 3 is an explanatory diagram illustrating the search prediction cycle. [Figure 4] Figure 4 shows an example of the configuration of a terminal device according to this embodiment. [Figure 5] Figure 5 shows an example of the configuration of a server device according to this embodiment. [Figure 6] Figure 6 is a flowchart showing the processing procedure according to the embodiment. [Figure 7] Figure 7 shows an example of a hardware configuration. [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 the following embodiments, and redundant descriptions are omitted.

[0010] [1. Overview of the Information Processing System] First, with reference to Figure 1, an overview of the information processing system according to the embodiment will be described. Figure 1 is an explanatory diagram showing an overview of the information processing system according to the embodiment. As shown in Figure 1, the information processing system 1 according to the embodiment includes a terminal device 10 and a server device 100. The terminal device 10 and the server device 100 are connected to each other via a network N, either by wired or wireless means, enabling communication between them. This allows the terminal device 10 to cooperate with the server device 100. The network N is, for example, a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet.

[0011] Terminal device 10 is an information processing device used by user U. For example, terminal device 10 may be a smart device such as a smartphone or tablet, a PC (Personal Computer) such as a desktop or notebook (laptop), a mobile phone such as a feature phone, a PDA (Personal Digital Assistant), a game console or AV equipment with communication functions, an information appliance or digital appliance, a car navigation system, a wearable device such as a smartwatch, head-mounted display, or smart glasses. Alternatively, terminal device 10 may be a house or building compatible with the Internet of Things (IoT), a car, a home appliance, an electronic device, etc.

[0012] In this embodiment, the terminal device 10 is a smart device such as a smartphone or tablet used by user U, and is a mobile terminal device that can communicate with any server device via wireless communication networks such as LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation), Bluetooth (registered trademark), or wireless LAN. The terminal device 10 also has a screen such as a liquid crystal display with touch panel functionality, and accepts various operations on displayed data such as content from user U using a finger or stylus, such as tapping, sliding, and scrolling. Operations performed on the area of ​​the screen where content is displayed may also be considered as operations on the content. Furthermore, the terminal device 10 may be an information processing device such as a desktop PC or notebook PC, not just a smart device.

[0013] The server device 100 is, for example, a computer such as a PC or blade server, or a mainframe or workstation. The server device 100 may also be implemented through cloud computing.

[0014] In this embodiment, the server device 100 is an information processing device that works in conjunction with each user U's terminal device 10 and provides each user U's terminal device 10 with API (Application Programming Interface) services for various applications (hereinafter referred to as "apps") and various data, and is implemented by a computer or cloud system.

[0015] Furthermore, the server device 100 may be an information processing device that provides some kind of online service to each user U's terminal device 10. For example, the server device 100 may provide services such as internet connection, search service, advertising distribution service, chat service, conversational service using voice, images, video, etc., SNS (Social Networking Service), e-commerce (EC), electronic payment, online games, online banking, online trading, accommodation / ticket reservations, video / music distribution, news, maps, route search, route guidance, route information, service information, and weather forecasts as online services. In practice, the server device 100 may cooperate with various servers that provide the above-mentioned online services and act as an intermediary for online services, or it may be responsible for processing online services.

[0016] The server device 100 can acquire user information about user U. For example, the server device 100 can acquire information about user U's attributes (attribute information), such as gender, age, and residential area. The server device 100 can also acquire information about user U's demographics, psychographics, geographics, behavioral attributes, etc. The server device 100 may also acquire information about the segment or persona to which user U belongs in the field of marketing, as user information. The server device 100 stores and manages information about user U's attributes (attribute information) along with identification information (user ID, etc.) that identifies user U.

[0017] In addition, the server device 100 acquires various types of history information (log data) indicating the actions of the user U from the terminal device 10 of the user U or from various servers, etc. based on the user ID, etc. For example, the server device 100 acquires a location history, which is a history of the location and time of the user U, from the terminal device 10. Further, the server device 100 acquires a search history, which is a history of the search queries input by the user U, from a search server (search engine). Further, the server device 100 acquires a browsing history, which is a history of the content browsed by the user U, from a content server. Further, the server device 100 acquires a purchase history (settlement history), which is a history of the user U's product purchases and settlement processing, from an e-commerce server or a settlement processing server. Further, the server device 100 may acquire a listing history or a sales history, which is a history of the user U's listings on the marketplace, from an e-commerce server or a settlement processing server. Further, the server device 100 acquires a posting history, which is a history of the user U's posts, from a posting server or an SNS server that provides a word-of-mouth posting service. Note that the above various servers, etc. may be the server device 100 itself. That is, the server device 100 may function as the above various servers, etc.

[0018] In addition, the number of each device included in the information processing system 1 shown in FIG. 1 is not limited to that shown. For example, in FIG. 1, for the sake of simplicity of illustration, only one terminal device 10 is shown, but this is merely an example and is not limited, and two or more may be provided.

