JP2016177620A - Information processing device, information processing method, information processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device, an information processing method, and an information processing program which are capable of extracting advertisement information which is likely to include an inappropriate keyword.SOLUTION: An information processing device 1 comprises an acquisition part 21, a reception part 22 and an extraction part 23. The acquisition part 21 acquires information on a hot-word of which a degree of attention inside a network has been rapidly increased. The reception part 22 receives a plurality of pieces of advertisement information including a keyword. The extraction part 23 extracts, from the plurality of pieces of advertisement information received by the reception part 22, advertisement information pieces in which the hot-word acquired by acquisition part 21 is included as a part or all of the keyword.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  In recent years, advertisement distribution via the Internet has been actively performed, and various advertisement contents are posted on web pages. When advertising content is newly posted on the above-described web page, for example, an advertisement distributor accepts advertising information including advertising content from an advertiser, and examines beforehand whether or not the advertising information is appropriate. .

  In connection with such advertisement screening, for example, a technique has been proposed in which, for example, the content of a web page on which advertisement content is posted is analyzed, and notification is made when an inappropriate pre-registered term is detected in the web page. (For example, refer to Patent Document 1).

JP 2002-189925 A

  By the way, a keyword is included in the advertisement information described above, and advertisement content may be distributed according to the keyword. For example, a search word input to a search site by a user is matched with a keyword of advertisement information, and the advertisement content may be posted on the search result page when they match.

  In this case, the keyword described above may be set to an inappropriate word that is not related to the content of the advertising content or the content of the landing page that is the link destination of the advertising content. For example, some advertisers may illegally include a search word that is likely to be input to a search site as a keyword in order to facilitate the posting of advertising content.

  The present application has been made in view of the above, and provides an information processing apparatus, an information processing method, and an information processing program capable of extracting advertisement information that may contain inappropriate keywords. The purpose is to provide.

  An information processing apparatus according to the present application includes an acquisition unit, a reception unit, and an extraction unit. The acquisition unit acquires information of a rapidly increasing word whose degree of attention on the network increases rapidly. The reception unit receives a plurality of advertisement information including keywords. The extraction unit extracts, from the plurality of advertisement information, the advertisement information in which the rapidly increasing word acquired by the acquisition unit is included as part or all of the keyword among the plurality of advertisement information received by the reception unit. To do.

  According to one aspect of the embodiment, it is possible to extract advertisement information that may contain inappropriate keywords.

FIG. 1 is a diagram illustrating an outline of processing executed by the information processing apparatus according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. FIG. 3 is a diagram illustrating an example of the sudden rise word table. FIG. 4 is a diagram illustrating an example of a predicted word table. FIG. 5 is a diagram illustrating an example of the priority word table. FIG. 6 is a diagram illustrating an example of the advertisement information table. FIG. 7 is a flowchart illustrating an extraction processing procedure performed by the information processing apparatus. FIG. 8 is a flowchart illustrating the processing procedure of the determination process. FIG. 9 is a diagram illustrating an example of a hardware configuration of a computer that executes a program.

  Hereinafter, embodiments of an information processing apparatus, an information processing method, and an information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment.

[1. Processing of information processing apparatus]
First, an example of processing executed by the information processing apparatus 10 according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an outline of processing executed by the information processing apparatus 10 according to the embodiment.

  The information processing device 10 is connected to the advertisement distribution device, the advertiser terminal device (none of which are shown in FIG. 1), and the surge word detection device 30 via the Internet or the like. A server that transmits and receives information. The various types of information described above include the advertisement information 40 and the information on the rapidly rising word 31, and the information processing apparatus 10, based on such information, for example, the advertisement information that satisfies a predetermined condition from the plurality of advertisement information 40. An extraction process for extracting 40 is performed.

  Note that the information processing device 10 and the suddenly rising word detection device 30 described above do not have to be a single processing device, and may be realized by a plurality of processing devices such as a cloud system operating in cooperation. Further, in FIG. 1, the information processing device 10 and the sudden rise word detection device 30 are separate devices, but this is an example and is not limited. For example, the information processing device 10 replaces the sudden rise word detection device 30. You may make it prepare.

  The advertisement information 40 is advertisement information submitted to the information processing apparatus 10 from the advertiser terminal device. The advertisement information 40 includes, for example, information on the keyword 41, information on the title 42a and description 42b, and information on a landing page 43 (hereinafter referred to as “LP43” in some cases). In the following, the title 42a and the description 42b may be collectively referred to as TD (Title and Description) 42.

  The keyword 41 is information indicating, for example, a condition for distributing advertisement content. Specifically, for example, in the advertisement distribution apparatus, the search word input to the search site by the user is matched with the keyword 41 of the advertisement information 40, and the advertisement content is distributed to the search result page when they match. Is done. Such advertising content includes a title 42a and a description 42b, and links to the landing page 43.

  In addition, although the example mentioned above is an advertisement delivery method called a search interlocking type | mold advertisement, it is not restricted to this example. For example, an advertisement distribution method called content matching that distributes advertisement content when the keyword 41 is related to a web page selected by the user may be used. Furthermore, for example, a technique such as targeting distribution that distributes advertising content when the keyword 41 matches user attribute information (such as psychographic attributes) may be used. The advertisement content matching described above may be performed based on the information of the TD 42 and the LP 43 in addition to the keyword 41 or instead of the keyword 41.

