JP6725829B2 - Information processing apparatus, information processing system, control method, and program - Google Patents

Description

The present invention relates to a technique of analyzing an evaluation of a product or service transmitted by SNS or the like and performing a promotion based on the analysis result.

2. Description of the Related Art In recent years, behavioral targeting advertisements have been widely performed in Internet advertisements, in which the behaviors of visitors on the operated sites are analyzed, the hobbies and tastes are estimated, and promotions suitable for the visitors are conducted.

However, it is not easy to get the direct mention of the user, because he/she can only infer the interest from the behavior on the site.

On the other hand, with the development of SNS, a mechanism for carrying out a promotion has been provided by an SNS service provider.

In the SNS promotion, it is possible to carry out the promotion to users who are classified in advance according to hobbies/preferences, age/gender, etc. based on profiling by an SNS service provider.

However, with regard to the target of promotion, only hobbies and preferences in large units such as “photos” or “cars” can be specified, and promotion to users who have already purchased the product or purchase is not considered. There is a problem that an ineffective promotion such as a promotion to the user is carried out.

Therefore, as a method for effective promotion, there is disclosed a technology for categorizing users by digitizing their preference based on the appearance frequency of a particular keyword in posting for the purpose of carrying out the promotion (for example, refer to Patent Document 1). ..

In addition, the number of customers who visit the store based on the location information is determined, and the customers are classified by various attributes such as the number of visits to the target store or competing stores, customer data such as POS, or the presence or absence of purchases determined from SNS comments. A technique for determining a promotion method according to the result is shown (for example, refer to Patent Document 2).

JP, 2015-164008, A JP, 2013-246747, A

However, the system described in Patent Document 1 does not consider whether or not the user has purchased the product, and as a result of the classification, there is a problem that the users who have already purchased the product are included in the promotion target.

In the system described in Patent Document 2, there is a problem in that purchase of a product, interest in the product, and interest in the product are taken into consideration, but the time of purchase, related products, and competing products are not taken into consideration.

An object of the present invention is to provide a mechanism for effectively promoting a user with respect to an object to be promoted.

A first aspect of the invention for solving the above-mentioned problems is to use the information posted by a user to analyze the purchase of the user with respect to a target to be promoted, and based on an analysis result of the analyzing means, the promotion. a user that has purchased the target object and the classification of performing, the specifying means for specifying a negative user for the classification of the subject, the information relating to the promotion for the user identified by said identification means And an output means for outputting.

A second invention for solving the above-mentioned problem is an information processing system comprising an information processing device communicatively connected to a client terminal for instructing analysis of posts, wherein the client terminal is The information processing apparatus comprises a receiving means for receiving the promotion information transmitted by the transmitting means of the information processing device, and a display means for displaying the promotion information received by the receiving means. using the information, analyzing means for analyzing for the purchase of the user for the target of promotion, based on the analysis result of said analyzing means, met users who have purchased the target object and the classification for performing the promotion Then, a specifying unit that specifies a user who is negative with respect to the target of the same classification, a generating unit that generates information regarding a promotion for the user specified by the specifying unit, and a promotion that is generated by the generating unit. And a transmitting means for transmitting the information.

A third invention for solving the above-mentioned problem is a method for controlling an information processing device that analyzes a posting, wherein the information processing device uses the information posted by the user to target the user for the promotion. an analysis step of analyzing for the purchase of, based on the analysis result of the analyzing step, a user that has purchased the target object and the classification for performing the promotion, negative for the target of the same classification a specifying step of specifying the user, and executes and an output step of outputting information related to promotional to the user identified by the specifying step.

A fourth invention for solving the above-mentioned problem is based on an analysis means for analyzing the purchase of the user with respect to an object to be promoted by a computer using information posted by the user, and an analysis result of the analysis means. , a user that has purchased the target object and the classification for performing the promotion, specifying means for specifying a negative user to the subject of the same classification, the user identified by said identification means It is characterized by functioning as an output means for outputting information related to promotion.

A fifth invention for solving the above-mentioned problem is a method for controlling an information processing system including a client terminal for instructing an analysis of posting on a site and an information processing device connected via a network, The client terminal executes a receiving step of receiving information on the promotion transmitted by the transmitting step of the information processing apparatus, and a display step of displaying the information on the promotion received by the receiving step, thereby performing the information processing. The device uses the information posted by the user to perform an analysis step of analyzing the purchase of the user with respect to the promotion target, and purchases a target of the same classification as the promotion target based on the analysis result of the analysis step. a user that has the a specifying step of specifying a negative user for the classification of the subject, a generating step of generating information relating to promotion to the user identified by said identification step, said generating And a transmitting step of transmitting information on the promotion generated by the step.

According to the present invention, there is an effect that an effective promotion can be performed for a user regarding an object to be promoted.

