Extraction device, extraction method, and extraction program

Abstract

To grasp a keyword expected to be used for contents from an event which has occurred.SOLUTION: An extraction device according to the present application is provided with an acquisition unit for acquiring event information (for example, information about contents whose number of views by a user is equal to or greater than a predetermined threshold) indicating an event that occurs in a predetermined period, and an extraction unit for extracting keywords related to the event based on the event information acquired by the acquisition unit and whose relationship with the provider of the contents to be distributed satisfies a predetermined condition.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an extraction device, an extraction method, and an extraction program. [Background technology]

[0002] In recent years, technologies for automatically inspecting content have become known. One example of such a technology is a technology that automatically inspects whether advertisements comply with policies such as prohibiting exaggeration and vulgar language, and uses the inspection results to decide whether to approve the advertisements. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2011-204248 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the above-mentioned conventional technology, it is not always possible to grasp keywords that are expected to be used in content from an event that has occurred.

[0005] For example, the above-mentioned conventional technology merely checks whether or not a content contains words that are offensive to public order and morals, such as exaggerated expressions, vulgar language, etc. Therefore, the above-mentioned conventional technology does not necessarily make it possible to grasp keywords that are expected to be used in the content from the event that has occurred.

[0006] The present application has been made in consideration of the above, and aims to grasp keywords that are expected to be used in content from an event that has occurred. [Means for solving the problem]

[0007] The extraction device according to the present application includes an acquisition unit that acquires event information indicating an event that occurs during a predetermined period, and an event extraction unit that extracts the event information based on the event information acquired by the acquisition unit. Identify the attributes of and indicate the concepts associated with the identified attributes. The present invention is characterized by comprising an extraction unit that extracts keywords. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to obtain an effect that keywords that are expected to be used in content can be grasped from an event that has occurred. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of an extraction process according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of a configuration of the extraction processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of an extraction device according to an embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a provider information storage unit according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of an event information storage unit according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of a procedure of the extraction process according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the extraction device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the extraction device, extraction method, and extraction program according to the present application will be described in detail with reference to the drawings. Note that the extraction device, extraction method, and extraction program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0011] 1. Embodiment The extraction process realized by the extraction device or the like of this embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the extraction process according to the embodiment. The extraction process according to the embodiment is performed by the extraction device 100 shown in Fig. 1.

[0012] Prior to the description of FIG. 1, an extraction processing system 1 according to an embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing a configuration example of the extraction processing system according to the embodiment. As shown in FIG. 2, the extraction processing system 1 according to the embodiment includes a provider terminal 10, an external device 20, and an extraction device 100. The provider terminal 10, the external device 20, and the extraction device 100 are connected to each other via a network N so as to be able to communicate with each other by wire or wirelessly. The extraction processing system 1 shown in FIG. 2 may include a plurality of provider terminals 10, a plurality of external devices 20, and a plurality of extraction devices 100.

[0013] The provider terminal 10 is an information processing device used by an advertisement provider (advertiser). For example, the provider terminal 10 is a smartphone, 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 provider terminal 10 is a notebook PC used by a user. The provider terminal 10 submits (provides) an advertisement to the extraction device 100 in response to an operation of the provider. In the example shown in FIG. 1, the provider terminal 10 is a notebook PC used by the provider.

[0014] The external device 20 is an information processing device that distributes various contents to a user. The contents distributed by the external device 20 may be, for example, contents related to a portal site, a news site, an auction site, a weather forecast site, a shopping (electronic commerce) site, a finance (stock price) site, a route search site, a map providing site, a travel site, a restaurant introduction site, a facility reservation site, a SNS (Social Networking Service) site, a web blog, or the like. The contents distributed by the external device 20 may be, for example, contents related to various applications (hereinafter, sometimes referred to as "apps") installed in a terminal device used by a user. Specifically, the contents may be contents related to a portal application, a news application, an auction site, a weather forecast application, a shopping application, a finance (stock price) application, a route search application, a map providing application, a travel application, a restaurant introduction application, a facility reservation application, a SNS application, a blog viewing application, or the like.