  The title 42a of the TD 42 is information indicating a text displayed as a title on the advertising content posted on the web page, and the description 42b is information indicating a text displayed as an explanation of the advertising content.

  The LP 43 is information on the web page linked to the advertising content posted on the web page. For example, the information indicating the URL (Uniform Resource Locator) where the data of the LP 43 is placed and the HTML (HyperText Markup constituting the LP 43). Language) file. In FIG. 1, for convenience of understanding, LP 43 is shown as a web page displayed on a user terminal device (not shown).

  Hereinafter, although the keyword 41, TD42, and LP43 of the advertisement information 40 described above will be described using a specific example shown in FIG. 1, this is merely an example and is not limited.

  The advertisement information 40 is advertisement information related to sales of supplements. The keyword 41 includes a plurality of text data such as “supplements”, “vitamins”, and “popular actor A”. Here, “supplements” and “vitamins” are appropriate keywords 41 corresponding to the sales of supplements. On the other hand, it is assumed that “popular actor A” is an inappropriate keyword 41 that does not correspond to the sale of supplements, in other words, a keyword 41 that is extremely unrelated to the sale of supplements.

  Further, the title 42a of the TD 42 includes text data such as “supplement sales” and the description 42b includes “here is a supplement that is currently sold ...”. The LP 43 also includes the URL of a supplement sales web page.

  In the above description, the text data is included as the keyword 41 or the TD 42 of the advertisement information 40. However, the present invention is not limited to this, and may be other data such as an image or a moving image.

  The sudden rise word detection device 30 is a server that performs processing for accessing information such as a search site or a news site, detecting information on the sudden rise word 31, and storing the detected information on the sudden rise word 31. The detection of the information of the soaring word 31 will be described later.

  Here, the rapidly increasing word 31 means, for example, a word whose degree of attention is rapidly increasing on the Internet. In other words, for example, a search that is relatively likely to be input to a search site by many users, for example. Is a word.

  1, the information of the soaring word 31 includes “popular actor A”, “popular athlete B”, “smash hit movie C”, “earthquake”, “pollen countermeasure”, and the like. Text data is included.

  By the way, it is preferable that the advertising content to be posted on the web page on the Internet is posted after a preliminary examination as to whether or not the advertising information 40 submitted by the advertiser is appropriate.

  However, the number of advertisement examinations mentioned above is increasing year by year. Therefore, for example, if the advertisement information 40 that may contain an inappropriate keyword 41 is extracted from the plurality of advertisement information 40 that is submitted, and the extracted advertisement information 40 can be a subject of examination. , Can reduce the burden of examination.

  Therefore, the information processing apparatus 10 according to the present embodiment is configured to be able to extract the advertisement information 40 that may contain an inappropriate keyword 41.

  In more detail, the information processing device 10 transmits a sudden rise word information request to the sudden rise word detection device 30, and the sudden rise word detection device 30 receives the transmitted sudden rise word information request (step S1).

  Subsequently, the sudden rise word detection device 30 transmits the information of the sudden rise word 31 to the information processing device 10, and the information processing device 10 acquires the transmitted information of the sudden rise word 31 (step S2).

  Further, the information processing apparatus 10 accepts the submission of the advertisement information 40 from the advertiser terminal device (step S3). In FIG. 1, only one advertisement information 40 is shown, but the present invention is not limited to this, and a plurality of pieces of information may be used. In addition, the order of the processes in steps S1 to S3 is not limited to the above. For example, the processes in steps S1 and S2 and the processes in step S3 are performed at the same timing or in the order of steps S3, S1 and S2. Also good.

  Then, the information processing apparatus 10 extracts the advertisement information 40 in which the acquired spike word 31 is included as a part or all of the keyword 41 of the advertisement information 40 from the plurality of advertisement information 40 (step S4).

  In the example shown in FIG. 1, as indicated by the dashed line D, the information processing apparatus 10 is configured to execute the advertisement because the keyword 41 of the advertisement information 40 includes the soaring word 31 of “popular actor A”. Information 40 is extracted.

  That is, as described above, “popular actor A” is a soaring word 31 that is likely to be input to a search site or the like by many users. For this reason, for example, a search word (here, “popular actor A”) that an advertiser thinks is likely to be input to a search site with the intention of facilitating the insertion of advertisement content is illegal as the keyword 41 of the advertisement information 40. It can be estimated that it may have been included.

  Therefore, the information processing apparatus 10 extracts advertisement information 40 including such keywords 41. Thereby, in the information processing apparatus 10, it is possible to extract the advertisement information 40 that may contain the inappropriate keyword 41.

  For example, when a plurality of submitted advertisement information 40 is reviewed, the extracted advertisement information 40 out of the plurality of advertisement information 40 is targeted for review, thereby reducing the burden of the review. It is also possible.

  In the above description, it is assumed that “popular actor A” is the keyword 41 that is extremely less relevant to the sale of supplements. However, for example, when the popular actor A is promoting the supplement, the “popular actor A” can be said to be the keyword 41 related to the sale of the supplement. In such a case, the examination result that the above-described advertisement information 40 is appropriate is made in the examination.

[2. Configuration of information processing system]
Next, the configuration of the information processing system 1 including the information processing apparatus 10 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing system 1 according to the embodiment.

  As illustrated in FIG. 2, the information processing system 1 according to the embodiment includes a terminal device 50 of a user U, terminal devices 60 and 60 of a plurality of advertisers M1 and M2, a web server 70, and a sudden rise word detection device. 30 and an advertisement distribution device 80 are included. Hereinafter, the terminal device 50 of the user U may be referred to as “user terminal 50”, and the terminal devices 60 and 60 of the advertisers M1 and M2 may be referred to as “advertiser terminals 60 and 60”.