It is a block diagram which shows schematic structure of the information processing system which concerns on embodiment of this invention. It is a block diagram which shows schematic structure of the hardware of the information processing apparatus which concerns on embodiment of this invention. It is a flow chart which shows collection and analysis processing of a post in an SNS site performed by an information processing system in an embodiment of the present invention. It is a flow chart which shows SNS contribution collection processing performed with an information processing system in an embodiment of the present invention. It is a block diagram which shows the structure of a setting storage area in embodiment of this invention. It is a block diagram which shows the structure of the SNS data storage area in embodiment of this invention. It is a block diagram which shows the structure of a search condition table in embodiment of this invention. It is a block diagram which shows the structure of a posting table in embodiment of this invention. It is a flow chart which shows purchase / examination detection processing performed with an information processing system in an embodiment of the present invention. FIG. 6 is an explanatory diagram showing an example of a result of morpheme analysis/dependency analysis for a post in the embodiment of the present invention. It is a block diagram which shows the structure of a purchase and examination predicate table in embodiment of this invention. It is a block diagram which shows the structure of a predicate attribute table in embodiment of this invention. It is a block diagram which shows the structure of the purchase and consideration information storage area in embodiment of this invention. It is a block diagram which shows the structure of a purchase/examination information table in embodiment of this invention. It is a block diagram which shows the structure of a product table in embodiment of this invention. It is a block diagram which shows the structure of a product class table in embodiment of this invention. It is a flowchart which shows the evaluation expression detection process performed with the information processing system in embodiment of this invention. It is a block diagram which shows the structure of an evaluation expression table in embodiment of this invention. FIG. 6 is an explanatory diagram showing an example of a result of morpheme analysis/dependency analysis for a post in the embodiment of the present invention. It is a block diagram which shows the structure of a user evaluation table in embodiment of this invention. It is a flowchart which shows the submission process which implements the promotion of the specific product performed with the information processing system in embodiment of this invention. It is a flowchart which shows the promotion target user candidate acquisition process with respect to the specific product performed by the information processing system in embodiment of this invention. It is a block diagram which shows the structure of the submission screen which concerns on embodiment of this invention. It is a flowchart which shows the submission process which implements the promotion of the specific product performed with the information processing system in embodiment of this invention. It is a block diagram which shows the structure of a setting storage area in embodiment of this invention. It is a block diagram which shows the structure of a premise product table in embodiment of this invention. It is a flowchart which shows the submission process when performing a promotion for every user performed in an information processing system in an embodiment of the present invention.

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

Next, a first embodiment of the present invention will be described.

FIG. 1 is a diagram showing an example of the configuration of an information processing system 100 of the present invention.

In the information processing system 100, when setting the information processing apparatus 110, the information acquisition method and the promotion method for the information processing apparatus 110, and analyzing the posting on the SNS site 130 and submitting based on the analysis result. The one or more analyst terminals 120 for inputting instructions are appropriately connected via a local area network.

Further, in the information processing system 100, the information processing device 110 is connected to an external network and is configured to be connectable to an SNS site 130 that provides an SNS service.

The information processing apparatus 110 sets, in the setting unit 101, collection conditions and the like for collecting posts from the SNS site 130 based on the settings input from the analyst terminal 120.

The setting storage area 102 stores collection conditions for collecting posts and the like from the SNS site 130, and the SNS post collection unit 103 collects posts and the like from the SNS site 130 based on the collection conditions and saves SNS data. The area 104 stores the posts and the like collected by the SNS post collection unit 103.

The purchase/examination information detection unit 105 analyzes the posts and the like stored in the SNS data storage area 104, and analyzes the purchase status of the product of the user such as the posting user has purchased the product or is considering the purchase. Further, the evaluation of the product is analyzed, and the purchase/study information storage area 106 stores the analysis result in the purchase/study information detection unit 105.

The submission unit 107 generates information for promoting a product purchase according to the result of analysis of the product stored in the purchase/study information storage area 106.

The details of each function will be described together with the description of the process in the flowchart described later.

The hardware configuration of the information processing apparatus applicable to the information processing apparatus 110 and the analyzer terminal 120 shown in FIG. 1 will be described below with reference to FIG.

FIG. 2 is a block diagram showing a hardware configuration of the information processing apparatus 110 and the information processing apparatus applicable to the analyzer terminal 120 shown in FIG.

In FIG. 2, reference numeral 201 denotes a CPU, which centrally controls each device and controller connected to the system bus 204.

Further, the ROM 202 or the external memory 211 is necessary to realize a control program of the CPU 201, such as a BIOS (Basic Input/Output System), an operating system program (hereinafter, OS), and a function executed by each server or each PC. Various programs to be described later are stored.

A RAM 203 functions as a main memory and a work area of the CPU 201. The CPU 201 loads various programs necessary for executing the processing from the ROM 202 or the external memory 211 into the RAM 203, and executes the loaded programs to realize various operations.

An input controller 205 controls inputs from a keyboard (KB) 209 and a pointing device such as a mouse (not shown). A video controller 206 controls display on a display device such as the display 210.

Although the display 210 is shown in FIG. 2, the display is not limited to a CRT, and may be a display such as a liquid crystal display. These are used by the administrator as needed.

A memory controller 207 is installed in an external storage device (hard disk (HD)) for storing a boot program, various applications, font data, user files, editing files, various data, a flexible disk (FD), or a PCMCIA card slot. It controls access to an external memory 211 such as a CompactFlash (registered trademark) memory connected via an adapter.

A communication I/F controller 208 connects and communicates with an external device via an external network, and executes communication control processing on the external network. For example, communication using TCP/IP is possible.

Note that the CPU 201 enables display on the display 210, for example, by executing outline font rasterization processing in a display information area in the RAM 203.

Further, the CPU 201 enables a user instruction using a mouse cursor or the like (not shown) on the display 210.

Various programs to be described later for implementing the present invention are recorded in the external memory 211 and are executed by the CPU 201 by being loaded into the RAM 203 as necessary.

Furthermore, the definition file and various information tables used when the above program is executed are also stored in the external memory 211, and a detailed description thereof will be described later.
(Overall flow)

Next, with reference to the flowchart of FIG. 3, a process of collecting and analyzing posts in the SNS site 130, which is regularly executed in the information processing apparatus 110 of the present embodiment, will be described.

First, in order to start this processing, for example, an instruction to start analysis of a post, that is, an instruction to request the result of analysis is received on a screen (not shown) displayed on the display 210 of the analyst terminal 120. Then, the process is started.

In step S301, the SNS post collection unit 103 acquires a post from the SNS site 130 based on the collection condition stored in the setting storage area 102, and stores the acquired post in the SNS data storage area 104.

In step S302, the purchase/examination information detection unit 105 starts the iterative process up to step S306 for the posting acquired in step S301.

In step S303, the purchase/examination information detection unit 105 performs morphological analysis/dependency analysis on the post that is the processing target.

In step S304, the purchase/study information detection unit 105 detects purchase/study information from the dependency analysis result obtained in step S303 for the post to be processed, and saves it in the purchase/study information storage area 106. Details will be described later.