[0015] The extraction device 100 is an information processing device that delivers advertisements to users. For example, the extraction device 100 manages information related to advertisements provided from the provider terminal 10. Then, in response to an advertisement delivery request (for example, a delivery request for an advertisement to be displayed on content delivered by the external device 20) transmitted from a terminal device used by a user, the extraction device 100 delivers the advertisement to the terminal device. Note that the extraction device 100 delivers advertisements that have been screened based on whether or not they violate guidelines established by an administrator of the extraction device 100 and that have been permitted to be delivered. Here, the screening of advertisements 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.

[0016] In addition, the extraction device 100 acquires input information related to search queries and comments input by users in content distributed by the external device 20, and information such as the browsing history of the content by the users.

[0017] The extraction process performed by the extraction device 100 will be described below with reference to FIG. 1. In the following description, the provider terminal 10 will be described as provider terminals 10-1 to 10-N (N is any natural number) according to the provider using the provider terminal 10. For example, the provider terminal 10 is a provider terminal 10 used by a provider (provider U1) identified by a provider ID "U1". In the following description, the provider terminals 10-1 to 10-N will be described as provider terminal 10 when there is no particular distinction between them.

[0018] First, the extraction device 100 acquires provider information related to the provider from the provider terminal 10 (step S1). For example, in the example of FIG. 1, the extraction device 100 acquires advertisement information related to advertisements provided by each provider. Specifically, the extraction device 100 acquires images (advertising images) related to the advertisements, text information, and the like, as the advertisement information. Then, the extraction device 100 stores the advertisement information and attributes of the advertisements (advertising targets) as provider information in a storage unit in association with the provider.

[0019] The extraction device 100 may acquire information indicating the business type of the provider, the products handled by the provider, the services provided by the provider, and the like, as attributes included in the provider information.

[0020] Next, the extraction device 100 acquires event information indicating events occurring within a predetermined period from the external device 20 (step S2). In the example of Fig. 1, it is assumed that the extraction device 100 acquires, as event information, information (e.g., image information, text information) regarding content C1 (news content) that has been viewed by users a predetermined period (e.g., the last 24 hours, one day, three days, etc.) that is equal to or greater than a predetermined threshold, among the contents distributed by the external device 20.

[0021] Next, the extraction device 100 identifies an attribute of the event based on the event information, and extracts keywords corresponding to information linked to the identified attribute (step S3). For example, in the example of FIG. 1, the extraction device 100 analyzes the text information of the content C1 using a natural language processing technique such as morphological analysis as appropriate, and thereby identifies the attribute "disaster" of the event indicated by the content C1. In this case, the extraction device 100 extracts keywords corresponding to information linked to the attribute "disaster" from information related to the content C1. Specifically, the extraction device 100 extracts character strings (e.g., common nouns and proper nouns) indicating concepts such as "disaster area" and "type of disaster" linked to the attribute "disaster" from the text information of the content C1 as keywords. Here, in the example of FIG. 1, the extraction device 100 extracts "area A" indicating the disaster area, and "heavy rain" and "landslide" indicating the type of disaster from the text information of the content C1 as keywords.

[0022] In the example of FIG. 1, the keyword extraction process by the extraction device 100 may be realized based on a rule in which attributes of events and information associated with the attributes are set, or may be realized using various models.

[0023] Next, 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 an attribute (advertising target) linked to the attribute "disaster" of the event indicated by the content C1. Here, in the example of FIG. 1, the extraction device 100 assumes that the attributes "infrastructure," "medical care," and "disaster prevention goods" are linked to the attribute "disaster." In this case, the extraction device 100 identifies a provider U1 who provides an advertisement belonging to the attribute "disaster prevention goods" as a provider who provides an advertisement related to the attribute "disaster" of the event indicated by the content C1.

[0024] In the example of FIG. 1, the process of identifying a provider by the extraction device 100 may be realized based on a rule in which attributes of an event and attributes of an advertisement associated with the attributes are set.

