JP7260439B2 - Extraction device, extraction method and extraction program - Google Patents

Description

The present invention relates to an extraction device, an extraction method, and an extraction program.

In recent years, techniques for automatically inspecting content are known. An example of such technology is automatically testing ads for compliance with policies such as no exaggeration and no profanity, and using the results of those tests to determine whether to approve the ad. There are known techniques for

Japanese Unexamined Patent Application Publication No. 2011-204248

However, with the conventional technology described above, it is not always possible to grasp the keywords expected to be used in the content from the events that have occurred.

For example, the conventional technology described above simply checks whether or not words that are offensive to public order and morals, such as exaggerated expressions and vulgar words, are included. Therefore, with the conventional technology described above, it is not always possible to grasp the keywords expected to be used in the content from the events that have occurred.

The present application has been made in view of the above, and an object of the present application is to grasp keywords that are assumed to be used in content from events that have occurred.

An extraction device according to the present application includes an acquisition unit that acquires event information indicating an event that occurs in a predetermined period, and based on the event information acquired by the acquisition unit, a keyword related to the event, which is distributed and an extracting unit that extracts a keyword that satisfies a predetermined condition with respect to the provider of the target content.

According to one aspect of the embodiment, there is an effect that a keyword that is assumed to be used in content can be grasped from an event that has occurred.

FIG. 1 is a diagram illustrating an example of extraction processing according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an extraction processing system according to the embodiment; FIG. 3 is a diagram illustrating a configuration example of an extraction device according to the embodiment; FIG. 4 is a diagram illustrating an example of a provider information storage unit according to the embodiment; 5 is a diagram illustrating an example of an event information storage unit according to the embodiment; FIG. FIG. 6 is a flowchart illustrating an example of an extraction process procedure according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the extraction device.

Embodiments for implementing the extraction device, extraction method, and extraction program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the extraction device, extraction method, and extraction program according to the present application are not limited to this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. embodiment]
Extraction processing realized by the extraction device and the like of this embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of extraction processing according to an embodiment. The extraction process according to the embodiment is performed by the extraction device 100 shown in FIG.

Before describing FIG. 1, an extraction processing system 1 according to an embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of an extraction processing system according to the embodiment; The extraction processing system 1 according to the embodiment includes a main provider terminal 10, an external device 20, and an extraction device 100, as shown in FIG. The main provider terminal 10, the external device 20, and the extraction device 100 are connected via a network N so as to be able to communicate by wire or wirelessly. The extraction processing system 1 shown in FIG. 2 may include multiple provider terminals 10 , multiple external devices 20 , and multiple extraction devices 100 .

The provider terminal 10 is an information processing device used by an advertisement provider (advertiser). For example, the main provider terminal 10 is a smart phone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example shown in FIG. 1, the main provider terminal 10 is a notebook PC used by the user. The provider terminal 10 submits (provides) an advertisement to the extraction device 100 according to the provider's operation. In the example shown in FIG. 1, the provider terminal 10 is a notebook PC used by the provider.

The external device 20 is an information processing device that distributes various contents to users. The contents distributed by the external device 20 include, for example, portal sites, news sites, auction sites, weather forecast sites, shopping (electronic commerce) sites, finance (stock prices) sites, route search sites, map providing sites, travel sites, The content may be a restaurant introduction site, a facility reservation site, an SNS (Social Networking Service) site, a web blog, or the like. Also, the content distributed by the external device 20 may be, for example, content related to various applications (hereinafter sometimes referred to as “apps”) installed in the terminal device used by the user. Specifically, portal applications, news applications, auction sites, weather forecast applications, shopping applications, finance (stock prices) applications, route search applications, map provision applications, travel applications, restaurant introduction applications, facility reservation applications, SNS applications, The content may be related to a blog browsing application or the like.

