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

Abstract

To streamline a marketing strategy.SOLUTION: An information processing device according to the present application includes: an estimation unit that estimates a relationship between predetermined target information and the parties involved; an acquisition unit that acquires behavior information of a user related to the target information; and a determination unit that determines the target information as an identification element related to the parties involved when the relationship estimated by the estimation unit and a utilization form of the target information indicated by the behavior information acquired by the acquisition unit satisfy a predetermined condition.SELECTED DRAWING: Figure 1

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] In recent years, with the rapid spread of the Internet, advertisement distribution via the Internet has become popular. In the field of advertisement distribution, there is keyword advertising, in which advertisements linked to keywords used in searches (e.g., search queries) are displayed on the search result display screen (e.g., see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-84992 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, while the search query that displays the advertisement is important, setting the search query requires complicated processing, so there is room for improvement in terms of improving the efficiency of the marketing strategy.

[0005] The present invention has been made in view of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can improve the efficiency of a marketing strategy. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the information processing device of the present invention comprises an estimation unit that estimates a relationship between specified target information and a related party, an acquisition unit that acquires behavioral information of a user regarding the target information, and a determination unit that, when the relationship estimated by the estimation unit and a usage pattern of the target information indicated by the behavioral information acquired by the acquisition unit satisfy specified conditions, determines the target information as an identifying element for the related party identified by the usage pattern. Effect of the Invention

[0007] According to the present invention, it is possible to improve the efficiency of a marketing strategy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of information stored in a search data storage unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in an identification word storage unit according to the embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating an example of an identification word determination process according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application 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 the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing method is executed by, for example, an information processing device 10 shown in Fig. 1.

[0011] In the following embodiment, the predetermined target information is a search query, and a case will be described in which it is determined whether the search query is used as an identification element for identifying an advertiser business. Note that, although the following describes a case in which the identification element is an identification word, the present invention is not limited to this, and the identification element may be any content such as an image or sound.

[0012] 1 is an information processing device that supports, for example, a contract for distribution of advertisement content with an advertiser. Specifically, for example, the information processing device 10 extracts an identification word that is an identification element of the advertiser.

[0013] For example, the identification word is proposed to the advertiser so that advertising content by the advertiser is displayed on a display screen that displays search results using the identification word extracted by the information processing device 10 as a search query.

[0014] For example, information processing device 10 acquires search data from search server 200 that operates a search site (step S01), and stores the acquired search data in a search data storage unit.

[0015] The search data here refers to, for example, data on the access history for search results for each search query used on a search site. In other words, the search data is data on what sites a user accessed when using what search query. Note that, among the search data, the search query is an example of target information, and the user's access history to sites is an example of user behavior information.

[0016] Next, the information processing device 10 performs a discrimination element determination process based on the search data (step S02). The information processing device 10, for example, extracts a search query from the search data and inputs it to a discrimination word estimation model.

[0017] For example, the discriminant word estimation model is a model that has learned the characteristics of discriminant words in advance and outputs the probability that an input search query is a discriminant word as a score. That is, the discriminant word estimation model is a model that estimates the relationship between a search query and an operator from the viewpoint of whether an input search query can be a discriminant word of a given operator.

[0018] The information processing device 10 also calculates the click occupancy rate based on the access history for each search query from the search data storage unit. The access history here refers to a history of which web pages the user U accessed in response to a search result using the search query. The information processing device 10 calculates the click occupancy rate by excluding, for example, access to advertisements displayed on the display screen of the search result from the access history.

[0019] For example, the information processing device 10 counts the number of accesses for each domain of the web pages accessed from the access history, and calculates the ratio of the number of accesses of a specific domain to the total number of accesses as the click occupancy rate.

[0020] In other words, if there is a concentration of accesses to the homepage of a specific business in response to the search results of a specific search query, it can be assumed that users are using the search query as an identification element to identify the business.

[0021] In other words, the information processing device 10 calculates the click share as an index for determining to what extent a target search query is recognized by users as an identification factor of a corresponding business.

