JP2017120628A - Information processor, control method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily analyze a purchase situation of a product in accordance with information browsed by a user and a user who has a relation with the user.SOLUTION: An information processor comprises: an SNS submission collection part for acquiring SNS submission adapted to a search condition from an SNS site; a purchase/consideration information detection part for analyzing the acquired submission, and for creating purchase/consideration information by associating a purchase/consideration predicative and its target product name and its type (purchase/consideration or the like) with a user name related to submission or the like; a browsing information acquisition part for acquiring a follow user who follows a user from the SNS site, and for creating browsing information as the information of a link destination which has been possibly browsed by the user from the submission of the follow user; and an analysis part for performing classification and tabulation processing to a product to be analyzed for each user in accordance with whether or not the information of the link destination of the follow user has been browsed, whether or not the product to be analyzed has been purchased, whether or not the other product has been purchased, and whether or not the product to be analyzed has been considered.SELECTED DRAWING: Figure 1

Description

SNS (Social
The present invention relates to an information processing apparatus and a control method for analyzing evaluations of products and services transmitted by Networking Service) and performing promotions based on the analysis results.

  2. Description of the Related Art In recent years, behavioral targeting advertisements have been widely used in Internet advertisements by analyzing the behaviors of visitors of sites that are operated, specifying hobbies and preferences, and performing promotions suitable for visitors. However, it is only possible to infer interest from the actions in the site, and it is not easy to obtain direct mention of the user.

On the other hand, with the development of SNS, a mechanism for performing a promotion from an SNS service provider has been provided.
In the promotion of SNS, based on profiling by an SNS service provider, it is possible to perform promotion for users classified in advance by hobbies / preferences, age / sex, and the like.

  However, as for the promotion target, it is only possible to specify hobbies and preferences in large units such as “photos” or “cars”, and we are not considering promotion or purchase for users who have already purchased the product There is a problem that ineffective promotions such as promotions for users are performed.

Japanese Patent Laying-Open No. 2015-164008 JP 2013-246747 A

In the system of the above-mentioned patent document 1, for the purpose of promotion, a technique for classifying users by quantifying the preference based on the appearance frequency of a specific keyword in a post is shown.
In the system of Patent Document 2, the store visit is determined based on the position information, and the number of visits to the target store or competing store, the purchase data determined from customer data such as POS or SNS comments, etc. A technique for classifying customers and determining a promotion method according to the classification result is shown.

However, the system disclosed in Patent Document 1 does not consider whether or not a user has purchased a product. As a result of classification, there is a problem that a user who has already purchased a product is included in the promotion.
In the system of Patent Document 2, consideration is given to product purchase and interest in products, but competing products are not considered. There is also a problem that information that has led to product purchase, interest and interest is not taken into consideration.

  The present invention has been made in view of the above-described problems, and its purpose is to easily analyze the purchase status of products according to information browsed by a user and a user related to the user. It is to provide an information processing apparatus, a control method, and a program.

A first invention for solving the above-described problem is to purchase a product from a first collection unit that collects a post related to a product from a posted document and the post collected by the first collection unit. Detecting means for detecting a first user making the posting, and the second user related to the first user detected by the detecting means among the postings collected by the first collecting means. A second collection unit that collects browsing information that the first user may browse from the post, and an analysis that analyzes the purchase status of the product based on the presence or absence of the browsing information collected by the second collection unit And an information processing apparatus.
According to the first invention, the purchase status of the product can be easily analyzed based on the posting of the first user and the information browsed by the first user regarding the posting by the second user related to the first user. can do.

The post relating to the purchase preferably includes a post considering purchase.
As a result, not only the product purchase information but also the product purchase consideration status can be analyzed.

The browsing information preferably includes information specified from link information included in a post.
Thereby, it is possible to analyze what information the user browses and purchases.

It is preferable that the analysis unit further analyzes the purchase status of the product by classifying the product into a target product to be analyzed or a product other than the target product.
Thereby, it is possible to analyze the purchase status of the product separately for the target product to be analyzed and the other products other than the target product.

It is desirable to further include a transmission unit that transmits an advertisement to a user corresponding to the item of the analysis result of the purchase status of the product.
Thereby, an advertisement can be effectively transmitted to a user corresponding to a specific item.

A second invention is a method for controlling an information processing apparatus, wherein a first collection step of collecting posts relating to a product from a posted document, and the post collected by the first collection step, A detecting step for detecting a first user making a posting related to the purchase, and a second user related to the first user detected by the detecting means among the postings collected by the first collecting step The second collection step of collecting browsing information that the first user may browse from the post of the above, and analyzing the purchase status of the product according to the presence or absence of the browsing information collected by the second collection step And an analysis step for controlling the information processing apparatus.
According to the second invention, the purchase status of the product can be easily analyzed based on the posting of the first user and the information viewed by the first user on the posting by the second user related to the first user. can do.

According to a third aspect of the present invention, the computer makes a posting relating to the purchase of a product from the posting collected by the first collecting means, the first collecting means collecting the posting relating to the product from the posted document. Detection means for detecting a first user, a first detected by the detection means from the posting of a second user related to the first user among the postings collected by the first collecting means. Program for functioning as second collecting means for collecting browsing information that may be browsed by a user, and analyzing means for analyzing the purchase status of the product according to presence or absence of browsing information collected by the second collecting means It is.
By installing the program of the third invention on a general-purpose computer, the information processing apparatus of the first invention can be obtained, and the control method of the information processing apparatus of the second invention can be executed.