The extraction device 100 is an information processing device that distributes advertisements to users. For example, the extraction device 100 manages information regarding advertisements provided from the provider terminal 10 . Then, the extraction device 100 responds to an advertisement distribution request (for example, a distribution request for an advertisement displayed on content distributed by the external device 20) transmitted from the terminal device used by the user, and distributes the advertisement to the terminal device. deliver to Note that the extraction device 100 distributes advertisements that have been examined based on whether or not the guidelines set by the administrator of the extraction device 100 are violated, and whose distribution is permitted. Here, the examination of the advertisement may be performed by the extraction device 100 or may be performed by an external information processing device having a predetermined relationship with the administrator of the extraction device 100 .

The extraction device 100 also acquires input information related to search queries and comments input by the user in the content distributed by the external device 20, and information such as the browsing history of the user's content.

Extraction processing performed by the extraction device 100 will be described below with reference to FIG. In the following explanation, provider terminal 10 will be explained as provider terminal 10-1 to 10-N (N is an arbitrary natural number) depending on the provider who uses provider terminal 10. FIG. For example, the provider terminal 10 is the provider terminal 10 used by the provider (provider U1) identified by the provider ID "U1". Further, hereinafter, the main provider terminals 10-1 to 10-N will be referred to as the main provider terminal 10 when they are described without distinction.

First, the extraction device 100 acquires provider information about the provider from the provider terminal 10 (step S1). For example, in the example of FIG. 1, the extraction device 100 acquires advertisement information regarding advertisements provided by each provider. Specifically, the extraction device 100 acquires an image related to the advertisement (advertisement image), text information, and the like as the advertisement information. Then, the extraction device 100 associates the advertisement information and the attribute of the advertisement (advertisement target) with the provider as provider information and stores them in the storage unit.

Note that the extraction device 100 may acquire, as attributes included in the provider information, information indicating the type of business of the provider, products handled by the provider, services provided by the provider, and the like.

Subsequently, the extraction device 100 acquires event information indicating events occurring in a predetermined period from the external device 20 (step S2). In the example of FIG. 1, the extraction device 100 determines that the content distributed by the external device 20 is viewed by the user in a predetermined period (for example, the most recent 24 hours, 1 day, 3 days, etc.). It is assumed that information (for example, image information, text information) related to content C1 (news content) that is equal to or greater than the threshold is acquired as event information.

Subsequently, the extraction device 100 identifies an event attribute based on the event information, and extracts a keyword corresponding to information linked to the identified attribute (step S3). For example, in the example of FIG. 1, the extraction device 100 identifies the attribute "disaster" of the event indicated by the content C1 by analyzing the text information of the content C1 using a natural language processing technique such as morphological analysis as appropriate. and In this case, the extraction device 100 extracts the keyword corresponding to the information linked to the attribute "disaster" from the information regarding the content C1. Specifically, the extraction device 100 uses character strings (for example, common nouns, proper nouns, etc.) indicating concepts such as “disaster area” and “disaster type” linked to the attribute “disaster” as keywords, Extract from the text information of the content C1. Here, in the example of FIG. 1, the extraction device 100 extracts from the text information of the content C1 using "region A" indicating the disaster area and "heavy rain" and "landslide disaster" indicating the type of disaster as keywords. shall be

In the example of FIG. 1, the keyword extraction processing by the extraction device 100 may be realized on a rule basis in which the attribute of the event and the information associated with the attribute are set, and may be realized using various models. may

Subsequently, the extraction device 100 identifies providers who provide advertisements related to the attribute of the event (step S4). For example, in the example of FIG. 1, the extraction device 100 identifies providers who provide advertisements belonging to attributes (advertising targets) linked to the attribute "disaster" of the event indicated by the content C1. Here, in the example of FIG. 1, the extraction device 100 associates the attribute "disaster" with the attributes "infrastructure", "medical care", and "disaster prevention goods". In this case, the extraction device 100 identifies the provider U1 who provides the advertisement belonging to the attribute "disaster prevention goods" as the provider who provides the advertisement related to the attribute "disaster" of the event indicated by the content C1.

Note that, in the example of FIG. 1, the process of specifying a provider by the extraction device 100 may be implemented on a rule basis in which an attribute of an event and an attribute of an advertisement linked to the attribute are set.

