WO2015137321A1 - Device, program, and method for analyzing transition in psychological state of poster on basis of comment text - Google Patents

Device, program, and method for analyzing transition in psychological state of poster on basis of comment text Download PDF

Info

Publication number
WO2015137321A1
WO2015137321A1 PCT/JP2015/056970 JP2015056970W WO2015137321A1 WO 2015137321 A1 WO2015137321 A1 WO 2015137321A1 JP 2015056970 W JP2015056970 W JP 2015056970W WO 2015137321 A1 WO2015137321 A1 WO 2015137321A1
Authority
WO
WIPO (PCT)
Prior art keywords
psychological
keyword
state
transition
psychological state
Prior art date
Application number
PCT/JP2015/056970
Other languages
French (fr)
Japanese (ja)
Inventor
池田　和史
服部　元
滝嶋　康弘
Original Assignee
Kddi株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Kddi株式会社 filed Critical Kddi株式会社
Priority to CN201580011398.1A priority Critical patent/CN106062809A/en
Publication of WO2015137321A1 publication Critical patent/WO2015137321A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Definitions

  • the present invention relates to a technique for analyzing comment text posted on a communication site server such as an SNS (Social Networking Service) site server.
  • a communication site server such as an SNS (Social Networking Service) site server.
  • SNS Social Networking Service
  • SNS site server publishes comment text posted by one user to many users in the group.
  • SNS includes, for example, facebook (registered trademark), twitter (registered trademark), google + (registered trademark), and mixi (registered trademark), and is generally called a miniblog site.
  • the comment text sent by this user often includes the user's own psychological state consciously or unconsciously.
  • comment sentences created by a user and profile information of the users are collected, and the tendency of a large number of comment sentences corresponding to profile items is analyzed. This is because even if the comment text is about the same product or the like, the content of the comment text may differ depending on the user's profile information (age, gender, hobby, etc.).
  • Patent Literature 1 discloses a technique for presenting advertisement information to a user based on a comment sentence posted from a user to an SNS or a blog site. According to this technology, a user who refers to a specific product service can be found, and advertisement information related to the product service can be distributed to the user. Furthermore, Patent Document 2 discloses a technique for collecting post contents of a specific user in the SNS retrospectively and estimating the user's profile information (such as age and gender) from the characteristics of words appearing in the post contents. ing. According to this technique, it is possible to estimate user fixed attribute information.
  • Patent Literature 3 discloses a technique for predicting a future change in the number of posts by modeling a time-series change in the number of posts related to a specific product service. According to this technology, it is possible to predict a tendency among a huge number of users.
  • the advertisement information is distributed suddenly for the user, it is generally easy to receive it. That is, if the user himself / herself intends to purchase the merchandise service, the advertisement information is favorably accepted. If the user does not intend to purchase the merchandise service, the advertisement information is troublesome. As described above, the effect of the advertisement information greatly varies depending on the user's psychological state with respect to the product service. Further, in the technique described in Patent Document 2, it is not assumed at all that information that changes in time series for a user is estimated. Furthermore, the technique described in Patent Document 3 does not predict a tendency for each user.
  • FIG. 5 is a schematic diagram for explaining the prior art.
  • an unspecified number of third parties can transmit comment text to the SNS site server 2 via the Internet using their own terminals 3.
  • S51 When the user is in a psychological state that is just “attention” to the smartphone of company ⁇ , he / she sent the comment sentence “Do not watch CM of company ⁇ smartphones well” to the SNS site server 2. To do.
  • S52 It is assumed that the comment text posted by this user is acquired by the advertisement distribution server 4 of ⁇ company, for example.
  • the advertisement distribution server 4 sells the smartphone to the user's terminal 3 with the advertisement information “smartphone is actually 0 yen! Click here for a special coupon! Http: // www ...” Send.
  • the inventors of the present application estimate the user's psychological state from the comment text regarding the product service posted to the SNS? I thought. For example, if the psychological state regarding the purchase behavior of the user with respect to the merchandise service can be estimated, can the appropriate advertisement information be distributed to the user? I thought.
  • an object of the present invention is to provide an apparatus, a program, and a method for analyzing a transition of a user's psychological state with respect to a target keyword such as a product service based on a comment sentence transmitted from the user.
  • a program that causes a computer mounted on the apparatus to function so as to analyze the transition of the psychological state with respect to the target keyword from the comment text transmitted,
  • Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
  • comment text acquisition means for acquiring a comment text including the target keyword,
  • the psychological state determining means for outputting the psychological state of the psychological keyword,
  • a program is provided for causing each computer to function as a psychological transition determination unit that outputs psychological transitions in which psychological states are arranged in time series.
  • the psychological keyword dictionary means that the psychological state corresponds to an AIDMA (Attention, Interest, Desire, Memory, Action) model, and the computer can function to register the psychological keyword for the target keyword for each psychological state. preferable.
  • AIDMA Adtention, Interest, Desire, Memory, Action
  • the psychological state is assigned numerical values that increase in the order of A, I, D, M, A, It is also preferable to cause the computer to function such that the psychological transition is a time series of psychological numerical values.
  • the comment text includes the call origination time
  • the psychological state determination means outputs the transmission time of the comment sentence including the psychological keyword together with the psychological state
  • the psychological transition determination means registers an elapsed time interval between psychological states arranged in time series
  • Psychological transitions cause the computer to function to decrease the weight for the numerical value arranged in time series as the previous elapsed time interval becomes longer, and increase the weight for the numerical value as the previous elapsed time interval becomes shorter It is also preferable.
  • the psychological transition determination means causes the computer to function so that the numerical values arranged in time series are set as the moving average value of the predetermined range in the previous stage.
  • Target keywords are keywords based on product services
  • This program Advertisement information storage means for storing advertisement information corresponding to each psychological state in advance; It is also preferable to search the advertisement information corresponding to the psychological transition up to now using the advertisement information storage means, and further function the computer as an advertisement information presentation means for presenting the advertisement information to the poster.
  • an apparatus for analyzing the transition of the psychological state for the target keyword For each contributor, from the sent comment text, an apparatus for analyzing the transition of the psychological state for the target keyword, Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state; For each contributor, comment text acquisition means for acquiring a comment text including the target keyword, For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary means, the psychological state determining means for outputting the psychological state of the psychological keyword, There is provided a device having psychological transition determination means for outputting psychological transitions in which psychological states are arranged in time series for each poster.
  • a psychological analysis method of a device that analyzes a transition of a psychological state with respect to a target keyword from a comment sentence transmitted
  • the apparatus has a psychological keyword dictionary part in which psychological keywords are registered in advance for each psychological state,
  • This psychological analysis method A first step of obtaining a comment sentence including the target keyword for each contributor; For each contributor, if the comment text contains a psychological keyword of the psychological keyword dictionary means, a second step of outputting the psychological state of the psychological keyword; And a third step of outputting psychological transitions in which psychological states are arranged in time series for each poster.
  • the apparatus, program, and method of the present invention it is possible to analyze the transition of the user's psychological state with respect to the target keyword such as product service based on the comment text transmitted from the user. Further, for each user, appropriate advertisement information can be transmitted to the user according to the transition of the psychological state with respect to the target keyword.
  • FIG. 1 is a schematic diagram illustrating one embodiment of a system including an apparatus according to the present invention. It is a functional block block diagram which shows one Embodiment of the psychological transition analyzer by this invention. 3A, 3B, and 3C are explanatory diagrams illustrating examples of comment sentences. It is a sequence which shows one Embodiment of the delivery method of the advertisement information in this invention. It is a schematic diagram for demonstrating a prior art.
  • FIG. 1 is a schematic diagram showing an embodiment of a system including an apparatus according to the present invention.
  • the psychological transition analysis apparatus 1 of the present invention is connected to the Internet.
  • the psychological transition analysis device 1 communicates with the SNS site server 2 via the Internet.
  • the psychological transition analysis apparatus 1 can acquire a comment sentence for each contributor from the SNS site server 2 via an API (Application Programming Interface).
  • the API is a rule interface for using the function of the application service, and is prepared as different for each of various servers.
  • the psychological transition analysis apparatus 1 may store comment sentences in a database in advance. That is, it is not essential for the psychological transition analysis device 1 to communicate with the SNS site server 2.
  • the psychological transition analysis apparatus 1 can estimate a psychological state from comment text transmitted from the user, and can transmit advertisement information corresponding to the psychological state to the user's terminal 3.
  • the comment sentence “Do not watch the CM of the ⁇ company smartphone” is sent to the SNS site server 2 To do.
  • S12 It is assumed that the comment sentence posted by this user is acquired by the psychological transition analysis apparatus 1.
  • the psychological transition analysis apparatus 1 analyzes the psychological state included in the comment sentence with respect to “ ⁇ company smartphone”. Here, it is determined that the user is only in a psychological state of a degree of “attention” to the smartphone of ⁇ company.
  • the psychological transition analysis apparatus 1 transmits advertisement information “Introducing the lineup of the ⁇ company smartphone from here http: // www... (S14) A user who has browsed the advertisement information displayed on the terminal 3 does not feel modest advertisement information relatively annoying, and conversely has a good feeling.
  • FIG. 2 is a functional block configuration diagram showing an embodiment of the psychological transition analysis apparatus according to the present invention.
  • the psychological transition analysis apparatus 1 of the present invention can analyze the transition of the psychological state with respect to the target keyword from the sent comment text for each contributor.
  • the psychological transition analysis apparatus 1 includes a psychological keyword dictionary unit 101, a comment sentence acquisition unit 11, a psychological state determination unit 12, a psychological transition determination unit 13, an advertisement information accumulation unit 102, and an advertisement information presentation together with a communication interface unit. Part 14. These functional components excluding the communication interface unit are realized by executing a program that causes a computer installed in the apparatus to function. It can also be understood as a psychological transition analysis method for the device.
  • the psychological keyword dictionary unit 101 registers psychological keywords in advance for each psychological state.
  • the psychological state is changed in the following time series in correspondence with the AIDMA model.
  • Cognitive stage Attention (A)-> Emotional stage: Interest (I)-> Desire (D)-> Memory (M)-> Action stage: Action (A)
  • the AIDMA model is a model that represents a consumer psychological process for advertising.
  • a target keyword for example, a target product service
  • the speech of the same user can be tracked in time series, and the psychological process can be estimated by applying a transition model of purchase psychological state in economics.
  • the psychological keyword dictionary unit 101 registers a psychological keyword for the target keyword (for example, “ ⁇ company smartphone”) for each psychological state (A, ID, M, A). Attention state: sale, CM, new work, new product, ... Interest state: Lineup, brochure, HP, friends, ... Desired state: Wanted, price, specs, design, ... Memory state: shop, exhibition, real thing, preview, ... Behavioral state: buy, get, give up, model change This is a dictionary in which words that appear characteristically in each psychological state are registered for the target keyword.
  • the psychological keyword dictionary unit 101 is basically created manually in advance. However, as a seed psychological keywords registered in advance by manually (teacher data), the characteristically appearing word to each psychological state, using a statistical index, such as chi 2 value and Akaike Information Criterion (AIC) is calculated You can also
  • the comment text acquisition unit 11 acquires a comment text from the SNS site server 2 for each contributor (for each user ID) using the target keyword (for example, “ ⁇ company smartphone”) as a search key.
  • the target keyword may be the name of the product service.
  • the acquired comment text is output to the psychological state determination unit 12.
  • 3A, 3B, and 3C are explanatory diagrams showing examples of comment texts.
  • FIG. 3A various comment texts for a large number of users are acquired for the target keyword ( ⁇ company smartphone).
  • FIG. 3B the comment text is narrowed down to that of the user AAA with respect to the target keyword ( ⁇ company smartphone).
  • the psychological state determination unit 12 outputs the psychological state of the psychological keyword when the comment text includes the psychological keyword of the psychological keyword dictionary unit for each poster. For example, it can be estimated that the user is in the attention (A) state from a comment sentence including the target keyword “ ⁇ company smartphone” and the psychological keyword “CM”. Further, for example, from the comment text including the target keyword “alpha company smartphone” and the psychological keyword “friend”, it can be estimated that the user is in an interest (I) state. Further, for example, from the comment text including the target keyword “ ⁇ company smartphone” and the psychological keyword “I want”, it can be estimated that the user is in the desire (D) state. Further, for example, from the comment text including the target keyword “alpha company smartphone” and the psychological keyword “shop”, it can be estimated that the user is in the memory (M) state.
  • the psychological state is estimated for each comment sentence in the user AAA with respect to the target keyword ( ⁇ company smartphone).
  • the psychological transition determination unit 13 outputs a psychological transition that is data in which psychological states are arranged in time series for each poster. For example, the following psychological transition is output. A, A, I, A, I, I, D, I, D, D, M, M, M, M
  • a psychological state may occur.
  • the psychological transition determination unit 13 corrects the numerical values arranged in time series in ascending order as much as possible. Specifically, the average value of the psychological states of adjacent n comments before and after is set as the psychological state of the comment. Alternatively, it is also preferable that the psychological state of the comment is a moving average value within a predetermined range in the previous stage.
  • the comment text includes the transmission time.
  • the psychological state determination part 12 outputs the transmission time of the comment sentence containing a psychological keyword with the said psychological state.
  • the psychological transition determination unit 13 can register an elapsed time interval between psychological states arranged in time series.
  • the psychological transition determination part 13 attaches weight as shown below to the numerical value arranged in a time series in the time series psychological transition. As the elapsed time interval in the previous stage becomes longer, the weight for the numerical value is reduced. As the elapsed time interval in the previous stage becomes shorter, the weight for the numerical value is increased.
  • the product of the likelihood of the estimated psychological state may be used for integer values of 0 to 4.
  • A 10%
  • I 70%
  • D 20%
  • M 0%
  • the advertisement information storage unit 102 stores in advance advertisement information corresponding to each psychological state of AIDMA for each product service (target keyword).
  • the advertisement information storage unit 102 is referred to the stored content from the advertisement information presentation unit 14.
  • the advertisement information presentation unit 14 uses the advertisement information storage unit 102 to search for advertisement information corresponding to the time-series psychological transitions up to now. Then, the advertisement information is presented to the poster.
  • the psychological transition determination unit 13 is “stagnated” in a psychological state when a predetermined time or more has elapsed between psychological states, or when one psychological state has continuously passed a predetermined number or more. Judge. In this case, it is also possible to distribute advertisement information that moves the mind to the user in a stagnation state. For example, when the same psychological state continues for 5 or more times in the psychological transition, the psychological state exceeding 5 times is corrected to the stagnation state S.
  • the psychological transition determination unit 13 determines that the psychological transition is “reversing” in the psychological state when the psychological transition is reversing in the transition direction in the AIDMA model. In this case, advertisement information that moves the mind can be distributed to the user in the retrograde state. In the case of retrograde, the retroactive psychological state is corrected to the retrograde state R.
  • FIG. 4 is a sequence showing an embodiment of the advertisement information distribution method according to the present invention.
  • the advertisement information “http: // www....” is transmitted to the user.
  • S44 In response to the comment sentence “Would you like to go to the shop of ⁇ company smartphone?”, The psychological state is determined as “memory” by “shop” in the sentence, and “campaign of ⁇ company smartphone at x shop” "Http: // www ." advertisement information is sent to the user. (S45) As a result, it can be expected that the psychological state of the user becomes “action” and visits the shop.
  • the apparatus, program and method of the present invention based on the comment text transmitted from the user, the transition of the psychological state of the user with respect to the target keyword such as product service is analyzed. Can do. Further, for each user, appropriate advertisement information can be transmitted to the user according to the transition of the psychological state with respect to the target keyword.