[0019] [2. Search-Induced Advertising] As an issue in advertising distribution, conventionally, the click-through rate (CTR) and conversion rate (CVR) for advertisements have been measured, but there is a problem that users who do not directly convert from an advertisement but later convert by another means cannot be grasped. For example, there are users who dislike clicking on advertisements and visit a page related to the advertiser's page or the product (merchandise) of the advertisement via a search, but they are not currently regarded as important.

[0020] Preliminary research indicates that approximately 50% of users convert (CV) after searching or viewing related content. A key characteristic of users who convert via search is that their conversion rate (CVR) tends to be significantly higher than that of users who click on ads.

[0021] Therefore, in this embodiment, search-driving ads are introduced that target users who are likely to perform a search if they see the ad.

[0022] For example, as shown in Figure 1, the server device 100 uses a machine learning model to predict search probabilities and estimate which users are likely to perform a search if an advertisement is displayed (Step S1).

[0023] Next, the server device 100 adjusts the ad delivery bid price (bid) based on the predicted search probability (step S2).

[0024] Next, the server device 100 delivers search-driving advertisements to users who are likely to perform a search if they see the advertisement (step S3).

[0025] Next, the server device 100 estimates the search keywords used by the user to whom the advertisement was delivered (step S4).

[0026] Next, the server device 100 determines whether to perform a search using the estimated search keywords (step S5).

[0027] The server device 100 may identify and analyze searches using search keywords. Furthermore, the server device 100 may determine user conversions (CVs). In this case, the server device 100 may determine a CV when a user visits the advertiser's page or a page related to the advertised product (merchandise). The server device 100 may also determine that a search is based on a search-driven ad when a user visits the advertiser's page or a page related to the advertised product (merchandise) after performing a search. The server device 100 may also measure the search probability and CVR for the delivery of search-driven ads. For example, the server device 100 may calculate the percentage (or number) of users who performed a search and the percentage of users who achieved a conversion among the users to whom the ad was delivered.

[0028] Next, the server device 100 creates search-related information indicating whether or not a search was performed by the user, and the search keywords used by the user (step S6).

[0029] Next, the server device 100 acquires user-related information and advertising-related information (step S7).

[0030] Next, the server device 100 trains a model using machine learning by combining user-related information, advertising-related information, and search-related information (step S8). The above process is repeated (returning to step S1).

[0031] The server device 100 may implement the above mechanism using AI (Artificial Intelligence) such as GPT (Generative Pre-trained Transformer). GPT is a text generation AI and a language model capable of generating text using natural language processing.

[0032] The advantages of search engine advertising include the ability to drive traffic to web pages other than the advertiser's own site, the ability to cultivate users with moderate levels of interest, and the fact that it is not subject to data privacy regulations.

[0033] Furthermore, it promotes user search behavior triggered by advertisements, rather than relying on traditional ad clicks. Businesses with a search engine can track user conversions via searches.

[0034] [2-1. Image of search guidance] Please refer to Figure 2 to explain the concept of search guidance. Figure 2 is an explanatory diagram illustrating the concept of search guidance.

[0035] For example, the server device 100 predicts the search probability of a user who has seen an advertisement using a Deep Neural Network (DNN) model that has been machine-learned about the search probability of a user who has seen an advertisement. Note that the DNN model is just one example. In practice, a similar model may be used.

[0036] This allows the server device 100 to determine which users are likely to perform a search if an ad is displayed, and which users are unlikely to perform a search even if an ad is displayed. Based on the predicted search probability, the server device 100 then adjusts the bid price for ad delivery.

[0037] Furthermore, the server device 100 delivers advertisements to users who are likely to search for the advertised product. Users who are interested in the advertised product will use a search engine provided or linked to by the server device 100 to search for the advertised product and will be directed to the advertiser's website or the product page on the e-commerce site.

[0038] Furthermore, the server device 100 trains a DNN model with pairs of user-related information, advertising-related information, and search-related information. User-related information may be user features based on user attribute information, history information, etc. Advertising-related information may be advertiser features obtained / extracted from advertisement placement applications (insertion orders: IO). Search-related information includes whether or not a search was performed, and search keywords, etc.

[0039] In practice, the server device 100 may train its DNN model not only on search-related information, but also on action probabilities such as site visit probability (site traffic probability), ad click probability, search probability, and conversion probability. The server device 100 may train its DNN model on multiple action probabilities. Furthermore, the server device 100 may use the action probability as the probability of engagement (response to advertisements).

[0040] Furthermore, it is presumed that users interested in the advertised product will search using keywords such as "○○×× (product name)", "×× (part of product name)", "○○×× (product name) price", and "○○×× (product name) reviews".

[0041] To define searches for each campaign, it's necessary to determine which queries qualify as search keywords. However, doing this for each campaign individually would be impractical. Therefore, the server device 100 automatically extracts search keywords using a method that combines AI (or an AI API) such as GPT with natural language processing.