[0025] Next, the extraction device 100 determines whether the advertisement to be distributed is subject to a predetermined review or to a target for distribution suspension (step S5). For example, in the example of Fig. 1, the extraction device 100 determines that the advertisement including the keyword extracted in step S3 among the advertisements provided by the provider U1 is subject to a review (re-review) on whether to permit distribution or not, or is subject to a target for distribution suspension.

[0026] The extraction device 100 may determine that an advertisement including a predetermined number (e.g., half of the extracted keywords) of the extracted keywords is subject to a predetermined screening process or is subject to distribution suspension. The extraction device 100 may also determine that an advertisement including a specific keyword (e.g., a proper noun such as a place name or a person's name) among the extracted keywords is subject to a predetermined screening process or is subject to distribution suspension.

[0027] Furthermore, the extraction device 100 may realize the keyword extraction process by using a model that has been trained on a character string included in an advertisement that has been subject to reexamination. For example, the extraction device 100 realizes the keyword extraction process by using a model that has been trained so that a distributed representation of a character string that is the reason for determining that the advertisement cannot be delivered in the reexamination is similar to a distributed representation of a keyword that the model outputs when event information is input.

[0028] It is expected that content providers will use current topics that are likely to attract users' attention in their advertisements in order to increase the effectiveness of their advertising to users. In response to this, the extraction device 100 according to the embodiment extracts keywords related to events that have occurred in the most recent period, and therefore can grasp current topics that content providers are expected to use in their content. As a result, the extraction device 100 according to the embodiment can identify content that uses words related to current events that are expected to negatively affect users who come into contact with the content, such as natural disasters and obituaries, and therefore can ensure the quality of the content from the perspective of public order and morals.

[0029] 2. Configuration of the Extraction Apparatus Next, the configuration of the extraction device 100 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the extraction device according to an embodiment. As shown in Fig. 3, the extraction device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0030] (Regarding communication unit 110) The communication unit 110 is realized by, for example, a network interface card (NIC) etc. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information between the provider terminal 10, the external device 20, etc.

[0031] (Regarding the storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 has a provider information storage unit 121 and an event information storage unit 122.

[0032] (Regarding the provider information storage unit 121) The provider information storage unit 121 stores provider information related to providers. An example of provider information stored in the provider information storage unit 121 will be described with reference to Fig. 4. Fig. 4 is a diagram illustrating an example of the 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", "attributes", and "advertising information".

[0033] "Provider ID" indicates identification information for identifying the provider. "Attributes" indicates the attributes of the advertisement (advertised target). The "Attributes" item may store information indicating the provider's industry, the products handled by the provider, the services offered by the provider, etc. "Advertisement information" indicates information related to the advertisement provided by the provider. In the example shown in Figure 4, conceptual information such as "Advertisement information #1" is stored in "Advertisement information", but in reality, text information included in the advertisement, still images, moving images, etc., or URLs (Uniform Resource Locators) indicating the locations of these, file path names indicating the storage locations, etc. are stored.

[0034] That is, FIG. 4 shows an example in which a provider identified by a provider ID "U1" provides an advertisement with the attribute "disaster prevention goods" and advertisement information "advertisement information #1".

[0035] (Regarding the event information storage unit 122) The event information storage unit 122 stores event information indicating an event that has occurred. An example of information stored in the event information storage unit 122 will now be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of an event information storage unit according to an embodiment. 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".

[0036] "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, and stores, for example, information on content that has been viewed by users a certain threshold or more, or information on search queries that have been entered by users a certain threshold or more. Note that FIG. 5 shows an example in which conceptual information such as "content information #1" is stored in "event information", but in reality, text information indicating an event, still images, video images, etc. or URLs indicating the locations of these, file path names indicating storage locations, etc. are stored. "Attribute" indicates the attributes of the event. "Keyword" indicates keywords related to the event.

[0037] That is, Figure 5 shows an example in which event information "Content Information #1" is acquired on date and time "Date and Time #1", the event indicated by the event information is identified by event ID "M1", the attributes of the event are "disaster", and the keywords are "Area A, heavy rain, ...".