  According to the present invention, it is possible to specify whether or not a purchaser purchases a product and whether or not to consider purchasing, and at the same time, information that is highly likely to have been contacted can be specified.

It is a figure which shows an example of a structure of the information processing system containing an information processing apparatus and an analyzer terminal. It is a block diagram which shows the structure of the hardware applicable to an information processing apparatus and an analyzer terminal. It is a flowchart which shows the flow of the collection and analysis process which an information processing apparatus performs regularly. It is a flowchart which shows the flow of a SNS contribution collection process. It is a figure which shows an example of a setting preservation | save area | region. It is a figure which shows an example of a SNS data storage area. It is a figure which shows an example of a search condition table. It is a figure which shows an example of a contribution table. It is a flowchart which shows the flow of a purchase and examination information detection process. It is a figure which shows an example of the result of a morphological analysis and dependency analysis. It is a figure which shows an example of a purchase and examination predicate table. It is a figure which shows an example of a predicate attribute table. It is a figure which shows an example of a purchase and examination information storage area. The figure which shows an example of the purchase and examination information table It is a flowchart which shows the flow of a browsing information collection process. It is a figure which shows an example of a follow user table. It is a figure which shows an example of a browsing information table. It is a flowchart which shows the flow of a total process. It is a figure which shows an example of a total table. It is a figure which shows an example of an analysis and placement screen. It is a flowchart which shows the flow of the collection and analysis process which an information processing apparatus performs regularly. It is a flowchart which shows the flow of a transmission information collection process. It is a figure which shows an example of a browsing information table. It is a figure which shows an example of a total table.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a diagram showing an example of the configuration of an information processing system according to the present invention.
The information processing system of the present invention includes an information processing apparatus 100 and one or a plurality of analyst terminals 110.
The information processing apparatus 100 and one or more analyst terminals 110 are configured to be connected via a network such as a local area network.
The information processing apparatus 100 is connected to an external network and is configured to be connected to the SNS site 120 and the Internet 130.

  The information processing apparatus 100 acquires information from the SNS site 120 and the Internet 130 based on the settings input from the analyst terminal 110 and performs analysis.

  The information processing apparatus 100 includes a setting unit 101, a setting storage area 102, an SNS post collection unit 103, an SNS data storage area 104, a purchase / review information detection unit 105, a browsing information collection unit 106, The examination information storage area 107 and the analysis unit 108 are included.

The setting storage area 102 (FIG. 5) includes a search condition table 501 (FIG. 7), a purchase / review predicate table 502 (FIG. 11), and a predicate attribute table 503 (FIG. 12).
The SNS data storage area 104 (FIG. 6) consists of a posting table 601 (FIG. 8).
The purchase / review information storage area 107 (FIG. 13) includes a purchase / review information table 1301 (FIG. 14) and a browsing information table 1302 (FIG. 17).
The setting storage area 102, the SNS data storage area 104, and the purchase / review information storage area 107 are configured by being stored in an external memory 211 such as a hard disk, which will be described later.

  The setting unit 101 receives settings of the search condition table 501, the purchase / review predicate table 502, the predicate attribute table 503, and the like. These may be received from the analyst terminal 110 via a network.

  The SNS post collection unit 103 acquires search conditions from the search condition table 501, acquires SNS posts that match the search conditions from the SNS site 120, and stores the acquired posts in the post table 601.

  The purchase / review information detection unit 105 analyzes the posting in the posting table 601 and responds to the purchase / review predicate and the type (purchase / review, etc.) for each product name, and the user name and the like related to the post. In addition, purchase / review information is created and stored in the purchase / review information table 1301.

  The browsing information collection unit 106 acquires a user (following user) that the user follows from the SNS site 120, creates browsing information that is information of a link destination that the user may have browsed from the post of the following user, This is stored in the browsing information table 1302.

  The analysis unit 108 refers to the purchase / consideration information table 1301 and the browsing information table 1302, and for each user, browses the link information of the follow user with respect to the product to be analyzed, and The data is classified according to whether the product to be analyzed has been purchased, another product has been purchased, or the product to be analyzed has been examined.

  The analyst terminal 110 sets information acquisition methods and analysis methods for the information processing apparatus 100. Further, the analyst terminal 110 displays the analysis result obtained from the information processing apparatus 100.

Hereinafter, the hardware configuration of the information processing apparatus applicable to the information processing apparatus 100 and the analyzer terminal 110 illustrated in FIG. 1 will be described with reference to FIG.
FIG. 2 is a block diagram illustrating a hardware configuration of the information processing apparatus applicable to the information processing apparatus 100 and the analyst terminal 110 illustrated in FIG.
In FIG. 2, the CPU (Central
Processing Unit) 201 comprehensively controls each device and controller connected to the system bus 204. A ROM (Read Only Memory) 202 or an external memory 211 also has a BIOS (Basic Input / Output System) and an operating system program (hereinafter referred to as OS) that are control programs for the CPU 201, and functions executed by each server or each PC. Various programs and the like which will be described later necessary for the realization are stored.

RAM (Random
(Access Memory) 203 functions as a main memory, work area, and the like of the CPU 201. The CPU 201 implements various operations by loading a program or the like necessary for execution of processing from the ROM 202 or the external memory 211 into the RAM 203 and executing the loaded program.