Abstract

Provided are a device and the like for analyzing transitions in the psychological state of a user with respect to subject keywords for products/services and the like, on the basis of comment texts produced by the user. This device has: a psychological keyword dictionary means in which psychological keywords are registered for each psychological state; a comment text acquisition means that obtains, for each poster, comment texts that include subject keywords; a psychological state determination means that, for each poster, outputs the psychological state for the relevant psychological keyword when the comment text incudes a psychological keyword that is in the psychological keyword dictionary; and a psychological transition determination means that, for each poster, outputs a psychological transition, in which the psychological states are arranged chronologically. The psychological states correspond to the Attention, Interest, Desire, Memory, Action (AIDMA) model. The psychological keywords are registered in the psychological keyword dictionary for each psychological state.

Description

コメント文章に基づいて投稿者の心理状態の遷移を分析する装置、プログラム及び方法Apparatus, program, and method for analyzing transition of contributor's psychological state based on comment text
　本発明は、例えばＳＮＳ(Social Networking Service)サイトサーバのようなコミュニケーションサイトサーバに投稿されるコメント文章を分析する技術に関する。 The present invention relates to a technique for analyzing comment text posted on a communication site server such as an SNS (Social Networking Service) site server.
　本出願は、パリ条約の下、２０１４年３月１０日に出願された日本国特許出願ＪＰ２０１４－０４６０００についての優先権の利益を主張しており、その日本国特許出願は、ＰＣＴ規則第２０．６の規定によって、引用によりその全体が本明細書に組み込まれる。 This application claims the benefit of priority with respect to the Japanese patent application JP2014-046000 filed on March 10, 2014 under the Paris Convention. The provisions of 6 are hereby incorporated by reference in their entirety.
　近年、不特定多数の第三者が、ＳＮＳサイトサーバを介して、自ら作成したコメント文章（テキスト情報）を発信することが活発に行われている。ＳＮＳサイトサーバは、１人のユーザによって投稿されたコメント文章を、グループ内の多数のユーザへ公開する。ＳＮＳには、例えばfacebook（登録商標）やtwitter（登録商標）、google＋（登録商標）、mixi（登録商標）があり、一般にミニブログサイトとも称される。 In recent years, a large number of unspecified third parties are actively sending out comment sentences (text information) created by themselves via the SNS site server. The SNS site server publishes comment text posted by one user to many users in the group. SNS includes, for example, facebook (registered trademark), twitter (registered trademark), google + (registered trademark), and mixi (registered trademark), and is generally called a miniblog site.
　このユーザによって発信されるコメント文章には、そのユーザ自身の心理状態が、意識的又は無意識的に含まれている場合が多い。ここで、特に、マーケティングでは、商品役務に関するユーザの心理面に係る発言を分析することが所望される。そのための手法として、具体的には、ユーザの作成したコメント文章と、そのユーザのプロフィール情報とを収集し、プロフィール項目に応じた多数のコメント文章の傾向を分析することが挙げられる。これは、同じ商品等に対するコメント文章であっても、ユーザのプロフィール情報（年代、性別、趣味等）によって、そのコメント文章の内容が異なり得ることによる。 The comment text sent by this user often includes the user's own psychological state consciously or unconsciously. Here, in particular, in marketing, it is desired to analyze a speech related to a user's psychological aspect regarding product services. As a technique for that purpose, specifically, comment sentences created by a user and profile information of the users are collected, and the tendency of a large number of comment sentences corresponding to profile items is analyzed. This is because even if the comment text is about the same product or the like, the content of the comment text may differ depending on the user's profile information (age, gender, hobby, etc.).
　また、例えば特許文献１には、ユーザからＳＮＳやブログサイトへ投稿されたコメント文章に基づいて、そのユーザに広告情報を提示する技術が開示されている。この技術によれば、特定の商品役務に対して言及したユーザを発見し、そのユーザへ当該商品役務に関する広告情報を配信することができる。
　さらに、特許文献２には、ＳＮＳにおける特定ユーザの投稿内容を遡って収集し、それら投稿内容に出現する単語の特徴から、当該ユーザのプロフィール情報（年代、性別など）を推定する技術が開示されている。この技術によれば、ユーザの固定された属性情報を推定することができる。
　さらにまた、特許文献３には、特定の商品役務に関する投稿数の時系列変化をモデル化することによって、将来的な投稿数の変化を予測する技術が開示されている。この技術によれば、膨大な数のユーザにおける傾向を予測することができる。 Further, for example, Patent Literature 1 discloses a technique for presenting advertisement information to a user based on a comment sentence posted from a user to an SNS or a blog site. According to this technology, a user who refers to a specific product service can be found, and advertisement information related to the product service can be distributed to the user.
Furthermore, Patent Document 2 discloses a technique for collecting post contents of a specific user in the SNS retrospectively and estimating the user's profile information (such as age and gender) from the characteristics of words appearing in the post contents. ing. According to this technique, it is possible to estimate user fixed attribute information.
Furthermore, Patent Literature 3 discloses a technique for predicting a future change in the number of posts by modeling a time-series change in the number of posts related to a specific product service. According to this technology, it is possible to predict a tendency among a huge number of users.
日本国特開２０１３－００４０２７号公報Japanese Unexamined Patent Publication No. 2013-004027 日本国特開２０１３－１９６０７０号公報Japanese Unexamined Patent Publication No. 2013-196070 日本国特開２００６－２２７９６５号公報Japanese Unexamined Patent Publication No. 2006-227965
　特許文献１に記載の技術では、広告情報は、ユーザにとって唐突に配信されるので一般的に煩わしく受け止められやすい。即ち、ユーザ自身その商品役務の購入意志が有れば、その広告情報は好意的に受け入れられるが、その商品役務の購入意志が無い場合、その広告情報は煩わしいものとなる。このように、広告情報の効果は、当該商品役務に対するユーザの心理状態によって大きく異なるものとなってしまう。また、特許文献２に記載の技術では、ユーザについて時系列に変化する情報を推定することは全く想定されていない。さらに、特許文献３に記載の技術は、ユーザ毎の傾向を予測するものではない。 In the technique described in Patent Document 1, since the advertisement information is distributed suddenly for the user, it is generally easy to receive it. That is, if the user himself / herself intends to purchase the merchandise service, the advertisement information is favorably accepted. If the user does not intend to purchase the merchandise service, the advertisement information is troublesome. As described above, the effect of the advertisement information greatly varies depending on the user's psychological state with respect to the product service. Further, in the technique described in Patent Document 2, it is not assumed at all that information that changes in time series for a user is estimated. Furthermore, the technique described in Patent Document 3 does not predict a tendency for each user.
　図５は、従来技術を説明するための模式図である。 FIG. 5 is a schematic diagram for explaining the prior art.
　図５によれば、不特定多数の第三者は、各自の端末３を用いて、インターネットを介してＳＮＳサイトサーバ２へ、コメント文章を送信することができる。
（Ｓ５１）ユーザは、α社のスマホに少しだけ「注目」している程度の心理状態にあるときに、コメント文章「α社スマホのＣＭよく見るなあ」を、ＳＮＳサイトサーバ２へ発信したとする。
（Ｓ５２）このユーザによって投稿されたコメント文章は、例えばα社の広告配信サーバ４によって取得されたとする。
（Ｓ５３）このとき、広告配信サーバ４が、当該ユーザの端末３へ、スマホを売り込むための広告情報「スマホが実質０円！お得なクーポンはこちら！http://www・・・」を送信する。
（Ｓ５４）ユーザは、α社のスマホに少しだけ「注目」した程度の心理状態である。そのために、端末３に表示された広告情報を閲覧したユーザは、その広告情報を煩わしく感じることとなる。
　逆に、α社のスマホを直ぐにも購入したいと「記憶」しているような心理状態であれば、その広告情報にお得感を持つこととなる。 According to FIG. 5, an unspecified number of third parties can transmit comment text to the SNS site server 2 via the Internet using their own terminals 3.
(S51) When the user is in a psychological state that is just “attention” to the smartphone of company α, he / she sent the comment sentence “Do not watch CM of company α smartphones well” to the SNS site server 2. To do.
(S52) It is assumed that the comment text posted by this user is acquired by the advertisement distribution server 4 of α company, for example.
(S53) At this time, the advertisement distribution server 4 sells the smartphone to the user's terminal 3 with the advertisement information “smartphone is actually 0 yen! Click here for a special coupon! Http: // www ...” Send.