[0042] [2-2. Keyword Extraction] Server device 100 extracts campaign keywords using AI such as GPT (or an AI API). However, campaign information in the ad submission information is often unusable as is. For example, if the company name in the submission is "□□□ Beer Co., Ltd.", few users will search using this company name directly. What is needed is an abbreviation (shortened name) of the company name, such as "□□□," which is more likely to be used as an actual search keyword. Therefore, server device 100 inputs the submission information into AI such as GPT and extracts appropriate keywords.

[0043] For example, the server device 100 inputs information such as "Account name: □□□", "Campaign name: xxx", and "Ad creative" into an AI such as GPT, along with a prompt (prompt: instruction text) that says, "Extract the 'company name', 'abbreviated company name', 'product category', and 'product name' from the following information!".

[0044] The server device 100 then obtains keywords such as "Company name: □□□ Beer Co., Ltd.", "Abbreviation of company name: □□□", "Product category: Beer", and "Product name: ○○××" as output of AI such as GPT.

[0045] In practice, the server device 100 may acquire keywords such as "brand name," "abbreviation of company name," "product category," and "product name," as well as "brand name," "abbreviation of product name," "common name or nickname of company / product name," "catchphrase" or "catchphrase," "image character," "BGM," "CM series," and "name or abbreviation of the company's (famous) representative or founder." Furthermore, the server device 100 may also acquire keywords such as "company name / product name (abbreviation)" + "new product" or "limited time offer." In other words, the server device 100 is not limited to the above examples and may acquire keywords that are likely to be used in searches in relation to advertising, or keywords associated with advertising.

[0046] [2-3. Filter search queries by keyword] Server device 100 filters the search queries using extracted keywords. First, server device 100 performs primary filtering (partial matching) on ​​the output of AI such as GPT and the search queries. Here, server device 100 extracts from the search queries that partially match the output of AI such as GPT.

[0047] Next, the server device 100 performs secondary filtering (natural language processing). Here, the server device 100 vectorizes the output of AI such as GPT and the partially matching search query using BERT (Bidirectional Encoder Representations from Transformers), and determines the degree of agreement (similarity score) between the AI ​​output and the search query. Note that BERT is just one example. In practice, other vectorization methods may be used.

[0048] For example, the server device 100 may vectorize the estimated search keywords and search queries, calculate the cosine similarity of each vector, and select search queries that are similar to the estimated search keywords. Although the above describes the case using cosine similarity, in practice, it is also possible to use simply the similarity or distance of the vectorized data without using cosine similarity. In other words, the method for calculating the degree of agreement (similarity score) is not limited, and any method, including known methods, can be used.

[0049] The server device 100 then determines that a search query whose degree of similarity (similarity score) is above a threshold corresponds to a search keyword. This allows the server device 100 to distinguish between searches performed by a user that are related to advertisements and those that are unrelated to advertisements.

[0050] [2-4. Predicting users who are likely to search] The server device 100 predicts which users are likely to perform a search. The search prediction cycle will be explained with reference to Figure 3. Figure 3 is an explanatory diagram illustrating the image of the search prediction cycle.

[0051] (Process A) The server device 100 trains the DNN model with advertising-related information, user-related information, and search-related information.

[0052] (Process B) The server device 100 inputs advertising-related information and user-related information into the DNN model to perform search prediction, adjusts the bid price based on the results, and delivers advertisements.

[0053] (Process C) When a user performs a search in response to an advertisement delivery and a search result is generated, the server device 100 reflects this in the search-related information. Then, it trains the DNN model again (returning to Process A).

[0054] The server device 100 continuously performs search predictions by running the above processes A, B, and C in cycles. In the initial stages of distribution (immediately after distribution starts or for a certain period after the start), there is no search data, so search data from other campaigns is used for predictions.

[0055] [2-5. Another perspective] From another perspective, the server device 100 estimates potential search terms that a user U (user) viewing an advertisement might input, based on information related to the advertisement. In this case, the server device 100 estimates the advertiser's company name, an abbreviated version of the company name, the product category, the product name, or an abbreviated version of the product name as potential search terms. Alternatively, the server device 100 may have an AI generate potential search terms from the advertisement image.

[0056] The server device 100 then identifies search queries from the actual input that have a similarity to a candidate that exceeds a predetermined threshold. For example, the server device 100 extracts search queries containing candidates from the actual input search queries and identifies search queries whose similarity to the extracted search queries exceeds a predetermined threshold.

[0057] The server device 100 trains a model to output whether or not user U viewed an advertisement when it receives user U information and advertisement-related information of user U who entered a specified search query. The server device 100 also inputs the advertisement-related information to be delivered and user U information to the trained model and estimates the probability that user U will enter a search query after viewing an advertisement based on the model's output. Then, the server device 100 decides whether or not to deliver the advertisement based on the estimated probability.

