JP7607692B2 - Information processing system, information processing method, and information processing device - Google Patents

Description

The present invention relates to an information processing system, an information processing method, and an information processing device that process log information including the usage history of web content by web users.

Log information including the usage history of web content by web users may be used to understand the behavior and interests of web users (see, for example, Patent Document 1). The device described in Patent Document 1 accepts input of download history information about files (content) downloaded by the user, estimates the user's interests according to the file formats included in the download history information, and registers the estimated user's interests in a database.

JP 2013-242718 A

Incidentally, information regarding the area where a Web user is located (hereinafter referred to as location) can be used for various purposes. For example, it is desirable to be able to estimate the location of a Web user based on log information regarding the usage history of Web content.
On the other hand, the location of a Web user can be estimated from information such as an IP address contained in the log information. However, it is desirable to be able to estimate the location area of a Web user with higher accuracy, and there is a demand for the development of a system, device, and method that can estimate the location of a Web user with a method with improved accuracy compared to the above estimation methods.

The present invention has been made in consideration of the above circumstances, and aims to achieve the following objectives, specifically, to provide an information processing system, method, and device for solving the problems of the conventional technology and accurately estimating the location of a web user.

To achieve the above object, the information processing system of the present invention is characterized by comprising: a first acquisition unit that acquires first log information including a usage history of Web content by a Web user and first identification information assigned to a terminal used when using the Web content; an area estimation unit that estimates a receiving area based on acquired information obtained according to a receiving area when broadcast content is received by a receiving device of the broadcast user; and an association unit that associates the estimation result of the receiving area based on the acquired information to the first log information based on the correspondence between the second identification information assigned to the receiving device and the first identification information.

The information processing system of the present invention can more accurately estimate the location of a web user by utilizing first log information related to the usage history of web content and identification information (second identification information) assigned to the receiving device that received the broadcast content.

The information processing system may further include a second acquisition unit that acquires second log information including a usage history of the broadcast content by the broadcast user and the second identification information. In this case, the acquired information may be associated with the second log information.
According to the above configuration, the acquired information is acquired in association with the second log information regarding the usage history of the broadcast content, and the location of the Web user can be more accurately estimated by utilizing the acquired information and the first log information.

Furthermore, data indicating the correspondence between the second identification information and the first identification information may be stored in the storage device. In this case, the associating unit may associate the estimation result of the receiving area based on the acquired information associated with the second log information with the first log information including the first identification information corresponding to the second identification information included in the second log information.
According to the above configuration, even if the second identification information and the first identification information are different, it is possible to appropriately identify the correspondence between the second identification information and the first identification information from the data stored in the storage device. Then, based on the correspondence, it is possible to appropriately determine the first log information to which the estimation result of the reception area is to be associated.

In addition, in the above correspondence relationship, a first identification information may be associated with a second identification information assigned to a receiving device of a broadcast user who is the same as the Web user who uses the terminal to which the first identification information is assigned.
According to the above configuration, it is possible to appropriately define the correspondence relationship between the second identification information and the first identification information, and therefore it is possible to more appropriately determine the first log information to be associated with the estimation result of the reception area based on the correspondence relationship.

The first log information may include identification information of the Web user. In this case, the associating unit may associate the identification information of the Web user in the first log information with an estimation result of the receiving area based on the acquired information.
According to the above configuration, the reception area estimation result is associated with the identification information of the Web user, so that the location of the Web user can be estimated more accurately.

The acquired information may also include identification information of a provider of the broadcast content used by the broadcast user. In this case, the area estimation unit may estimate the receiving area based on the correspondence between the provider's identification information and the provider's location, and the provider's identification information included in the acquired information.
According to the above configuration, it is possible to accurately estimate the reception area when the broadcast content is received by the receiving device from the identification information of the provider of the broadcast content used by the broadcast user. Furthermore, by using the estimation result, it is possible to estimate the location of the Web user more accurately.

In addition, for a broadcast user who uses a plurality of broadcast contents, the acquisition information may be obtained for each broadcast content. In this case, the area estimation unit may identify candidates for the receiving area based on the acquisition information for each broadcast content, and estimate the most common candidate among the candidates identified for each broadcast content, which has the largest number of candidates that are the same area, as the receiving area.
According to the above configuration, it is possible to accurately estimate the reception area when the broadcast contents are received by the receiving device based on the acquired information obtained for each of the plurality of broadcast contents. Furthermore, by using the estimation result, it is possible to more accurately estimate the location of the Web user.

In addition, for a broadcast user who uses multiple broadcast contents, acquisition information may be obtained for each broadcast content, and each acquisition information may include information indicating the reception strength when the broadcast content is received by the receiving device. In this case, the area estimation unit may identify candidates for the receiving area based on the acquisition information for each broadcast content, and estimate the candidate with the highest reception strength from among the candidates identified for each broadcast content as the receiving area.
According to the above configuration, it is possible to accurately estimate the reception area when the broadcast content is received by the receiving device from the reception strength when the broadcast content is received. Furthermore, by using the estimation result, it is possible to more accurately estimate the location of the Web user.