  These various apparatuses are connected via a network N (for example, a communication network such as the Internet) so that they can communicate with each other by wire or wirelessly. The network N is, for example, a WAN (Wide Area Network) such as the Internet.

  In addition, the number of the various apparatuses which comprise the information processing system 1 is not restricted to what was illustrated in FIG. For example, the information processing system 1 illustrated in FIG. 2 may include a plurality of user terminals 50, a single advertiser terminal 60, and a plurality of web servers 70.

  The user terminal 50 is realized by, for example, a desktop PC (Personal Computer), a notebook PC, a smartphone, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like.

  For example, the user terminal 50 obtains a web page provided from the web server 70 by accessing the web server 70 and displays the obtained web page on a display device (for example, a liquid crystal display). Then, the user terminal 50 transmits an advertisement content distribution request to the advertisement distribution device 80 in order to distribute the advertisement content displayed in the advertisement space in the web page.

  Advertiser terminals 60 and 60 are used by advertisers M1 and M2 that request distribution of advertising content. The advertiser terminals 60 and 60 are realized by, for example, a desktop PC, a notebook PC, a smartphone, a tablet terminal, a mobile phone, a PDA, or the like.

  The advertiser terminals 60 and 60 submit the advertisement information 40 to the information processing apparatus 10 in accordance with operations by the advertisers M1 and M2. In the example shown in FIG. 2, the advertisers M1 and M2 are shown as being different persons, but they may be the same person, and a plurality of pieces of advertisement information 40 may be obtained from the same advertiser terminal 60 or 60. You may make it submit to the information processing apparatus 10. FIG.

  In addition, the advertisers M1 and M2 may request the submission from the agency without using the advertiser terminals 60 and 60 to submit the advertisement information 40 to the information processing apparatus 10. In this case, it is the agency that submits the advertisement information 40 to the information processing apparatus 10. Therefore, in the following, the notation “advertiser” is a concept that includes not only the advertiser but also the agency, and the notation “advertiser terminal” is an agency device that is used not only by the advertiser terminal but also by the agency. It is a concept including

  The web server 70 is a server device that provides various web pages when accessed from the user terminal 50. The web server 70 provides various web pages related to, for example, a search site, a news site, a posting site, a blog site, a shopping site, a route search site, a map providing site, a travel site, a restaurant introduction site, and a web blog.

  As described above, the web page distributed by the web server 70 includes an advertising space for displaying the advertising content. The web page including the advertising space includes the distribution request described above. For example, the URL or the like of the advertisement distribution device 80 is described as a distribution request in an HTML file or the like that forms a web page. In this case, the user terminal 50 receives the advertisement content from the advertisement distribution device 80 by accessing the URL described in the HTML file or the like.

  As described above, the sudden rise word detection device 30 performs processing for detecting information of the sudden rise word 31. For example, the soaring word detection device 30 accesses a search site, a news site, a posting site, a blog site, and the like provided from the web server 70 every predetermined period, and acquires content information including words in each site.

  Then, the rapidly increasing word detection device 30 compares the content acquired this time with the content acquired last time, and counts the number of contents including a new word for each new word type. Subsequently, the rapidly increasing word detection device 30 detects a word whose total number of contents exceeds the reference value as the rapidly increasing word 31.

  Note that the detection of the sudden rise word 31 in the sudden rise word detection device 30 is not limited to the above. That is, in the above, the number of contents including words is totaled, but the number of words themselves is totaled, and words whose rate of increase in the total number of words (that is, the number of appearances) exceeds the reference value are rapidly increased. For example, the sudden rise word 31 may be detected by other methods.

  As described above, the advertisement distribution device 80 is a server device that distributes the advertisement content based on the advertisement content distribution request transmitted from the user terminal 50 on which the web page is displayed.

[3. Configuration example of information processing apparatus 10]
As illustrated in FIG. 2, the information processing apparatus 10 includes a communication unit 11, a storage unit 12, and a control unit 13. In the following, “database” is described as “DB”.

[3.1. Configuration example of communication unit 11]
The communication unit 11 is a communication interface for communicating with the advertiser terminal 60, the sudden rise word detection device 30 and the like via the network N, and is realized by, for example, a NIC (Network Interface Card) or the like.

[3.2. Configuration example of storage unit 12]
The storage unit 12 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. Further, the storage unit 12 stores a sudden rise word DB 14, a prediction word DB 15, a priority degree word DB 16, and an advertisement information DB 17.

  In the sudden rise word DB 14, information on the sudden rise word 31 acquired from the sudden rise word detection device 30 is registered. FIG. 3 is a diagram illustrating an example of the sudden rise word table stored in the sudden rise word DB 14.

  As shown in FIG. 3, the surge word table includes information on sites where the surge word 31 is detected, such as “search site”, “news site”, “posting site”, and “blog site”. The ranking soaring word 31 is registered.

  The ranking described above is performed, for example, in the order of increasing rate of attention within each site during a predetermined period, but this is an example and is not limited. In the example illustrated in FIG. 3, for example, in the search site, it is assumed that the rate of increase is high in the order of “popular actor A”, “popular sports player B”, and “big hit movie C”.