  The input controller 205 controls input from a keyboard (KB) 209 or a pointing device such as a mouse (not shown). The video controller 206 controls display on a display device such as a CRT display (CRT) 210. In FIG. 2, although described as CRT 210, the display device is not limited to the CRT, but may be another display device such as a liquid crystal display. These are used by the administrator as needed.

  The memory controller 207 is an adapter for an external storage device (hard disk (HD)), flexible disk (FD), or PCMCIA card slot for storing a boot program, various applications, font data, user files, editing files, various data, and the like. Is used to control access to an external memory 211 such as a compact flash (registered trademark) memory connected via the network.

  The communication I / F controller 208 is connected to and communicates with an external device via a network, and executes communication control processing on the network. For example, communication using TCP / IP (Transmission Protocol / Internet Protocol) or the like is possible.

  Note that the CPU 201 enables display on the CRT 210 by executing outline font rasterization processing on a display information area in the RAM 203, for example. In addition, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the CRT 210.

  Various programs to be described later for realizing the present invention are recorded in the external memory 211 and executed by the CPU 201 by being loaded into the RAM 203 as necessary. Furthermore, definition files and various information tables used when executing the program are also stored in the external memory 211, and a detailed description thereof will be described later.

(Overall flow of collection and analysis processing)
Next, an overall flow of collection and analysis processing that is periodically executed in the information processing apparatus 100 according to the present embodiment will be described with reference to a flowchart of FIG.

  In step S301, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 acquires a post from the SNS site 120 based on the search condition stored in the setting storage area 102 (FIG. 5), and the SNS data storage area 104 ( The acquired posting is stored in FIG. 6) (SNS posting collection processing). Details will be described later with reference to FIG.

In step S302, the CPU 201 (purchase / consideration information detection unit 105) of the information processing apparatus 100 starts the iterative process up to step S304 for each post acquired in step S301.
In step S303, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 analyzes a post to be processed, detects purchase / examination information from the result of dependency analysis, and purchase / examination information storage area. 107 (FIG. 13) (Purchase / consideration information detection processing). Details will be described later with reference to FIG.

  In step S304, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs the processing from step S302 when there is a next posting. If there is no next post, the process proceeds to step S305.

In step S <b> 305, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a list of users who have made postings as processing targets from the SNS site 120.
In step S306, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S308 for each user included in the list of users acquired in step S305.

In step S307, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100, from the SNS data storage area 104 (FIG. 6), posts a user that the user to be processed follows (the user may have browsed). High posting) is acquired as browsing information, and the browsing information is stored in the purchase / review information storage area 107 (FIG. 13) (browsing information collection processing). Details will be described later with reference to FIG.
In step S308, if there is a next user, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S306. If there is no next user, the process ends.

  In this description, it is described that the CPU 201 of the information processing apparatus 100 executes the SNS post acquisition process (S301), the purchase / review information detection process (S303), and the browsing information collection process (S307) synchronously. It may be configured to execute asynchronously.

(SNS post collection process)
Next, details of the SNS post collection processing in step S301 of FIG. 3 will be described with reference to FIGS. 4 and 5 to 8.

  In step S401, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 acquires a list of search conditions from the search condition table 501 (FIG. 7) stored in the setting storage area 102 (FIG. 5).

FIG. 7 is a diagram illustrating an example of the search condition table 501.
The search condition table 501 includes an ID for uniquely identifying a search condition, a search condition represented by a logical expression including a character string, and a final acquisition time that means acquisition of posts after that time.

  In step S402, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 starts the iterative process up to step S405 for each search condition acquired in step S401.

In step S403, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 makes an inquiry to the SNS site 120 using a search condition that is a processing target, and acquires an SNS post.
In step S404, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 stores the SNS post acquired in step S403 in the post table 601 (FIG. 8) in the SNS data storage area 104 (FIG. 6). If a post that has already been acquired is registered, a search condition ID is added to the post.

FIG. 8 is a diagram illustrating an example of the posting table 601.
The post table 601 includes an ID that uniquely indicates a post, a user who is the name of the user who made the post, a post that is the content of the SNS post, a storage time that is the time when the post is stored, and a search condition. It consists of a search condition ID that indicates whether it has been searched.

  In step S405, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 performs the processing from step S402 when there is a next search condition. If there is no next search condition, the SNS post collection process is terminated.

(Specific example of SNS post collection processing)
Details of the SNS post collection processing will be described using a specific example.

  In step S401, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 acquires a list of search conditions (ID, search conditions, and last acquisition time) from the search condition table 501 illustrated in FIG.

  In step S402, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 starts the iterative process up to step S405 for the first search condition 701 in the list of search conditions acquired in step S401.

  In step S403, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 makes an inquiry to the SNS site 120 using the search condition 701, and the last acquisition time (2015-11-23 09:00:00) The SNS post including any of the character strings “32D Mark II”, “32dmk2”, or “32D Mark2” is acquired after that.

  In step S404, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 stores the SNS post acquired in step S403 in the post table 601 shown in FIG.

The search condition 701 is “32D
Since the search condition includes any of the character strings “Mark II”, “32dmk2”, or “32D Mark2”, the posts 801 to 806, 808, and 809 are searched among the SNS posts shown in the post table 601. This is a post acquired and stored under the condition 701, and the ID of the search condition 701 is 1 as the search condition ID.