The acquired information may also include content information related to the content of the broadcast content used by the broadcast user. In this case, the area estimation unit may extract character information related to the receiving area from the content information and estimate the receiving area based on the extracted character information.
According to the above configuration, it is possible to accurately estimate the reception area when the broadcast content is received by the receiving device based on the character information extracted from the content information of the broadcast content. Furthermore, by using the estimation result, it is possible to more accurately estimate the location of the Web user.

The area estimation unit may also estimate the receiving area when the receiving device receives broadcast content via an Internet line.
According to the above configuration, the reception area when broadcast content is received via an Internet line is estimated, and the location of the Web user can be estimated using the estimation result.

The first identification information may be an IP address assigned to the terminal, a terminal identifier of the terminal, or an advertisement identifier, and the second identification information may be an IP address assigned to the receiving device, a device identifier of the receiving device, or an advertisement identifier.
According to the above configuration, the estimation result of the receiving area can be appropriately associated with the first log information by using the correspondence relationship between the information set as the first identification information and the information set as the second identification information, thereby making it possible to accurately estimate the location of the Web user.

In addition, in order to solve the above-mentioned problems, the information processing method of the present invention is characterized in that it comprises the steps of: a computer acquiring first log information including a usage history of Web content by a Web user and first identification information assigned to the Web user's terminal used when using the Web content; a computer estimating a receiving area based on acquired information obtained according to the receiving area when the broadcast content is received by the broadcast user's receiving equipment; and a computer associating the estimation result of the receiving area based on the acquired information to the first log information based on the correspondence between the second identification information assigned to the receiving equipment and the first identification information.
According to the information processing method of the present invention, the location of a Web user can be estimated more accurately.

In addition, according to the present invention, it is also possible to realize an information processing device that includes a first acquisition unit that acquires first log information including a usage history of Web content by a Web user and first identification information assigned to the Web user's terminal used when using the Web content, an area estimation unit that estimates a receiving area based on acquired information obtained according to the receiving area when broadcast content is received by the broadcast user's receiving equipment, and an association unit that associates the estimation result of the receiving area based on the acquired information to the first log information based on the correspondence between the second identification information assigned to the receiving equipment and the first identification information.
The information processing device of the present invention can estimate the location of a Web user more accurately.

According to the present invention, the location of a web user can be estimated more precisely based on the correspondence between the first identification information included in the first log information regarding the usage history of the web content and the second identification information assigned to the receiving device that received the broadcast content.

FIG. 2 is an explanatory diagram of a Web log. FIG. 13 is an explanatory diagram of a viewing log. FIG. 13 is a diagram showing a procedure for associating a Web log with regional information. FIG. 4 is a diagram showing a correspondence relationship between first identification information and second identification information. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment of the present invention. FIG. 2 is an explanatory diagram of functions of an information processing system according to an embodiment of the present invention. 1 is a diagram showing the correspondence between identification information of broadcasting stations and the locations of the broadcasting stations. FIG. 1 is a diagram showing an example of a viewing log for each of a plurality of programs viewed by a broadcast user within a given period of time. FIG. 2 is a diagram showing an information processing flow according to an embodiment of the present invention.

One embodiment of the present invention (the present embodiment) will be described in detail below with reference to the attached drawings. However, the embodiment described below is merely an example given to facilitate understanding of the present invention, and does not limit the present invention. In other words, the present invention may be modified or improved from the embodiment described below without departing from the spirit of the present invention. Furthermore, the present invention includes its equivalents.

In addition, in describing this embodiment, the definitions, meanings, and interpretations of some of the terms used in this specification are explained below.

[Device]
In this specification, the term "device" includes a single device that performs a specific function by itself, and also includes a combination of multiple devices that are present in a distributed manner but work together to perform a specific function.

[People/Persons]
As used herein, a "person" and "person" primarily refer to individuals, but the terms "person" and "person" also include groups such as households, corporations such as companies, and non-corporate organizations.

[content]
The content is information such as video, still images, audio, games, advertisements, and text that is provided or distributed by broadcasting or Internet communication and is used by users. The content also includes web content and broadcast content.

[Web Content]
Web content is content that can be used by receiving data distributed via the Internet and using a web browser or a dedicated application (application program). Web content includes, for example, websites, video content and music content for web distribution, search sites, electronic commerce sites, SNS (Social Networking Service), games that can be played on the web, web services that can be used through applications, and content uploaded to a server by web users, such as posted videos.

[Broadcast Content]
Broadcast content is content provided through broadcasting, specifically, programs and advertisements that broadcast stations (corresponding to providers of broadcast content) broadcast according to a program guide, such as television programs and radio programs. Broadcasting includes terrestrial broadcasting, cable broadcasting, BS broadcasting, satellite broadcasting, and the like. Some broadcast content can be received over the Internet, such as Internet television and IP simulcast radio, and in this specification, such broadcast content is distinguished from Web content. Broadcast content is not limited to content divided by program, and may be divided by a predetermined time unit, such as by hour, minute, or second.
In the following description, the broadcast content will be described as a television program (including television commercials) as an example.

[Information Association]
In this specification, "associating information" means storing information by linking (associating) it with another information, that is, storing each piece of associated information so that one piece of information can be identified from the other piece of associated information. In addition, in this specification, "associating information" also includes adding or appending associated information to the target information.