[0058] [3. Example of terminal device configuration] Next, the configuration of the terminal device 10 will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the terminal device 10 according to this embodiment. As shown in Figure 4, the terminal device 10 comprises a communication unit 11, a display unit 12, an input unit 13, a positioning unit 14, a sensor unit 20, a control unit 30 (controller), and a storage unit 40.

[0059] (Communications Section 11) The communication unit 11 is connected to the network N by wire or wireless connection and transmits and receives information to and from the server device 100 via the network N. For example, the communication unit 11 can be implemented using a NIC (Network Interface Card) or an antenna.

[0060] (Display section 12) The display unit 12 is a display device that displays various information such as location information. For example, the display unit 12 may be a liquid crystal display (LCD) or an organic electro-luminescent display (OLED). The display unit 12 may also be a touch panel display, but is not limited to this.

[0061] (Input section 13) The input unit 13 is an input device that receives various operations from the user U. For example, the input unit 13 has buttons for inputting characters, numbers, etc. The input unit 13 may also be an input / output port (I / O port) or a USB (Universal Serial Bus) port. If the display unit 12 is a touch panel display, a part of the display unit 12 functions as the input unit 13. The input unit 13 may also be a microphone that receives voice input from the user U. The microphone may be wireless.

[0062] (Positioning unit 14) The positioning unit 14 receives signals (radio waves) transmitted from GPS (Global Positioning System) satellites and, based on the received signals, acquires position information (e.g., latitude and longitude) indicating the current position of the terminal device 10. In other words, the positioning unit 14 determines the position of the terminal device 10. Note that GPS is just one example of a GNSS (Global Navigation Satellite System).

[0063] Furthermore, the positioning unit 14 can determine its position using various methods other than GPS. For example, the positioning unit 14 may use various communication functions of the terminal device 10 to determine its position as an auxiliary positioning means for position correction, etc., as described below.

[0064] (Wi-Fi positioning) For example, the positioning unit 14 determines the location of the terminal device 10 by utilizing the Wi-Fi® communication function of the terminal device 10 and the communication network provided by each telecommunications company. Specifically, the positioning unit 14 determines the location of the terminal device 10 by performing Wi-Fi communication, etc., and determining the distance to nearby base stations and access points.

[0065] (Beacon positioning) Furthermore, the positioning unit 14 may determine the location using the Bluetooth® function of the terminal device 10. For example, the positioning unit 14 determines the location of the terminal device 10 by connecting to a beacon transmitter connected via the Bluetooth® function.

[0066] (Geomagnetic positioning) Furthermore, the positioning unit 14 determines the position of the terminal device 10 based on the geomagnetic pattern of the structure, which has been measured in advance, and the geomagnetic sensor provided by the terminal device 10.

[0067] (RFID positioning) Furthermore, if, for example, the terminal device 10 is equipped with an RFID (Radio Frequency Identification) tag function equivalent to that of a contactless IC card used at a train station ticket gate or in a store, or if it is equipped with a function to read RFID tags, the location where it was used will be recorded along with the information on the payment or other transactions made by the terminal device 10. The positioning unit 14 may determine the location of the terminal device 10 by acquiring such information. Alternatively, the location may be determined by an optical sensor or infrared sensor equipped in the terminal device 10.

[0068] The positioning unit 14 may, if necessary, determine the position of the terminal device 10 using one or a combination of the positioning means described above.

[0069] (Sensor unit 20) The sensor unit 20 includes various sensors mounted on or connected to the terminal device 10. The connection can be wired or wireless. For example, the sensors may be detection devices other than the terminal device 10, such as wearable devices or wireless devices. In the example shown in Figure 4, the sensor unit 20 includes an acceleration sensor 21, a gyro sensor 22, a barometric pressure sensor 23, a temperature sensor 24, a sound sensor 25, a light sensor 26, a magnetic sensor 27, and an image sensor (camera) 28.

[0070] The sensors 21-28 described above are merely examples and not limiting. In other words, the sensor unit 20 may be configured to include some of the sensors 21-28, or it may include other sensors such as humidity sensors in addition to or instead of the sensors 21-28.

[0071] The acceleration sensor 21 is, for example, a 3-axis acceleration sensor and detects the physical movement of the terminal device 10, such as its direction of movement, velocity, and acceleration. The gyro sensor 22 detects the physical movement of the terminal device 10, such as its tilt in the three axes, based on its angular velocity. The barometric pressure sensor 23 detects the atmospheric pressure around the terminal device 10, for example.

[0072] Since the terminal device 10 is equipped with the acceleration sensor 21, gyroscope 22, barometric pressure sensor 23, etc., it becomes possible to determine the position of the terminal device 10 using technologies such as pedestrian dead-reckoning (PDR) that utilize these sensors 21 to 23. This makes it possible to obtain indoor location information that is difficult to obtain with positioning systems such as GPS.