(S54) The user is in a psychological state to the extent that he / she has just “focused” on the smartphone of α company. Therefore, the user who browsed the advertisement information displayed on the terminal 3 will feel the advertisement information troublesome.
Conversely, if you are in a psychological state that you “remember” that you want to purchase a smartphone of company α immediately, you will have a good feeling in the advertisement information.
　この状況に対し、本願の発明者らは、ＳＮＳに投稿された商品役務に関するコメント文章から、ユーザの心理状態を推定することはできないか？と考えた。例えば当該商品役務に対するユーザの購買行動に関する心理状態を推定することができれば、適切な広告情報を当該ユーザに配信することができるのではないか？と考えた。 In this situation, can the inventors of the present application estimate the user's psychological state from the comment text regarding the product service posted to the SNS? I thought. For example, if the psychological state regarding the purchase behavior of the user with respect to the merchandise service can be estimated, can the appropriate advertisement information be distributed to the user? I thought.
　そこで、本発明は、ユーザから発信されたコメント文章に基づいて、商品役務等の対象キーワードに対する当該ユーザの心理状態の遷移を分析する装置、プログラム及び方法を提供することを目的とする。 Therefore, an object of the present invention is to provide an apparatus, a program, and a method for analyzing a transition of a user's psychological state with respect to a target keyword such as a product service based on a comment sentence transmitted from the user.
　本発明によれば、投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析するように、装置に搭載されたコンピュータを機能させるプログラムであって、
　心理状態毎に、心理キーワードを予め登録した心理キーワード辞書手段と、
　投稿者毎に、対象キーワードを含むコメント文章を取得するコメント文章取得手段と、
　各投稿者について、コメント文章が心理キーワード辞書手段の心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する心理状態判定手段と、
　投稿者毎に、心理状態を時系列に並べた心理遷移を出力する心理遷移判定手段と
してコンピュータを機能させるプログラムが提供される。 According to the present invention, for each contributor, a program that causes a computer mounted on the apparatus to function so as to analyze the transition of the psychological state with respect to the target keyword from the comment text transmitted,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
For each contributor, comment text acquisition means for acquiring a comment text including the target keyword,
For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary means, the psychological state determining means for outputting the psychological state of the psychological keyword,
A program is provided for causing each computer to function as a psychological transition determination unit that outputs psychological transitions in which psychological states are arranged in time series.
　本発明のプログラムにおける一実施形態によれば、
　心理キーワード辞書手段は、心理状態を、ＡＩＤＭＡ(Attention、Interest、Desire、Memory、Action）モデルに対応させており、心理状態毎に、対象キーワードに対する心理キーワードを登録する
ようにコンピュータを機能させることも好ましい。 According to one embodiment of the program of the present invention,
The psychological keyword dictionary means that the psychological state corresponds to an AIDMA (Attention, Interest, Desire, Memory, Action) model, and the computer can function to register the psychological keyword for the target keyword for each psychological state. preferable.
　本発明のプログラムにおける他の実施形態によれば、
　心理状態には、Ａ、Ｉ、Ｄ、Ｍ、Ａの順に大きくなる数値が割り当てられており、
　心理遷移は、心理状態の数値を時系列に並べたものである
ようにコンピュータを機能させることも好ましい。 According to another embodiment of the program of the present invention,
The psychological state is assigned numerical values that increase in the order of A, I, D, M, A,
It is also preferable to cause the computer to function such that the psychological transition is a time series of psychological numerical values.
　本発明のプログラムにおける他の実施形態によれば、
　コメント文章に、発信時刻が含まれており、
　心理状態判定手段は、心理キーワードを含むコメント文章の発信時刻も、当該心理状態と共に出力し、
　心理遷移判定手段は、時系列に並ぶ心理状態の間に、経過時間間隔を登録しており、
　心理遷移は、時系列に並ぶ数値に対して、前段の経過時間間隔が長くなるほど当該数値に対する重みを小さくし、前段の経過時間間隔が短くなるほど当該数値に対する重みを大きくする
ようにコンピュータを機能させることも好ましい。 According to another embodiment of the program of the present invention,
The comment text includes the call origination time,
The psychological state determination means outputs the transmission time of the comment sentence including the psychological keyword together with the psychological state,
The psychological transition determination means registers an elapsed time interval between psychological states arranged in time series,
Psychological transitions cause the computer to function to decrease the weight for the numerical value arranged in time series as the previous elapsed time interval becomes longer, and increase the weight for the numerical value as the previous elapsed time interval becomes shorter It is also preferable.
　本発明のプログラムにおける他の実施形態によれば、
　心理遷移判定手段は、時系列に並ぶ数値を、前段所定範囲の移動平均値とする
ようにコンピュータを機能させることも好ましい。 According to another embodiment of the program of the present invention,
It is also preferable that the psychological transition determination means causes the computer to function so that the numerical values arranged in time series are set as the moving average value of the predetermined range in the previous stage.
　本発明のプログラムにおける他の実施形態によれば、
　対象キーワードは、商品役務に基づくキーワードであり、
　このプログラムは、
　各心理状態に対応した広告情報を予め蓄積する広告情報蓄積手段と、
　広告情報蓄積手段を用いて、現在までの心理遷移に応じた広告情報を検索し、該広告情報を当該投稿者へ提示する広告情報提示手段と
してコンピュータを更に機能させることも好ましい。 According to another embodiment of the program of the present invention,
Target keywords are keywords based on product services,
This program
Advertisement information storage means for storing advertisement information corresponding to each psychological state in advance;
It is also preferable to search the advertisement information corresponding to the psychological transition up to now using the advertisement information storage means, and further function the computer as an advertisement information presentation means for presenting the advertisement information to the poster.
　本発明によれば、投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析する装置であって、
　心理状態毎に、心理キーワードを予め登録した心理キーワード辞書手段と、
　投稿者毎に、対象キーワードを含むコメント文章を取得するコメント文章取得手段と、
　各投稿者について、コメント文章が心理キーワード辞書手段の心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する心理状態判定手段と、
　投稿者毎に、心理状態を時系列に並べた心理遷移を出力する心理遷移判定手段と
を有する装置が提供される。 According to the present invention, for each contributor, from the sent comment text, an apparatus for analyzing the transition of the psychological state for the target keyword,
Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
For each contributor, comment text acquisition means for acquiring a comment text including the target keyword,
For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary means, the psychological state determining means for outputting the psychological state of the psychological keyword,
There is provided a device having psychological transition determination means for outputting psychological transitions in which psychological states are arranged in time series for each poster.
　本発明によれば、投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析する装置の心理分析方法であって、
　装置は、心理状態毎に、心理キーワードを予め登録した心理キーワード辞書部を有し、
　本心理分析方法は、
　投稿者毎に、対象キーワードを含むコメント文章を取得する第１のステップと、
　各投稿者について、コメント文章が心理キーワード辞書手段の心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する第２のステップと、
　投稿者毎に、心理状態を時系列に並べた心理遷移を出力する第３のステップと
を有することを特徴とする。 According to the present invention, for each contributor, a psychological analysis method of a device that analyzes a transition of a psychological state with respect to a target keyword from a comment sentence transmitted,
The apparatus has a psychological keyword dictionary part in which psychological keywords are registered in advance for each psychological state,
This psychological analysis method
A first step of obtaining a comment sentence including the target keyword for each contributor;
For each contributor, if the comment text contains a psychological keyword of the psychological keyword dictionary means, a second step of outputting the psychological state of the psychological keyword;