<<Outline of this embodiment>>
This embodiment is a technology in the field of information processing related to the acquisition, analysis, and utilization of Web logs. The Web log corresponds to the first log information of the present invention, and is generated by a distribution server of the Web content when a user of the Web content (hereinafter, Web user) uses the Web content. In this embodiment, regional information regarding the location of the Web user can be associated with the Web log. As a result, in this embodiment, the location of the Web user can be estimated using the regional information associated with the Web log. Here, the location refers to a region having a certain range, for example, an area equivalent to a unitary section determined based on an administrative division, and specifically, may be a prefecture or a region with a smaller division such as a city, ward, town, or village.

In order to associate regional information with a web log, a viewing log regarding the viewing history of television programs is required. The viewing log corresponds to the second log information of the present invention, and is generated by a receiving device possessed by a viewer of a television program (hereinafter, a broadcast user) when the viewer uses a television program, i.e., when the viewer watches a television program. The receiving device is a device that receives a television program (strictly speaking, the broadcast radio waves or data of a television program) when the broadcast user watches the television program, and specifically, is a television receiver.

In this embodiment, the reception area in which a broadcast user received a television program is estimated from the acquired information associated with the viewing log, and the estimation result is associated as regional information with a Web log that matches the viewing log.
The acquired information and the matching between the viewing log and the Web log will be described later.

<<Procedure for associating regional information with Web logs>>
The procedure for associating area information with a Web log will now be described.
In describing the association procedure, first, a Web log and a viewing log will be described with reference to FIGS. 1 and 2, respectively.

(Web log)
As shown in Fig. 1, the web log includes a user ID, which is identification information of a web user, a usage history of web content (hereinafter, usage history), and first identification information. The usage history is associated (linked) with the user ID of the web user. The usage history may include, for example, a uniform resource locator (URL) of an accessed (viewed) web site, a log related to the web user's behavior such as a purchase behavior at an electronic commerce site, a log of an application started when using the web content, and a log measuring the number of times the web content is accessed. The usage history may also include the date and time of use of the web content.
The usage history may be identified from the results of a questionnaire survey conducted on Web users.

The first identification information is identification information (access identifier) assigned to a terminal used when using the Web content, specifically, an IP address assigned to the terminal, or a terminal identifier or an advertising identifier of the terminal. The terminal is an information communication terminal in which a browser or an application for using the Web content is installed, such as a personal computer, a smartphone, a tablet terminal, a game device, or other device that is connected to an Internet line and can communicate.
The first identification information may be specified by referring to the usage history included in the web log, more specifically, information such as the application log, browser version information, and the website URL.

Note that the web log does not necessarily have to include the user ID of the web user. For example, in the case where web content is used by a shared device installed in a shared space in the web user's home, the web log does not necessarily have to include the user ID.

(Viewing log)
As shown in Fig. 2, the viewing log includes a user ID, which is identification information of the broadcast user, a viewing history of television programs by the broadcast user (hereinafter, viewing history), and second identification information. In addition, the viewing log may use an ID of a household to which the broadcast user belongs as the user ID of the broadcast user. In addition, the television program viewing history may be a history of real-time viewing, or a history corresponding to so-called time-shift viewing.

The viewing history is a usage history of broadcast content by a broadcast user, and is associated (linked) with the user ID of the broadcast user. The viewing history may include the ID of the broadcast station that broadcast the television program viewed by the broadcast user (hereinafter, the viewed program), the date and time when the broadcast user viewed the viewed program, the ID or program name of the viewed program, and an outline of the viewed program, etc. The program name and outline of the viewed program correspond to content information regarding the content of the viewed program.
The viewing history may be determined from the results of a questionnaire survey conducted on broadcast users.

The broadcast station ID may be identification information unique to each broadcast station, such as the abbreviation of the broadcast station or a service ID defined in accordance with broadcast standards. Information such as the ID or name of the program being viewed and an outline of the program being viewed is generated by the broadcast station, transmitted over the airwaves of the program being viewed, and received by the receiving device.

In addition, some information in the viewing history, specifically the ID of the broadcasting station of the viewed program, the ID or name of the viewed program, and an outline of the viewed program, corresponds to acquired information. The acquired information is information obtained according to the reception area when the viewed program is received by the broadcast user's receiving device, and the reception area corresponds to the location of the broadcast user when the broadcast user viewed the viewed program. The acquired information is associated with the viewing log, and specifically, is included in the viewing log as shown in FIG. 2.

The second identification information is an IP address assigned to the receiving device used by the broadcast user when watching a television program, or a device identifier or advertising identifier of the receiving device. The second identification information may include, in addition to or instead of the receiving device identification information, an identification information (ID) of a measuring device built into the receiving device for the purpose of measuring whether or not a television program is being watched and the channel being watched.

Furthermore, the viewing log may be associated with information indicating the reception strength (more precisely, the reception strength of broadcast radio waves) when the receiving device receives the viewed program as acquired information. The reception strength is identified by the receiving device when it receives the viewed program, and information on the identified reception strength (hereinafter, reception strength information) can be associated with the viewing log.