In step S305, the purchase/consideration information detection unit 105 detects an evaluation expression from the dependency analysis result obtained in step S303 for the post to be processed, and stores it in the purchase/consideration information storage area 106. Details will be described later.

In step S306, the purchase/examination information detection unit 105 performs the processing from step S302 when the next posting is made. If there is no next post, the process ends.

In the present description, the acquisition of the SNS post, the purchase/examination information detection process, and the evaluation expression detection process are described to be executed synchronously, but they may be executed asynchronously.
(SNS post collection process)

Details of the SNS post collection process S301 will be described with reference to FIG.

FIG. 5 shows the configuration of the setting storage area 102. The setting storage area 102 includes a search condition table 501, a purchase/study predicate table 502, a predicate attribute table 503, an evaluation expression table 504, a product table 505, and a product class table. 506 is provided.

FIG. 6 shows the configuration of the SNS data storage area 104. The SNS data storage area 104 includes a post table 601.

In step S401, the SNS post collection unit 103 refers to the search condition table 501 in the setting storage area 102 and acquires the search condition whose last acquisition time is before the specified value.

In step S402, the SNS post collection unit 103 starts the iterative process up to step S405 for the search condition acquired in step S401.

In step S403, the SNS post collection unit 103 makes an inquiry to the SNS site 130 using the search condition to be processed, and acquires the post after the last acquisition time.

In step S404, the SNS post collection unit 103 stores the post acquired in step S403 in the post table 601 in the SNS data storage area 104.

If the post has already been registered, the post ID is issued so that the post ID is unique in the post table 601 and the post is added.

In step S405, the SNS post collection unit 103 executes the process from step S402 when there is the next search condition, and ends the process when there is no next search condition.
(Concrete example)

FIG. 7 shows a specific example of the search condition table 501. The search condition table 501 includes, for the SNS site 130, a search condition indicating a condition for searching a post to be processed, and a last acquisition time indicating a time at which a post was searched using the search condition last time. ing.

Further, FIG. 8 shows a specific example of the posting table 601. The post table 601 is a post ID for uniquely identifying posts collected by searching the SNS site 130, a post user who posted, a post time indicating a time when a post was made, and a search when a search was made. It is configured to include conditions and the like.

In step S401, the SNS post collection unit 103 acquires search conditions from the search condition table 501 shown in FIG.

In step S402, the SNS post collection unit 103 starts the iterative process up to step S405 for the first search condition 701 of the search conditions acquired in step S401.

In step S403, the SNS post collection unit 103 makes an inquiry to the SNS site 130 using the search condition 701, and is posted after the last acquisition time (2015-11-23 09:00:00) "32D Mark II". Acquire an SNS post containing any of the character strings "32dmk2" and "32D Mark2".

In step S404, the SNS post collection unit 103 stores the SNS posts 803 and 804 acquired in step S403 in the post table 601 shown in FIG.

In step S405, the SNS post collection unit 103 performs the processing from step S402 since the next search condition 702 exists.

In step S402, the SNS post collection unit 103 starts the iterative process up to step S405 for the search condition 702.

In step S403, the SNS post collection unit 103 makes an inquiry to the SNS site 130 using the search condition 702, and the character string “N12000” posted after the last acquisition time (2015-11-23 09:00:00). Get posts that include.

In step S404, the SNS post collection unit 103 stores the SNS posts 801 and 804 acquired in step S403 in the post table 601 shown in FIG.

Since the SNS post 804 is already registered, 2 is added to the search condition ID in the SNS post 804, and the SNS post 801 is registered in the post table 601.

In step S405, the SNS post collection unit 103 has the next search condition 703, so the process from step S402 is performed, and the SNS post 802 and the SNS post 803 are registered.
After that, similar processing is repeated and the processing ends.
(Purchase/Study detection processing)

Next, details of the purchase/examination detection process S304 will be described with reference to FIG.

FIG. 10 shows an example of the result of the morphological analysis/dependency analysis which is the input of the purchase/examination detection process.

The morphological analysis is a process of analyzing a character string that is not divided into pieces and identifying the morphemes forming the character string, and the dependency analysis is a process of analyzing the dependency relationship of the morphemes identified by the morphological analysis.

In the present embodiment, when the post is composed of a plurality of sentences, the plurality of analysis results are collectively processed, but it is also possible to process each sentence included in the post. Absent.

In step S901, the purchase/examination information detection unit 105 refers to the purchase/examination predicate table 502 with respect to the predicate in the result of the morphological analysis/dependency analysis received as an input, and the item whose predicate and predicate attribute match If there is, it is acquired as a predicate indicating purchase or consideration.

A specific example of the purchase/study predicate table 502 is shown in FIG. The purchase/examination predicate table 502 is a predicate of a statement, a predicate attribute indicating a state related to a predicate of the action nominative of the predicate, a word shown in the predicate is a purchase nominative of the action nominative related to purchase or considering purchase. It is configured to include a type indicating a situation and a target case indicator for determining a target to which the predicate relates.

The attribute of the predicate is determined by the predicate attribute table 503 based on the combination of adjuncts following the predicate.

FIG. 12 shows a specific example of the predicate attribute table 503. The predicate attribute table 503 includes an adjunct word of a predicate of a sentence and a predicate attribute indicated by the adjunction of the predicate to the predicate.

In step S902, the purchase/examination information detection unit 105 starts repetitive processing up to step S909 for the predicate indicating the purchase or consideration acquired in step S901.

In step S903, the purchase/examination information detection unit 105 determines the action subject of the predicate indicating purchase or consideration.

If the action nominative is first person or omitted, the process moves to step S904. If the action nominative is not first person, the process moves to step S909.

In step S904, the purchase/examination information detection unit 105 detects the target case related to the predicate. The target case is determined based on the target case indicator defined in the purchase/study predicate table 502.