And a third step of outputting psychological transitions in which psychological states are arranged in time series for each poster.
　本発明の装置、プログラム及び方法によれば、ユーザから発信されたコメント文章に基づいて、商品役務等の対象キーワードに対する当該ユーザの心理状態の遷移を分析することができる。また、ユーザ毎に、当該対象キーワードに対する心理状態の遷移に応じて、そのユーザに適切な広告情報を送信することができる。 According to the apparatus, program, and method of the present invention, it is possible to analyze the transition of the user's psychological state with respect to the target keyword such as product service based on the comment text transmitted from the user. Further, for each user, appropriate advertisement information can be transmitted to the user according to the transition of the psychological state with respect to the target keyword.
本発明による装置を含むシステムの一実施形態を示す模式図である。1 is a schematic diagram illustrating one embodiment of a system including an apparatus according to the present invention. 本発明による心理遷移分析装置の一実施形態を示す機能ブロック構成図である。It is a functional block block diagram which shows one Embodiment of the psychological transition analyzer by this invention. 図３Ａ、図３Ｂ及び図３Ｃは、コメント文章の例を表す説明図である。3A, 3B, and 3C are explanatory diagrams illustrating examples of comment sentences. 本発明における広告情報の配信方法の一実施形態を示すシーケンスである。It is a sequence which shows one Embodiment of the delivery method of the advertisement information in this invention. 従来技術を説明するための模式図である。It is a schematic diagram for demonstrating a prior art.
　以下、本発明のいくつかの例示的な実施形態について、図面を用いて詳細に説明する。 Hereinafter, some exemplary embodiments of the present invention will be described in detail with reference to the drawings.
　図１は、本発明による装置を含むシステムの一実施形態を示す模式図である。 FIG. 1 is a schematic diagram showing an embodiment of a system including an apparatus according to the present invention.
　図１によれば、図５の従来技術とは異なり、本発明の心理遷移分析装置１がインターネットに接続されている。心理遷移分析装置１は、インターネットを介してＳＮＳサイトサーバ２と通信する。心理遷移分析装置１は、ＳＮＳサイトサーバ２から、ＡＰＩ(Application Programming Interface)を介して、投稿者毎のコメント文章を取得することができる。ＡＰＩは、アプリケーションサービスの機能を利用するための規則インタフェースであって、種々のサーバ毎に異なるものとして用意されている。 According to FIG. 1, unlike the prior art of FIG. 5, the psychological transition analysis apparatus 1 of the present invention is connected to the Internet. The psychological transition analysis device 1 communicates with the SNS site server 2 via the Internet. The psychological transition analysis apparatus 1 can acquire a comment sentence for each contributor from the SNS site server 2 via an API (Application Programming Interface). The API is a rule interface for using the function of the application service, and is prepared as different for each of various servers.
　尚、心理遷移分析装置１は、コメント文章を予めデータベースに蓄積していてもよい。即ち、心理遷移分析装置１がＳＮＳサイトサーバ２と通信することは必須ではない。 Note that the psychological transition analysis apparatus 1 may store comment sentences in a database in advance. That is, it is not essential for the psychological transition analysis device 1 to communicate with the SNS site server 2.
　図１によれば、心理遷移分析装置１は、ユーザから発信されたコメント文章から、心理状態を推定し、その心理状態に応じた広告情報を、ユーザの端末３へ送信することができる。
（Ｓ１１）ユーザは、α社のスマホに少しだけ「注目」している程度の心理状態にあるときに、コメント文章「α社スマホのＣＭよく見るなあ」を、ＳＮＳサイトサーバ２へ発信したとする。
（Ｓ１２）このユーザによって投稿されたコメント文章は、心理遷移分析装置１によって取得されたとする。
（Ｓ１３）このとき、心理遷移分析装置１は、「α社スマホ」に対して、そのコメント文章に含まれる心理状態を分析する。ここで、そのユーザは、α社のスマホに少しだけ「注目」した程度の心理状態に過ぎないと判定される。そうすると、心理遷移分析装置１は、スマホのラインナップを紹介する程度の広告情報「α社スマホのラインナップは、こちらからどうぞ　http://www・・・」を送信する。
（Ｓ１４）端末３に表示された広告情報を閲覧したユーザは、控えめな広告情報を比較的煩わしく感じることがなく、逆に好感を持つこととなる。 According to FIG. 1, the psychological transition analysis apparatus 1 can estimate a psychological state from comment text transmitted from the user, and can transmit advertisement information corresponding to the psychological state to the user's terminal 3.
(S11) When the user is in a psychological state that is only “attention” to the smartphone of the α company, the comment sentence “Do not watch the CM of the α company smartphone” is sent to the SNS site server 2 To do.
(S12) It is assumed that the comment sentence posted by this user is acquired by the psychological transition analysis apparatus 1.
(S13) At this time, the psychological transition analysis apparatus 1 analyzes the psychological state included in the comment sentence with respect to “α company smartphone”. Here, it is determined that the user is only in a psychological state of a degree of “attention” to the smartphone of α company. Then, the psychological transition analysis apparatus 1 transmits advertisement information “Introducing the lineup of the α company smartphone from here http: // www...
(S14) A user who has browsed the advertisement information displayed on the terminal 3 does not feel modest advertisement information relatively annoying, and conversely has a good feeling.
　図２は、本発明による心理遷移分析装置の一実施形態を示す機能ブロック構成図である。 FIG. 2 is a functional block configuration diagram showing an embodiment of the psychological transition analysis apparatus according to the present invention.
　本発明の心理遷移分析装置１は、投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析することができる。心理遷移分析装置１は、通信インタフェース部と共に、心理キーワード辞書部１０１と、コメント文章取得部１１と、心理状態判定部１２と、心理遷移判定部１３と、広告情報蓄積部１０２と、広告情報提示部１４とを有する。通信インタフェース部を除くこれら機能構成部は、装置に搭載されたコンピュータを機能させるプログラムを実行することによって実現される。また、装置の心理遷移分析方法としても理解できる。 The psychological transition analysis apparatus 1 of the present invention can analyze the transition of the psychological state with respect to the target keyword from the sent comment text for each contributor. The psychological transition analysis apparatus 1 includes a psychological keyword dictionary unit 101, a comment sentence acquisition unit 11, a psychological state determination unit 12, a psychological transition determination unit 13, an advertisement information accumulation unit 102, and an advertisement information presentation together with a communication interface unit. Part 14. These functional components excluding the communication interface unit are realized by executing a program that causes a computer installed in the apparatus to function. It can also be understood as a psychological transition analysis method for the device.
［心理キーワード辞書部１０１］
　心理キーワード辞書部１０１は、心理状態毎に、心理キーワードを予め登録したものである。心理状態は、ＡＩＤＭＡモデルに対応させて、以下のような時系列に遷移させる。
　　　認知段階：　注目（Ａ） -->
　　　感情段階：　興味（Ｉ） -->
　　　　　　　　　欲望（Ｄ） -->
　　　　　　　　　記憶（Ｍ） -->
　　　行動段階：　行動（Ａ） [Psychological keyword dictionary unit 101]
The psychological keyword dictionary unit 101 registers psychological keywords in advance for each psychological state. The psychological state is changed in the following time series in correspondence with the AIDMA model.
Cognitive stage: Attention (A)->
Emotional stage: Interest (I)->
Desire (D)->
Memory (M)->
Action stage: Action (A)
　ＡＩＤＭＡモデルとは、広告宣伝に対する消費者の心理のプロセスを表すモデルである。対象キーワード、例えば対象となる商品役務に関して、同一ユーザの発言を時系列に追跡し、経済学における購買心理状態の遷移モデルを適用して、当該心理プロセスを推定することができる。 The AIDMA model is a model that represents a consumer psychological process for advertising. With respect to a target keyword, for example, a target product service, the speech of the same user can be tracked in time series, and the psychological process can be estimated by applying a transition model of purchase psychological state in economics.
　心理キーワード辞書部１０１は、心理状態（Ａ，Ｉ．Ｄ，Ｍ，Ａ）毎に、対象キーワード（例えば「α社スマホ」）に対する心理キーワードを登録する。
　　　注目状態：発売、ＣＭ、新作、新製品、・・・
　　　興味状態：ラインナップ、パンフレット、ＨＰ、友達、・・・
　　　欲望状態：欲しい、価格、スペック、デザイン、・・・
　　　記憶状態：ショップ、展示、実物、下見、・・・
　　　行動状態：買う、ゲット、諦め、機種変
　これは、対象キーワードに対して、各心理状態に特徴的に表れる語を、辞書の形で登録したものである。 The psychological keyword dictionary unit 101 registers a psychological keyword for the target keyword (for example, “α company smartphone”) for each psychological state (A, ID, M, A).
Attention state: sale, CM, new work, new product, ...