Furthermore, the viewing log may be associated with the ID of the broadcasting station of other television programs that can be viewed during the same period as the television program viewed by the broadcast user (viewed program) as the acquired information. Other television programs that can be viewed during the same period as the television program viewed by the broadcast user (viewed program) are television programs that can be received during the same period as the viewed program in the area in which the broadcast user's receiving device received the viewed program.

(Procedure for Associating Regional Information with Web Logs)
Next, a procedure for associating region information with a Web log will be described with reference to FIGS.
To associate the web log with regional information, first, a viewing log generated for each viewed program for each of a plurality of broadcast users is obtained. When each broadcast user views a television program on a television set, which is a receiving device 60, the receiving device 60 generates a viewing log. The generated viewing log is transmitted to a predetermined destination (specifically, the viewing log server 20).

Next, as shown in FIG. 3, estimated information on the receiving area of the viewed program related to each viewing log is associated with each acquired viewing log. The estimated information on the receiving area indicates the receiving area when the viewed program related to the viewing log was received by the receiving device used to view the viewed program. The procedure for estimating the receiving area will be described later.

A viewing log associated with estimated information (hereinafter, associated viewing log) is obtained for each broadcast user. Then, as shown in FIG. 3, for Web logs associated with regional information, matching ones are identified from among associated viewing logs in a number equivalent to the number of broadcast users.

More specifically, a viewing log that matches (corresponds to) a Web log is identified based on the correspondence between the second identification information included in the viewing log and the first identification information included in the Web log. The correspondence between the second identification information and the first identification information is used when identifying the first identification information that corresponds to the second identification information, or when identifying the second identification information that corresponds to the first identification information.

To explain in more detail, in the correspondence relationship of this embodiment, the first identification information is associated with the second identification information that satisfies the following condition A.
Condition A: The receiving device to which the second identification information corresponding to the first identification information is assigned is a receiving device of a broadcast user who is the same as the Web user who uses the terminal to which the first identification information is assigned.
Here, being the same person as the Web user means a person who watches a television program on a receiving device used in the same place as the Web user's terminal (for example, the Web user's residence).

In this embodiment, the second identification information included in the viewing log and the first identification information included in the Web log are different from each other; for example, the first identification information is an IP address, and the second identification information is an advertising identifier and a device identifier. Therefore, in this embodiment, the correspondence between the IP address, the advertising identifier, and the device identifier is predefined as table data shown in FIG. 4. By referring to this table data, it is possible to identify the second identification information that corresponds to the first identification information of the Web log to which the regional information is associated.

Then, as shown in Figure 3, the associated viewing log (the viewing log surrounded by a dashed line in Figure 3) containing the identified second identification information is extracted, and the estimated information associated with that viewing log is associated with the Web log as regional information.
In addition, in this embodiment, the estimated information (i.e., the estimation result of the receiving area based on the acquired information) is associated with the user ID of the Web user included in the Web log. In other words, in this embodiment, the estimated information as regional information is associated with the Web log as personal information.

As described above, in this embodiment, the estimated reception area when a broadcast user receives a viewing program using the receiving device can be used as the location of a Web user who is the same as the broadcast user.

<<Configuration of information processing system according to this embodiment>>
An information processing system according to this embodiment (hereinafter, referred to as information processing system 100) will be described with reference to FIG.
The information processing system 100 is constructed to associate regional information with Web logs, and as shown in Fig. 5, is composed of a Web log server 10, a viewing log server 20, a compilation server 30, a content distribution server 40, a Web user's terminal 50, and a broadcast user's receiving device 60. These devices are connected to each other via a communication network N in a state in which they can communicate with each other.

The web log server 10 communicates with the content distribution server 40 to obtain web logs. When a web user makes a request for content distribution on the terminal 50, the content distribution server 40 distributes web content to the web user in response to the request, and generates and transmits a web log accompanying the content distribution. The web log server 10 receives the web log transmitted from the content distribution server 40, and transmits the received web log to the aggregation server 30.

The viewing log server 20 receives the viewing log transmitted from the receiving device 60. Based on the acquired information contained in the received viewing log, the viewing log server 20 estimates the receiving area when the viewing program related to the viewing log was received by the receiving device 60. Furthermore, the viewing log server 20 associates the estimated information indicating the estimated result of the receiving area with the viewing log. The viewing log server 20 then transmits the associated viewing log to the aggregation server 30.

The aggregation server 30 acquires the Web logs and viewing logs (more specifically, the viewing logs after association) and executes a process of aggregating and analyzing the acquired information. The processes executed by the aggregation server 30 include a process of associating regional information with the Web logs and a process of analyzing the number of times each Web content is used (number of accesses). The aggregation results and analysis results by the aggregation server 30 are used for various purposes using the regional information associated with the Web logs, for example, to estimate the behavioral patterns and interests of Web users and deliver or recommend advertisements and video content appropriate to these to the Web users.