Subsequently, the extraction device 100 determines whether or not the advertisement to be distributed is subject to a predetermined examination or to suspension of distribution (step S5). For example, in the example of FIG. 1, the extraction device 100 is subject to examination (re-examination) as to whether or not to permit distribution of advertisements including the keyword extracted in step S3 among the advertisements provided by the provider U1. Alternatively, it is determined that the distribution is to be stopped.

Note that the extraction device 100 may determine that an advertisement including a predetermined number (for example, half of the extracted keywords) or more of the extracted keywords is subject to a predetermined examination or distribution suspension. Further, the extraction device 100 may determine that an advertisement including a specific keyword (for example, a proper noun such as a place name or a person's name) among the extracted keywords is subject to a predetermined examination or distribution suspension.

In addition, the extraction device 100 may implement keyword extraction processing using a model that has learned the character strings included in the advertisements that are subject to reexamination. For example, the extraction device 100 is trained so that the distributed representation of the character string that is the reason for the determination that the distribution is not possible in the reexamination is similar to the distributed representation of the keyword output by the model when the event information is input. Keyword extraction processing is realized by using the model.

Content providers are expected to use topical words that tend to attract the interest of users in advertisements for the purpose of enhancing the effect of appealing to users. On the other hand, since the extraction device 100 according to the embodiment extracts keywords related to events that occurred in the most recent period, it is possible to grasp topical keywords that providers are expected to use in content. . As a result, the extraction device 100 according to the embodiment identifies content that uses words related to current events that are estimated to negatively affect the user's feelings, such as natural disasters and obituaries. Therefore, it is possible to guarantee the quality of contents from the viewpoint of public order and morals.

[2. Configuration of extraction device]
Next, the configuration of the extraction device 100 will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of an extraction device according to the embodiment; As shown in FIG. 3, the extraction device 100 has a communication unit 110, a storage unit 120, and a control unit .

(Regarding communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the provider terminal 10, the external device 20, and the like.

(Regarding storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3 , storage unit 120 has provider information storage unit 121 and event information storage unit 122 .

(Regarding provider information storage unit 121)
The provider information storage unit 121 stores provider information about the provider. Here, an example of provider information stored in the provider information storage unit 121 will be described with reference to FIG. FIG. 4 is a diagram illustrating an example of a provider information storage unit according to the embodiment; In the example of FIG. 4, the provider information storage unit 121 has items such as "provider ID", "attribute", and "advertisement information".

"Provider ID" indicates identification information for identifying a provider. "Attribute" indicates the attribute of the advertisement (advertisement target). The "attribute" item may store information indicating the type of industry of the provider, the merchandise handled by the provider, the service provided by the provider, and the like. "Advertisement information" indicates information about advertisements provided by providers. In the example shown in FIG. 4, conceptual information such as "advertisement information #1" is stored in "advertisement information". Images, etc., URLs (Uniform Resource Locators) indicating their locations, file path names indicating storage locations, and the like are stored.

That is, FIG. 4 shows an example in which the provider identified by the provider ID "U1" provides an advertisement having the attribute "disaster prevention goods" and the advertisement information "advertisement information #1".

(Regarding event information storage unit 122)
The event information storage unit 122 stores event information indicating events that have occurred. An example of information stored in the event information storage unit 122 will now be described with reference to FIG. 5 is a diagram illustrating an example of an event information storage unit according to the embodiment; FIG. In the example of FIG. 5, the event information storage unit 122 has items such as "event ID", "date and time", "event information", "attribute", and "keyword".

"Event ID" indicates identification information for identifying an event. "Date and time" indicates the date and time when the event information was acquired. "Event information" is information indicating an event that has occurred. For example, information related to content that has been viewed by users more than a predetermined threshold, or search queries that have been entered by users more than a predetermined threshold. store information about FIG. 5 shows an example in which conceptual information such as "content information #1" is stored in "event information". A URL indicating the location of the file, a file path name indicating the storage location, and the like are stored. "Attribute" indicates an attribute of an event. "Keyword" indicates a keyword associated with the event.