Interest state: Lineup, brochure, HP, friends, ...
Desired state: Wanted, price, specs, design, ...
Memory state: shop, exhibition, real thing, preview, ...
Behavioral state: buy, get, give up, model change This is a dictionary in which words that appear characteristically in each psychological state are registered for the target keyword.
　尚、心理キーワード辞書部１０１は、基本的に予め人手で作成されたものである。但し、予め人手によって登録された心理キーワードをシード（教師データ）として、各心理状態に特徴的に表れる語を、統計的な指標、例えばΧ2値や赤池情報量基準（ＡＩＣ）を用いて算出することもできる。 The psychological keyword dictionary unit 101 is basically created manually in advance. However, as a seed psychological keywords registered in advance by manually (teacher data), the characteristically appearing word to each psychological state, using a statistical index, such as chi 2 value and Akaike Information Criterion (AIC) is calculated You can also
［コメント文章取得部１１］
　コメント文章取得部１１は、ＳＮＳサイトサーバ２から、投稿者毎（ユーザＩＤ毎）に、対象キーワード（例えば「α社スマホ」）を検索キーとして、コメント文章を取得する。対象キーワードは、商品役務の名称であってもよい。取得されたコメント文章は、心理状態判定部１２へ出力される。 [Comment text acquisition unit 11]
The comment text acquisition unit 11 acquires a comment text from the SNS site server 2 for each contributor (for each user ID) using the target keyword (for example, “α company smartphone”) as a search key. The target keyword may be the name of the product service. The acquired comment text is output to the psychological state determination unit 12.
　図３Ａ、図３Ｂ及び図３Ｃは、コメント文章の例を表す説明図である。 3A, 3B, and 3C are explanatory diagrams showing examples of comment texts.
　図３Ａによれば、対象キーワード（α社スマホ）について、多数のユーザにおける様々なコメント文章が取得されている。
　図３Ｂによれば、対象キーワード（α社スマホ）について、コメント文章がユーザＡＡＡのものに絞り込まれている。 According to FIG. 3A, various comment texts for a large number of users are acquired for the target keyword (α company smartphone).
According to FIG. 3B, the comment text is narrowed down to that of the user AAA with respect to the target keyword (α company smartphone).
［心理状態判定部１２］
　図２に戻って、心理状態判定部１２は、投稿者のそれぞれについて、コメント文章が心理キーワード辞書手段の心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する。
　例えば対象キーワード「α社スマホ」と心理キーワード「ＣＭ」とを含むコメント文章から、そのユーザは、注目（Ａ）状態にあると推定することができる。また、例えば対象キーワード「α社スマホ」と心理キーワード「友達」とを含むコメント文章から、そのユーザは、興味（Ｉ）状態にあると推定することができる。更に、例えば対象キーワード「α社スマホ」と心理キーワード「欲しい」とを含むコメント文章から、そのユーザは、欲望（Ｄ）状態にあると推定することができる。また、例えば対象キーワード「α社スマホ」と心理キーワード「ショップ」とを含むコメント文章から、そのユーザは、記憶（Ｍ）状態にあると推定することができる。 [Psychological state determination unit 12]
Returning to FIG. 2, the psychological state determination unit 12 outputs the psychological state of the psychological keyword when the comment text includes the psychological keyword of the psychological keyword dictionary unit for each poster.
For example, it can be estimated that the user is in the attention (A) state from a comment sentence including the target keyword “α company smartphone” and the psychological keyword “CM”. Further, for example, from the comment text including the target keyword “alpha company smartphone” and the psychological keyword “friend”, it can be estimated that the user is in an interest (I) state. Further, for example, from the comment text including the target keyword “α company smartphone” and the psychological keyword “I want”, it can be estimated that the user is in the desire (D) state. Further, for example, from the comment text including the target keyword “alpha company smartphone” and the psychological keyword “shop”, it can be estimated that the user is in the memory (M) state.
　図３Ｃによれば、対象キーワード（α社スマホ）について、ユーザＡＡＡにおけるコメント文章毎に、心理状態が推定されている。 According to FIG. 3C, the psychological state is estimated for each comment sentence in the user AAA with respect to the target keyword (α company smartphone).
　他の実施形態として、１つのコメント文章に複数の心理キーワードが含まれる場合、その出現頻度に基づいてコメント文章全体の心理状態を決定してもよい。また、教師データにおける語の出現傾向から、サポートベクタマシンのような識別器を用いて心理状態を決定してもよい。更に、ＡＩＤＭＡモデルに加えて、その尤度を付与して分析を行ってもよい。
　　　「α社スマホの新作発売されるのか」について、
　　　　新作＝Ａ、発売＝Ａ
　　　　Ａ＝２、Ｉ＝０、Ｄ＝０、Ｍ＝０、Ａ＝０
　　　　Ａの尤度＝１００％ As another embodiment, when a plurality of psychological keywords are included in one comment sentence, the psychological state of the entire comment sentence may be determined based on the appearance frequency. Further, the psychological state may be determined from a tendency of appearance of words in the teacher data using a discriminator such as a support vector machine. Further, in addition to the AIDMA model, the likelihood may be given for analysis.
About “whether a new α company smartphone will be released”
New work = A, release = A
A = 2, I = 0, D = 0, M = 0, A = 0
Likelihood of A = 100%
［心理遷移判定部１３］
　図２に戻って、心理遷移判定部１３は、投稿者毎に、心理状態を時系列に並べたデータである心理遷移を出力する。例えば以下のような心理遷移が出力される。
　　　Ａ，Ａ，Ｉ，Ａ，Ｉ，Ｉ，Ｄ，Ｉ，Ｄ，Ｄ，Ｍ，Ｍ，Ｍ [Psychological transition determination unit 13]
Returning to FIG. 2, the psychological transition determination unit 13 outputs a psychological transition that is data in which psychological states are arranged in time series for each poster. For example, the following psychological transition is output.
A, A, I, A, I, I, D, I, D, D, M, M, M
　ここで、心理遷移には、Ａ、Ｉ、Ｄ、Ｍ、Ａ（Ａ->Ｉ->Ｄ->Ｍ->Ａ）の順に大きくなる数値を割り当てることも好ましい。これによって、心理遷移は、心理状態の数値を時系列に並べたものとなる。数値の大きさによって、次の心理状態へ遷移したことが理解できる。
　　Ａ＝０、Ｉ＝１、Ｄ＝２、Ｍ＝３
　　Ａ，Ａ，Ｉ，Ａ，Ｉ，Ｉ，Ｄ，Ｉ，Ｄ，Ｄ，Ｍ，Ｍ，Ｍ
　　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓
　　０，０，１，０，１，１，２，１，２，２，３，３，３
　ここで、このような心理遷移において、心理状態が前後する場合も当然に生じる。 Here, it is also preferable to assign numerical values that increase in the order of A, I, D, M, and A (A->I->D->M-> A) to the psychological transition. As a result, the psychological transition is obtained by arranging the numerical values of the psychological state in time series. It can be understood that the state has shifted to the next psychological state depending on the magnitude of the numerical value.
A = 0, I = 1, D = 2, M = 3
A, A, I, A, I, I, D, I, D, D, M, M, M
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
0,0,1,0,1,1,2,1,2,2,3,3,3
Here, naturally, in such a psychological transition, a psychological state may occur.
＜心理遷移の移動平均による補正＞
　これに対し、心理遷移判定部１３は、時系列に並ぶ数値を、できる限り昇順となるように補正する。具体的には、隣接する前後ｎコメントの心理状態の平均値を、当該コメントの心理状態とする。または、当該コメントの心理状態を、前段所定範囲の移動平均値とすることも好ましい。
　　隣接する前後２項の平均を取る場合、
　　Ａ，Ａ，Ｉ，Ａ，Ｉ，Ｉ，Ｄ，Ｉ，Ｄ，Ｄ，Ｍ，Ｍ，Ｍ
　　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓
　　０，０，１，０，１，１，２，１，２，２，３，３，３
　　0.3,0.3,0.4,0.6,１，１，1.4,1.6,２, 2.2,2.4,2.6,2.75,３
　　（（（（（（（（（↓四捨五入↓））））））））））））
　　０，０，０，１，１，１，１，２，２，２，２，３，３，３
　　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓　↓
　　Ａ，Ａ，Ａ，Ｉ，Ｉ，Ｉ，Ｉ，Ｄ，Ｄ，Ｄ，Ｄ，Ｍ，Ｍ，Ｍ <Correction by moving average of psychological transition>
On the other hand, the psychological transition determination unit 13 corrects the numerical values arranged in time series in ascending order as much as possible. Specifically, the average value of the psychological states of adjacent n comments before and after is set as the psychological state of the comment. Alternatively, it is also preferable that the psychological state of the comment is a moving average value within a predetermined range in the previous stage.
When taking the average of two adjacent terms,
A, A, I, A, I, I, D, I, D, D, M, M, M
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
0,0,1,0,1,1,2,1,2,2,3,3,3
0.3, 0.3, 0.4, 0.6, 1, 1, 1.4, 1.6, 2, 2.2, 2.4, 2.6, 2.75, 3
((((((((((↓ rounding down ↓))))))))))))))
0,0,0,1,1,1,1,2,2,2,2,3,3,3
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
A, A, A, I, I, I, I, D, D, D, D, M, M, M
＜心理状態の遷移間の時間差に基づく補正＞
　コメント文章には、発信時刻が含まれている。また、心理状態判定部１２は、心理キーワードを含むコメント文章の発信時刻も、当該心理状態と共に出力する。この両時刻を用いることによって、心理遷移判定部１３は、時系列に並ぶ心理状態の間に、経過時間間隔を登録することができる。 <Correction based on time difference between transitions of psychological state>