In step S905, the purchase/examination information detection unit 105 starts the iterative process up to step S908 for the target case acquired in step S904.

In step S906, the purchase/examination information detection unit 105 determines whether the target case to be processed matches the product name or the product class name.

If it matches the product name or product class name, the process proceeds to step S907. If it does not match the product name or product class name, the process proceeds to step S907.

In the present embodiment, the determination of the product name is made based on whether the product name defined in the product table 505 shown in FIG.

The product table 505 includes a product manufacturer, a product name, another notation for the product name, a class indicating a product classification, a product grade, and a product release date.

Further, the product class name is determined by whether or not it matches the product class name of the product class table 506 shown in FIG. 16 or another notation, and is unified into the product class name.

In step S907, the purchase/examination information detection unit 105 associates the product name or the product class name with the post predicate, the predicate, the predicate attribute described above, the target case, the type described above, the post ID, and the posting user, It is stored in the purchase/study information table 1301 in the purchase/study information storage area 106.

FIG. 13 shows the configuration of the purchase/study information storage area 106. The purchase/study information storage area 106 includes a purchase/study information table 1301 and a user evaluation table 1302.

FIG. 14 shows a specific example of the purchase/study information table 1301. The purchase/examination information table 1301 is configured to include a predicate that is a postfix of a predicate and an adjunct, a predicate, a predicate target described above, a target indicating a target case, the type described above, a post ID, and a posting user. ..

In step S908, the purchase/examination information detection unit 105 performs the process from step S905 if there is the next target case, and moves the process to step S909 if there is no next target case.

In step S909, when the next type has a predicate indicating purchase or consideration, the purchase/examination information detection unit 105 executes the processing from step S902. If the next type does not have a predicate indicating purchase or consideration, the process ends.

In the present embodiment, the explanation of the action nominative case and the first person judgment, the omission of the parallel particles and particles in the judgment of the target case, the correspondence to the change of the case marker due to the change in the use of the predicate and the combination of the adjuncts is not complicated. However, these are naturally taken into consideration.
(Concrete example)

Next, as a specific example of the purchase/examination detection process S304, a case where the process shown in FIG. 9 is performed on the SNS post 804 will be described.

FIG. 10 shows the result of morphological analysis/dependency analysis performed on the SNS post 804.

In Figure 10, as a result of analyzing the SNS post 804 "I'm worried about N12000 and 32dmk2." Is obtained.

In step S<b>901, the purchase/examination information detection unit 105 sets the purchase/examination predicate table 502 for the predicate 1001 (predicate: “worry”, predicate attribute: none) in the result of the morphological analysis/dependency analysis for the SNS post 804. The item 1101 in which the predicate and the predicate attribute match is acquired by reference.

In step S902, the purchase/examination information detection unit 105 starts the iterative process up to step S909 for the predicate “worry” acquired in step S901.

In step S903, the purchase/examination information detection unit 105 moves the process to step S904 because the action subject of the predicate “worry” is omitted.

In step S904, the purchase/examination information detection unit 105 detects “N12000” (target case marker “to”) and “32dmk2” (target case marker “de”) as target cases related to the predicate.

In step S905, the purchase/examination information detection unit 105 starts the iterative process up to step S908 for the target case “N12000” acquired in step S904.

In step S906, the purchase/examination information detection unit 105 shifts the processing to step S907 because the target case “N12000” acquired in step S904 has a product name that matches the product table 505.

In step S907, the purchase/consideration information detection unit 105 stores the predicate “worry” and the product name “N12000” in the purchase/consideration information table 1301 in association with the post (post ID=1) and the posting user “okazaki” ( 1401 in FIG. 14).

In step S908, the purchase/examination information detection unit 105 has the next target case “32dmk2”, and thus executes the processing from step S905.

In step S905, the purchase/examination information detection unit 105 starts repetitive processing up to step S908 for the target case “32dmk2” acquired in step S904.

In step S906, the purchase/examination information detection unit 105 shifts the processing to step S907 because the target case “32dmk2” acquired in step S904 has a product name that matches the product table 505.

In step S907, the purchase/consideration information detection unit 105 stores the predicate “worry” and the product name “32dmk2” in the purchase/consider information table 1301 in association with the post (post ID=1) and the posting user “okazaki” ( 1402 in FIG. 14).

In step S908, the purchase/examination information detection unit 105 moves the process to step S909 because there is no next target case.

In step S909, the purchase/examination information detection unit 105 ends the process because there is no predicate indicating the next purchase or examination.
(Evaluation expression detection process)

Next, the details of the evaluation expression detection process S305 will be described with reference to FIG.

In step S1701, the purchase/examination information detection unit 105 refers to the evaluation expression table 504 for the predicate in the result of the morpheme analysis/dependency analysis received as an input, and if there is an item in which the predicate and the evaluation predicate match, Get as an evaluation expression.

FIG. 18 shows a specific example of the evaluation expression table 504. The evaluation expression table 504 has a positive predicate to be evaluated, an evaluation attribute indicating which of the evaluations the subject of the predicate is about, an evaluation attribute case indicator for determining the subject of the evaluation predicate, and the evaluation predicate. Alternatively, it is configured to include an evaluation that identifies that it is negative or the like.

The predicate attribute is determined by the predicate attribute table 503 based on the combination of adjuncts following the predicate, as in the predicate indicating purchase or consideration of purchase.

In step S1702, the purchase/examination information detection unit 105 starts the iterative process up to step S1706 for the evaluation expression acquired in step S1701.

In step S1703, the purchase/examination information detection unit 105 determines the subject of the predicate used as the evaluation expression.

If the subject is the product name, the process proceeds to step S1704, and if the subject is other than the product name, the process proceeds to step S1706.

In the present embodiment, in order to simplify the explanation, the determination of the subject is a word accompanied by the particle "ha".

In step S1704, the purchase/examination information detection unit 105 determines whether or not some of the words related to the predicate match the evaluation attribute of the evaluation expression to be processed and the evaluation attribute case indicator.