[0022] Then, the information processing device 10 judges whether or not to set the corresponding search query as an identifying word based on the output result of the identifying word estimation model and the calculation result of the click share. For example, when the score, which is the output result of the identifying word estimation model, is equal to or greater than a predetermined threshold and the click share for a predetermined business is equal to or greater than a predetermined threshold, the information processing device 10 judges the search query as an identifying word, and when both conditions are not satisfied, does not judge the search query as an identifying word.

[0023] In other words, when a search query has sufficient characteristics of an identification word and the usage pattern of the user is treated as an identification factor of a predetermined business, the information processing device 10 determines the search query as an identification word and registers it in the identification word storage unit. Note that, in order to improve the accuracy of the identification word determination result, the information processing device 10 may, for example, appropriately adjust both thresholds.

[0024] For example, the identification words registered in the identification word storage unit are proposed to businesses that will be advertisers. The businesses that will be advertisers can then consider various marketing strategies, such as whether or not to deliver advertisements linked to the proposed identification words.

[0025] In this manner, the information processing device 10 according to the embodiment determines whether or not a search query is an identification word of a predetermined business operator, depending on the characteristics of the search query as an identification word and the usage pattern of the search query by the user.

[0026] As a result, the information processing device 10 according to the embodiment can automatically extract identification words from search data, for example, thereby making it possible to improve the efficiency of marketing strategies of each business operator.

[0027] 2. Example of the configuration of an information processing device Next, a configuration example of the information processing device 10 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 10 according to an embodiment. As shown in Fig. 2, the information processing device 10 has a communication unit 110, a control unit 120, and a storage unit 130.

[0028] The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0029] The storage unit 130 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. The storage unit 130 also has a search data storage unit 131, a word vector model storage unit 132, a discriminative word estimation model storage unit 133, and a discriminative word storage unit 134.

[0030] The search data storage unit 131 stores search data related to a search query used by a user and a web page visited by the user in response to a search result based on the search query. Fig. 3 is a diagram illustrating an example of information stored in the search data storage unit 131 according to the embodiment.

[0031] 3, the search data storage unit 131 stores information items such as "search query," "user ID," "date and time," and "URL" in association with each other. "Search query" indicates a search query used by a user.

[0032] "User ID" refers to an identifier for identifying a user in search data. Note that the search data storage unit 131 may store various information related to the user instead of the user ID. The various information here may include, for example, information related to the user's age, sex, residential area, annual income, hobbies, and the like. In other words, the search data storage unit 131 may store information necessary for classifying the attributes of the user who uses the search query.

[0033] The "date and time" indicates the date and time when the user used the corresponding search query. The "URL" indicates the URL of the web page that the user accessed in response to the search results of the corresponding search query.

[0034] Returning to the description of Fig. 2, a description will be given of the word vector model storage unit 132. The word vector model storage unit 132 stores a word vector model for converting a search query into a word vector.

[0035] A word vector model is a model that is trained to vectorize search queries using techniques such as W2V and output similar word vectors for similar search queries.

[0036] The discriminative word estimation model storage unit 133 stores the discriminative word estimation model. The discriminative word estimation model is, for example, a model that learns the features (word vectors) of discriminative words, and outputs the possibility that an input search query is a discriminative word as a score. For example, the discriminative word estimation model is generated by learning using word vectors of a huge number of discriminative words as teacher data.

[0037] The identification word storage unit 134 stores identification words. Fig. 4 is a diagram showing an example of information stored in the identification word storage unit 134 according to the embodiment. In the example shown in Fig. 4, the identification word storage unit 134 stores information items such as "identification word" and "business operator" in association with each other.

[0038] "Identification word" indicates the search query determined as the identification word. "Business" indicates the business identified by the identification word. In the example shown in the figure, it is shown that the identification word W1 is a word that identifies the business G01.

[0039] Returning to the explanation of Fig. 2, the control unit 120 will be described. The control unit 120 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, executing various programs stored in a storage device inside the information processing device 10 using a RAM as a working area.