  In the prediction word DB 15, for example, information in which words and periods that are predicted to rapidly increase the degree of attention on the Internet are registered as “prediction words” and “prediction periods” is registered. FIG. 4 is a diagram illustrating an example of a predicted word table stored in the predicted word DB 15.

  In the example shown in FIG. 4, the prediction period “summer season” and the prediction word “summer vacation, bathing,...” Are associated with each other. In addition, the prediction period “December” and the prediction word “Christmas, present,...” Are associated with each other, and the prediction period “July to September” and the prediction word “event name, event place name,. Are associated and registered.

  In this way, the prediction word is a word that can be predicted in advance, for example, a word having a seasonal meaning or an event name having a predetermined schedule in advance when the degree of attention rises at that time. .

  In the priority word DB 16, words to be preferentially extracted in the process of extracting the advertisement information 40 described later are registered. Specifically, a word (hereinafter referred to as “priority word”) associated with a priority based on a predetermined criterion. Is also registered). FIG. 5 is a diagram illustrating an example of the priority word table stored in the priority word DB 16.

  Here, an example of the predetermined standard is whether or not the priority word includes a relatively negative element or meaning, and is set so that the priority level of the priority word including the negative element is high. In the example shown in FIG. 5, priority words such as “earthquake”, “case name”, and “case name” often include negative elements and meanings, and thus have a high priority level. . On the other hand, priority words such as “Popular Actor A” and “Popular Sports Player B” often do not include negative elements, and are therefore associated with a low priority.

  Advertisement information 40 is registered in the advertisement information DB 17. FIG. 6 is a diagram illustrating an example of the advertisement information table stored in the advertisement information DB 17. As shown in FIG. 6, examples of the advertisement information table include “advertisement ID”, “advertiser address”, “keyword”, “TD”, “LP”, “keyword update count”, “relationship between keywords”. , “Relationship between analysis result and keyword”, “determination flag”, “notification flag”, and the like, and these pieces of information are associated with each other.

  “Advertisement ID” is identification information assigned to each advertisement information 40. The “advertiser address” is information indicating the addresses of the advertisers M1 and M2, and is used in the notification process described later.

  The “keyword” is information on the keyword 41 in the advertisement information 40 described above. In the example illustrated in FIG. 6, the keywords 41 of the advertisement IDs “a001” and “a002” include the “popular actor A” and “earthquake”, which are the rapidly increasing words 31, respectively.

  “TD” is information of the TD 42 of the advertisement information 40, and “LP” is information of the LP 43 of the advertisement information 40. In the example shown in FIG. 6, “LP” indicates the URL where the data of LP43 is placed.

  The “keyword update count” is information indicating the update count of the keyword 41 received by the information processing apparatus 10 after the advertisement information 40 is submitted. In the example illustrated in FIG. 6, the advertisement IDs “a001” and “a002” have received the update of the keyword 41 “10 times”, and the advertisement ID “a003” has received “one time”.

  “Relationship between keywords” is information indicating whether or not there is a relationship between keywords 41. In the example shown in FIG. 6, for example, the advertisement ID “a001” means the relevance of the keywords 41 “supplements”, “vitamins”, and “popular actor A”. It is shown that. On the other hand, for example, the advertisement ID “a003” indicates that the keywords 41 “supplements” and “vitamins” are “related”.

  “Relationship between analysis result and keyword” is information indicating whether or not there is a relationship between the result of cluster analysis (described later) performed based on TD42 and LP43 and the keyword 41.

  The “determination flag” is information indicating the result of the determination process for the advertisement information 40. For example, if the information processing apparatus 10 determines that there is a possibility that the advertisement information 40 includes an inappropriate keyword 41, the information processing apparatus 10 registers “0” in the determination flag of the corresponding advertisement ID. On the other hand, when the information processing apparatus 10 determines that there is no possibility that the inappropriate keyword 41 is included in the advertisement information 40 or is low, the information processing apparatus 10 registers “1” in the determination flag.

  The “notification flag” is information indicating whether or not to notify an advertisement distributor or an advertiser of such content according to the content of determination processing described later. In the example illustrated in FIG. 6, when the information processing apparatus 10 determines that there is a possibility that the advertisement information 40 includes an inappropriate keyword 41, “1” is registered in the notification flag and notified. I do. Further, when the information processing apparatus 10 determines that there is no possibility that the inappropriate keyword 41 is included in the advertisement information 40 or is low, the information processing apparatus 10 registers “0” in the notification flag and does not perform notification.

  In the above description, conditions for registering “1” and “0” in the “determination flag” and “notification flag” are shown, but these are examples, and such conditions can be arbitrarily set.

[3.3. Configuration example of control unit 13]
The control unit 13 is realized, for example, by executing various programs stored in a storage device inside the control unit 13 using the RAM as a work area by a CPU, an MPU, or the like. The control unit 13 is realized by an integrated circuit such as an ASIC or FPGA, for example.

  As illustrated in FIG. 2, the control unit 13 includes a request unit 20, an acquisition unit 21, a reception unit 22, an extraction unit 23, a determination unit 24, an analysis unit 25, and a notification unit 26. The internal configuration of the control unit 13 is not limited to the configuration illustrated in FIG. 2, and may be another configuration as long as the information processing described later is performed. In addition, the connection relationship between the processing units included in the control unit 13 is not limited to the connection relationship illustrated in FIG. 2, and may be another connection relationship.

  The requesting unit 20 transmits a sudden rise word information request to the sudden rise word detection device 30. The acquisition unit 21 acquires information on the sudden rise word 31 transmitted from the sudden rise word detection device 30 in response to the above-described sudden rise word information request.