If there is a word in which the evaluation attribute and the evaluation attribute case indicator match, the process proceeds to step S1705. If there is no word in which the evaluation attribute and the evaluation attribute case indicator match, the process proceeds to step S1706.

In step S1705, the purchase/study information detection unit 105 associates the product name, which is the subject, with the evaluation expression, the post, and the posting user, and saves the product name in the user evaluation table 1302 (see FIG. 20) in the purchase/study information storage area 106.

FIG. 20 shows a specific example of the user evaluation table 1302. The user evaluation table 1302 is configured to include the above-described predicate, evaluation predicate, evaluation attribute, predicate attribute for identifying whether the evaluation predicate is affirmative or negative, the above-described target, type, post ID, and post user. ing.

In step S1706, the purchase/examination information detection unit 105 performs the processing from step S1702 when there is the next evaluation expression, and ends the processing when there is no next evaluation expression.
(Concrete example)

Next, as a specific example of the evaluation expression detection processing S305, a case where the result of the morphological analysis/dependency analysis on the SNS post 801 shown in FIG. 19 is input will be described.

The SNS post 801 “N12000 has poor operability...” is obtained as a result of analysis of the evaluation predicate as “bad”. If the subject of this evaluation predicate is “N12000”, the evaluation attribute is “operability”. can get.

In step S1701, the purchase/examination information detection unit 105 refers to the evaluation expression table 504 for the predicate 1901 (predicate: “bad”, predicate attribute: none) in the result of the morpheme analysis/dependency analysis illustrated in FIG. Then, the evaluation expressions 1801 and 1802 in which the predicate matches the evaluation expression predicate are acquired.

In step S1702, the purchase/examination information detection unit 105 starts the iterative process up to step S1706 for the evaluation expression 1801 acquired in step S1701.

In step S1703, the purchase/examination information detection unit 105 determines that the subject is a product because the subject “N12000” of the predicate “bad” of the evaluation expression 1801 is included in the product table 505, and the process proceeds to step S1704. Transfer.

In step S1704, the purchase/examination information detection unit 105 determines that “operability” of “N12000” and “operability” related to the predicate matches the evaluation attribute of the evaluation expression 1801, and the particle “according to “operability” is Also matches the evaluation attribute case indicator, the process moves to step S1705.

In step S1705, the purchase/study information detection unit 105 associates the product name “N12000”, which is the subject, with the evaluation expression 1801, the SNS post 801, and the posting user “kagawa”, and the user evaluation table 1302 in the purchase/study information storage area 106. Save to.

In step S1706, the purchase/examination information detection unit 105 has the following evaluation expression 1802, and thus executes the processing from step S1702.

In step S1702, the purchase/examination information detection unit 105 starts the iterative process up to step S1706 for the evaluation expression 1802 acquired in step S1701.

In step S1703, the purchase/examination information detection unit 105 determines that the subject is a product because the subject “N12000” of the predicate “bad” of the evaluation expression 1802 is included in the product table 505, and the process proceeds to step S1704. Transfer.

In step S1704, the purchase/examination information detection unit 105 does not match the evaluation attribute “image quality” of the evaluation expression 1802 with both “N12000” and “operability” related to the predicate, and thus moves the process to step S1706.

In step S1706, the purchase/examination information detection unit 105 ends the process because there is no next evaluation expression.
(Publishing process)

Next, with reference to FIG. 21, a submission process for promoting a specific product will be described.

First, in order to start this processing, for example, after receiving a placement start instruction, that is, an instruction requesting a placement result, on a screen (not shown) displayed on the display 210 of the analyzer terminal 120, Start processing.

In step S2101, the advertisement generation unit 107 receives a product name that is a promotion target as an input, and acquires a promotion target user candidate. Details will be described later.

In step S2102, the submission unit 107 starts the iterative process up to step S2107 for the candidate users acquired in step S2101.

In step S2103, the submission unit 107 determines whether the candidate user has purchased the promotion target product.

If so, the process proceeds to step S2106. If not, the process proceeds to step S2104.

In step S2104, the submission unit 107 determines whether the candidate user has a negative opinion about the replacement target product.

If the user has a negative opinion, the process moves to step S2106. If the user does not have a negative opinion, the process moves to step S2105.

In step S2105, the submission unit 107 determines whether the candidate user has purchased the replacement target product after the specified time.

If so, the process proceeds to step S2107. If not, the process proceeds to step S2106.

In step S2106, the submission unit 107 adds the candidate user to the promotion target user list.

In step S2107, the submission unit 107 performs the process from step S2102 if there is a next candidate user, and moves the process to step S2108 if there is no next candidate user.

In step S2108, the submission unit 107 performs submission processing for the users registered in the promotion target user list.

Regarding the submission process, the promotion may be directly performed to the user, or the list may be created and collectively promoted.

Also, the advertisement to be placed may be changed according to the purchased product of the user. For example, an advertisement of "upgrade campaign" may be presented to a purchaser of a lower product of the company, and an advertisement of "transfer campaign" may be presented to a purchaser of another product.
(Promotion target user candidate acquisition process)

Next, a promotion target user candidate acquisition process for a specific product will be described with reference to FIG.

In step S2201, the advertisement generation unit 107 receives the product name of the promotion target product as an input, and acquires the class and grade corresponding to the product name of the promotion target product from the product table 505. For example, this input is information related to the product input on the screen (not shown) displayed on the display 210 of the analyzer terminal 120.

In step S2202, the advertisement generation unit 107 refers to the product table 505 based on the class and grade of the promotion target product, and acquires a product of the same class/grade as the promotion target product as a replacement product.

In step S2203, the advertisement generation unit 107 refers to the product table 505 based on the class and grade of the promotion target product, and acquires the product of the next lower class/grade as the promotion target as the replacement target product.