[0040] As shown in FIG. 2, the control unit 120 includes an acquisition unit 121, an estimation unit 122, a calculation unit 123, and a determination unit .

[0041] The acquiring unit 121 acquires search data from, for example, the search server 200 (see FIG. 1 ). For example, the acquiring unit 121 acquires, as the search data, data related to a search query used by a user, an identifier for identifying the user (for example, a user ID), the date and time when the search query was used, and the URL of a web page accessed using the search query, and stores the data in the search data storage unit 131.

[0042] The acquisition unit 121 corresponds to an example of an acquisition unit that acquires behavioral information of a user related to target information. The behavioral information here corresponds to data related to the URL of a web page accessed using a search query.

[0043] Furthermore, the acquisition unit 121 may acquire, for example, in addition to the search data, posted information posted on various SNSs (Social Networking Services). For example, the acquisition unit 121 may extract and acquire words indicating a business and words related to a product name from the posted information by using a predetermined language processing. As a specific example, the business A and product B (product name) may be extracted and acquired from posted information such as "Product B by business A is good, isn't it?" That is, in this case, the identification element to be determined does not need to be a search query, and may be a keyword used by a user other than the search query.

[0044] The estimation unit 122 estimates a relationship between the target information on the content and the related person, and passes a score as an estimation result to the determination unit 124. The estimation unit 122 estimates a relationship between the search query, which is the target information, and the business. First, the estimation unit 122 refers to the search data storage unit 131 and extracts data related to the search query whose sampling count has reached a predetermined number.

[0045] Next, the estimation unit 122 inputs the extracted search query to a word vector model stored in the word vector model storage unit 132, thereby converting the search query into a word vector.

[0046] Next, the estimation unit 122 calculates a score related to the probability that the search query is a discriminative word by inputting the word vector to a discriminative word estimation model stored in the discriminative word estimation model storage unit 133. That is, the estimation unit 122 estimates the relationship between the search query and the business operator from the viewpoint of whether the search query can be a discriminative word of the business operator.

[0047] The calculation unit 123 calculates a click share related to the usage pattern of the search query. For example, the calculation unit 123 analyzes URLs related to a predetermined search query from the search data, and calculates the number of accesses for each domain.

[0048] The ratio of the number of accesses to a specific domain to the total number of accesses is calculated as a click occupancy rate and passed to the determination unit 124. In other words, when accesses are concentrated on a web page of a specific business due to a specific search query, the search query can be considered to be widely used as an identification factor for the specific business, but when the accesses are distributed among a plurality of businesses, it is difficult to say that the search query is widely used as an identification factor.

[0049] Therefore, the click share of each domain is an indicator of whether it can function as an identifying factor in terms of whether the way search queries are used is to identify a specific business.

[0050] If the relationship estimated by the estimation unit 122 and the usage pattern of the target information indicated by the behavioral information acquired by the acquisition unit 121 satisfy a predetermined condition, the determination unit 124 determines the target information as an identification element related to the related person.

[0051] For example, the determination unit 124 determines whether a search query used by a user is an identifying word of a particular business operator based on a score related to the characteristics of the identifying word estimated by the estimation unit 122 and a click share calculated by the calculation unit 123.

[0052] For example, the determination unit 124 determines, as an identification word, a search query in which the score regarding the characteristics of the identification word estimated by the estimation unit 122 is a predetermined value or more and the click occupancy rate calculated by the calculation unit 123 is a predetermined value or more.

[0053] That is, the determination unit 124 determines a search query that meets the above conditions as an identification word for identifying a business entity that occupies a high position in click share, and registers the identification word and the business entity in the identification word storage unit 134.

[0054] The determination unit 124 may register an identification word for each user attribute, for example. This is because it is assumed that the same search query may indicate different businesses depending on the user's age, residential area, etc.

[0055] Therefore, for example, the calculation unit 123 may calculate a click occupancy rate for each user attribute, and the determination unit 124 may determine the search query as an identification word based on the result of the calculation.

[0056] This allows the determination unit 124 to extract an appropriate identification word according to the user attributes. Note that any method may be used as the method for classifying the user attributes.

