advertising device

Abstract

An advertising device, method, and program are provided that perform advertising that meets user needs based on a computer-based interaction history. [Solution] The advertising device 100 has a dialogue history storage means 130 that stores dialogue history information using a computer for each user, a dialogue history analysis means 150 that analyzes the dialogue history information and extracts combinations of topics and products discussed in the dialogue, a model generation means 160 that trains a learning dataset consisting of combinations of topics and products and generates a machine learning model that outputs a specific product when a topic is input, a topic extraction means 170 that analyzes a dialogue conducted by a single user and extracts a single topic discussed in the dialogue, a product information generation means 180 that inputs a single topic to the trained machine learning model and outputs a specific product, and an advertisement execution means 190 that performs processing to execute an advertisement for a specific product to a single user.

Description

[Technical Field]

[0001] Regarding advertising techniques. [Background technology]

[0002] Advertising is the active dissemination of information about products and services to the public in order to promote sales of those products and services. Traditionally, advertising for products and services has been frequent, but it has been difficult to carry out effective advertising. Under such circumstances, technological developments to improve the effectiveness of advertisements are being actively carried out. For example, Patent Document 1 proposes a technology for appropriately determining advertisements to be distributed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6125700 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology has a problem in that it is not possible to fully grasp customer needs and to implement advertisements that meet those needs.

[0005] In view of the above problems, the present invention has an object to provide an advertising device that performs advertising that meets the needs of a user based on a conversation history using a computer. [Means for solving the problem]

[0006] One form of the disclosed advertising device is characterized by having: a dialogue history storage means for storing dialogue history information using a computer for each user; a dialogue history analysis means for analyzing the dialogue history information and extracting combinations of topics and products discussed in the dialogue; a model generation means for training a learning dataset consisting of combinations of the topics and the products and generating a machine learning model that outputs a specific product when the topic is input; a topic extraction means for analyzing a dialogue conducted by one of the users and extracting one of the topics discussed in the dialogue; a product information generation means for inputting the one topic to the trained machine learning model and outputting one of the specific products; and an advertising execution means for executing an advertisement for the one specific product to the one user. [Effects of the Invention]

[0007] The disclosed advertising device performs advertisements that meet the needs of users based on a conversation history using a computer. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing an outline of an advertising device according to an embodiment of the present invention; [Figure 2] FIG. 2 is a functional block diagram of an advertising device according to the present embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a hardware configuration of an advertising device according to the present embodiment. [Figure 4] 10 is a flowchart illustrating a flow of a processing example performed by the advertising device according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described with reference to the drawings. (Operation principle of the advertising device according to this embodiment)

[0010] The operation principle of an advertising device 100 according to this embodiment (hereinafter simply referred to as "the device") will be described with reference to Figures 1 and 2. Figure 1 is a diagram showing the connection relationship between the device 100 and other devices, and Figure 2 is a functional block diagram of the device 100.

[0011] 1, the device 100 is connected to a user terminal 310 operated by a user 300 and other devices 320 for advertisement distribution via a communication network 330. The communication network 330 may be either wired or wireless. The user terminal 310 may be a mobile information terminal such as a smartphone or a personal computer.

[0012] As shown in FIG. 2, the device 100 includes a learning data storage means 110, a model information storage means 120, a dialogue history storage means 130, a purchase history storage means 140, a dialogue history analysis means 150, a model generation means 160, a topic extraction means 170, a product information generation means 180, and an advertisement execution means 190. The training data storage means 110 stores a training data set 270, which will be described later. The model information storage means 120 stores parameters that define the operation of the machine learning model 270, which will be described later.

[0013] The dialogue history storage means 130 stores dialogue history information 230 using a computer for each user 300. The dialogue history storage means 130 stores dialogue history information 230 with the dialogue system for each user 300. The purchase history storage means 140 stores purchase history information 290 for each user 300.

[0014] The device 100 may not directly have the storage means 110 , 120 , 130 , and 140 , but may use external storage means 110 , 120 , 130 , and 140 connected via the communication network 330 .

[0015] The dialogue history analysis means 150 analyzes the dialogue history information 230 stored in the dialogue history storage means 130 and extracts combinations 260 of topics 240 and products 250 discussed in individual dialogues 220 .

[0016] The dialogue history analysis means 150 also analyzes the dialogue history information 230 stored in the dialogue history storage means 130 and the purchase history information 290 stored in the purchase history storage means 140. The dialogue history analysis means 150 may also be configured to extract combinations 260 of topics 240 discussed in individual dialogues 220 and products 250 purchased by the dialogue host 300 within a predetermined period of time since the dialogue 220 was held.