In step S2204, the submission unit 107 refers to the purchase/examination information table 1301 and acquires the posting user who purchased the replacement target product.

In step S2205, the submission unit 107 refers to the user evaluation table 1302 and acquires a posting user who has a negative evaluation of the replacement target product.

In step S2206, the advertisement generation unit 107 refers to the purchase/consideration information table 1301 and acquires a post-promotion user or a product in the same class or a posting user who is considering the product class in the same class.
(Concrete example)

Next, as a specific example of the submission processing shown in FIGS. 21 and 22, a case of promoting “32dmk2” will be described.

In step S2101, the advertisement generation unit 107 receives the promotion target “32dmk2” as an input, performs a promotion target user candidate acquisition process, and acquires a promotion target user candidate list.

In step S2201, the advertisement generation unit 107 acquires the class “3” and the grade “3” (1501) corresponding to the product name “32dmk2” of the promotion target product from the product table 505.

In step S2202, the submission unit 107 refers to the product table 505 and acquires the same products as the class “3” and the grade “3” of “32dmk2” as the products “32D” and “N44” as replacement products.

In step S2203, the publication unit 107 refers to the product table 505, and the class grade (“class=3, grade=2” or “class=3” or “class” of “32dmk2”, which is one class lower than the class “3” and the grade “3”. =2, grade=3”) products “800D” and “N12000” are acquired as replacement products.

In step S2204, the submission unit 107 refers to the purchase/examination information table 1301 and posts the user “endo” (1403) who purchased the replacement target product (“32D”, “800D”, “N44”, “N12000”). To get

In step S2205, the submission unit 107 refers to the user evaluation table 1302, and the posting user “kagawa” who has a negative evaluation of the replacement target product (“32D”, “800D”, “N44”, “N12000”). (2001) is acquired.

In step S2206, the publication unit 107 refers to the purchase/consideration information table 1301 and refers to the promotion target product “32dmk2”, the product of the same class (“32D”, “N44”), the product class of the same class “Full size”, Acquire users (“uchida”, “okazaki”, “honda”) who are considering “single-lens reflex” and “single-lens”).

As a result, in step S2101, the advertisement generation unit 107 obtains “endo”, “kagawa”, “uchida”, “okazaki”, and “honda” as promotion target user candidates.

In step S2102, the submission unit 107 starts the iterative process up to step S2107 for the candidate user “endo” acquired in step S2101.

In step S2103, the submission unit 107 shifts the processing to step S2104 because the candidate user “endo” has not purchased “32dmk2”.

In step S2104, the delivery unit 107 shifts the processing to step S2105 because the candidate user “endo” does not have a negative opinion on the replacement target product.

In step S2105, the submission unit 107 shifts the processing to step S2106 because the candidate user “endo” has not purchased the replacement target product after the specified time (here, one year ago).

In step S2106, the submission unit 107 adds the candidate user “endo” to the promotion target user list.

In step S2107, the submission unit 107 performs the processing from step S2102 because there is the next candidate user “kagawa”.

In step S2103, the submission unit 107 shifts the processing to step S2104 because the candidate user “kagawa” has not purchased “32dmk2”.

In step S2104, the submission unit 107 shifts the processing to step S2106 because the candidate user “kagawa” has a negative opinion about the replacement target product “N12000”.

In step S2106, the submission unit 107 adds the candidate user “kagawa” to the promotion target user list.

In step S2107, the submission unit 107 performs the processing from step S2102 because there is the next candidate user “uchida”.

In step S2102, the submission unit 107 starts the iterative process up to step S2107 for the candidate user “uchida” acquired in step S2101.

In step S2103, the submission unit 107 shifts the processing to step S2107 because the candidate user “uchida” has purchased “32dmk2”.

In step S2107, the submission unit 107 performs the processing from step S2102 because there is the next candidate user “okazaki”.

By repeating the same process thereafter, “endo”, “kagawa”, “okazaki”, and “honda” are obtained as the list of users targeted for promotion.

In step S2108, the submission unit 107 performs submission processing for the users “endo”, “kagawa”, “okazaki”, and “honda” registered in the promotion target user list.

As a result, "uchida", which has already purchased "32dmk2", is no longer targeted for promotion, and users ("endo" "honda") who are considering purchasing "32dmk2" are considering "full size". The user (“okazaki”) and the user (“kagawa”) who is dissatisfied with “N12000” in the same class as “32dmk2” can be promoted, and the promotion suitable for the user can be performed.

After finishing the submission process, as an example of actually transmitting the advertisement to the user targeted for promotion using the result obtained by the submission process, the submission screen 2301 shown in FIG. 23 is displayed on the display 210 of the analyzer terminal 120. A method of transmitting an advertisement using the submission screen 2301 can be mentioned.

The submission screen 2301 is displayed in the product display area 2302 for displaying the product to be promoted, the advertisement display area 2303 for displaying the advertisement content for the product displayed in the product display area 2302, and the product display area 2302. An advertisement selection button 2304 that is pressed when selecting the advertisement content for the product is provided.

As for the advertisement content for the product, a plurality of advertisement content can be set in advance and is stored and managed by the submission section 107.

The submission screen 2301 shows the advertisement content displayed in the advertisement display area 2303 for the promotion target user, that is, the target user display area 2305 for displaying the promotion target user list and the product displayed in the product display area 2302. Accordingly, a submission button 2306 to be pressed when transmitting an advertisement to the user displayed in the target user display area 2305 and an end button 2307 to be pressed when the advertisement is stopped are provided.

An example of transmitting this advertisement is to transmit a tweet to the target user, and it is assumed that the content of the advertisement is displayed on this tweet and then transmitted.