[0073] For example, a pedometer using an accelerometer 21 can calculate the number of steps, walking speed, and distance walked. Additionally, a gyroscope 22 can be used to determine the user U's direction of movement, gaze direction, and body tilt. Furthermore, the barometric pressure detected by the barometric pressure sensor 23 can be used to determine the altitude and floor number of the user U's terminal device 10.

[0074] The temperature sensor 24 detects, for example, the ambient temperature around the terminal device 10. The sound sensor 25 detects, for example, the ambient sound around the terminal device 10. The light sensor 26 detects the ambient illumination around the terminal device 10. The magnetic sensor 27 detects, for example, the Earth's magnetic field around the terminal device 10. The image sensor 28 captures an image of the area around the terminal device 10.

[0075] The aforementioned pressure sensor 23, temperature sensor 24, sound sensor 25, light sensor 26, and image sensor 28 can detect the surrounding environment and conditions of the terminal device 10 by detecting atmospheric pressure, temperature, sound, and illuminance, respectively, and by capturing images of the surroundings. Furthermore, it becomes possible to improve the accuracy of the location information of the terminal device 10 based on the surrounding environment and conditions.

[0076] (Control Unit 30) The control unit 30 includes, for example, a microcomputer having a CPU (Central Processing Unit) or MPU (Micro Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), input / output ports, and various circuits. Alternatively, the control unit 30 may be composed of hardware such as an integrated circuit (ASIC) or FPGA (Field Programmable Gate Array). The control unit 30 includes a transmission unit 31, a reception unit 32, and a processing unit 33.

[0077] (Transmitter 31) The transmission unit 31 can transmit various information, such as information input by the user U using the input unit 13, various information detected by sensors 21-28 mounted on or connected to the terminal device 10, and location information of the terminal device 10 determined by the positioning unit 14, to the server device 100 via the communication unit 11.

[0078] (Receiving unit 32) The receiving unit 32 can receive various information provided by the server device 100, as well as requests for various information from the server device 100, via the communication unit 11.

[0079] (Processing 33) The processing unit 33 controls the entire terminal device 10, including the display unit 12. For example, the processing unit 33 can output and display various information transmitted by the transmission unit 31 and various information received from the server device 100 by the reception unit 32 to the display unit 12.

[0080] (Storage unit 40) The storage unit 40 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as HDD (Hard Disk Drive), SSD (Solid State Drive), and optical discs. Various programs and various data are stored in this storage unit 40.

[0081] [4. Example of Server Device Configuration] Next, the configuration of the server device 100 according to the embodiment will be described using Figure 5. Figure 5 is a diagram showing an example of the configuration of the server device 100 according to the embodiment. As shown in Figure 5, the server device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0082] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection.

[0083] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as HDDs, SSDs, and optical discs. The storage unit 120 may store identification information (such as a user ID) indicating user U, as well as attribute information and history information (log data) of user U.

[0084] (Control unit 130) The control unit 130 is a controller, and is realized by executing various programs (corresponding to an example of an information processing program) stored in the internal storage device of the server device 100 using a storage area such as RAM as a working area, for example, by a CPU (Central Processing Unit), MPU (Micro Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), or FPGA (Field Programmable Gate Array). In the example shown in Figure 5, the control unit 130 has an acquisition unit 131, a prediction unit 132, an adjustment unit 133, a distribution control unit 134, an estimation unit 135, a determination unit 136, and a learning unit 137.

[0085] (Acquisition part 131) The acquisition unit 131 acquires the search query entered by the user U. For example, when the user U enters a search query into a search engine or the like and performs a keyword search, the acquisition unit 131 acquires the search query via the communication unit 110. In other words, the acquisition unit 131 acquires the keyword entered by the user U into the search box of a search engine, website, or application via the communication unit 110.

[0086] Furthermore, the acquisition unit 131 acquires user information about user U via the communication unit 110. For example, the acquisition unit 131 acquires identification information (such as user ID), location information, and attribute information of user U from user U's terminal device 10. The acquisition unit 131 may also acquire identification information and attribute information of user U when user U is registered. The acquisition unit 131 then stores the user information in the storage unit 120.

[0087] Furthermore, the acquisition unit 131 acquires various historical information (log data) indicating the user U's actions via the communication unit 110. For example, the acquisition unit 131 acquires various historical information indicating the user U's actions from the user U's terminal device 10, or from various servers based on the user ID, etc. The acquisition unit 131 then stores the various historical information in the storage unit 120.

[0088] Furthermore, the acquisition unit 131 acquires user-related information and advertising-related information. User-related information may be user features based on user U's attribute information, history information, etc. Advertising-related information may be advertiser features acquired / extracted from advertising placement applications (insertion orders: IO).

[0089] Furthermore, the acquisition unit 131 may, via the communication unit 110, accept bids and applications for advertising distribution, as well as submissions of advertisements (search engine advertising).