The web log server 10, the viewing log server 20, the aggregation server 30, and the content distribution server 40 each correspond to an example of a computer, specifically, a general-purpose server computer. That is, as shown in FIG. 5, each server has a processor 10a, 20a, 30a, 40a consisting of a CPU or the like, and a memory 10b, 20b, 30b, 40b consisting of a ROM and a RAM or the like. In addition, each server can communicate with each other through a communication interface 10c, 20c, 30c, 40c, and saves and accumulates various information in storage 10d, 20d, 30d, 40d as a storage device.

In addition, a program (hereinafter, information processing program) that enables each server to perform its functions is installed in each server. When the processors 10a, 20a, 30a, and 40a in each server execute the information processing program, each server executes the corresponding process among the processes for associating regional information with the web log.

6, the information processing system 100 includes a first acquisition unit 101, a second acquisition unit 102, an area estimation unit 103, and an association unit 104. Each of the above functional units is realized by cooperation between a hardware device of a server computer corresponding to the functional unit and an information processing program installed on the computer.
Each functional unit will be described below.

(First Acquisition Unit)
The first acquisition unit 101 is configured by the Web log server 10 , acquires the Web log from the content distribution server 40 , and transmits the acquired Web log to the tallying server 30 .
The timing of acquiring the Web logs is not particularly limited, and each time the content distribution server 40 generates a Web log, the Web log may be transmitted to the Web log server 10 and received by the first acquisition unit 101. Alternatively, it may be possible to acquire all Web logs generated within a certain period (e.g., one day or several days) at once.

(Second Acquisition Unit)
The second acquisition unit 102 is constituted by the viewing log server 20, and acquires the viewing log from the receiving device 60 of each broadcast user.
The timing of acquiring the viewing log is not particularly limited, and each time the receiving device 60 generates a viewing log, the viewing log may be transmitted to the viewing log server 20 and received by the second acquisition unit 102. Alternatively, the viewing logs generated within a certain period (for example, one day or several days) may be acquired all at once.

(Area Estimation Unit)
The area estimation unit 103 is constituted by the viewing log server 20, and estimates the receiving area when a viewing program is received by the broadcast user's receiving device 60 based on acquired information associated with the viewing log for that viewing program. The area estimation unit 103 also associates information indicating the estimation result of the receiving area, i.e., the estimation information, with the viewing log, and transmits the associated viewing log to the aggregation server 30.

In this embodiment, the methods for estimating the receiving area based on the acquired information include the following first to fourth methods. The area estimation unit 103 estimates the receiving area according to a method selected from these four methods depending on the information included in the acquired information. According to each of the methods below, the receiving area can be appropriately estimated based on the information included in the acquired information.

[First method]
The first method is used when the acquired information includes identification information of the broadcasting station of the television program (viewed program) viewed by the broadcast user. In the first method, the receiving area is estimated based on the correspondence between the identification information of the broadcasting station and the location of the broadcasting station, and the identification information of the broadcasting station included in the acquired information.

To explain in more detail, the storage 20d of the viewing log server 20 stores table data as shown in Figure 7, and this table data specifies the correspondence between the broadcast station ID and broadcast station name, which are the identification information of the broadcast station, and the address of the broadcast station's location.By referring to this table data, the location of the broadcast station is identified from the identification information of the broadcast station included in the acquired information, and the identified location is estimated as the receiving area.
That is, in the first method, the location of the broadcast station of the viewed program is estimated as the receiving area for that viewed program.

[Second method]
The second method is an application of the first method, and is used when a viewing log is obtained for each program for a broadcast user who has viewed multiple television programs, and each viewing log is associated with acquired information including the ID of the broadcast station of the viewed program. In the second method, for each of the multiple television programs viewed by the broadcast user, candidate receiving areas are identified for each program based on the ID of the broadcast station included in the acquired information, using a procedure similar to that of the first method.

Then, of the candidates for the reception area identified for each program, the candidate with the greatest number of candidates that are the same area is estimated as the reception area. For example, in the case where multiple viewing logs were obtained for a certain broadcast user as shown in Figure 8, Prefecture A is the most common among the locations (prefectures) of the broadcast stations of the viewed programs, so Prefecture A is the most common candidate and is estimated as the reception area.

As described above, in the second method, for multiple television programs viewed by a broadcast user within a specified period, the location of the broadcasting station that broadcast each viewed program is identified, and the location of the most prevalent broadcasting station among those programs is estimated as the receiving area.
In addition, when the second method is adopted, the viewing logs will be analyzed for each of the multiple television programs viewed by the broadcast user within a specified period. The specified period in this case is not particularly limited, but can be set to, for example, one hour or several hours, or one day or several days.

[Third Method]
The third method is an application of the first method, and is used when a viewing log is obtained for each program for a broadcast user who has viewed multiple television programs, and each viewing log is associated with acquired information including reception strength information. In the third method, for each of multiple television programs viewed by the broadcast user, candidate receiving areas are identified for each program based on the broadcast station ID included in the acquired information, using a procedure similar to that of the first method.

Then, of the candidate reception areas identified for each program, the candidate with the highest reception strength for the program being viewed (more precisely, the broadcast radio waves of the program being viewed) is estimated as the reception area. For example, in the case shown in Figure 8, where multiple viewing logs were obtained for a certain broadcast user, the reception strength for the television program with program ID "idbbb" is the highest, so prefecture A, where the broadcast station of that program is located, is estimated as the reception area.