In addition, the target user is displayed only with the purchaser of the lower product of the company, and an advertisement for urging the purchase of the higher product is provided in advance so that the "upgrade campaign" is displayed in the advertisement content, or It is possible to adopt a mode in which only the purchaser of another person's product is displayed and an advertisement for urging the purchase of another company's product is provided in advance so that the "transfer campaign" is displayed in the advertisement content.
"Second embodiment"

The second embodiment of the present invention will be described. The second embodiment differs from the first embodiment in the submission process. Since the second embodiment has substantially the same configuration and the like as the first embodiment, the description of the same configuration and the like as the first embodiment will be omitted.

FIG. 24 shows an example of the submission process in the second embodiment. The submission process in the second embodiment differs from the submission process of the first embodiment in the following steps.

In step S2401, the advertisement generation unit 107 determines whether or not a product that is a prerequisite for using the promotion target product has been purchased. If the prerequisite product is purchased, the process proceeds to step S2106, and if the prerequisite product is not purchased. , And moves the processing to step S2107.

The prerequisite product is determined by referring to the prerequisite product table 2501 added to the setting storage area 102.

FIG. 25 shows the configuration of the expanded setting storage area 102, and a prerequisite product table 2501 is added.

The structure of the prerequisite product table 2501 is shown in FIG. The prerequisite product table 2501 includes a product name and a prerequisite product indicating a product indispensable for using the product having the product name.
(Concrete example)

Next, as a specific example of the submission process shown in FIG. 24, a case of promoting “AF60mmMF2.8” will be described.

In step S2101, the advertisement generation unit 107 receives “AF60mmMF2.8” that is a promotion target as an input, and obtains “uchida” as a user candidate who is considering “macro” as a result of the promotion target user candidate acquisition process.

In step S2102, the submission unit 107 starts the iterative process up to step S2107 for the candidate user “uchida” acquired in step S2101.

In step S2103, the submission unit 107 shifts the processing to step S2104 because the candidate user “uchida” has not purchased “AF60mmMF2.8”.

In step S2104, the submission unit 107 shifts the processing to step S2105 because the candidate user “uchida” does not have a negative opinion on the replacement target product.

In step S2105, the submission unit 107 shifts the processing to step S2401 because the candidate user “uchida” has not purchased a product other than the promotion target after the specified time (here, one year ago).

In step S2401, the submission unit 107 acquires the prerequisite products “2000D” and “800D” of the “AF60mmMF2.8” from the prerequisite product table 2501 and refers to the purchase/examination information table 1301 to assume the candidate user “uchida”. It is determined that the product "2000D" or "800D" has not been purchased. Since the candidate user “uchida” has not purchased the prerequisite product of “AF60mmMF2.8”, the process is moved to step S2107.

In step S2107, the submission unit 107 shifts the processing to step S2108 because there is no next candidate user.

In step S2108, the publication unit 107 ends the processing without executing the publication processing because there is no user registered in the promotion target user list.

As a result, inappropriate promotion can be suppressed for the user "uchida" who has not purchased the product that is a prerequisite for using "AF60mmMF2.8".
"Third Embodiment"

Next, a third embodiment of the present invention will be described. Since the third embodiment has substantially the same configuration and the like as the first and second embodiments, description of the same configuration and the like as the first and second embodiments will be omitted.

FIG. 27 is an example of a submission process when a promotion is performed for each user.

Although the selection of the user who is the target of the promotion is omitted, for example, the user who posted the product in a specific period may be selected.

In step S2701, the advertisement generation unit 107 acquires, as an input, the purchase/study information of the user from the purchase/study information table 1301 for the promotion target user.

In step S2702, the submission unit 107 starts the iterative process up to step S2711 for the purchase/consideration information of the user acquired in step S2701.

In step S2703, the submission unit 107 determines whether the purchase/examination information is information regarding “purchase” or information regarding “examination”.

If the information is “purchase”, that is, if the type is “purchase”, the process proceeds to step S2704. If the information is “review”, that is, if the type is “review”, the process proceeds to step S2708.

In step S2704, the advertisement generation unit 107 refers to the product table 505 to determine whether there is a higher grade class product of the purchased product or a product of the same grade class with a newer release time.

If there is a higher grade class or a new product of the same grade class, the process moves to step S2707. If there is no higher grade class or new product of the same grade class, the process moves to step S2705.

In step S2705, the advertisement generation unit 107 refers to the prerequisite product table 2501 to acquire products that include the purchased product as a prerequisite product, and if there is a product that the posting user has not purchased, the process proceeds to step S2706. If there is no unpurchased product, the process moves to step S2711.

Regarding whether or not there is an unpurchased product, if the type of the purchasing/considering information in the purchasing/considering information table 1301 of the posting user is “purchase” for the product, it is determined that the product is not an unpurchased product, and “ If “examination” or purchase/examination information does not exist in the purchase/examination information table 1301, it is determined that the product is an unpurchased product.

It should be noted that the posting user may also purchase the product in the same class as the purchased product.

In step S2706, the submission unit 107 refers to the prerequisite product table 2501 and acquires an unpurchased product that includes the purchased product as a prerequisite product.

When a plurality of products can be acquired, a new product on the release date is acquired in the present embodiment, but the product may be acquired according to another standard.

In step S2707, the submission unit 107 acquires a higher-rank product of the products. If there is a higher grade product, obtain the higher grade product. If there is no higher grade product, obtain the higher grade product.

In step S2708, the submission unit 107 determines whether or not the purchase/examination information including the type of “purchase” for the product or class that the posting user is “examining” is in the purchase/examination information after “examination”.

If there is information on “purchase”, the process proceeds to step S2711. If there is no information on “purchase”, the process proceeds to step S2709.

In step S2709, an unpurchased product that is a product or class that the posting user is “examining” is acquired.

In step S2710, the submission unit 107 sets the acquired product as a promotion target product.

In step S2711, the advertisement generation unit 107 performs the processing from step S2702 when there is the next purchase/examination information and the promotion target product is not set.

If there is next purchase/examination information or a product to be promoted is set, the process moves to step S2712.

In step S2712, the submission unit 107 executes the promotion of the promotion target product to the user.