The comment text includes the transmission time. Moreover, the psychological state determination part 12 outputs the transmission time of the comment sentence containing a psychological keyword with the said psychological state. By using both times, the psychological transition determination unit 13 can register an elapsed time interval between psychological states arranged in time series.
　そして、心理遷移判定部１３は、時系列の心理遷移における時系列に並ぶ数値に対して、以下に示したような重みを付ける。
　　　前段の経過時間間隔が長くなるほど当該数値に対する重みを小さくする。
　　　前段の経過時間間隔が短くなるほど当該数値に対する重みを大きくする。 And the psychological transition determination part 13 attaches weight as shown below to the numerical value arranged in a time series in the time series psychological transition.
As the elapsed time interval in the previous stage becomes longer, the weight for the numerical value is reduced.
As the elapsed time interval in the previous stage becomes shorter, the weight for the numerical value is increased.
　尚、他の実施形態として、０～４の整数値に対して、推定された心理状態の尤度の積を用いてもよい。Ａ＝１０％、Ｉ＝７０％、Ｄ＝２０％、Ｍ＝０％の場合、０～３の整数値を使って以下のように乗算する。
　　　０×１０％＋１×７０％＋２×２０％＋３×０％＝１．１ As another embodiment, the product of the likelihood of the estimated psychological state may be used for integer values of 0 to 4. When A = 10%, I = 70%, D = 20%, and M = 0%, multiplication is performed as follows using integer values of 0 to 3.
0 × 10% + 1 × 70% + 2 × 20% + 3 × 0% = 1.1
［広告情報蓄積部１０２］
　対象キーワードは、商品役務に基づくキーワードであるとする。広告情報蓄積部１０２は、図２に示すように、その商品役務（対象キーワード）毎に、ＡＩＤＭＡの各心理状態に対応した広告情報を予め蓄積する。広告情報蓄積部１０２は、広告情報提示部１４から蓄積内容を参照される。 [Advertising Information Storage Unit 102]
It is assumed that the target keyword is a keyword based on the product service. As shown in FIG. 2, the advertisement information storage unit 102 stores in advance advertisement information corresponding to each psychological state of AIDMA for each product service (target keyword). The advertisement information storage unit 102 is referred to the stored content from the advertisement information presentation unit 14.
［広告情報提示部１４］
　広告情報提示部１４は、広告情報蓄積部１０２を用いて、現在までの時系列の心理遷移に応じた広告情報を検索する。そして、その広告情報を、当該投稿者へ提示する。 [Advertising Information Presentation Unit 14]
The advertisement information presentation unit 14 uses the advertisement information storage unit 102 to search for advertisement information corresponding to the time-series psychological transitions up to now. Then, the advertisement information is presented to the poster.
＜停滞状態の検出＞
　心理遷移判定部１３は、心理状態間で所定時間以上の時間が経過している場合、又は、１つの心理状態が所定数以上連続して経過した場合、その心理状態で「停滞」していると判断する。この場合、停滞状態にあるユーザに対して、心理を動かすような広告情報を配信することもできる。例えば、心理遷移において投稿回数にして５回以上同じ心理状態が連続している場合、５回を超える回の心理状態を停滞状態Ｓに補正する。
　　　Ａ，Ａ，Ａ，Ｉ，Ｉ，Ｉ，Ｉ，Ｉ，Ｉ，Ｉ，・・・
　　　↓
　　　Ａ，Ａ，Ａ，Ｉ，Ｉ，Ｉ，Ｉ，Ｉ，Ｓ，Ｓ <Detection of stagnation>
The psychological transition determination unit 13 is “stagnated” in a psychological state when a predetermined time or more has elapsed between psychological states, or when one psychological state has continuously passed a predetermined number or more. Judge. In this case, it is also possible to distribute advertisement information that moves the mind to the user in a stagnation state. For example, when the same psychological state continues for 5 or more times in the psychological transition, the psychological state exceeding 5 times is corrected to the stagnation state S.
A, A, A, I, I, I, I, I, I, I, ...
↓
A, A, A, I, I, I, I, I, S, S
＜逆行状態の検出＞
　心理遷移判定部１３は、心理遷移がＡＩＤＭＡモデルでの遷移方向に逆行している場合、その心理状態で「逆行」していると判断する。この場合、逆行状態にあるユーザに対して、心理を動かすような広告情報も配信することができる。逆行した場合、逆行している心理状態を逆行状態Ｒに補正する。
　　　Ａ，Ａ，Ａ，Ｉ，Ｉ，Ｉ，Ｄ，Ｄ，Ｄ，Ｉ，Ｉ，・・・
　　　↓
　　　Ａ，Ａ，Ａ，Ｉ，Ｉ，Ｉ，Ｄ，Ｄ，Ｄ，Ｒ，Ｒ，・・・ <Reverse state detection>
The psychological transition determination unit 13 determines that the psychological transition is “reversing” in the psychological state when the psychological transition is reversing in the transition direction in the AIDMA model. In this case, advertisement information that moves the mind can be distributed to the user in the retrograde state. In the case of retrograde, the retroactive psychological state is corrected to the retrograde state R.
A, A, A, I, I, I, D, D, D, I, I, ...
↓
A, A, A, I, I, I, D, D, D, R, R, ...
　図４は、本発明における広告情報の配信方法の一実施形態を示すシーケンスである。 FIG. 4 is a sequence showing an embodiment of the advertisement information distribution method according to the present invention.
（Ｓ４１）コメント文章「α社スマホのＣＭよく見るなあ」に対して、文章中の「ＣＭ」によって心理状態が「注目」と判定され、「α社スマホのラインナップは、これ！　http://www.・・・」の広告情報がユーザへ送信される。
（Ｓ４２）コメント文章「α社スマホ、確か友達が持ってたよな？」に対して、文章中の「友達」によって心理状態が「興味」と判定され、「α社スマホがお勧めです。これ！　http://www.・・・」の広告情報がユーザへ送信される。
（Ｓ４３）コメント文章「α社スマホ、欲しい」に対して、文章中の「欲しい」によって心理状態が「欲望」と判定され、「α社スマホが実質０円！お得なクーポンはこちらからどうぞ　http://www.・・・」の広告情報がユーザへ送信される。
（Ｓ４４）コメント文章「α社スマホのショップに行ってみるか？」に対して、文章中の「ショップ」によって心理状態が「記憶」と判定され、「ｘショップでは、α社スマホのキャンペーン実施中　http://www.・・・」の広告情報がユーザへ送信される。
（Ｓ４５）結果的に、ユーザの心理状態が「行動」となって、ショップへ訪問することが期待できる。 (S41) In response to the comment sentence “Do not watch CM of α company smartphone”, the psychological state is determined as “attention” by “CM” in the sentence, and “The lineup of α company smartphone is this! Http: // The advertisement information “www ....” is transmitted to the user.
(S42) In response to the comment sentence “α company smartphone, surely have a friend?”, The “friend” in the sentence determines the psychological state as “interesting”, and “α company smartphone is recommended. Http: // www .... "is sent to the user.
(S43) In response to the comment “α company smartphone, I want”, the psychological state is determined as “desire” by “I want” in the sentence, “α company smartphone is actually 0 yen! The advertisement information “http: // www....” is transmitted to the user.
(S44) In response to the comment sentence “Would you like to go to the shop of α company smartphone?”, The psychological state is determined as “memory” by “shop” in the sentence, and “campaign of α company smartphone at x shop” "Http: // www ...." advertisement information is sent to the user.
(S45) As a result, it can be expected that the psychological state of the user becomes “action” and visits the shop.
　以上、詳細に説明したように、本発明の装置、プログラム及び方法によれば、ユーザから発信されたコメント文章に基づいて、商品役務等の対象キーワードに対する当該ユーザの心理状態の遷移を分析することができる。また、ユーザ毎に、当該対象キーワードに対する心理状態の遷移に応じて、そのユーザに適切な広告情報を送信することができる。 As described above in detail, according to the apparatus, program and method of the present invention, based on the comment text transmitted from the user, the transition of the psychological state of the user with respect to the target keyword such as product service is analyzed. Can do. Further, for each user, appropriate advertisement information can be transmitted to the user according to the transition of the psychological state with respect to the target keyword.
　前述した本発明の種々の実施形態について、本発明の技術思想及び見地の範囲の種々の変更、修正及び省略は、当業者によれば容易に行うことができる。前述の説明はあくまで例であって、何ら制約しようとするものではない。本発明は、特許請求の範囲及びその均等物として限定するものにのみ制約される。 For the various embodiments of the present invention described above, various changes, modifications, and omissions in the technical idea and scope of the present invention can be easily made by those skilled in the art. The above description is merely an example, and is not intended to be restrictive. The invention is limited only as defined in the following claims and the equivalents thereto.
　１　心理遷移分析装置
　１０１　心理キーワード辞書部
　１０２　広告情報蓄積部
　１１　コメント文章取得部
　１２　心理状態判定部
　１３　心理遷移判定部
　１４　広告情報提示部
　２　ＳＮＳサイトサーバ
　３　端末
　４　広告配信サーバ DESCRIPTION OF SYMBOLS 1 Psychological transition analyzer 101 Psychological keyword dictionary part 102 Advertising information storage part 11 Comment text acquisition part 12 Psychological state determination part 13 Psychological transition determination part 14 Advertising information presentation part 2 SNS site server 3 Terminal 4 Advertisement distribution server