[0090] (Prediction unit 132) The prediction unit 132 predicts the search probability using a pre-trained model. For example, the prediction unit 132 uses a DNN model that has been machine-trained on the search probability of users who have seen an advertisement to predict the search probability of users who have seen an advertisement. In this case, the prediction unit 132 inputs user-related information and advertisement-related information into the DNN model and predicts the search probability of users who have seen an advertisement as an output (or based on the output).

[0091] (Adjustment section 133) The adjustment unit 133 adjusts the ad delivery bid price based on the predicted search probability.

[0092] (Distribution control unit 134) The distribution control unit 134 delivers search-driving advertisements to users who are expected to perform a search, based on the predicted search probability.

[0093] (Estimation part 135) The estimation unit 135 estimates the search keywords used for searches resulting from search-directed advertisements. In this case, the estimation unit 135 uses AI to estimate search keywords from the search-directed advertisements. For example, the estimation unit 135 extracts the company name, product name, abbreviation of the name, and product category as search keywords from the account name, campaign name, and ad creative of the search-directed advertisement.

[0094] In practice, the estimation unit 135 achieves automatic extraction of search keywords by combining AI such as GPT (or an AI API) with natural language processing.

[0095] (Judgment unit 136) The determination unit 136 determines which searches made by users who received search-direction ads used the estimated search keywords. The determination unit 136 may also identify or analyze searches that used the search keywords. In this case, the determination unit 136 filters the search queries made by users who received search-direction ads using the estimated search keywords.

[0096] For example, the determination unit 136 vectorizes the search query from the user to whom the search-direction ad was delivered and the estimated search keyword, determines the degree of match between the search query and the search keyword, and determines that the search uses a search keyword whose degree of match is above a threshold.

[0097] At this point, the determination unit 136 performs primary filtering by extracting search queries from users who have received search-direction advertisements that partially match the estimated search keywords. Furthermore, as a secondary filtering step, the determination unit 136 vectorizes the partially matching search queries and the estimated search keywords using BERT, determines the degree of match between the search queries and the search keywords, and identifies searches using search keywords with a match degree above a threshold.

[0098] The determination unit 136 then creates search-related information, including whether a search was performed and the search keywords.

[0099] (Learning Section 137) The learning unit 137 trains the model on pairs of user-related information about the user, advertising-related information about search-driving advertisements, and search-related information about whether a search was performed and the search keywords.

[0100] User-related information may include user features based on user attribute information and history information. Advertising-related information may include advertiser features obtained / extracted from advertisement placement applications (insertion orders: IO). Search-related information includes whether or not a search was performed and the search keywords.

[0101] [5. Processing Procedure] Next, the processing procedure by the server device 100 according to the embodiment will be described using Figure 6. Figure 6 is a flowchart of the processing procedure according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 130 of the server device 100.

[0102] For example, as shown in Figure 6, the prediction unit 132 of the server device 100 predicts the search probability of a user who has seen an advertisement using a DNN model that has been machine-learned about the search probability of a user who has seen an advertisement (step S101).

[0103] Next, the adjustment unit 133 of the server device 100 adjusts the bid price (bid) for ad delivery based on the predicted search probability (step S102).

[0104] Next, the distribution control unit 134 of the server device 100 delivers search-driving advertisements to users who are expected to perform a search, based on the predicted search probability (step S103).

[0105] Next, the estimation unit 135 of the server device 100 uses AI such as GPT to estimate the search keywords used for searches resulting from search-directed advertisements, and extracts company names, product names, abbreviations of names, and product categories as search keywords from the account name, campaign name, and ad creative of the search-directed advertisement (step S104).

[0106] Next, the determination unit 136 of the server device 100 filters the search queries of users who have received the search-direction advertisement using estimated search keywords. As a first-order filter, it extracts search queries that partially match the estimated search keywords from among the search queries of users who have received the search-direction advertisement (step S105).

[0107] Next, the determination unit 136 of the server device 100 performs a secondary filtering by vectorizing the partially matching search queries and the estimated search keywords using BERT, determining the degree of agreement between the search queries and the search keywords, and determining whether to perform a search using search keywords with an agreement degree equal to or greater than a threshold (step S106).

[0108] Next, the determination unit 136 of the server device 100 creates search-related information including whether or not a search was performed and the search keywords (step S107).

[0109] Next, the acquisition unit 131 of the server device 100 acquires user-related information about the user and advertising-related information about search-direction advertisements (step S108).

[0110] Next, the learning unit 137 of the server device 100 trains the model on sets of user-related information, advertising-related information, and search-related information (step S109).

[0111] [6. Variant Example] The terminal device 10 and server device 100 described above may be implemented in various other forms besides those of the embodiment described above. Therefore, the following describes modifications of the embodiment.