  In step S405, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 performs the processing from step S402 because the search condition list includes the next search condition 702.

  In step S402, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 starts the iterative process up to step S405 for the search condition 702.

  In step S403, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 makes an inquiry to the SNS site 120 using the search condition 702, and the last acquisition time (2015-11-23 09:00:00) Subsequently, an SNS post including the character string “N12000” is acquired.

  In step S404, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 stores the SNS post acquired in step S403 in the post table 601 shown in FIG.

Since the search condition 702 is a search condition that includes the character string “N12000”, among the SNS posts shown in the post table 601, posts 801, 807, and 808 are posts acquired and stored by the search criteria 702. Yes, 2 which is the ID of the search condition 702 is added as a search condition ID.
Since the SNS posts 801 and 808 are already registered, the ID 2 of the search condition 702 is added to the search condition IDs of these posts and becomes 1, 2 without re-registration.

In step S405, the CPU 201 (SNS post collection unit 103) of the information processing apparatus 100 performs the processing from step S402 because the search condition list includes the next search condition 703.
Thereafter, the same processing is repeated and the processing is terminated.

  Note that the SNS post collection unit 103 constitutes an example of a “first collection unit” according to the present invention.

(Purchase / consideration information detection processing)
Next, details of the purchase / consideration information detection processing in step S303 in FIG. 3 will be described with reference to FIGS. 9 and 10 to 14.

  In step S <b> 901, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs morphological analysis and dependency analysis on the posting that is the processing target acquired from the posting table 601 (FIG. 8).

The morpheme analysis is a process of analyzing a character string that is not divided and identifying a morpheme constituting the character string, and the dependency analysis is a process of analyzing a dependency relationship of morphemes identified by the morpheme analysis. FIG. 10 shows an example of the results of morphological analysis and dependency analysis.
In the present embodiment, when a posting is composed of a plurality of sentences, it is configured to process a plurality of analysis results together, but may be configured to process each sentence included in the posting. Absent.

  In step S902, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs a predicate on the predicate (consisting of a predicate and an attached word) in the result of the morphological analysis and dependency analysis acquired in step S901. Referring to the attribute table 503 (FIG. 12), the predicate attribute corresponding to the predicate adjunct is acquired. Then, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 refers to the purchase / review predicate table 502 (FIG. 11), the predicate of the predicate, the acquired predicate attribute, the predicate and the predicate. If there is an item that matches the attribute, the predicate of the item is acquired as a purchase / review predicate. At this time, the type of the item and the target case indicator are also acquired.

FIG. 11 is a diagram illustrating an example of the purchase / review predicate table 502.
The purchase / review predicate table 502 includes a predicate, a predicate attribute that is an attribute of a predicate including the predicate, a type representing purchase or review, and a target case indicator indicating a target case of the predicate (predicate). Become.

FIG. 12 is a diagram illustrating an example of the predicate attribute table 503.
The predicate attribute table 503 includes an adjunct and a predicate attribute that is an attribute of the predicate including the adjunct. The predicate attribute is determined by the predicate attribute table 503 based on an adjunct that follows the predicate in the predicate.

In step S903, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 starts the iterative process up to step S910 for the purchase / review predicate acquired in step S902.
In step S <b> 904, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 determines the action principal of the purchase / review predicate from the result of morphological analysis / dependency analysis. If the action main character is first person or omitted, the process proceeds to step S905. If the action main character is not omitted and it is other than the first person, the process proceeds to step S910.

In step S905, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 detects a target case related to the predicate (purchase / review predicate). The target case is determined from the results of morphological analysis and dependency analysis based on the target case indicator defined in the purchase / review predicate table 502.
In step S906, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 starts the iterative process up to step S909 for the target case acquired in step S907.

In step S907, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 determines whether the target case acquired in step S907 matches the product name. Specifically, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 refers to the posting table 601 (FIG. 8), acquires the post search condition ID, and searches the search table 501 (FIG. 7). The product name is acquired from the search condition of the acquired search condition ID, and it is determined whether or not the target case matches the acquired product name. Product names shall be unified in either notation. Further, a product name may be configured to use a dictionary or the like.
If the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 matches the product name, the process proceeds to step S908. If it does not match the product name, the process proceeds to step S909.

  In step S908, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 associates the purchase / review predicate and the product name with the type (purchase / review, etc.), the purchase / review user, etc. The data is stored in the purchase / review information table 1301 (FIG. 14) in the review information storage area 107 (FIG. 13).

FIG. 14 is a diagram illustrating an example of the purchase / review information table 1301.
The purchase / review information table 1301 includes a predicate, a predicate included in the predicate (purchase / review predicate), a predicate attribute that is a predicate attribute, a product name, a type, and a post ID related to the posting. , And the user who is the posted user name.
In step S908, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 specifically refers to the above purchase / review information detection process and posting table 601 (FIG. 8), and stores these pieces of information. Are stored in the purchase / review information table 1301.

  In step S909, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 performs the processing from step S906 when there is the next target case. If there is no next target case, the process proceeds to step S910.

  In step S910, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs the processing from step S903 when there is a next purchase / review predicate. If there is no next purchase / review predicate, the purchase / review information detection process is terminated.