[0057] [3. Processing flow] Next, a process procedure executed by the information processing device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of an identification word determination process according to the embodiment.

[0058] 5, first, the information processing device 10 acquires search data (step S101) and converts the search query into a vector (step S102). Next, the information processing device 10 inputs the vector of the search query into a discriminative word estimation model to calculate a score related to the discriminative word (step S103).

[0059] Next, the information processing device 10 calculates a click occupancy rate for the search query (step S104), and determines whether or not both the results of steps S103 and S104 satisfy the condition of the identification word (step S105).

[0060] If it is determined in step S105 that the condition of the identification word is satisfied (step S105; Yes), the information processing device 10 determines the corresponding search query as an identification word (step S106), and ends the process.

[0061] Furthermore, when it is determined in step S105 that the condition of the identification word is not satisfied (step S105; No), the information processing device 10 skips the process in step S106 and ends the process.

[0062] 4. Modifications In the above embodiment, for example, the case where the target information is a search query and the related party is a business operator has been described, but the present invention is not limited to this. The target information may be any content such as a sound or an image, and the related party may be, for example, an artist or a copyright holder. In this case, for example, the information processing device 10 may determine whether the sound or image that is the target information is an identification element for identifying the artist.

[0063] 5. Effects The information processing device 10 according to the embodiment described above includes an estimation unit 122 that estimates a relationship between predetermined target information and a related person, an acquisition unit 121 that acquires behavioral information of a user related to the target information, and a determination unit 124 that determines the target information as an identification element related to the related person when the relationship estimated by the estimation unit 122 and the usage pattern of the target information indicated by the behavioral information acquired by the acquisition unit satisfy a predetermined condition. Therefore, the information processing device 10 according to the embodiment can improve the efficiency of a marketing strategy.

[0064] Moreover, the estimation unit 122 according to the embodiment described above estimates the relationship between the target information and the related person by using a model that has learned the characteristics of the identification element. Therefore, according to the information processing device 10 according to the embodiment, it is possible to estimate the relationship from the viewpoint of whether the target information has the characteristics of the identification element, and therefore it is possible to appropriately determine the identification element.

[0065] Moreover, the estimation unit 122 according to the embodiment described above uses a keyword as target information to estimate a relationship, and the determination unit 124 determines the keyword as an identification element when the relationship and the usage pattern of the keyword satisfy a predetermined condition. Therefore, according to the information processing device 10 according to the embodiment, it is possible to appropriately determine an identification word.

[0066] Moreover, the estimation unit 122 according to the embodiment described above estimates a relationship using a search query, which is a keyword used by a user, as target information, and the determination unit 124 determines the search query as an identification element when the relationship and the usage pattern of the search query satisfy a predetermined condition. Therefore, according to the information processing device 10 according to the embodiment, it is possible to appropriately determine whether the search query can be an identification word.

[0067] Moreover, the acquisition unit 121 according to the embodiment described above acquires information on an access history selected by a user in response to a search result based on a search query as behavioral information, and the determination unit 124 determines the search query as an identification element when the access history satisfies a predetermined condition. Therefore, according to the information processing device 10 according to the embodiment, a large amount of behavioral information can be easily acquired, and therefore an identification word can be accurately determined.

[0068] Furthermore, the determination unit 124 according to the embodiment described above determines the search query as an identification element when the click occupancy rate of the domain related to the related person included in the access history exceeds a predetermined value. Therefore, according to the information processing device 10 according to the embodiment, it is possible to determine the identification word while appropriately reflecting the usage pattern of the user, thereby improving the accuracy of the determination of the identification word.

[0069] Moreover, the acquisition unit 121 according to the embodiment described above acquires information posted by a user as behavioral information, and when a keyword extracted from the posted information satisfies a predetermined condition, determines the keyword as an identification element. Therefore, according to the information processing device 10 according to the embodiment, for example, information posted to an SNS or the like can be used to determine an identification word, so that it is possible to determine an identification word for various keywords other than a search query.