That is, in FIG. 5, the event information "content information #1" is acquired at the date and time "date and time #1", the event indicated by the event information is identified by the event ID "M1", and the attribute of the event is "disaster". An example in which the keywords are "region A, heavy rain, ..." is shown.

(Regarding the control unit 130)
The control unit 130 is a controller. For example, various programs stored in a storage device inside the extraction device 100 are controlled by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., using the RAM as a work area. It is realized by being executed. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 3, the control unit 130 according to the embodiment includes an acquisition unit 131, an extraction unit 132, an identification unit 133, and a determination unit 134, and performs information processing functions and actions described below. Realize or carry out.

(Regarding the acquisition unit 131)
Acquisition unit 131 acquires event information indicating an event occurring in a predetermined period. For example, in the example of FIG. 1, event information indicating events occurring within the last 24 hours, 1 day, or 3 days is acquired and stored in the event information storage unit 122 .

Further, the acquiring unit 131 may acquire, as event information, information indicating a search query whose number of times of input in a predetermined period is equal to or greater than a predetermined threshold. For example, in the example of FIG. 1, the acquisition unit 131 acquires text information indicating search queries whose number of inputs has increased by a predetermined rate based on the input information acquired from the external device 20 .

Further, the acquisition unit 131 may acquire, as the event information, information indicating content for which the number of viewing times during a predetermined period is equal to or greater than a predetermined threshold. For example, in the example of FIG. 1 , the acquisition unit 131 acquires information indicating content that has been viewed more than a predetermined threshold based on the user's content viewing history acquired from the external device 20 .

Further, the acquisition unit 131 may acquire information indicating an event held during a predetermined period as the event information. For example, the acquisition unit 131 acquires information indicating events that will be held in the future for a predetermined period from the present time, such as concerts, stage performances, sports, etc., that are expected to attract a predetermined number of people or more.

Further, the acquisition unit 131 may acquire event information indicating an event, among the events, that is estimated to cause the contacting user's emotion to become negative. For example, the acquisition unit 131 acquires event information indicating an event such as a natural disaster, an obituary, a war, an accident, etc., which is estimated to make the user in contact feel negative.

In addition, the acquisition unit 131 may acquire, as the event information, information indicating content whose number of times of display in a predetermined period is equal to or greater than a predetermined threshold among the content to be distributed. For example, the acquisition unit 131 acquires advertisement information indicating advertisements whose number of impressions or CTR (Click Through Rate) is equal to or greater than a predetermined threshold among advertisements to be distributed.

The acquisition unit 131 may also acquire, as the event information, information about content that has been examined as to whether or not it should be distributed, and that has been determined to be undistributable within a predetermined period of time. For example, the acquisition unit 131 acquires advertisement information indicating advertisements that are judged to be undistributable after being examined based on whether or not they violate guidelines set by the administrator of the extraction device 100 during a predetermined period of time. get.

(Regarding the extraction unit 132)
Based on the event information acquired by the acquisition unit 131, the extraction unit 132 extracts keywords that are related to the event and that satisfy a predetermined condition for the relationship with the provider of the content to be distributed. For example, the extraction unit 132 extracts keywords that the provider is expected to use in his/her own content from the event information. For example, in the example of FIG. 1, the extraction unit 132 identifies the attribute "disaster" of the event indicated by the content C1 by analyzing the text information of the content C1 using a natural language processing technique such as morphological analysis as appropriate, A keyword corresponding to the specified attribute is extracted from the information about the content C1.

Also, the extracting unit 132 may extract a keyword corresponding to information linked to the attribute of the event. For example, in the example of FIG. 1, the extraction unit 132 extracts a keyword corresponding to information linked to the attribute "disaster" of the event indicated by the content C1 from the information regarding the content C1.