[0017] The model generation means 160 trains a training data set 270 consisting of combinations 260 extracted by the dialogue history analysis means 150, and generates a machine learning model 280 that outputs a specific product 250 when a topic 240 is input. Note that the training algorithm in the model generation means 160 is not particularly limited.

[0018] The topic extraction means 170 analyzes a dialogue 220 conducted by one user 300, and extracts one topic 240 discussed in the dialogue 220. The topic extraction means 170 analyzes a dialogue 220 currently being conducted by one user 300, and extracts one topic 240 discussed in the dialogue 220.

[0019] The product information generating means 180 inputs one topic 240 extracted by the topic extracting means 170 to the trained machine learning model 280, and causes it to output one specific product 250.

[0020] The advertisement execution means 190 executes a process of executing an advertisement 210 for one specific product 250 obtained by the product information generation means 180 for one user 300. The advertisement 210 may be executed directly by the device 100, or the advertisement execution means 190 may instruct an external device 320 to execute the advertisement 210. The advertisement 210 may be executed using any advertising medium or advertising method, and may be executed in a manner in which, for example, user terminal identification information (e.g., an advertisement ID or an advertisement identifier) ​​is specified and the advertisement 210 is delivered to a user terminal 310 operated by one user 300. Based on the above-described operating principle, the device 100 performs advertisements 210 that meet the needs of the user 300 based on the computer-assisted interaction history 230 . (Hardware configuration of advertising device according to this embodiment)

[0021] An example of the hardware configuration of the present device 100 will be described using Fig. 3. Fig. 3 is a diagram showing an example of the hardware configuration of the present device 100. As shown in Fig. 3, the present device 100 has a CPU (Central Processing Unit) 510, a ROM (Read-Only Memory) 520, a RAM (Random Access Memory) 530, an auxiliary storage device 540, a communication I / F 550, an input device 560, a display device 570, and a storage medium I / F 580.

[0022] CPU 510 is a device that executes programs stored in ROM 520, performs arithmetic processing on data loaded into RAM 530 in accordance with program instructions, and controls the entire device 100. ROM 520 stores programs and data to be executed by CPU 510. When CPU 510 executes a program stored in ROM 520, the programs and data to be executed are loaded into RAM 530, and RAM 530 temporarily holds the arithmetic data during the calculation.

[0023] The auxiliary storage device 540 is a device that stores the OS (Operating System), which is basic software, the application program according to this embodiment, and other related data. The auxiliary storage device 540 is, for example, a hard disk drive (HDD) or flash memory, and includes the learning data storage means 110, the model information storage means 120, the interaction history storage means 130, and the purchase history storage means 140.

[0024] The communication I / F 550 is an interface for connecting to a communication network 330 such as a wired or wireless LAN (Local Area Network) or the Internet, and for transmitting and receiving data to and from other devices 310 and 320 that provide communication functions.

[0025] The input device 560 is a device such as a keyboard for inputting data to the device 100. The display device (output device) 570 is a device formed of an LCD (Liquid Crystal Display) or the like, and functions as a user interface when the user uses the functions of the device 100 or when making various settings. The storage medium I / F 580 is an interface for sending and receiving data to and from a storage medium 590 such as a CD-ROM, DVD-ROM, or USB memory.

[0026] Each of the means included in device 100 may be realized by CPU 510 executing a program corresponding to each of the means stored in ROM 520 or auxiliary storage device 540. Each of the means included in device 100 may also be realized by hardware that performs the processing associated with the means. Alternatively, device 100 may be caused to execute the program by loading the program according to the present invention from an external server device via communication I / F 550 or from storage medium 590 via storage medium I / F 580. (Processing example by advertising device according to the present embodiment) An example of processing by the device 100 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing the flow of an example of processing by the device 100.

[0027] In S10, the dialogue history analysis means 150 analyzes the dialogue history information 230 stored in the dialogue history storage means 130, and extracts combinations 260 of topics 240 and products 250 discussed in individual dialogues 220.

[0028] The dialogue history analysis means 150 also analyzes the dialogue history information 230 stored in the dialogue history storage means 130 and the purchase history information 290 stored in the purchase history storage means 140. The dialogue history analysis means 150 may also be configured to extract combinations 260 of topics 240 discussed in individual dialogues 220 and products 250 purchased by the dialogue host 300 within a predetermined period of time since the dialogue 220 was held.

[0029] In S20, the model generation means 160 trains a training data set 270 consisting of the combinations 260 extracted in S10, and generates a machine learning model 280 that outputs a specific product 250 when a topic 240 is input. Note that the training algorithm in the model generation means 160 is not particularly limited.