Although a specific example is omitted, with this configuration, it is possible to carry out product promotion according to the user.

As described above, according to the present invention, it is possible to carry out a promotion according to the status of purchase or consideration of a product by specifying whether or not the product is purchased or considered from the user's post.

As described above, the recording medium recording the program that realizes the functions of the above-described embodiments is supplied to the system or apparatus, and the computer (or CPU or MPU) of the system or apparatus executes the program stored in the recording medium. It goes without saying that the object of the present invention can be achieved by reading and executing.

In this case, the program itself read from the recording medium realizes the novel function of the present invention, and the recording medium storing the program constitutes the present invention. As a recording medium for supplying the program, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a DVD-ROM, a magnetic tape, a non-volatile memory card, a ROM, an EEPROM, and a silicon. A disk or the like can be used.

Further, not only the functions of the above-described embodiments are realized by executing the program read by the computer, but also the OS or the like running on the computer executes a part of the actual processing based on the instructions of the program. Needless to say, this includes a case where all the processing is performed and the functions of the above-described embodiments are realized by the processing.

Furthermore, after the program read from the recording medium is written in the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, the function expansion board is instructed based on the instruction of the program code. Needless to say, this also includes the case where the CPU or the like included in the function expansion unit performs some or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

Further, it goes without saying that the present invention can be applied to the case where it is achieved by supplying a program to a system or an apparatus.

In this case, by reading the recording medium storing the program for achieving the present invention into the system or device, the system or device can enjoy the effects of the present invention.

Furthermore, by downloading and reading a program for achieving the present invention from a server, a database or the like on a network using a communication program, the system or device can enjoy the effects of the present invention. It should be noted that the present invention also includes all configurations that combine the above-described embodiments and modifications thereof.

100 Information Processing System 110 Information Processing Device 120 Analyst Terminal 130 SNS Site 140 Other External Network 201 CPU
202 RAM
203 ROM
204 System Bus 205 Input Controller 206 Video Controller 207 Memory Controller 208 Communication I/F (Interface) Controller 209 Keyboard (KB)
210 display device 211 external memory

Claims (13)

Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who is a user who purchases a target of the same category as the target of the promotion and is negative with respect to the target of the same category,
Output means for outputting information related to the promotion for the user identified by the identifying means,
An information processing apparatus comprising: The information processing apparatus according to claim 1, wherein the specifying unit specifies a user who is considering purchasing the target of the promotion. The specifying unit specifies a user who purchases a target of the same category as the target of the promotion,
The information processing apparatus according to claim 1 or 2, wherein the output unit outputs, to the user identified by the identifying unit, information regarding the promotion regarding an object to be promoted. The said identification means identifies the user who is a negative user with respect to the said object of the said classification, and has passed a predetermined period since purchasing the said object of the said classification. The information processing apparatus according to any one of 3 above. A storage means for storing necessary information about the target required for the promotion target,
The specifying unit is a user who has purchased a target of the same category as the target of the promotion, and selects a target required for the target of the promotion based on the necessary information stored in the storage unit. The information processing apparatus according to any one of claims 1 to 4, wherein a user who has purchased is specified. Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who has not purchased the target of the promotion and has purchased the target of the same category as the target of the promotion,
Generating means for generating information relating to the promotion for the user identified by the identifying means,
An information processing apparatus comprising: Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who has not purchased the target of the promotion and has purchased the target of the same category as the target of the promotion,
Output means for outputting information related to the promotion for the user identified by the identifying means,
An information processing apparatus comprising: An information processing system comprising an information processing device communicably connected to a client terminal for instructing analysis of a post,
The client terminal is
Receiving means for receiving information related to the promotion transmitted by the transmitting means of the information processing device,
Display means for displaying information relating to the promotion received by the receiving means,
Equipped with
The information processing device,
Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who is a user who purchases a target of the same category as the target of the promotion and is negative with respect to the target of the same category,
Generating means for generating information related to promotion for the user identified by the identifying means,
Transmitting means for transmitting information relating to the promotion generated by the generating means,
An information processing system comprising: A method for controlling an information processing device that analyzes a post, comprising:
The information processing device is
Using the information posted by the user, an analysis step of analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis step, a specific step of identifying a user who is a user who purchases a target of the same category as the target of the promotion and is a negative user for the target of the same category,
An output step of outputting information regarding the promotion to the user identified by the identifying step,
A method for controlling an information processing device, comprising: Computer,
Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who is a user who purchases a target of the same category as the target of the promotion and is negative with respect to the target of the same category,
Output means for outputting information related to promotion to the user identified by the identifying means,
A program characterized by causing it to function. A method for controlling an information processing system comprising a client terminal for instructing analysis of postings on a site and an information processing device connected via a network,
The client terminal is
A receiving step of receiving information related to the promotion transmitted by the transmitting step of the information processing device,
A display step for displaying information related to the promotion received by the receiving step,
Run
The information processing device,
Using the information posted by the user, an analysis step of analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis step, a specifying step of specifying a user who is a user who purchases a target of the same category as the target of the promotion and is a negative user for the target of the same category,
A generation step of generating information regarding a promotion for the user identified in the identification step,
A transmission step of transmitting the promotion information generated by the generation step,
A method for controlling an information processing system, the method comprising: A method for controlling an information processing device that analyzes a post, comprising:
The information processing device is
Using the information posted by the user, an analysis step of analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis step, a specifying step of specifying a user who has not purchased the target to perform the promotion, and who has purchased the target of the same category as the target to perform the promotion,
An output step of outputting information related to the promotion for the user identified by the identifying step,
A method for controlling an information processing device, comprising: Computer,
Using the information posted by the user, analysis means for analyzing the purchase of the user for the promotion target,
Based on the analysis result of the analysis unit, a specifying unit that specifies a user who has not purchased the target of the promotion and has purchased the target of the same category as the target of the promotion,
Output means for outputting information related to the promotion for the user identified by the identifying means,
A program to make it work.

Images