[0112] In the above embodiment, some or all of the processing performed by the server device 100 may actually be performed by the terminal device 10 (or an application running on the terminal device 10). For example, the processing may be completed in a standalone manner (by the terminal device 10 alone). In this case, the terminal device 10 is assumed to have the same functions as the server device 100 in the above embodiment. Furthermore, in the above embodiment, since the terminal device 10 is in cooperation with the server device 100, from the perspective of the user U, it appears as if the processing of the server device 100 is also being performed by the terminal device 10. In other words, from another perspective, it can be said that the terminal device 10 is equipped with the server device 100.

[0113] Furthermore, in the above embodiment, instead of filtering search queries by keyword, the server device 100 may extract searches from the search history in which the search query matches the keyword.

[0114] Furthermore, in the above embodiment, the server device 100 may limit the period between the display of the advertisement (impression) on the user's terminal device 10 and the user's search. For example, the server device 100 may only target searches performed within 30 minutes of delivering the advertisement to the user, and exclude searches performed more than 30 minutes later. The period between advertisement delivery and search can be set arbitrarily.

[0115] Furthermore, in the above embodiment, the server device 100 can also deliver search-driving advertisements to users who are likely to perform a search if an advertisement is displayed, thereby guiding users to listing advertisements displayed on the search results screen through searches on search engines triggered by the search-driving advertisements.

[0116] Furthermore, in the above embodiment, the search-driving advertisement may be a video advertisement or an audio advertisement. Alternatively, the search-driving advertisement may be an image advertisement consisting only of illustrations or photographs. The server device 100 may also display keywords when the user hovers over the search-driving advertisement. In other words, the search-driving advertisement can be any advertisement that induces the user's search behavior, and its form is not limited.

[0117] [7. Effects] As described above, the information processing device (terminal device 10 and server device 100) according to the present application is characterized by comprising: a prediction unit 132 that predicts the probability of a search using a trained model; a distribution control unit 134 that delivers search-guided advertisements to users who are expected to perform a search based on the predicted probability of a search; an estimation unit 135 that estimates the search keywords used in searches performed as a result of the search-guided advertisements; a determination unit 136 that determines whether a search performed by a user to whom a search-guided advertisement has been delivered uses the estimated search keywords; and a learning unit 137 that trains a model on user-related information about the user, advertising-related information about the search-guided advertisement, and search-related information about whether a search was performed and the search keywords.

[0118] This allows for the delivery of search-direction ads to users who visit the ad page via search.

[0119] Furthermore, the information processing device according to the present invention is characterized by further comprising an adjustment unit 133 that adjusts the bid price for ad delivery based on the predicted search probability.

[0120] This allows advertisers to be offered new services or advertising delivery options.

[0121] Furthermore, the estimation unit 135 uses AI to estimate search keywords from search-driving advertisements.

[0122] Since campaign information included in the submission data is often unusable as is, the AI ​​can be used to input the submission data and extract appropriate keywords.

[0123] For example, the estimation unit 135 extracts company name, product name, abbreviation of the name, and product category as search keywords from the account name, campaign name, and ad creative of the search-directed ad.

[0124] This allows for the efficient extraction of keywords that are highly likely to be used in searches.

[0125] Furthermore, the determination unit 136 filters the search queries made by users who have received search-direction advertisements using estimated search keywords.

[0126] This allows us to identify searches that are related to advertisements from among the searches performed by users. Furthermore, it allows us to exclude searches unrelated to advertisements and extract only those that are.

[0127] For example, the determination unit 136 vectorizes the search query from the user to whom the search-direction ad was delivered and the estimated search keyword, determines the degree of match between the search query and the search keyword, and determines that the search uses a search keyword whose degree of match is above a threshold.

[0128] This allows us to distinguish between searches using search keywords based on vector similarity.

[0129] At this time, the determination unit 136 performs primary filtering by extracting search queries from users who have received search-directed advertisements that partially match the estimated search keywords, and then performs secondary filtering by vectorizing the partially matching search queries and the estimated search keywords, determining the degree of match between the search queries and the search keywords, and determining searches that use search keywords with a degree of match equal to or greater than a threshold.

[0130] This allows for the extraction of search queries that partially match the search keywords from a vast number of search queries before determining the degree of match between the search query and the search keyword, thereby eliminating irrelevant search queries and significantly reducing the number of target search queries.

[0131] Through any or a combination of the above-described processes, the information processing device according to the present invention can deliver search-direction advertisements to users who visit the advertisement page via search.

[0132] [8. Hardware Configuration] Furthermore, the terminal device 10 and server device 100 according to the above-described embodiment are realized by a computer 1000 having a configuration such as that shown in Figure 7. The following explanation will use the server device 100 as an example. Figure 7 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0133] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The arithmetic unit 1030 can be implemented using, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array).