  At this time, for example, the acquisition unit 21 acquires, as a sudden increase word 31, a word in which the rate of increase in the degree of attention on the Internet satisfies a predetermined condition during a predetermined period. As an example of such a predetermined condition, for example, words up to the top 100 in the increase rate are acquired as the rapidly increasing word 31. Thereby, for example, a search word that can be easily input to a search site or the like can be reliably acquired as the rapidly rising word 31. Note that the specific numerical value “upper 100” is merely an example and is not limited, and can be arbitrarily set.

  Moreover, when it is between the start timing and the end timing of the prediction period registered in the prediction word DB 15, the acquisition unit 21 reads the prediction word from the prediction word DB 15 and acquires the prediction word as the sudden increase word 31.

  That is, the spike word 31 obtained from the spike word detection device 30 described above is a word based on the rate of increase in the attention level in each site. In other words, the word that the user U is interested in in real time, It can be said that the word has begun to have.

  On the other hand, as described above, the predicted word is a word (for example, “summer vacation” or “Christmas”) that is expected to increase the degree of attention due to seasonal factors. By making such a predicted word a sudden rise word 31, it is possible to make a sudden rise word 31 that appropriately reflects a word whose attention level rises due to a seasonal factor, and thus, extraction of advertisement information 40 described later The accuracy can be further improved. And the acquisition part 21 registers the information of the acquired rapid increase word 31 in the rapid increase word DB14.

  The accepting unit 22 accepts a plurality of advertisement information 40 submitted from the advertiser terminals 60 and 60 directly or via another device. The reception unit 22 registers the received advertisement information 40 in the advertisement information DB 17. The accepting unit 22 accepts an update of the keyword 41 of the advertisement information 40 transmitted from the advertiser terminals 60 and 60 after submission. When receiving the update of the keyword 41, the receiving unit 22 updates the keyword 41 of the advertisement information 40 in the advertisement information DB 17 and increases the “keyword update count” of the advertisement information 40 by one.

  The extraction unit 23 reads the sudden rise word 31 from the sudden rise word DB 14 and reads the advertisement information 40 from the advertisement information DB 17. Further, the extraction unit 23 reads the priority word from the priority degree word DB 16. The extraction unit 23 performs an extraction process of the advertisement information 40 based on the rapidly rising word 31 or the like, which will be described later.

  The determination unit 24 reads the advertisement information 40 from the advertisement information DB 17 and determines whether or not the relevance of the plurality of keywords 41 included in the advertisement information 40 satisfies a predetermined condition. Specifically, the plurality of keywords 41 It is determined whether there is a relationship between the two.

  For example, when the advertisement information 40 includes a plurality of keywords 41, the determination unit 24 classifies which category (for example, food, car, travel, etc.) the keywords 41 belong to.

  For example, when the keyword 41 belongs to the same or similar category, the determination unit 24 determines that the keywords 41 are related, that is, satisfy a predetermined condition. On the other hand, when the keywords 41 are dissimilar and belong to different categories, the determination unit 24 determines that the keywords 41 are not related to each other, that is, determines that the predetermined condition is not satisfied.

  And the determination part 24 registers the information which shows the presence or absence of the relevance of the keywords 41 mentioned above in the "relevance between keywords" of the advertising information 40 of advertising information DB17.

  The analysis unit 25 reads the advertisement information 40 from the advertisement information DB 17 and performs a cluster analysis of the advertisement information 40 based on at least one of the TD 42 and the LP 43 included in the advertisement information 40. Then, the analysis unit 25 determines whether or not the relationship between the analysis result and the keyword 41 satisfies a predetermined condition. Specifically, whether or not there is a relationship between the analysis result and the keyword 41. Determine.

  Specifically, since the text data of TD42 and LP43 has a relatively large quantity, the analysis unit 25 first collects and classifies similar text data from among a plurality of text data of TD42 and LP43 by cluster analysis. .

  Then, the analysis unit 25 uses, for example, similar text data such as the TD 42 most frequently classified as being similar to each other as a result of analysis, and determines whether or not there is a relevance between the analysis result and the keyword 41. For example, the analysis unit 25 classifies to which category (for example, food, car, travel, etc.) the similar text data and the keyword 41 described above belong.

  For example, when the similar text data and the keyword 41, which are analysis results, belong to the same or similar category, the analysis unit 25 determines that these are related, that is, determines that a predetermined condition is satisfied. . On the other hand, when the similar text data and the keyword 41 are dissimilar and belong to different categories, the determination unit 24 determines that they are not related, that is, determines that the predetermined condition is not satisfied.

  And the analysis part 25 registers the information which shows the presence or absence of the relevance of the similar text data mentioned above and the keyword 41 in "relationship between an analysis result and a keyword" of the advertisement information 40 of advertisement information DB17.

  The notification unit 26 notifies the advertisement distributor and the advertiser. Specifically, for example, the notification unit 26 informs the advertisement distributor and the advertiser that it has been extracted that there is a possibility that an inappropriate keyword 41 is included in the submitted advertisement information 40. Notice.

[4. Processing flow of information processing apparatus 10]
Next, an example of the procedure of the advertisement information 40 extraction process by the information processing apparatus 10 will be described. FIG. 7 is a flowchart illustrating an extraction processing procedure performed by the information processing apparatus 10.