[0038] (Regarding the control unit 130) The control unit 130 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the extraction device 100 using a RAM as a working area. The control unit 130 is also a controller, and is realized, for example, 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 has an acquisition unit 131, an extraction unit 132, an identification unit 133, and a determination unit 134, and realizes or executes the functions and actions of information processing described below.

[0039] (Regarding the acquisition unit 131) The acquiring unit 131 acquires event information indicating events occurring within a predetermined period. For example, in the example of FIG. 1, the acquiring unit 131 acquires event information indicating events occurring within the last 24 hours, 1 day, and 3 days, and stores the information in the event information storage unit 122.

[0040] The acquiring unit 131 may also acquire, as the event information, information indicating a search query whose number of inputs in a predetermined period is equal to or greater than a predetermined threshold. For example, in the example of Fig. 1, the acquiring unit 131 acquires, based on the input information acquired from the external device 20, text information indicating a search query whose number of inputs has increased by a predetermined percentage.

[0041] The acquisition unit 131 may also acquire, as the event information, information indicating a content whose number of times of browsing 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 information indicating a content whose number of times of browsing is equal to or greater than a predetermined threshold, based on the browsing history of the content of the user acquired from the external device 20.

[0042] The acquisition unit 131 may also acquire, as the event information, information indicating an event to be held in a predetermined period of time. For example, the acquisition unit 131 acquires information indicating an event to be held a predetermined period of time from the present, such as a concert, a stage performance, or a sporting event that is expected to attract a predetermined number of people or more.

[0043] The acquisition unit 131 may also acquire event information indicating an event that is estimated to cause a user who comes into contact with the event to have a negative emotion, such as a natural disaster, a death notice, a war, or an accident.

[0044] The acquisition unit 131 may also acquire, as the event information, information indicating a content that has been displayed a predetermined number of times in a predetermined period of time among the contents to be distributed. For example, the acquisition unit 131 acquires advertisement information indicating an advertisement that has a number of impressions or a click-through rate (CTR) that is a predetermined threshold or more among the advertisements to be distributed.

[0045] The acquisition unit 131 may also acquire, as event information, information on content that has been examined as to whether it should be distributed and that has been determined as undistributable within a predetermined period. For example, the acquisition unit 131 acquires advertisement information indicating advertisements that have been examined based on whether they violate guidelines established by the administrator of the extraction device 100 within a predetermined period and that have been determined as undistributable.

[0046] (Regarding the extraction unit 132) The extraction unit 132 extracts keywords related to the event and whose relationship with the provider of the content to be distributed satisfies a predetermined condition based on the event information acquired by the acquisition unit 131. For example, the extraction unit 132 extracts keywords that are expected to be used by the provider for his / her own content from the event information. For example, in the example of FIG. 1, the extraction unit 132 analyzes the text information of the content C1 by appropriately using a natural language processing technique such as morphological analysis, thereby identifying the attribute "disaster" of the event indicated by the content C1, and extracts keywords corresponding to the identified attribute from information related to the content C1.

[0047] In addition, the extraction unit 132 may extract a keyword corresponding to information linked to an attribute of an 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 related to the content C1.

[0048] Furthermore, the extraction unit 132 may extract keywords whose appearance count is equal to or greater than a predetermined threshold from among keywords included in the information related to the content acquired by the acquisition unit 131. For example, the extraction unit 132 extracts keywords whose appearance count is equal to or greater than a predetermined threshold from among keywords included in advertisements determined to be undeliverable during a predetermined period, or keywords whose appearance count has increased by a predetermined percentage.

[0049] In addition, the extraction unit 132 may extract a keyword that is the reason why an advertisement was determined to be undeliverable in the screening. For example, the extraction unit 132 extracts a keyword that is included in an advertisement that was determined to be undeliverable during a predetermined period and is the reason why the advertisement was determined to be undeliverable.

[0050] In addition, the extraction unit 132 may extract keywords from content that has an attribute similar to that of the content provided by the provider among the contents that have been determined to be undeliverable. For example, the extraction unit 132 extracts keywords from content that has an attribute similar to that of an advertisement provided by the provider among the contents that have been determined to be undeliverable during a predetermined period.