[0030] In S30, the topic extraction means 170 analyzes a dialogue 220 conducted by one user 300, and extracts one topic 240 discussed in the dialogue 220. The topic extraction means 170 analyzes a dialogue 220 currently being conducted by one user 300, and extracts one topic 240 discussed in the dialogue 220.

[0031] In S40, the product information generation means 180 inputs the one topic 240 extracted in S30 to the machine learning model 280 trained in S20, and causes it to output one specific product 250.

[0032] In S50, the advertisement execution means 190 executes a process of executing an advertisement 210 for one specific product 250 obtained in S40 for one user 300. The advertisement 210 may be executed directly by the device 100, or the advertisement execution means 190 may instruct an external device 320 to execute the advertisement 210. The advertisement 210 may be executed using any advertising medium or advertising method, and may be executed in a manner in which, for example, user terminal identification information (e.g., an advertisement ID or an advertisement identifier) ​​is specified and the advertisement 210 is delivered to a user terminal 310 operated by one user 300.

[0033] By carrying out the above-mentioned processing, the device 100 performs advertisement 210 that meets the needs of the user 300 based on the interaction history 230 using a computer.

[0034] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and variations are possible within the scope of the gist of the present invention as defined in the claims. [Explanation of symbols]

[0035] 100 Advertising Devices 110 Learning data storage means 120 Model information storage means 130 Dialogue history storage means 140 Purchase history storage means 150 Dialogue History Analysis Method 160 Model Generation Method 170 Topic extraction means 180 Product information generation means 190 Advertising Execution Methods 210 Advertisements 220 Dialogue 230 Dialogue history information 240 Topics 250 items 260 Topic and Product Combinations 270 training datasets 280 Machine Learning Models 290 Purchase history information 300 users 310 User Terminals 320 Advertising distribution equipment 330 Communication Network 510 CPU 520 ROM 530 RAM 540 Auxiliary storage 550 Communication Interface 560 Input Device 570 Output Device 580 Storage Media Interface 590 Storage medium

Claims

1. a dialogue history storage means for storing dialogue history information using a computer for each user; a dialogue history analysis means for analyzing the dialogue history information and extracting combinations of topics and products discussed in the dialogue; a model generation means for generating a machine learning model that learns a learning dataset consisting of a combination of the topic and the product, and that outputs a specific product when the topic is input; a topic extraction means for analyzing a conversation carried out by one of the users and extracting one of the topics discussed in the conversation; a product information generation means for inputting the one topic to the trained machine learning model and outputting one of the specific products; and an advertisement execution means for executing an advertisement for the one specific product to the one user.

2. a purchase history storage means for storing purchase history information for each user; the dialogue history analysis means analyzes the dialogue history information and the purchase history information, and extracts combinations of the topic and the product purchased by the dialogue host within a predetermined period from the time the dialogue was held; The advertising device according to claim 1, characterized in that the model generation means causes the machine learning model to learn a learning dataset consisting of combinations of the topic and products purchased by the conversation host within a predetermined period from the time the conversation took place.

3. a training data storage means for storing the training data set; The advertising device according to claim 1 , further comprising: a model information storage means for storing parameters that define the operation of the machine learning model.

4. An advertising method carried out by a computer having an interaction history storage means for storing interaction history information using the computer for each user, a step in which a dialogue history analysis means analyzes the dialogue history information and extracts combinations of topics and products discussed in the dialogue; a step in which a model generation means trains a training data set consisting of a combination of the topic and the product, and generates a machine learning model that outputs a specific product when the topic is input; A step in which a topic extraction means analyzes a conversation performed by one of the users and extracts one of the topics discussed in the conversation; a step in which a product information generation means inputs the one topic into the trained machine learning model and outputs one of the specific products; an advertisement execution means for executing an advertisement for the one specific product to the one user.

5. The computer includes a purchase history storage means for storing purchase history information for each user, the dialogue history analysis means analyzes the dialogue history information and the purchase history information, and extracts combinations of the topic and the product purchased by the dialogue host within a predetermined period from the time the dialogue was held; The advertising method according to claim 4, characterized in that the model generation means causes the machine learning model to learn a learning dataset consisting of combinations of the topic and products purchased by the conversation host within a predetermined period from the time the conversation took place.

6. 5. The advertising method according to claim 4, wherein the computer comprises a training data storage means for storing the training data set, and a model information storage means for storing parameters that define the operation of the machine learning model.

7. An advertising program for causing a computer to execute the method according to any one of claims 4 to 6.

Images