Claims (8)

  1. 　投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析するように、装置に搭載されたコンピュータを機能させるプログラムであって、
    　心理状態毎に、心理キーワードを予め登録した心理キーワード辞書手段と、
    　投稿者毎に、前記対象キーワードを含むコメント文章を取得するコメント文章取得手段と、
    　各投稿者について、前記コメント文章が前記心理キーワード辞書手段の前記心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する心理状態判定手段と、
    　投稿者毎に、前記心理状態を時系列に並べた心理遷移を出力する心理遷移判定手段と
    してコンピュータを機能させることを特徴とするプログラム。     For each contributor, a program that causes the computer installed in the device to function so as to analyze the transition of the psychological state with respect to the target keyword from the sent comment text,
    Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
    For each contributor, comment sentence acquisition means for acquiring a comment sentence including the target keyword;
    For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary unit, a psychological state determination unit that outputs a psychological state of the psychological keyword;
    A program that causes a computer to function as psychological transition determination means for outputting psychological transitions in which the psychological states are arranged in time series for each poster.
  2. 　前記心理キーワード辞書手段は、前記心理状態を、ＡＩＤＭＡ(Attention, Interest, Desire, Memory, Action）モデルに対応させており、心理状態毎に、前記対象キーワードに対する心理キーワードを登録する
    ようにコンピュータを機能させることを特徴とする請求項１に記載のプログラム。     The psychological keyword dictionary means associates the psychological state with an AIDMA (Attention, Interest, Desire, Memory, Action) model, and functions a computer to register a psychological keyword for the target keyword for each psychological state. The program according to claim 1, wherein:
  3. 　前記心理状態には、Ａ、Ｉ、Ｄ、Ｍ、Ａの順に大きくなる数値が割り当てられており、
    　前記心理遷移は、前記心理状態の数値を時系列に並べたものである
    ようにコンピュータを機能させることを特徴とする請求項２に記載のプログラム。     The psychological state is assigned numerical values that increase in the order of A, I, D, M, A,
    The program according to claim 2, wherein the psychological transition causes the computer to function such that the numerical values of the psychological states are arranged in time series.
  4. 　コメント文章に、発信時刻が含まれており、
    　前記心理状態判定手段は、前記心理キーワードを含むコメント文章の発信時刻も、当該心理状態と共に出力し、
    　前記心理遷移判定手段は、時系列に並ぶ心理状態の間に、経過時間間隔を登録しており、
    　前記心理遷移は、時系列に並ぶ数値に対して、前段の経過時間間隔が長くなるほど当該数値に対する重みを小さくし、前段の経過時間間隔が短くなるほど当該数値に対する重みを大きくする
    ようにコンピュータを機能させることを特徴とする請求項３に記載のプログラム。     The comment text includes the call origination time,
    The psychological state determination means also outputs a comment text including the psychological keyword together with the psychological state,
    The psychological transition determination means registers an elapsed time interval between psychological states arranged in time series,
    The psychological transition functions the computer to decrease the weight for the numerical value arranged in time series as the previous elapsed time interval becomes longer, and increase the weight for the numerical value as the previous elapsed time interval becomes shorter. The program according to claim 3, wherein:
  5. 　前記心理遷移判定手段は、時系列に並ぶ数値を、前段所定範囲の移動平均値とする
    ようにコンピュータを機能させることを特徴とすることを特徴とする請求項３に記載のプログラム。     The program according to claim 3, wherein the psychological transition determination unit causes the computer to function so that numerical values arranged in a time series are set to a moving average value within a predetermined range in the previous stage.
  6. 　前記対象キーワードは、商品役務に基づくキーワードであり、
    　前記プログラムは、
    　前記各心理状態に対応した広告情報を予め蓄積する広告情報蓄積手段と、
    　前記広告情報蓄積手段を用いて、現在までの前記心理遷移に応じた広告情報を検索し、該広告情報を当該投稿者へ提示する広告情報提示手段と
    してコンピュータを更に機能させることを特徴とする請求項１に記載のプログラム。     The target keyword is a keyword based on product service,
    The program is
    Advertisement information storage means for storing advertisement information corresponding to each psychological state in advance;
    The advertisement information storage means is used to search for advertisement information corresponding to the psychological transition up to now, and the computer is further functioned as advertisement information presentation means for presenting the advertisement information to the poster. Item 1. The program according to item 1.
  7. 　投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析する装置であって、
    　心理状態毎に、心理キーワードを予め登録した心理キーワード辞書手段と、
    　投稿者毎に、前記対象キーワードを含むコメント文章を取得するコメント文章取得手段と、
    　各投稿者について、前記コメント文章が前記心理キーワード辞書手段の前記心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する心理状態判定手段と、
    　投稿者毎に、前記心理状態を時系列に並べた心理遷移を出力する心理遷移判定手段と
    を有することを特徴とする装置。     For each contributor, it is a device that analyzes the transition of the psychological state for the target keyword from the sent comment text,
    Psychological keyword dictionary means for registering psychological keywords in advance for each psychological state;
    For each contributor, comment sentence acquisition means for acquiring a comment sentence including the target keyword;
    For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary unit, a psychological state determination unit that outputs a psychological state of the psychological keyword;
    An apparatus comprising: a psychological transition determination unit that outputs a psychological transition in which the psychological states are arranged in time series for each poster.
  8. 　投稿者毎に、発信されたコメント文章から、対象キーワードに対する心理状態の遷移を分析する装置の心理分析方法であって、
    　前記装置は、心理状態毎に、心理キーワードを予め登録した心理キーワード辞書部を有し、
    　前記心理分析方法は、
    　投稿者毎に、前記対象キーワードを含むコメント文章を取得する第１のステップと、
    　各投稿者について、前記コメント文章が前記心理キーワード辞書手段の前記心理キーワードを含んでいる場合、当該心理キーワードの心理状態を出力する第２のステップと、
    　投稿者毎に、前記心理状態を時系列に並べた心理遷移を出力する第３のステップと
    を有することを特徴とする装置の心理分析方法。     For each contributor, a psychological analysis method of a device that analyzes a transition of a psychological state with respect to a target keyword from a comment sentence transmitted,
    The apparatus has a psychological keyword dictionary part in which psychological keywords are registered in advance for each psychological state,
    The psychological analysis method is:
    A first step of obtaining a comment sentence including the target keyword for each contributor;
    For each contributor, if the comment text includes the psychological keyword of the psychological keyword dictionary means, a second step of outputting the psychological state of the psychological keyword;
    A psychological analysis method for an apparatus, comprising: a third step of outputting a psychological transition in which the psychological states are arranged in time series for each poster.
PCT/JP2015/056970 2014-03-10 2015-03-10 Device, program, and method for analyzing transition in psychological state of poster on basis of comment text WO2015137321A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201580011398.1A CN106062809A (en) 2014-03-10 2015-03-10 Device, program, and method for analyzing transition in psychological state of poster on basis of comment text