  In this embodiment, the explanation is simplified so as not to be complicated, but the case indicator by the combination of the action particle and the first person determination, the parallel particle or particle omission in the determination of the target case, the change in the use of the predicate and the appendix. Naturally, the response to such changes is considered.

(Specific example of purchase / examination information detection processing)
Next, as a specific example of the purchase / review information detection process, a case where the purchase / review information detection process shown in FIG. 9 is performed on the SNS post 801 in FIG. 8 will be described.

  In step S <b> 901, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs morphological analysis and dependency analysis on the post 801 and obtains the result of the morphological analysis and dependency analysis shown in FIG. 10.

  In FIG. 10, as a result of the morphological analysis of the post 801 “I'm worried about N12000 and 32dmk2”, it is analyzed into the morphemes “N12000” “to” “32dmk2” “de” “worried”, and “N12000” and “32dmk2” "Is a target case, and" I'm worried "is a predicate. As a result of dependency analysis, “N12000” is related to “to”, “32dmk2” is related to “de”, “N12000 and” is related to “32dmk2”, and “N12000 and 32dmk2” is “worried” ".

  In step S902, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 determines the predicate 1001 “I am worried” (predicate: “worried”) in the result of the morphological analysis and dependency analysis acquired in step S901. On the other hand, referring to the predicate attribute table 503 (FIG. 12), since there is no predicate attribute corresponding to the adjunct, the predicate attribute is set to “none”. Then, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 refers to the purchase / review predicate table 502 (FIG. 11) and purchases the predicate “worried” of the item 1101 whose predicate and predicate attribute match.・ Acquire as examination predicate. At this time, the type “consideration” and the target case indicator “detoka” of the item 1101 are also acquired.

In step S903, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 starts the iterative process up to step S910 for the purchase / review predicate “worried” acquired in step S902.
In step S904, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 omits the action principal of the purchase / review predicate “worried” from the result of the morphological analysis / dependence analysis. Move processing.

In step S905, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 uses the target case indicator “de, toka” as the target case related to the purchase / review predicate “worries” and uses “N12000”. ”(Target case indicator“ to ”) and“ 32dmk2 ”(target case indicator“ de ”) are detected.
In step S <b> 906, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 starts the iterative processing up to step S <b> 909 for the target case “N12000” acquired in step S <b> 907.

  In step S907, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 uses the search condition ID2 of the post 801 in the post table 601 (FIG. 8) as the target case “N12000” acquired in step S907. Since it matches the product name “N12000” in the search condition 702 of the search table 501 (FIG. 7), the process proceeds to step S908.

  In step S908, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 posts the predicate “I am worried”, the purchase / review predicate “I worried”, the product name “N12000”, and the type “review”. (Posting ID = 1) and the posting user “kagawa” are associated with each other and stored in the purchase / review information table 1301 (1401 in FIG. 14).

In step S909, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 performs the processing from step S906 because there is the next target case “32dmk2”.
In step S906, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 starts the iterative process up to step S909 for the target case “32dmk2” acquired in step S907.

  In step S907, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 determines that the target case “32dmk2” acquired in step S907 is via the search condition ID1 of the post 801 in the post table 601 (FIG. 8). Since it matches the product name “32dmk2” in the search condition 701 of the search table 501 (FIG. 7), the process proceeds to step S908.

  In step S908, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 posts the predicate “worried”, the purchase / review predicate “worried”, the product name “32dmk2”, and the type “review”. (Posting ID = 1) and the posting user “kagawa” are associated and stored in the purchase / review information table 1301 (1402 in FIG. 14).

In step S909, the CPU 201 (purchase / examination information detection unit 105) of the information processing apparatus 100 moves the process to step S910 because there is no next target case.
In step S910, the CPU 201 (purchase / review information detection unit 105) of the information processing apparatus 100 ends the purchase / review information detection process because there is no next purchase / review predicate.

  The purchase / review information detection unit 105 constitutes an example of the “detection unit” according to the present invention.

(Browsing information collection process)
Next, details of the browsing information collection processing in step S307 in FIG. 3 will be described with reference to FIGS. 15 and 16 to 17.

  In step S1501, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a list of users (hereinafter, also referred to as follow users) that the user who is the processing target follows from the SNS site 120, and follows the follow user table 602 ( FIG. 16).

FIG. 16 is a diagram illustrating an example of the follow user table 602.
In the follow user table 602, the user name of the user and the user name of the user that the user follows are registered.

  In step S1502, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S1509 for the follow user acquired in step S1501.

In step S1503, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a post of a follow user who is a processing target from the posting table 601 (FIG. 8).
In the present embodiment, since posts regarding products and competing products are acquired from the SNS site 120, the posting is acquired from the posting table, but may be configured to be acquired directly from the SNS site 120. .

In step S1504, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the repetitive processing up to step S1508 for the follow user post acquired in step S1503. In step S1505, the CPU 201 of the information processing apparatus 100. The (browsing information collection unit 106) determines whether there is link information (URL (Uniform Resource Locator)) in the post. If there is link information, the process proceeds to step S1506. If there is no link information, the process proceeds to step S1508.

In step S <b> 1506, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a title as link destination information of link information from the Internet 130.
In step S1507, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 associates the link information (URL) and the link destination information (title) acquired in step S1506 with the user, and displays the browsing information table 1302 ( FIG. 17).