  Note that the processing shown in FIG. 7 is performed not only when the advertisement information 40 is submitted, but also after the advertisement content of the advertisement information 40 is posted on the web page. May be repeatedly executed.

  As illustrated in FIG. 7, the control unit 13 determines whether it is the acquisition timing of the sudden rise word 31 (step S <b> 101). Such acquisition timing can be arbitrarily set. In addition, for example, the control unit 13 may determine that it is the acquisition timing of the sudden rise word 31 when it is currently between the start timing and the end timing of the prediction period.

  When it determines with it being the acquisition timing of the sudden rise word 31 (step S101, Yes), the control part 13 acquires the sudden rise word 31 from the sudden rise word DB14 or the prediction word DB15 (step S102).

  When the control unit 13 determines that the advertisement information 40 has been submitted from the advertiser terminals 60 and 60 after the process of step S102 or when it is determined that it is not the acquisition timing of the suddenly rising word 31 (No in step S101). Determination is made (step S103).

  When it is determined that the advertisement information 40 is submitted (Yes in step S103), the control unit 13 determines whether the advertisement information 40 is the advertisement information 40 that may include an inappropriate keyword. The determination process is performed (step S104). FIG. 8 is a flowchart showing the processing procedure of such determination processing.

  As illustrated in FIG. 8, the control unit 13 determines whether or not the sudden increase word 31 is included as a part or all of the keyword 41 of the advertisement information 40 (Step S <b> 201). When it is determined that the keyword 41 of the advertisement information 40 does not include the sudden increase word 31 (No at Step S201), the control unit 13 sets a determination flag to 1 (Step S202). That is, the control unit 13 determines that there is no possibility that the inappropriate keyword 41 is included in the advertisement information 40 or that the keyword 41 is low.

  On the other hand, if it is determined that the keyword 41 of the advertisement information 40 includes the sudden rise word 31 (Yes in step S201), the control unit 13 updates the keyword 41 of the advertisement information 40, and the update is performed under a predetermined condition. It is determined whether or not the condition is satisfied (step S203).

  Here, the predetermined condition in step S203 is, for example, a case where the number of times of updating is equal to or greater than a predetermined number of times set or a time period after the update is less than a predetermined time set arbitrarily. However, the present invention is not limited to this.

  When it is determined that the update of the keyword 41 does not satisfy the predetermined condition (No at Step S203), the control unit 13 skips the process of Step S204 described later. On the other hand, when it is determined that the update of the keyword 41 satisfies the predetermined condition (step S203, Yes), the control unit 13 determines whether or not the sudden increase word 31 is included in the keyword 41 updated by the advertiser terminals 60 and 60. Is determined (step S204).

  When the rapidly increasing word 31 is not included in the updated keyword 41 (No in step S204), the control unit 13 determines that the keyword 41 that has been determined as the rapidly increasing word 31 in step S201 exists even at the time of submission. Since it can be estimated that it has already passed, the determination flag is set to 1 (step S202).

  On the other hand, if the control unit 13 determines that the rapidly increasing word 31 is included in the updated keyword 41 (step S204, Yes), it subsequently determines whether the keywords 41 are related to each other (step S204). Step S205).

  The process of step S205 is a process of determining whether or not there is a relevance between the rapidly increasing word 31 and the other keywords 41 because the rapidly increasing word 31 is included in the keyword 41.

  When the control unit 13 determines that the keywords 41 are related to each other (Yes in step S205), for example, the suddenly rising word 31 can be estimated as the keyword 41 suitable for the advertising content like the other keywords 41. From this, the determination flag is set to 1 (step S202).

  When it is determined that the keywords 41 are not related to each other in the advertisement information 40 (step S205, No), the control unit 13 performs a cluster analysis of the advertisement information 40 (step S206).

  Subsequently, the control unit 13 determines whether or not the analysis result and the keyword 41 are related (step S207). The process of step S207 is a process of determining whether or not there is a relevance between the keyword 41 including the rapid increase word 31 and the TD 42 or LP 43 because the keyword 41 includes the rapid increase word 31.

  If the control unit 13 determines that the analysis result and the keyword 41 are related (step S207, Yes), for example, the sudden rise word 31 is estimated to be the keyword 41 suitable for the advertising content such as TD42 and LP43. Since this is possible, the determination flag is set to 1 (step S202).

  On the other hand, if it is determined that the analysis result and the keyword 41 are not related (No in step S207), it is determined that the advertisement information 40 may include an inappropriate keyword 41, and the determination flag is set. It is set to 0 (step S208).

  As described above, in the information processing apparatus 10, by performing the processing of steps S <b> 203 to S <b> 207, the advertisement information 40 including the rapidly rising word 31 may be immediately included with the inappropriate keyword 41. The advertisement information 40 is not determined to be sexual. Thereby, in the information processing apparatus 10, it can be determined more accurately whether or not there is a possibility that the advertisement information 40 includes an inappropriate keyword 41.

  Note that it is not always necessary to execute all of steps S203 and S204, step S205, and steps S206 and S207 described above. For example, any one or two of them may be combined. In addition, no further processing is required.

  Returning to the description of FIG. 7, the control unit 13 determines whether there is no submission of the advertisement information 40 after the process of step S104 (No in step S103), based on the content of the determination process described above. Then, the advertisement information 40 is extracted and a notification setting process is performed (step S105).

  Specifically, in the determination process described above, the control unit 13 sets the determination flag to 0 and sets the advertisement information 40 that may contain an inappropriate keyword 41 in the advertisement information 40 to a plurality of pieces of advertisement information. Extract from 40.