Further, the extracting unit 132 may extract a keyword whose number of appearances is equal to or greater than a predetermined threshold among the keywords included in the information about the content acquired by the acquiring unit 131 . For example, the extracting unit 132 extracts keywords whose number of appearances is equal to or greater than a predetermined threshold, or keywords whose number of appearances has increased by a predetermined rate, from the keywords included in the advertisements determined to be undeliverable in a predetermined period. do.

Moreover, the extraction unit 132 may extract a keyword that is the reason why the distribution is determined to be impossible in the examination. For example, the extracting unit 132 extracts a keyword included in an advertisement that was determined to be undeliverable during a predetermined period of time and that is the reason why the advertisement was determined to be undeliverable.

Further, the extracting unit 132 may extract keywords from content similar in attribute to content provided by the provider, among the content determined to be undistributable. For example, the extraction unit 132 extracts keywords from content similar in attributes to advertisements provided by the provider, among the content determined to be undistributable during a predetermined period.

(Regarding the specifying unit 133)
The identifying unit 133 identifies a provider having a predetermined relationship with the event among the providers. For example, in the example of FIG. 1, the identifying unit 133 identifies the provider U1 who provides advertisements belonging to the attribute linked to the attribute "disaster" of the event indicated by the content C1.

Further, the identifying unit 133 may identify, among the providers, providers who provide content related to the attribute of the event. For example, in the example of FIG. 1, the identifying unit 133 identifies a provider U1 who provides an advertisement belonging to the attribute "disaster prevention goods" related to the attribute "disaster" of the event indicated by the content C1.

(Regarding the determination unit 134)
Based on the keyword extracted by the extracting unit 132 and the information on the content provided by the provider specified by the specifying unit 133, the determining unit 134 determines whether the content is subject to a predetermined examination or is subject to suspension of distribution. Determine whether or not to be targeted. For example, in the example of FIG. 1, the determination unit 134 determines whether or not to permit the distribution of advertisements provided by the provider U1 based on keywords extracted from the information about the content C1. Alternatively, it is determined whether or not the distribution is to be stopped.

Further, the determination unit 134 may determine that content including a keyword is subject to a predetermined examination or distribution suspension. For example, in the example of FIG. 1, the determination unit 134 examines (re-examines) whether or not to permit distribution of an advertisement including a keyword extracted from information about the content C1 among advertisements provided by the provider U1. It is judged as a target or a target for distribution suspension.

[3. Extraction process flow]
Here, a procedure of extraction processing of the extraction device 100 according to the embodiment will be described with reference to FIG. 6 . FIG. 6 is a flowchart illustrating an example of an extraction process procedure according to the embodiment.

As shown in FIG. 6, the extraction device 100 acquires event information indicating events occurring in a predetermined period (step S101). For example, in the example of FIG. 1, the extraction device 100 acquires, as event information, information related to the content C1 for which the user's browsing count in the most recent period is equal to or greater than a predetermined threshold.

Subsequently, the extracting device 100 extracts keywords that satisfy a predetermined condition of the relationship with the provider of the content to be distributed (step S102). For example, the extraction device 100 extracts topical keywords that the provider is expected to use in the content from the event information. Subsequently, the extraction device 100 identifies a provider who has a predetermined relationship with the event (step S103). For example, in the example of FIG. 1, the extraction device 100 identifies providers who provide advertisements belonging to attributes linked to the attributes of the event.

Subsequently, the extraction device 100 determines whether or not the content to be distributed is subject to a predetermined examination or to suspension of distribution (step S104). For example, in the example of FIG. 1, the extraction device 100 selects, from among the advertisements provided by the specified provider, the advertisements containing the extracted keywords as targets for examination as to whether or not to permit distribution, or for suspension of distribution. I judge.

[4. Modification]
The above-described embodiment is an example, and various modifications and applications are possible.