As described above, in the third method, the location of the broadcasting station that broadcast each of multiple television programs viewed by a broadcast user within a specified period is identified, and the location of the broadcasting station of the television program with the highest reception strength at the receiving device 60 is estimated as the receiving area.
In addition, when the third method is adopted, the viewing logs will be analyzed for each of the multiple television programs viewed by the broadcast user within a specified period. The specified period in this case is not particularly limited, but can be set to, for example, one hour or several hours, or one day or several days.

[Fourth Method]
The fourth method is used when the acquired information includes content information on the content of the television program viewed by the broadcast user (viewed program), specifically, the program name and summary of the viewed program. In the fourth method, natural language processing is applied to the content information included in the acquired information to extract text information related to the receiving area from the content information, specifically, words related to the area and words that can identify the area are extracted. Then, the receiving area is estimated based on the extracted text information.
The method for extracting character information related to the receiving area from the content information and the method for estimating the receiving area from the character information are not particularly limited, but a method utilizing machine learning or artificial intelligence (AI) may be used.

(Association section)
The associating unit 104 is configured by the tallying server 30, and acquires the Web log transmitted from the Web log server 10 and the viewing log (more specifically, the viewing log after association) transmitted from the viewing log server 20. Then, the associating unit 104 associates the estimation result of the receiving area by the area estimation unit 103 with the Web log as regional information.

Specifically, the associating unit 104 refers to the table data shown in FIG. 4 and identifies the second identification information that corresponds to the first identification information of the target Web log based on the correspondence between the second identification information and the first identification information defined in this data. The associating unit 104 then associates the estimated information associated with the viewing log that includes the identified second identification information, i.e., the estimation result of the reception area based on the acquired information, with the target Web log (in other words, the Web log that includes the first identification information that corresponds to the second identification information included in the viewing log).

Furthermore, in this embodiment, as described above, estimated information associated with the viewing log, that is, the estimated result of the receiving area based on the acquired information, is associated with the user ID of the Web user in the target Web log.
Furthermore, the Web log associated with the regional information (i.e., the reception area estimation result) is stored in the storage 30d of the tallying server 30, and can be read out from the storage 30d as needed for use.

The table data of FIG. 4, which is referenced by the association unit 104 and defines the correspondence between the second identification information and the first identification information, may be stored, for example, in the storage 30d of the tallying server 30. However, this is not limited to the above, and the above table data may be stored in the storages 10d, 20d, and 40d of a server other than the tallying server, or in other external storage devices such as a NAS (Network Attached Storage).

<<Information Processing Method According to the Present Embodiment>>
Next, a process flow (hereinafter, information processing flow) for associating region information with a Web log using the information processing system 100 of this embodiment will be described. The information processing flow employs the information processing method of the present invention. That is, the following description includes a description of the information processing method of the present invention, and each step in the information processing flow corresponds to a component of the information processing method of the present invention.
It should be noted that the information processing flow described below is merely an example, and unnecessary steps may be deleted, new steps may be added, or the order of steps may be changed without departing from the spirit of the present invention.

The information processing flow proceeds according to the flow shown in FIG. 9. More specifically, in the information processing flow, first, the Web log server 10 executes a process of acquiring a Web log (S001). That is, when a Web user uses Web content, a Web log including the usage history is transmitted from the content distribution server 40 and received (acquired) by the Web log server 10. The Web log server 10 then transmits the acquired Web log to the aggregation server 30 (S002).

On the other hand, the viewing log server 20 executes a step of acquiring viewing logs from the receiving devices 60 of each broadcast user (S003). The acquired viewing log may already be associated with the acquired information, or the viewing log may be associated with the acquired information by the viewing log server 20 after the viewing log is acquired.

The viewing log server 20 also performs a process of estimating the receiving area for each viewing log when the viewing program related to each viewing log is received by the broadcast user's receiving device 60 based on the acquired information associated with each viewing log (S004). In this process, the viewing log server 20 estimates the receiving area according to any one of the first to fourth methods described above. Thereafter, the viewing log server 20 associates the estimation information indicating the estimation result of the receiving area with the viewing log, and transmits the associated viewing log to the aggregation server 30 (S005).

The web log sent from the web log server 10 and the associated viewing log sent from the viewing log server 20 are received and acquired by the aggregation server 30 (S006).

Next, the tallying server 30 performs a process of associating regional information with the target Web log based on the correspondence between the second identification information included in the acquired associated viewing log and the first identification information included in the Web log (S007). In this process, the tallying server 30 refers to the table data of FIG. 4 stored in the storage 20d, and identifies the second identification information that corresponds to the first identification information included in the target Web log from the correspondence defined in the table data.

Then, the aggregation server 30 associates the estimated information associated with the viewing log including the identified second identification information, i.e., the estimation result of the receiving area in step S004, with the target Web log. More specifically, it associates the estimation result of the receiving area with the user ID of the Web user included in the target Web log.

When the above series of steps is completed, the information processing flow ends. The information processing flow is then repeatedly performed, for example, each time a new Web log is acquired (i.e., each time step S001 is performed).