[0051] (Regarding the specific unit 133) The identification unit 133 identifies a provider having a predetermined relevance to the event among the providers. For example, in the example of Fig. 1, the identification unit 133 identifies a provider U1 that provides an advertisement belonging to an attribute linked to the attribute "disaster" of the event indicated by the content C1.

[0052] Furthermore, the identification unit 133 may identify a provider that provides content related to an attribute of an event among the providers. For example, in the example of Fig. 1, the identification unit 133 identifies a provider U1 that provides an advertisement belonging to an attribute "disaster prevention goods" related to the attribute "disaster" of the event indicated by the content C1.

[0053] (Regarding the determination unit 134) The determination unit 134 determines whether or not the content is subject to a predetermined review or to distribution suspension, based on the keywords extracted by the extraction unit 132 and information related to the content provided by the provider identified by the identification unit 133. For example, in the example of Fig. 1, the determination unit 134 determines whether or not the advertisement provided by the provider U1 is subject to a review (re-review) on whether or not to permit distribution, or is subject to distribution suspension, based on the keywords extracted from information related to the content C1.

[0054] Furthermore, the determination unit 134 may determine that, among the contents, the contents including the keyword are subject to a predetermined review or to a target for distribution suspension. For example, in the example of Fig. 1, the determination unit 134 determines that, among the advertisements provided by the provider U1, the advertisement including the keyword extracted from the information related to the content C1 is subject to a review (re-review) on whether or not to permit distribution, or is subject to a target for distribution suspension.

[0055] [3. Extraction process flow] Here, the procedure of the extraction process of the extraction device 100 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the procedure of the extraction process according to the embodiment.

[0056] 6, the extraction device 100 acquires event information indicating an event occurring during a predetermined period (step S101). For example, in the example of FIG. 1, the extraction device 100 acquires, as the event information, information on a content C1 that has been viewed by users a predetermined threshold or more during a recent period.

[0057] Next, the extraction device 100 extracts keywords whose relationship with the provider of the content to be distributed satisfies a predetermined condition (step S102). For example, the extraction device 100 extracts, from the event information, topical keywords that the provider is expected to use in the content. Next, the extraction device 100 identifies providers that have a predetermined relevance to the event (step S103). For example, in the example of FIG. 1, the extraction device 100 identifies providers that provide advertisements that belong to attributes linked to attributes of the event.

[0058] Next, the extraction device 100 determines whether the content to be distributed is subject to a predetermined examination or to a distribution suspension (step S104). For example, in the example of Fig. 1, the extraction device 100 determines that an advertisement including the extracted keyword among advertisements provided by the identified provider is subject to an examination as to whether to permit distribution or to a distribution suspension.

[0059] 4. Modifications The above-described embodiment is merely an example, and various modifications and applications are possible.

[0060] [4-1. About the content provided by the provider] In the above embodiment, an example has been shown in which the determination unit 134 determines whether an advertisement is subject to a predetermined screening or to a distribution suspension based on keywords extracted from event information and information on the advertisement related to the attribute of the event, but the object of determination by the determination unit 134 is not limited to advertisements. For example, the determination unit 134 may determine whether a piece of content is subject to a predetermined screening or to a distribution suspension based on keywords extracted from event information and information on various pieces of content related to the attribute of the event.

[0061] [4-2. Identification of providers related to the event] In the above embodiment, an example has been described in which the identifying unit 133 identifies a provider who provides content related to an attribute of an event, but the function of the identifying unit 133 is not limited to this configuration. For example, when the extracting unit 132 extracts a keyword from event information indicating an event in which the user is highly interested (for example, information on content whose number of views is higher than the average by a predetermined threshold or more), the identifying unit 133 may identify not only providers who provide content related to the attribute of the event, but also providers who provide content unrelated to the attribute of the event.