[4-1. Regarding the content provided by the provider]
In the above-described embodiment, the determination unit 134 determines whether the advertisement is subject to a predetermined examination or distribution suspension based on the keyword extracted from the event information and the information on the advertisement related to the attribute of the event. Although an example of determining whether or not is shown, the determination target of the determination unit 134 is not limited to advertisements. For example, the determination unit 134 determines whether the content is subject to a predetermined examination or distribution suspension based on the keyword extracted from the event information and the information on various content related to the attribute of the event. It may be determined whether

[4-2. Concerning the identification process of the provider who is related to the event]
In the above-described embodiment, an example was given in which the identifying unit 133 identifies a provider who provides content related to the attribute of an event, but the function of the identifying unit 133 is not limited to such a configuration. For example, when the extracting unit 132 extracts a keyword from event information indicating an event of which the degree of interest of the user is extremely high (for example, information about content whose number of views is higher than the average by a predetermined threshold or more), the identifying unit 133 , not only providers providing content related to the attributes of the event, but also providers providing content unrelated to the attributes of the event may be specified.

[5. effect〕
As described above, the extraction device 100 according to the embodiment has the acquisition unit 131, the extraction unit 132, the identification unit 133, and the determination unit . Acquisition unit 131 acquires event information indicating an event occurring in a predetermined period. Based on the event information acquired by the acquisition unit 131, the extraction unit 132 extracts keywords that are related to the event and that satisfy a predetermined condition for the relationship with the provider of the content to be distributed. Also, the extracting unit 132 extracts a keyword corresponding to information linked to the attribute of the event. The identifying unit 133 identifies a provider having a predetermined relationship with the event among the providers. Based on the keyword extracted by the extracting unit 132 and the information on the content provided by the provider specified by the specifying unit 133, the determining unit 134 determines whether the content is subject to a predetermined examination or is subject to suspension of distribution. Determine whether or not to be targeted.

As a result, since the extraction device 100 according to the embodiment extracts keywords related to events that occurred in the most recent period, it is possible to grasp the keywords that the provider is expected to use in the content.

Further, in the extraction device 100 according to the embodiment, for example, the acquisition unit 131 acquires, as event information, information indicating search queries whose number of inputs during a predetermined period is equal to or greater than a predetermined threshold. In addition, the acquisition unit 131 acquires, as the event information, information indicating the content for which the number of viewing times in a predetermined period is equal to or greater than a predetermined threshold. In addition, the acquisition unit 131 acquires information indicating an event held during a predetermined period as event information. In addition, the acquisition unit 131 acquires event information indicating an event that is estimated to cause the contacting user's emotion to become negative among the events. In addition, the acquisition unit 131 acquires, as event information, information indicating content whose number of times of display in a predetermined period is equal to or greater than a predetermined threshold among the content to be distributed. In addition, the acquisition unit 131 acquires, as event information, information about content that has been examined as to whether or not it should be distributed, and that has been determined to be undistributable within a predetermined period. Then, the extracting unit 132 extracts keywords whose number of appearances is equal to or greater than a predetermined threshold, from the keywords included in the information about the content acquired by the acquiring unit 131 . Also, the extracting unit 132 extracts a keyword that is the reason why distribution is determined to be impossible in the examination. Further, the extracting unit 132 extracts keywords from content similar in attributes to content provided by the provider, among the content determined to be undistributable.

As a result, since the extraction device 100 according to the embodiment extracts keywords from various types of event information, it is possible to grasp a wide range of keywords that the provider is expected to use for content.

Further, in the extraction device 100 according to the embodiment, for example, the identifying unit 133 identifies, among the providers, providers who provide content related to the attribute of the event. Further, the determining unit 134 determines that the content including the keyword is subject to a predetermined examination or distribution suspension.

As a result, even if the keyword is abused, the extraction device 100 according to the embodiment can identify the provider according to the attribute of the event and the extracted keyword, and can determine the content provided by the identified provider. , to ensure the quality of the content.