As described above, in this embodiment, the first identification information of the Web log is used as a key to identify a viewing log including the corresponding second identification information and an estimation result (estimated information) of the receiving area based on the acquired information associated with the viewing log. Then, based on the identified viewing log and estimated information, regional information can be associated with the above Web log. Specifically, the estimation result of the receiving area indicated by the estimated information is associated with the above Web log as regional information. This makes it possible to more accurately estimate the location of the content user related to the Web log from the associated regional information (i.e., the estimation result of the receiving area).

To explain in more detail, it is generally possible to estimate the current location of a content user from information contained in a web log, such as an IP address, but there is a demand for higher accuracy in estimating the location of a content user.
In contrast, in the present embodiment, the location of the content user can be estimated with high accuracy from the estimated information associated with the viewing log. Furthermore, by comparing the estimation result, the validity of the current location (location) of the content user estimated based on the IP address, etc. can be evaluated, and a more precise estimation can be realized.

<<Other embodiments>>
Although an example of the information processing device and information processing method of the present invention has been described above, the above-described embodiment is merely an example, and other embodiments are also possible.

In the above embodiment, the area estimation unit 103 estimates the receiving area when the broadcast user receives a viewing program by the receiving device 60 using any of the above-mentioned first to fourth methods. However, the method for estimating the receiving area is not limited to the above four methods, and other methods may be used.
For example, when the receiving device 60 is first installed in a household, it is connected to a television antenna, and a process called an initial scan is performed manually or automatically to obtain a list of broadcast stations from which broadcast waves can be received. This list of broadcast stations includes the IDs of viewable broadcast stations as acquired information associated with the viewing log. At this time, the location of each of N broadcast stations (N is a natural number of 3 or more) is identified from the broadcast station ID. Then, among the locations of the broadcast stations identified for each broadcast station ID, the area with the largest number of broadcast stations in the same location (prefecture) may be estimated as the receiving area.

In the above embodiment, the web log is obtained from the content distribution server 40, and the viewing log is obtained from the receiving device 60 of each broadcast user. However, the source from which the web log and viewing log are obtained is not particularly limited. For example, the web log may be obtained from the terminal 50 of the web user, and the viewing log may be obtained from the broadcast station of the television program.

In the above embodiment, the broadcast user receives radio waves of the broadcast content (specifically, a television program) with a receiving device and uses the broadcast content, but this is not limited to the above. For example, the broadcast user may use the broadcast content through an Internet line, such as Internet TV, IP simulradio, or OTT (Over-the-Top Media) services. In other words, the broadcast user's receiving device is an information and communications terminal, and the broadcast user may use the broadcast content by receiving the data of the broadcast content via the Internet using the information and communications terminal. In this case, the area estimation unit 103 may estimate the receiving area when the information and communications terminal as the receiving device receives the broadcast content through an Internet line.

In the above embodiment, the first identification information included in the web log and the second identification information included in the viewing log are different from each other, and when determining the correspondence between the two identification information, table data (see FIG. 4) that specifies the correspondence is used. However, this is not limited to this, and the first identification information and the second identification information may be the same type of information, and both identification information may be IP addresses. In this case, data that specifies the correspondence between the two identification information, such as the table data shown in FIG. 4, is not necessary.

In the above embodiment, a viewing log is acquired for the programs viewed by each broadcast user, and the receiving area when the viewed program related to the viewing log is received by the broadcast user's receiving device is estimated based on the acquired information associated with the viewing log for each program, but this is not limited to this. For example, the viewing log may include the viewing date and time, and a candidate receiving area may be identified for the date and time corresponding to the viewing date and time based on the acquired information associated with the viewing log. Then, a candidate receiving area may be identified for each viewing time, and a candidate selected based on the length of the viewing time may be estimated as the receiving area when the viewed program is received by the broadcast user's receiving device.

In addition, in the above embodiment, the series of functions for associating regional information with a web log is realized by multiple devices, specifically multiple servers, that make up the information processing system 100. However, this is not limited to this, and the series of functions described above, specifically the first acquisition unit 101, the second acquisition unit 102, the area estimation unit 103, and the association unit 104, may all be configured by a single device, for example a single server computer. In other words, the functions performed by the above-mentioned information processing system 100 may be realized by a single device. Such a device will function as the information processing device of the present invention.

REFERENCE SIGNS LIST 10 Web log server 20 Viewing log server 30 Aggregation server 40 Content distribution server 10a, 20a, 30a, 40a Processor 10b, 20b, 30b, 40b Memory 10c, 20c, 30c, 40c Communication interface 10d, 20d, 30d, 40d Storage 50 Terminal 60 Receiving device 100 Information processing system 101 First acquisition unit 102 Second acquisition unit 103 Area estimation unit 104 Association unit N Communication network