FIG. 17 is a diagram illustrating an example of the browsing information table 1302.
The browsing information table 1302 includes an ID for uniquely identifying browsing information, a user as a user name, a URL as link information, and a title (or tweet (registered trademark) as link destination information of link information. It may be the content that was made). This means that there is a high possibility that the user followed the link information and browsed the title of the linked information.

In step S1508, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S1504 when there is a next posting. If there is no next post, the process proceeds to step S1509.
In step S1509, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S1502 when there is a next follow user. If there is no next follower, the browsing information collection process is terminated.

(Specific example of browsing information collection processing)
Next, as a specific example of the browsing information collection process, a case where the browsing information collection process illustrated in FIG. 15 is performed on the user “kagawa” when there is a follow relationship illustrated in FIG. 16 will be described.

  In step S1501, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a list of users that the user “kagawa” to be processed follows from the SNS site 120, and stores the list in the follow user table 602 (FIG. 16 of 1601).

In step S1502, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S1509 for the follow user 1601 acquired in step S1501.
In step S1503, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a post 802 of the first follow user “dcnews” to be processed from the post table 601 (FIG. 8).

In step S1504, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S1508 for the post 802 of the follow user “dcnews” acquired in step S1503.
In step S1505, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 moves the process to step S1506 because link information (URL) is included in the post 802.

In step S1506, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 releases the title “Kannon 32D Mark II” linked to the link information (http://www.dcnews.com/20151123-1) from the Internet 130. "Commemorative campaign start!"
In step S1507, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires the link information (URL = http: //www.dcnews.com/20151123-1) acquired in step S1506 and the title that is the link destination information. = "Cannon 32D Mark II release commemoration campaign start!") Is associated with the user "kagawa" and stored in the browsing information table 1302 (FIG. 17) as browsing information 1701.

In step S <b> 1508, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S <b> 1504 since there is a next post 805 of the follow user “dcnews”.
In step S <b> 1504, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S <b> 1508 for the post 805 of the follow user “dcnews”.

In step S <b> 1505, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 moves the process to step S <b> 1506 because there is link information (URL) in the post 805.
In step S <b> 1506, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 links the title ““ Kannon 32D Mark II ”of the link information (http://www.dcnews.com/20151123-3) from the Internet 130. Get a review "".

  In step S1507, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 obtains the link information (URL = http: //www.dcnews.com/20151123-3) acquired in step S1506 and the title that is the link destination information. = ““ Cannon 32D Mark II Review ”) is associated with the user“ kagawa ”and stored in the browsing information table 1302 (FIG. 17) as browsing information 1702.

In step S1508, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 moves the process to step S1509 because there is no next post of the follow user “dcnews”.
In step S <b> 1509, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S <b> 1502 because there is the next follow user “okazaki”.

In step S1502, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S1509 for the follow user “okazaki”.
In step S <b> 1503, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a post from the follow user “okazaki” as a processing target from the posting table 601.

In step S1504, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the repetitive processing up to step S1508 for the post 807 of the follow user “okazaki” acquired in step S1503. The CPU 201 (browsing information collection unit 106) of the apparatus 100 moves the process to step S1508 because there is no link information (URL) in the post 807.

In step S <b> 1508, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 performs the processing from step S <b> 1504 because there is the next post 809 of the follow user “okazaki”.
In step S1504, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts the iterative process up to step S1508 for the post 809 of the follow user “okazaki”.

In step S1505, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 moves the process to step S1508 because there is no link information (URL) in the post 809.
In step S1508, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 moves the process to step S1509 because there is no post following the follow user “okazaki”.

In step S <b> 1509, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 ends the browsing information collection process because there is no next follow user for the user “kagawa”.
As a result, information (browsing information 1701 and 1702) that is likely to be browsed by the user “kagawa” is stored in the browsing information table 1302.

  The browsing information collection unit 106 constitutes an example of a “second collection unit” according to the present invention.

(Aggregation process)
Next, the counting process executed by the analysis unit 108 of the information processing apparatus 100 will be described with reference to the flowchart of FIG. 18 and FIG.

In step S1801, the CPU 201 (analysis unit 108) of the information processing apparatus 100 acquires the product name of the product to be analyzed. You may accept the designation of the product name.
In step S1802, the CPU 201 (analysis unit 108) of the information processing apparatus 100 acquires a list of URLs from the browsing information table 1302 (FIG. 17).

In step S1803, the CPU 201 (analysis unit 108) of the information processing apparatus 100 acquires a list of users from the purchase / review information table 1301 (FIG. 14).
In step S1804, the CPU 201 (analysis unit 108) of the information processing apparatus 100 initializes the tabulation table 1901 (FIG. 19).

FIG. 19 is a diagram showing an example of the tabulation table 1901.
The tabulation table 1901 is a tabulation table for the products to be analyzed. For the URL and each user, an analysis target product purchase indicating that the analysis target product has been purchased, and a product other than the analysis target have been purchased. The product is classified into one of the states of product purchase or analysis of product to be analyzed indicating that the product to be analyzed has been examined, and further browsing of URL destination information or browsing of URL destination information is being browsed. It is classified as either non-browsing indicating that there is no data, and the result of aggregation is shown.

In step S1805, the CPU 201 (analysis unit 108) of the information processing apparatus 100 starts the iterative process up to step S1812, for each URL in the list of URLs acquired in step S1802.
In step S1806, the CPU 201 (analysis unit 108) of the information processing apparatus 100 adds URLs to the tabulation table 1901 (FIG. 19).