[6. Hardware configuration]
Also, the extraction device 100 according to each of the embodiments described above is implemented by, for example, a computer 1000 configured as shown in FIG. Hereinafter, the extraction device 100 will be described as an example. FIG. 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the extraction device. Computer 1000 has CPU 1100 , ROM 1200 , RAM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1200 or HDD 1400 and controls each section. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs dependent on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from another device via communication network 500 (corresponding to network N in the embodiment) and sends it to CPU 1100, and also transmits data generated by CPU 1100 via communication network 500 to other devices. Send to device.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . Also, CPU 1100 outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1300 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1300 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the extraction device 100 , the CPU 1100 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the RAM 1300 . In addition, each data in the storage device of the extraction device 100 is stored in the HDD 1400 . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via a predetermined communication network.

[7. others〕
As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

In addition, the configuration of the extraction apparatus 100 described above can be flexibly changed, for example, by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like, depending on the function.

In addition, the "unit" described in the claims can be read as "means", "circuit", or the like. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

10 provider terminal 20 external device 100 extraction device 110 communication unit 120 storage unit 121 provider information storage unit 122 event information storage unit 130 control unit 131 acquisition unit 132 extraction unit 133 identification unit 134 determination unit

Claims (13)

An acquisition unit that acquires, as event information indicating an event that occurs during a predetermined period, information about content that has been examined as to whether or not it should be distributed and that has been determined to be undistributable during the predetermined period. and,
An extraction unit for extracting a keyword whose number of appearances is equal to or greater than a predetermined threshold, among keywords included in information about content similar in attributes to content provided by a provider, among the content determined to be undistributable in the examination. and . The extractor is
The extracting device according to claim 1, extracting a keyword corresponding to information linked to the attribute of the event. The acquisition unit
3. The extracting device according to claim 1, wherein information indicating a search query whose number of times of input in the predetermined period is equal to or greater than a predetermined threshold is acquired as the event information. The acquisition unit
4. The extracting device according to any one of claims 1 to 3, wherein, as the event information, information indicating a content whose number of viewing times in the predetermined period is equal to or greater than a predetermined threshold is acquired. The acquisition unit
5. The extracting device according to any one of claims 1 to 4, wherein information indicating an event held during the predetermined period is obtained as the event information. The acquisition unit
6. The extracting device according to any one of claims 1 to 5, wherein event information indicating an event, among the events, that is estimated to cause the contacting user's emotion to become negative, is acquired. The acquisition unit
7. Acquiring, as the event information, information indicating content whose number of times of display in the predetermined period is equal to or greater than a predetermined threshold among the contents to be distributed as the event information. The extraction device according to . The extractor is
8. The extracting device according to any one of claims 1 to 7, extracting a keyword that is a reason why distribution is determined to be impossible in the examination. a specifying unit that specifies a provider having a predetermined relationship with the event, from among the providers;
Based on the keyword extracted by the extracting unit and the information on the content provided by the provider specified by the specifying unit, whether the content is subject to a predetermined examination or distribution suspension The extracting device according to any one of claims 1 to 8 , further comprising a determination unit that determines whether. The identification unit
10. The extracting device according to claim 9 , wherein, among the providers, a provider who provides content related to the attribute of the event is specified. The determination unit is
11. The extracting device according to claim 9 , wherein, among the contents, contents including the keyword are determined to be subject to a predetermined examination or to be subject to suspension of distribution. An extraction method performed by an extraction device, comprising:
An acquisition step of acquiring, as event information indicating an event that occurs during a predetermined period, information relating to content that has been examined as to whether or not it should be distributed and that has been determined to be undistributable during the predetermined period. and,
An extraction step of extracting a keyword whose number of appearances is equal to or greater than a predetermined threshold among keywords included in information about content similar in attributes to content provided by a provider, among the content determined to be undistributable in the examination. An extraction method characterized by comprising and . Acquisition procedure for acquiring, as event information indicating an event that occurs during a predetermined period, information relating to content that has been examined as to whether or not it should be distributed and that has been determined to be undistributable during the predetermined period. and,
An extraction procedure for extracting a keyword whose number of appearances is equal to or greater than a predetermined threshold among keywords included in information about content similar in attributes to content provided by a provider, among the content determined to be undistributable in the examination. An extraction program for executing and on a computer.

Images