[0062] 5. Effects As described above, the extraction device 100 according to the embodiment includes the acquisition unit 131, the extraction unit 132, the identification unit 133, and the determination unit 134. The acquisition unit 131 acquires event information indicating an event occurring during a predetermined period. The extraction unit 132 extracts keywords related to the event and whose relationship with the provider of the content to be distributed satisfies a predetermined condition based on the event information acquired by the acquisition unit 131. The extraction unit 132 also extracts keywords corresponding to information linked to the attribute of the event. The identification unit 133 identifies a provider having a predetermined relationship with the event among the providers. The determination unit 134 determines whether the content is subject to a predetermined review or to distribution suspension based on the keywords extracted by the extraction unit 132 and information related to the content provided by the provider identified by the identification unit 133.

[0063] In this way, the extraction device 100 according to the embodiment extracts keywords related to events that have occurred in the most recent period, and is therefore able to grasp keywords that are expected to be used by the provider in the content.

[0064] In the extraction device 100 according to the embodiment, for example, the acquisition unit 131 acquires, as the event information, information indicating a search query whose number of inputs in a predetermined period is equal to or greater than a predetermined threshold. The acquisition unit 131 acquires, as the event information, information indicating a content whose number of views in a predetermined period is equal to or greater than a predetermined threshold. The acquisition unit 131 acquires, as the event information, information indicating an event held in a predetermined period. The acquisition unit 131 acquires, among the events, event information indicating an event that is estimated to cause a user who comes into contact with the content to have a negative emotion. The acquisition unit 131 acquires, as the event information, information indicating a content whose number of views in a predetermined period is equal to or greater than a predetermined threshold among the contents to be distributed. The acquisition unit 131 acquires, as the event information, information regarding a content that has been screened as to whether or not to be a distribution target and that has been determined to be undistributable in the predetermined period. Then, the extraction unit 132 extracts, from among keywords included in the information regarding the content acquired by the acquisition unit 131, a keyword whose number of appearances is equal to or greater than a predetermined threshold. The extraction unit 132 extracts a keyword that is the reason why the content was determined to be undistributable in the screening. Furthermore, the extraction unit 132 extracts keywords from content that has been determined to be undeliverable and has attributes similar to those of the content provided by the provider.

[0065] As a result, the extraction device 100 according to the embodiment extracts keywords from various types of event information, and is therefore able to grasp a wide range of keywords that are expected to be used by content providers in their content.

[0066] In the extraction device 100 according to the embodiment, for example, the identification unit 133 identifies a provider who provides content related to an attribute of the event among the providers. Furthermore, the determination unit 134 determines that content including a keyword among the contents is subject to a predetermined review or subject to distribution suspension.

[0067] As a result, the extraction device 100 according to the embodiment can identify a provider based on the attributes of an event and the extracted keywords, and can judge the content provided by the identified provider, even if the keywords are misused, thereby ensuring the quality of the content.

[0068] [6. Hardware Configuration] Moreover, the extraction device 100 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 7. The extraction device 100 will be described below as an example. Fig. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the extraction device. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0069] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0070] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0071] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs data generated via the input / output interface 1600 to the output devices.

[0072] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. 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.

[0073] For example, when the computer 1000 functions as the extraction device 100, the CPU 1100 of the computer 1000 executes a program loaded onto the RAM 1300 to realize the function of the control unit 130. In addition, the HDD 1400 stores each piece of data in the storage device of the extraction device 100. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0074] [7. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0075] Furthermore, the above-described extraction device 100 can be flexibly modified in configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing to realize some functions.

[0076] Furthermore, the term "unit" in the claims may be read as "means" or "circuit," etc. For example, an acquisition unit may be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0077] 10. Main terminal 20 External device 100 extraction equipment 110 Communications Department 120 Storage section 121 Provider information storage unit 122 Event information storage unit 130 Control section 131 Acquisition Department 132 Extraction part 133 Specific section 134 Judgment section

Claims

1. an acquisition unit that acquires, from an external device that distributes predetermined content to users, text information that has been viewed or entered by users a number of times within a predetermined period of time that exceeds a predetermined threshold as event information including information on events, natural disasters, obituaries, wars, or accidents that occurred during the predetermined period of time; an extraction unit that performs a morphological analysis on the event information acquired by the acquisition unit to identify attribute text information, which is text information indicating attributes that are set in advance as information indicating the content of the event, and extracts keywords indicating concepts associated with the identified attribute text information as related keywords related to the event based on a preset rule base; an identification unit that identifies a provider of content to be distributed, the provider providing the content having an attribute associated with the attribute of the event, among providers of the content to be distributed, based on a rule base in which an attribute of the event and an attribute of the content to be distributed associated with the attribute of the event are set; a determination unit that determines, based on text information of the content provided by the provider identified by the identification unit, that the content including the related keyword is subject to a predetermined review or subject to distribution suspension; An extraction apparatus comprising:

2. The acquisition unit is A search query that has been input a number of times in the predetermined period equal to or greater than a predetermined threshold is acquired from the external device as the event information.