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014-046000 2014-03-10
JP2014046000A JP6169511B2 (en) 2014-03-10 2014-03-10 Apparatus, program, and method for analyzing poster's psychological transition based on comment text

Publications (1)

Publication Number Publication Date
WO2015137321A1 true WO2015137321A1 (en) 2015-09-17

Family

ID=54071765

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2015/056970 WO2015137321A1 (en) 2014-03-10 2015-03-10 Device, program, and method for analyzing transition in psychological state of poster on basis of comment text

Country Status (3)

Country Link
JP (1) JP6169511B2 (en)
CN (1) CN106062809A (en)
WO (1) WO2015137321A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10453099B2 (en) * 2015-12-11 2019-10-22 Fuji Xerox Co., Ltd. Behavior prediction on social media using neural networks
JP6815235B2 (en) * 2017-03-16 2021-01-20 ヤフー株式会社 Information processing equipment, information processing methods, and programs
JP6461290B1 (en) * 2017-11-24 2019-01-30 株式会社ドワンゴ Content providing server, content providing program, content providing system, and user program
KR102183412B1 (en) * 2020-07-23 2020-11-26 주식회사 에프엘이에스 Method and artificial intelligence system of servicing affiliate marketing using personal data that is based on the results of fortune-telling information contents
JP7146025B1 (en) 2021-06-16 2022-10-03 ヤフー株式会社 Information processing device, information processing method, and information processing program

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005032197A (en) * 2003-07-11 2005-02-03 Nippon Telegr & Teleph Corp <Ntt> Information analysis system and method
JP2008242762A (en) * 2007-03-27 2008-10-09 Nec Corp Portable terminal device and blog creation system
WO2013179340A1 (en) * 2012-05-30 2013-12-05 株式会社日立製作所 Information analysis system and information analysis method

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5423380B2 (en) * 2009-12-16 2014-02-19 富士ゼロックス株式会社 Information processing program and information processing method
JP5344623B2 (en) * 2010-01-06 2013-11-20 Ｎｅｃシステムテクノロジー株式会社 E-mail system, e-mail receiving apparatus and display method
CN102012913A (en) * 2010-11-23 2011-04-13 天津道格科技有限公司 Global comment board system and realization method thereof
US20120143693A1 (en) * 2010-12-02 2012-06-07 Microsoft Corporation Targeting Advertisements Based on Emotion
JP5845200B2 (en) * 2012-06-25 2016-01-20 株式会社コナミデジタルエンタテインメント Message browsing system, server, terminal device, control method, and program
CN103207855B (en) * 2013-04-12 2019-04-26 广东工业大学 For the fine granularity sentiment analysis system and method for product review information

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005032197A (en) * 2003-07-11 2005-02-03 Nippon Telegr & Teleph Corp <Ntt> Information analysis system and method
JP2008242762A (en) * 2007-03-27 2008-10-09 Nec Corp Portable terminal device and blog creation system
WO2013179340A1 (en) * 2012-05-30 2013-12-05 株式会社日立製作所 Information analysis system and information analysis method

Also Published As

Publication number Publication date
JP6169511B2 (en) 2017-07-26
JP2015170244A (en) 2015-09-28
CN106062809A (en) 2016-10-26

Similar Documents

Publication Publication Date Title
WO2016009985A1 (en) Program, device, and method for analyzing effect of promotion site on transition of psychological state of user
WO2015137321A1 (en) Device, program, and method for analyzing transition in psychological state of poster on basis of comment text
US10832283B1 (en) System, method, and computer program for providing an instance of a promotional message to a user based on a predicted emotional response corresponding to user characteristics
US10332161B2 (en) Retrieving reviews based on user profile information
JP6101620B2 (en) Purchase forecasting apparatus, method, and program
US20140372207A1 (en) Profit index value generation system and profit index value generation method
JP2013171436A (en) Recommendation program, device, and method for recommending reviewer suited to user&#39;s preference
CN111787042B (en) Method and device for pushing information
US20160260147A1 (en) Determining the Credibility of an On-Line User&#39;s Review
CN110598766B (en) Training method and device for commodity recommendation model and electronic equipment
EP2587446B1 (en) Information providing device, method of processing reward payment, reward payment processing program, and recording medium with reward payment processing program recorded theron
CN116842478A (en) User attribute prediction method based on twitter content
US20240078585A1 (en) Method and apparatus for sharing information
JP6219795B2 (en) Program, apparatus and method for detecting influencers with high influence of comment text to be posted
JP2013205875A (en) Recommend item detection program, device and method for detecting item to be reviewed by reviewer
CN111126649B (en) Method and device for generating information
JP6100741B2 (en) Extraction apparatus, extraction method and extraction program
US20160132903A1 (en) Identifying an industry specific e-maven
JP2013218369A (en) Information processing unit, program, information processing method and commodity introduction support system
JP6487204B2 (en) Program, apparatus, and method for detecting a place that affects a person&#39;s psychological state from comment text
JP2016040719A (en) Profit index value generation system and profit index value generation method
CN111626776A (en) Method for training strategy model, method and device for determining advertisement putting strategy
KR20150116506A (en) System and method for targeting a user terminal
JP6025155B2 (en) Information processing apparatus, method, and program
KR102402551B1 (en) Method, apparatus and computer program for providing influencer searching service

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15761185

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15761185

Country of ref document: EP

Kind code of ref document: A1