[0134] The primary storage device 1040 is a memory device, such as RAM (Random Access Memory), that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and can be implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. The secondary storage device 1050 may also be a removable storage medium such as USB (Universal Serial Bus) memory or SD (Secure Digital) memory card. The secondary storage device 1050 may also be cloud storage (online storage), NAS (Network Attached Storage), file server, etc.

[0135] The output I / F 1060 is an interface for transmitting information to be output to output devices 1010, such as displays, projectors, and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). The input I / F 1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, keypads, buttons, and scanners, and is implemented using, for example, USB.

[0136] Furthermore, the output interface 1060 and input interface 1070 may be wirelessly connected to the output device 1010 and input device 1020, respectively. In other words, the output device 1010 and input device 1020 may be wireless devices.

[0137] Furthermore, the output device 1010 and the input device 1020 may be integrated as a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as an input / output I / F.

[0138] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), 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.

[0139] The network interface 1080 receives data from other devices via network N and sends it to the computing unit 1030, and also transmits data generated by the computing unit 1030 to other devices via network N.

[0140] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output interface 1060 and the input interface 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0141] For example, when computer 1000 functions as a server device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the primary storage device 1040. Alternatively, the arithmetic unit 1030 of computer 1000 may load a program obtained from another device via the network interface 1080 onto the primary storage device 1040 and execute the loaded program. Furthermore, the arithmetic unit 1030 of computer 1000 may cooperate with other devices via the network interface 1080 and call and use program functions, data, etc., from other programs on other devices.

[0142] [9. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0143] 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 information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0144] 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.

[0145] For example, the server device 100 described above may be implemented using multiple server computers, and the configuration can be flexibly changed, such as by calling external platforms via APIs (Application Programming Interfaces) or network computing depending on the function.

[0146] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0147] 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]

[0148] 1. Information Processing System 10 Terminal devices 100 Server Devices 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Prediction Section 133 Adjustment section 134 Distribution Control Unit 135 Estimation Department 136 Judgment section 137 Learning Department

Claims

1. A prediction unit that predicts the search probability using a pre-trained model, A delivery control unit delivers search-driving ads to users who are expected to perform a search based on their predicted search probability, An estimation unit that estimates the search keywords used for searches initiated by the aforementioned search-driving advertisement, A determination unit that determines searches performed by users to whom the aforementioned search-driving advertisement was delivered, using estimated search keywords, A learning unit that trains the model on a set of user-related information about the user, advertising-related information about the search-driving advertisement, and search-related information about whether a search was performed and the search keywords. An information processing device characterized by comprising:

2. Adjustment unit that adjusts ad delivery bid prices based on predicted search probability. The information processing apparatus according to claim 1, further comprising:

3. The estimation unit uses AI to estimate search keywords from the search-driving advertisement. The information processing apparatus according to feature 1.

4. The estimation unit extracts company name, product name, abbreviation of the name, and product category as search keywords from the account name, campaign name, and ad creative of the search-directed ad. The information processing apparatus according to feature 1.

5. The determination unit filters the search queries made by users who have received the search-driving advertisement using estimated search keywords. The information processing apparatus according to feature 1.

6. The determination unit vectorizes the search query from the user to whom the search-driving advertisement was delivered and the estimated search keyword, determines the degree of match between the search query and the search keyword, and determines that the search uses the search keyword whose degree of match is above a threshold. The information processing apparatus according to feature 1.

7. The determination unit, As a primary filter, search queries that partially match the estimated search keywords are extracted from the search queries of users to whom the aforementioned search-driving advertisement was delivered. As a secondary filtering step, partially matching search queries and estimated search keywords are vectorized, the degree of matching between the search queries and search keywords is determined, and searches using search keywords with a matching degree above a certain threshold are determined. The information processing apparatus according to feature 1.

8. An information processing method performed by an information processing device, A prediction process that predicts the search probability using a pre-trained model, Based on the predicted search probability, the delivery process involves delivering search-driving ads to users who are expected to perform a search, and An estimation process for estimating the search keywords used in searches initiated by the aforementioned search-driving advertisements, A determination step to determine which searches were performed by users to whom the aforementioned search-driving advertisement was delivered, using estimated search keywords, A learning process in which the model is trained to learn combinations of user-related information about the user, advertising-related information about the search-driving advertisement, and search-related information about whether a search was performed and the search keywords. An information processing method characterized by including

9. A prediction procedure for predicting search probability using a pre-trained model, A delivery procedure for delivering search-driving ads to users who are expected to perform searches based on their predicted search probability, An estimation procedure for estimating the search keywords used in searches initiated by the aforementioned search-driving advertisements, A determination procedure for determining searches using estimated search keywords among searches performed by users to whom the aforementioned search-driving advertisement was delivered, A learning procedure for training the model on a set of user-related information about the user, advertising-related information about the search-driving advertisement, and search-related information about whether a search was performed and the search keywords. An information processing program characterized by causing a computer to execute it.

Images