In step S1807, the CPU 201 (analysis unit 108) of the information processing apparatus 100 starts the iterative process up to step S1811 for each user in the user list acquired in step S1803.
In step S1808, the CPU 201 (analysis unit 108) of the information processing apparatus 100 refers to the browsing information table 1302 (FIG. 17) to confirm whether or not the target URL is registered in the user's URL. Thus, the presence / absence of browsing of the user's link (URL) destination information is acquired.

  In step S1809, the CPU 201 (analysis unit 108) of the information processing apparatus 100 refers to the purchase / review information table 1301 (FIG. 14), and the user performs “analysis target product purchase”, “other product purchase”, “analysis target”. It is determined whether the product is in the “product review” state.

  Specifically, the CPU 201 (analysis unit 108) of the information processing apparatus 100 acquires the product name and type (purchase, review, etc.) of the target user from the purchase / review information table 1301 (FIG. 14). If the analysis target product is purchased, that is, if the product name matches the product name of the product to be analyzed and the type is purchase, it is determined that “analysis target product purchase”. If the product to be analyzed has not been purchased and other products have been purchased, that is, if the product name is different from the product name of the product to be analyzed and the type is purchase, Product purchase ”is determined. In addition, if the product to be analyzed is not in any of the states, that is, if the product name matches the product name of the product to be analyzed and the type is considered, It is determined that the target product is considered.

In this embodiment, other products are aggregated together, but may be configured to aggregate for each product. Moreover, you may comprise so that the examination of other products may also be totaled.
Further, the determination of the state is rejected, but it is not necessary to do so. For example, for a certain user, it may be determined that “analysis target product purchase” and “other product purchase” are determined.

In step S <b> 1810, the CPU 201 (analysis unit 108) of the information processing apparatus 100 sets 1 in the tabulation table item corresponding to whether or not the link (URL) destination information acquired in step S <b> 1808 is browsed and the state determined in step S <b> 1809. to add.
At this time, an item and a user may be associated and stored.

In step S1811, the CPU 201 (analysis unit 108) of the information processing apparatus 100 performs the processing from step S1807 when there is a next user. If there is no next user, the process proceeds to step S1812.
In step S1812, the CPU 201 (analyzing unit 108) of the information processing apparatus 100 performs the processing from step S1805 when there is a next URL. If there is no next URL, the counting process is terminated.
As a result of the tabulation process, a tabulation table 1901 as shown in FIG. 19 can be obtained.

  The analysis unit 108 constitutes an example of “analysis means” according to the present invention.

(Analysis and placement process)
FIG. 20 is a diagram illustrating an example of a screen (analysis / posting screen 2001) for performing analysis and placement based on the summary table 1901 (FIG. 19).

  The CPU 201 of the information processing apparatus 100 may display the analysis / delivery screen 2001 on the display 210 of the information processing terminal 100 and accept input from the keyboard 209 or the like. When the CPU 201 of the information processing apparatus 100 receives a request from the analyst terminal 110 via the network, the CPU 201 transmits an analysis / manufacture screen 2001 to be displayed on the display 210 of the analyst terminal 100 and is operated from the analyst terminal 110. May be accepted.

  When the target product is specified in the target product specification column 2002, the CPU 201 (analyzing unit 108) of the information processing apparatus 100 executes the totaling process shown in FIG. 18, and displays the totaling table 1901 (FIG. 19) as the totaling result. Based on this, the aggregation column 2003 is updated. Although the tabulation column 2003 is a table for easy explanation, it may be expressed using a graph or the like.

  As a result, it is possible to analyze the influence given at the time of purchase for each piece of link destination information. For example, in the example of FIG. 20, posts including a campaign link are not browsed so much, but it can be seen that the percentage of people who browsed is high. In addition, it can be seen from the total item 2004 that there are many people who are considering purchasing a product although they are not browsing posts including a campaign link.

  It is efficient if the CPU 201 of the information processing apparatus 100 executes the advertisement for the user corresponding to the total item 2004 by selecting the total item 2004 in the total column 2002 and pressing the submission button 2005. It is possible to carry out promotions. This can be achieved by configuring the items and users to be stored in association with each other in step S1810 of FIG.

  Note that an example of the “transmission means” according to the present invention is configured by the processing by the submission button 2005 on the analysis / submission screen 2001.

<Modification>
Next, a modified example in the embodiment of the present invention will be described. Note that the configuration, processing, and the like in the above-described embodiment are provided with the same configuration, processing, and the like, so that the same components are described using the same reference numerals, and only different portions are described.

  In the embodiment of the present invention, with respect to the URL included in the post of the user to follow, the presence / absence of browsing according to the purchase status such as the purchase of the product to be analyzed and the examination is analyzed. The post including the URL is a post sent by the user himself / herself, a post retweeted, or the presence / absence of browsing is analyzed.

FIG. 21 is a flowchart showing the overall flow of the collection and analysis process that is periodically executed in the information processing apparatus 100 of the present embodiment. This process is an improvement of the flowchart shown in FIG. is there.
A process different from the flowchart shown in FIG. 3 is that a transmission information collection process in step S2101 is added.
FIG. 22 is a flowchart showing details of the transmission information collection processing in step S2101.