2. The extraction device according to claim 1 .

3. The acquisition unit is The event information is obtained from the external device as text information of a content whose number of views in the predetermined period is equal to or exceeds a predetermined threshold value.

3. The extraction device according to claim 1 or 2.

4. The acquisition unit is As the event information, text information indicating information on an event to be held during the predetermined period is obtained from the external device.

4. An extraction device according to claim 1, wherein the extraction device is a refrigerant.

5. The acquisition unit is The event information including at least one text of a natural disaster, an obituary, a war, and an accident is acquired from the external device.

5. An extraction device according to claim 1 ,

6. The acquisition unit is As the event information, text information of the content to be distributed, the content of which the number of views in the predetermined period is equal to or greater than a predetermined threshold, is obtained from a provider of the content to be distributed.

6. An extraction device according to claim 1 ,

7. The acquisition unit is obtaining, as the event information, text information of content that has been examined as to whether it should be distributed and that has been determined to be undistributable during the predetermined period from a content provider; The extraction unit is A keyword having an occurrence count equal to or greater than a predetermined threshold is extracted as the related keyword from among the keywords included in the text information of the content acquired by the acquisition unit.

7. An extraction device according to any one of the preceding claims.

8. The extraction unit is Keywords that have been specified in advance as reasons why the content was determined to be undeliverable in the screening are extracted as the related keywords.

8. The extraction device according to claim 7.

9. The extraction unit is The related keywords are extracted from the content that has been determined to be undeliverable and has attributes similar to those of the content provided by the provider.

9. Extraction device according to claim 7 or 8.

10. An extraction method performed by an extraction device, comprising: an acquiring step of acquiring, from an external device that distributes predetermined content to users, text information that has been viewed or entered by users a number of times within a predetermined period of time exceeds a predetermined threshold as event information including information on events, natural disasters, obituaries, wars, or accidents that occurred during the predetermined period of time; an extraction step of performing a morphological analysis on the event information acquired by the acquisition step to identify attribute text information, which is text information indicating attributes set in advance as information indicating the content of the event, and extracting keywords indicating concepts linked to the identified attribute text information as related keywords related to the event based on a preset rule base; a step of identifying a provider who provides content that belongs to an attribute associated with the attribute of the event, among providers of content to be distributed, based on a rule base in which an attribute of the event and an attribute of content to be distributed that is associated with the attribute of the event are set; a determining step of determining, based on text information of the content provided by the provider identified by the identifying step, that content including the related keyword is subject to a predetermined review or subject to distribution suspension; An extraction method comprising the steps of:

11. an acquisition step of acquiring, from an external device that distributes predetermined content to users, text information that has been viewed or entered by users a number of times within a predetermined period of time exceeds a predetermined threshold as event information including information on events, natural disasters, obituaries, wars, or accidents during the predetermined period; an extraction step of performing a morphological analysis on the event information acquired by the acquisition step to identify attribute text information, which is text information indicating attributes that are set in advance as information indicating the content of the event, and extracting keywords indicating concepts associated with the identified attribute text information as related keywords related to the event based on a preset rule base; a step of identifying a provider who provides content that belongs to an attribute associated with the attribute of the event, among providers of content to be distributed, based on a rule base in which an attribute of the event and an attribute of content to be distributed that is associated with the attribute of the event are set; a determination step of determining, based on text information of the content provided by the provider identified by the identification step, that content including the related keyword is subject to a predetermined review or subject to distribution suspension; An extraction program for causing a computer to execute the above.

Images