  At this time, when the priority word 31 having a high priority is included in the rapidly increasing word 31 included in the keyword 41, the control unit 13 preferably extracts the advertisement information 40 by giving priority to the priority word.

  In other words, since the priority word having a high priority level includes negative elements and meanings, the advertisement information 40 including such a priority word as the keyword 41 is more likely to include the inappropriate keyword 41. It can be estimated that it is even higher.

  In this way, the control unit 13 extracts the advertisement information 40 by giving priority to the above-described priority word, so that, for example, the advertisement information that is estimated to be more likely to contain an inappropriate keyword. It becomes possible to make 40 an object of examination early.

  Further, the control unit 13 sets whether or not to notify the advertisement distributor and the advertiser of the content based on the content of the determination process described above. Here, for example, the advertisement information 40 that has been determined to be likely to contain an inappropriate keyword 41 in the advertisement information 40 is set so as to notify the advertisement distributor or the like. That is, “1” is registered in the notification flag.

  Subsequently, the control unit 13 determines whether there is a target to be notified to the advertisement distributor or the like (step S106). When it is determined that there is no notification target (No at Step S106), the control unit 13 ends the process as it is. On the other hand, when it is determined that there is a notification target (Yes in step S106), the control unit 13 notifies the advertisement distributor about the advertisement information 40 in which the notification flag is registered as “1” (step S107). Then, the advertisement distributor may start examining the notified advertisement information 40. Note that the control unit 13 may use an “advertiser address” corresponding to the advertisement information 40 when notifying the advertiser.

[5. effect]
The information processing apparatus 10 according to the embodiment acquires information on the keyword 41 whose degree of attention on the network increases rapidly, and receives a plurality of advertisement information 40 including the keyword 41. Then, the information processing apparatus 10 extracts, from the plurality of advertisement information 40, the advertisement information 40 in which the rapidly rising word 31 is included as part or all of the keyword 41 among the plurality of advertisement information 40. Thereby, the advertisement information 40 that may contain an inappropriate keyword can be extracted.

  In addition, the information processing apparatus 10 acquires, as a rapidly rising word 31, a word in which the rate of increase in the degree of attention on the network satisfies a predetermined condition during a predetermined period. Thereby, for example, a search word that can be easily input to a search site or the like can be reliably acquired as the rapidly rising word 31.

  The information processing apparatus 10 stores a word and a period that are predicted to have a rapidly increasing degree of attention as a prediction word and a prediction period in association with each other and stores the prediction word between the prediction period start timing and the end timing. Obtained as 31. As a result, it is possible to use the rapidly increasing word 31 that appropriately reflects a word whose attention level increases due to a seasonal factor, and thus the extraction accuracy of the advertisement information 40 can be further improved.

  The information processing apparatus 10 accepts the update of the keyword 41, and the keyword 41 to be updated when the update of the keyword 41 satisfies a predetermined condition and is included as part or all of the keyword 41 to be updated. Is extracted from the plurality of advertisement information 40. Thereby, for example, it is possible to extract the advertisement information 40 that is estimated that the update frequency of the keyword 41 is high and the possibility that an inappropriate keyword is included is even higher.

  In addition, the information processing apparatus 10 determines the relevance of the plurality of keywords 41 included in the advertisement information 40, determines that the relevance of the keywords 41 does not satisfy the predetermined condition, and the keyword 41 is the one of the plurality of keywords 41. When part or all of them are included, advertisement information 40 including a plurality of keywords 41 is extracted from the plurality of advertisement information 40. Thereby, it is possible to extract the advertisement information 40 that is estimated to have a higher possibility that the inappropriate keyword 41 is included in the advertisement information 40.

  In addition, the information processing apparatus 10 performs a cluster analysis of the advertisement information 40 based on at least one of the TD 42 and LP 43 information of the advertisement included in the advertisement information 40, and relates the result of the cluster analysis and the keyword 41. When the sex does not satisfy the predetermined condition and the rapidly increasing word 31 is included as part or all of the keyword 41, the advertisement information 40 including the plurality of keywords 41 is extracted from the plurality of advertisement information 40. Thereby, it is possible to extract the advertisement information 40 that is estimated to have a higher possibility that the inappropriate keyword 41 is included in the advertisement information 40.

  The information processing apparatus 10 stores the priority degree in association with the word (priority word) based on a predetermined criterion, and extracts the advertisement information 40 with priority given to the priority word having a high priority degree among the rapidly increasing words 31. Thereby, for example, it becomes possible to make the advertisement information 40, which is estimated to be even more likely to contain inappropriate keywords, to be subject to examination at an early stage.

[6. Hardware configuration]
Note that the information processing apparatus 10 in the above-described embodiment is realized, for example, when the computer 100 having a configuration illustrated in FIG. 9 executes a program. FIG. 9 is a diagram illustrating an example of a hardware configuration of the computer 100 that executes the program. The computer 100 includes a CPU 101, a RAM 102, a ROM (Read Only Memory) 103, an HDD (Hard Disk Drive) 104, a communication interface (I / F) 105, an input / output interface (I / F) 106, and a media interface (I / F). 107).

  The CPU 101 operates based on a program stored in the ROM 103 or the HDD 104 and controls each unit. The ROM 103 stores a boot program executed by the CPU 101 when the computer 100 is started up, a program depending on the hardware of the computer 100, and the like.