Claims (15)

a first acquisition unit that acquires first log information including a usage history of a web content by a web user and first identification information assigned to a terminal used when the web content is used;
an area estimation unit that estimates the receiving area based on acquired information obtained according to a receiving area when a broadcast content is received by a receiving device of a broadcast user;
an association unit that associates an estimation result of the receiving area based on the acquired information with the first log information based on a correspondence relationship between second identification information assigned to the receiving device and the first identification information ,
An information processing system in which, in the correspondence relationship, the first identification information is associated with the second identification information assigned to the receiving equipment of the broadcast user who is the same as the Web user who uses the terminal to which the first identification information is assigned . a second acquisition unit that acquires second log information including a usage history of the broadcast content by the broadcast user and the second identification information;
The information processing system according to claim 1 , wherein the second log information is associated with the acquired information. data indicating the correspondence between the second identification information and the first identification information is stored in a storage device;
The information processing system of claim 2, wherein the association unit associates the estimation result of the receiving area based on the acquired information associated with the second log information with the first log information including the first identification information corresponding to the second identification information included in the second log information. The first log information includes identification information of the Web user,
The information processing system according to claim 1 , wherein the associating unit associates the estimation result of the receiving area based on the acquired information with the identification information of the Web user in the first log information. An information processing system as described in any one of claims 1 to 3, wherein when the acquired information includes identification information of a provider of the broadcast content used by the broadcast user, the area estimation unit estimates the receiving area based on the correspondence between the provider's identification information and the provider's location, and the identification information of the provider included in the acquired information. When the acquisition information is obtained for each of the broadcast contents for the broadcast users who have used a plurality of the broadcast contents, the area estimation unit
Identifying a candidate receiving area for each of the broadcast contents based on the acquired information;
The information processing system according to claim 5 , wherein the most numerous candidate among the candidates identified for each of the broadcast contents is estimated as the receiving area. When the acquisition information is obtained for each of the broadcast contents for the broadcast users who have used a plurality of the broadcast contents, and each of the acquisition information includes information indicating a reception strength when the broadcast contents are received by the receiving device, the area estimation unit:
Identifying a candidate receiving area for each of the broadcast contents based on the acquired information;
The information processing system according to claim 5 , wherein a candidate having the highest reception strength among the candidates identified for each of the broadcast contents is estimated as the reception area. An information processing system as described in any one of claims 1 to 3, wherein when the acquired information includes content information regarding the content of the broadcast content used by the broadcast user, the area estimation unit extracts text information related to the receiving area from the content information and estimates the receiving area based on the extracted text information. The information processing system according to claim 1 , wherein the area estimation unit estimates the receiving area when the receiving device receives the broadcast content via an Internet line. The first identification information is an IP address assigned to the terminal, a terminal identifier or an advertising identifier of the terminal,
The information processing system according to claim 1 , wherein the second identification information is an IP address assigned to the receiving device, a device identifier of the receiving device, or an advertisement identifier. A step of acquiring first log information including a usage history of a web content by a web user and first identification information assigned to a terminal of the web user used when the web content is used by the computer;
A step of estimating the receiving area based on acquired information obtained according to the receiving area when the broadcast content is received by the receiving device of the broadcast user by the computer;
and a step of associating, by the computer, an estimation result of the receiving area based on the acquired information with the first log information based on a correspondence relationship between second identification information assigned to the receiving device and the first identification information ,
An information processing method in which the correspondence relationship corresponds between the first identification information and the second identification information assigned to the receiving equipment of the broadcast user who is the same as the Web user who uses the terminal to which the first identification information is assigned . a first acquisition unit that acquires first log information including a usage history of a web content by a web user and first identification information assigned to a terminal of the web user that is used when the web content is used;
an area estimation unit that estimates the receiving area based on acquired information obtained according to a receiving area when a broadcast content is received by a receiving device of a broadcast user;
an association unit that associates an estimation result of the receiving area based on the acquired information with the first log information based on a correspondence relationship between second identification information assigned to the receiving device and the first identification information ,
An information processing device, in which the correspondence relationship corresponds between the first identification information and the second identification information assigned to the receiving equipment of the broadcast user who is the same as the Web user who uses the terminal to which the first identification information is assigned . a first acquisition unit that acquires first log information including a usage history of a web content by a web user and first identification information assigned to a terminal used when the web content is used;
an area estimation unit that estimates the receiving area based on acquired information obtained according to the receiving area when the broadcast content is received by the receiving device of the broadcast user;
An information processing system comprising: an association unit that associates an estimation result of the receiving area based on the acquired information obtained by the receiving device, to which the same information as the first identification information is assigned as second identification information, with the first log information. A step of acquiring first log information including a usage history of a web content by a web user and first identification information assigned to a terminal of the web user used when the web content is used by the computer;
A step of estimating the receiving area based on acquired information obtained according to the receiving area when the broadcast content is received by the receiving device of the broadcast user by the computer;
An information processing method comprising a step of a computer associating an estimation result of the receiving area based on the acquired information obtained by the receiving device to which information identical to the first identification information is assigned as second identification information, with the first log information. a first acquisition unit that acquires first log information including a usage history of a web content by a web user and first identification information assigned to a terminal of the web user that is used when the web content is used;
an area estimation unit that estimates the receiving area based on acquired information obtained according to the receiving area when the broadcast content is received by the receiving device of the broadcast user;
An information processing device comprising: an association unit that associates an estimation result of the receiving area based on the acquired information obtained by the receiving device to which the same information as the first identification information is assigned as second identification information, with the first log information.

Images