In step S2201, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a user's posting from the posting table 601 (FIG. 8).
In step S2202, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 starts an iterative process up to step S2206 for the user's post acquired in step S2201.

In step S2203, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 determines whether there is link information (URL) in the post. If there is link information, the process proceeds to step S2204. If there is no link information, the process proceeds to step S2206.
In step S <b> 2204, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 acquires a title as link destination information of link information from the Internet 130.

In step S2205, the CPU 201 (browsing information collection unit 106) of the information processing apparatus 100 associates the link information (URL) and the link destination information (title) acquired in step S1506 with the user, and displays the browsing information table 2302 ( 23).
When this browsing information is stored in the browsing information table 2302 (FIG. 23), it is determined whether the post to be processed is a post sent from the user itself or retweeted by the user. Stores the call type for identification.

  The browsing information table 2302 shown in FIG. 23 is an improvement of the browsing information table 1302 shown in FIG. 17 differs from the browsing information table 1302 shown in FIG. 17 in that a transmission type for identifying information “transmission” 2303 indicating a post transmitted by the user and information “RT” 2304 transmitted by retweeting by the user. It is a point equipped with.

  When the aggregation process shown in FIG. 18 is performed after the collection and analysis processes are completed in this way, in step S1808, the CPU 201 (analysis unit 108) of the information processing apparatus 100 refers to the browsing information table 2302 (FIG. 23). Then, it is confirmed whether or not the target URL is registered in the user's URL, and the transmission type is acquired.

  In step S1810, the CPU 201 (analysis unit 108) of the information processing apparatus 100 counts the presence / absence of browsing of the link (URL) destination information acquired in step S1808, the transmission type, and the state determined in step S1809. Add 1 to the item.

  FIG. 24 is a summary table 2401 in which the transmission type is added to the summary table 1901 in FIG. For each item of “analysis target product purchase”, “purchase other product”, and “analysis target product review”, items of “transmission” and “RT” are added.

At this time, if there is a transmission type, 1 is added to “transmission” or “RT”, and if there is no transmission type, 1 is added to “view”.
In addition, when performing the addition, the priority may be determined and added to any of them in the order of description of “transmission”, “RT”, and “browsing” in consideration of the priority. Also, at this time, the item and the user may be associated and stored.

  The preferred embodiments of the information processing apparatus 100 and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

DESCRIPTION OF SYMBOLS 100 ... Information processing apparatus 101 ... Setting part 102 ... Setting storage area 103 ... SNS contribution collection part 104 ... SNS data storage area 105 ...・ ・ Purchase / Review Information Detection Unit 106 ・ Browsing Information Collection Unit 107 ・ Purchase / Review Information Storage Area 108 ・ Analysis Unit 110 ・ Analyzer Terminal 120 ・ ・... SNS site 130 ... Internet 201 ... CPU
211... External memory 501... Search condition table 502... Purchase / consideration predicate table 503 .. Predicate attribute table 601 .. Posting table 602.・ ・ Follow User Table 1301 ・ Purchase / Review Information Table 1302 ・ Browsing Information Table 1901 ・ Aggregation Table 2001 ・ Analysis / Delivery Screen 2302 Information table 2401 ・ ・ ・ ・ ・ Total table

Claims (9)

A first collection means for collecting posts related to products from posted documents;
From the post collected by the first collection means, a detection means for detecting a first user making a post related to purchase of a product,
Browsing information that may be browsed by the first user from the posting of the second user related to the first user detected by the detecting means among the postings collected by the first collecting means. A second collecting means for collecting
Analyzing means for analyzing the purchase status of the product according to presence or absence of browsing information collected by the second collecting means;
An information processing apparatus comprising:   The information processing apparatus according to claim 1, wherein the posting related to the purchase includes a post considering purchase.   The information processing apparatus according to claim 1, wherein the browsing information includes information specified from link information included in a post.   The analysis unit further analyzes the purchase status of the product by classifying the product into a target product to be analyzed or a product other than the target product. The information processing apparatus according to any one of claims.   5. The information processing apparatus according to claim 1, further comprising a transmission unit configured to transmit an advertisement to a user corresponding to an item of an analysis result of the purchase status of the product. .   The information processing apparatus according to claim 3, wherein the browsing information includes information related to retweeting a post including the link information.   The information processing apparatus according to claim 3, wherein the browsing information includes information indicating that the user himself / herself has originated and transmitted the posting including the link information. A method for controlling an information processing apparatus,
A first collection step of collecting posts related to the product from posted documents;
From the post collected by the first collection step, a detection step of detecting a first user making a post related to purchase of a product;
Browsing information that may be browsed by the first user from the posting of the second user related to the first user detected by the detecting means among the postings collected by the first collecting step. A second collecting step to collect,
An analysis step of analyzing the purchase status of the product according to presence or absence of browsing information collected by the second collection step;
A method for controlling an information processing apparatus, comprising: Computer
A first collection means for collecting posts related to products from posted documents;
From the post collected by the first collection means, detection means for detecting a first user making a post related to the purchase of a product,
Browsing information that may be browsed by the first user detected by the detecting means from the posting of the second user related to the first user among the postings collected by the first collecting means. Second collecting means to collect,
Analyzing means for analyzing the purchase status of the product according to presence or absence of browsing information collected by the second collecting means;
Program to function as.

Images