  The HDD 104 stores data used by programs executed by the CPU 101. The communication interface 105 receives data from other devices via the network N and sends the data to the CPU 101, and transmits the data generated by the CPU 101 to other devices via the network N.

  The CPU 101 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 106. The CPU 101 acquires data from the input device via the input / output interface 106. Further, the CPU 101 outputs the generated data to the output device via the input / output interface 106.

  The media interface 107 reads a program or data stored in the recording medium 108 and provides it to the CPU 101 via the RAM 102. The CPU 101 loads the program from the recording medium 108 onto the RAM 102 via the media interface 107, and executes the loaded program. The recording medium 108 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  When the computer 100 functions as the information processing apparatus 10 according to the above-described embodiment, the CPU 101 of the computer 100 realizes the function of the control unit 13 by executing a program loaded on the RAM 102, for example. The HDD 104 stores data in the storage unit 12. The CPU 101 of the computer 100 reads the program from the recording medium 108 and executes it, but as another example, the program may be acquired from another device via the network N.

  In the above-described embodiment, the advertisement information is exemplified as an object to be examined or extracted. However, the present invention is not limited to this. That is, for example, the information to be examined or extracted may be any information as long as it includes a keyword or the like.

[7. Others]
Although one aspect of the embodiment of the present application has been described in detail with reference to the drawings, this is an exemplification, and various modifications based on the knowledge of those skilled in the art, including the aspect described in the column of the disclosure of the invention. It is possible to implement the present invention in other forms with improvements.

  Each of the information processing apparatuses 10 described above may be realized by a plurality of server computers, and depending on functions, an external platform or the like may be realized by calling an API (Application Programming Interface) or network computing. Can be changed flexibly. Further, the information processing apparatus 10 and the sudden rise word detection apparatus 30 may be realized by a single server computer.

  In addition, the above-mentioned “section (module, unit)” can be read as “means” or “circuit”. For example, the extraction unit can be read as extraction means or an extraction circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 10 Information processing apparatus 11 Communication part 12 Storage part 13 Control part 20 Request part 21 Acquisition part 22 Reception part 23 Extraction part 24 Determination part 25 Analysis part 26 Notification part 30 Rapidly rising word detection apparatus 31 Rapidly rising word 40 Advertisement information 41 Keyword 42a Title 42b Description 43 Landing page 70 Web server 80 Advertisement distribution device

Claims (9)

An acquisition unit that acquires information of a rapidly increasing word whose attention level on the network rapidly increases;
A reception unit for receiving a plurality of advertisement information including keywords,
An extraction unit that extracts, from the plurality of advertisement information, the advertisement information in which the rapidly increasing word acquired by the acquisition unit is included as part or all of the keywords among the plurality of advertisement information received by the reception unit; An information processing apparatus comprising: The acquisition unit
2. The information processing apparatus according to claim 1, wherein a word whose rate of increase in the degree of attention on the network satisfies a predetermined condition is acquired as the sudden increase word during a predetermined period. A storage unit that stores a word and a period, which are predicted to rapidly increase the degree of attention on the network, as a prediction word and a prediction period;
The acquisition unit
The information processing apparatus according to claim 1, wherein the prediction word is acquired from the storage unit as the suddenly rising word during a start timing to an end timing of the prediction period. The reception unit
Accept updates of the keywords,
The extraction unit includes:
When the update of the keyword received by the receiving unit satisfies a predetermined condition, and the suddenly rising word is included as part or all of the keyword to be updated, the advertisement information including the keyword to be updated is The information processing apparatus according to claim 1, wherein the information processing apparatus is extracted from a plurality of advertisement information. A determination unit for determining relevance of a plurality of keywords included in the advertisement information;
The extraction unit includes:
Advertisement information including the plurality of keywords when the determination unit determines that the relevance of the plurality of keywords does not satisfy a predetermined condition, and the rapidly increasing word is included as part or all of the plurality of keywords. The information processing apparatus according to any one of claims 1 to 4, wherein the information is extracted from the plurality of pieces of advertisement information. An analysis unit that performs a cluster analysis of the advertisement information based on at least one of an advertisement title and a description included in the advertisement information and link information of the advertisement;
The extraction unit includes:
The advertisement information including the plurality of keywords when the relationship between the result of the cluster analysis by the analysis unit and the keywords does not satisfy a predetermined condition and the rapidly increasing word is included as part or all of the keywords The information processing device according to claim 1, wherein the information processing device is extracted from the plurality of advertisement information. A storage unit for storing a priority level in association with a word based on a predetermined criterion;
The extraction unit includes:
The information processing according to any one of claims 1 to 6, wherein the advertisement information is extracted with priority given to a word having a high priority among the rapidly increasing words acquired by the acquisition unit. apparatus. An information processing method executed by a computer,
An acquisition process for acquiring information of a rapidly increasing word that has a rapidly increasing degree of attention on the network;
Accepting a plurality of advertisement information including keywords,
An extraction step of extracting, from among the plurality of advertisement information received by the reception step, the advertisement information in which the rapidly increasing word acquired by the acquisition step is included as a part or all of the keyword. Information processing method. On the computer,
An acquisition procedure to get information on the soaring word whose attention on the network soars,
Acceptance procedure to accept multiple advertising information including keywords,
An extraction procedure for extracting, from among the plurality of advertisement information received by the reception procedure, the advertisement information in which the rapidly increasing word acquired by the acquisition procedure is included as part or all of the keyword. Information processing program.

Images