[0070] Moreover, the estimation unit 122 according to the embodiment described above uses an image as target information to estimate a relationship with a related person, and the determination unit 124 determines the image as an identification element when the relationship and the usage form of the image satisfy a predetermined condition. Therefore, according to the information processing device 10 according to the embodiment, it is possible to determine whether an image is a symbol for identifying a related person, and therefore to determine whether an image is an identification element for various contents.

[0071] [6. Hardware Configuration] The information processing device 10 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0072] The CPU 1100 operates and controls each unit based on a program 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 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0073] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0074] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 6, the output devices and the input devices are collectively referred to as "input / output devices") via an 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.

[0075] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The 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.

[0076] For example, when the computer 1000 functions as the information processing device 10 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 120. 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 the network N.

[0077] 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 embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0078] [7. Other] Furthermore, among the processes described in the above embodiments and modifications, 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 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 arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0079] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.

[0080] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0081] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, the acquisition unit 121 can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0082] 10. Information processing device 110 Communications Department 120 Control section 121 Acquisition Department 122 Estimation Department 123 Calculation section 124 Judgment section 130 Storage section 131 Search data storage unit 132 Word Vector Model Storage 133 Discrimination word estimation model memory unit 134 Identification word storage unit 200 Search Server

Claims

1. An estimation unit that estimates a relationship between predetermined target information and a related person; An acquisition unit that acquires user behavior information related to the target information; a determination unit that, when the relationship estimated by the estimation unit and a usage pattern of the target information indicated by the behavioral information acquired by the acquisition unit satisfy a predetermined condition, determines the target information as an identification element related to the related person identified by the usage pattern; An information processing device comprising:

2. The estimation unit is Using a model that has learned the characteristics of the identification element, the relationship between the target information and the person concerned is estimated.

2. The information processing apparatus according to claim 1,

3. The estimation unit is Using keywords as the target information, the relationship is estimated; The determination unit is If the relationship and the usage pattern of the keyword satisfy a predetermined condition, the keyword is determined to be the discrimination element.

3. The information processing device according to claim 1, wherein:

4. The estimation unit is A search query, which is the keyword used by the user, is used as the target information to estimate the relationship; The determination unit is If the relationship and the usage pattern of the search query satisfy a predetermined condition, the search query is determined to be the identification element.

4. The information processing apparatus according to claim 3,

5. The acquisition unit is acquiring information regarding an access history of the user to a search result based on the search query as the behavioral information; The determination unit is If the access history satisfies a predetermined condition, the search query is determined to be the distinguishing element.

5. The information processing apparatus according to claim 4,

6. The determination unit is determining that the search query is the identifying element when a click occupancy rate of a domain related to the person included in the access history exceeds a predetermined value; 6. The information processing device according to claim 5,

7. The acquisition unit is Acquires posted information posted by the user as the behavioral information; If the keyword extracted from the posted information satisfies a predetermined condition, the keyword is determined to be the identification element.

7. The information processing device according to claim 3, wherein:

8. The estimation unit is Using an image as the target information, a relationship with the person concerned is estimated; The determination unit is When the relationship and the usage form of the image satisfy a predetermined condition, the image is determined to be the identification element.

8. The information processing device according to claim 1,

9. 1. A computer-implemented information processing method, comprising: An estimation step of estimating a relationship between predetermined target information and a related person; An acquisition step of acquiring user behavior information related to the target information; a determination step of determining, when the relationship estimated by the estimation step and a usage pattern of the target information indicated by the behavioral information acquired by the acquisition step satisfy a predetermined condition, the target information as an identification element related to the related person identified by the usage pattern; 13. An information processing method comprising:

10. An estimation procedure for estimating a relationship between predetermined target information and a related person; An acquisition step of acquiring user behavior information related to the target information; a determination step of determining, when the relationship estimated by the estimation step and a usage pattern of the target information indicated by the behavioral information acquired by the acquisition step satisfy a predetermined condition, the target information as an identification element related to the related person identified by the usage pattern; An information processing program characterized by causing a computer to execute the above.

Images