JP2018128805A - Generation apparatus, generation method, and generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To contribute to purchasing activity of users.SOLUTION: A generation apparatus includes an acquisition unit, an extraction unit, and a generation unit. The acquisition unit acquires text data associated with a commercial material to be transacted on a network. The extraction unit extracts characteristics information which is information indicating characteristics of the commercial material, from the text data acquired by the acquisition unit. The generation unit generates a content with advertisement information for advertising the commercial material, on the basis of the characteristics information extracted by the extraction unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a generation device, a generation method, and a generation program.

  In recent years, with the rapid spread of the Internet, various contents are actively provided through a network. Also, with the increase in the amount of content provided, summary processing is being performed on content in order to quickly convey the content of each content to the user.

  Here, as a technology related to content summarization, a technology that outputs customer service information that meets customer requirements, a technology that extracts summary sentences reflecting the meaning of words in the order of words, and a user's content related to content such as broadcast programs A technique for generating a content summary sentence that reflects a preference tendency is known.

JP 2003-196547 A JP, 2006-189089, A Japanese Patent Laid-Open No. 2006-118813

  However, the above-described conventional technology does not always contribute to user purchasing activities. Specifically, in the above-described conventional technology, even if the contents can be summarized, the information desired by the user cannot be efficiently provided regarding the purchase activity of the user.

  The present application has been made in view of the above, and an object thereof is to provide a generation device, a generation method, and a generation program that can contribute to a user's purchasing activities.

  The generation apparatus according to the present application includes an acquisition unit that acquires text data associated with a commercial product that is a target of a commercial transaction on a network, and information that indicates characteristics of the commercial product from the text data acquired by the acquisition unit An extraction unit that extracts feature information that is, and a generation unit that generates content to which advertisement information that is information for promoting the product is provided based on the feature information extracted by the extraction unit. It is characterized by having.

  According to one aspect of the embodiment, there is an effect that it is possible to contribute to the purchase activity of the user.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the generation processing system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a learning information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the exhibition information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of a product information storage unit according to the embodiment. FIG. 7 is a flowchart (1) illustrating a processing procedure according to the embodiment. FIG. 8 is a flowchart (2) illustrating a processing procedure according to the embodiment. FIG. 9 is a flowchart (3) illustrating the processing procedure according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus.

  Hereinafter, a mode for implementing a generation device, a generation method, and a generation program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. In addition, the embodiments can be appropriately combined within a range that does not contradict processing contents. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

[1. Example of generation process)
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 1 shows an example in which the generation device 100 according to the present application generates content for introducing a product in electronic commerce (for example, a product sales page on a shopping site).

  The generation apparatus 100 shown in FIG. 1 is a model (learning device) for extracting feature information, which is information indicating features of a product, from text data associated with the product that is the object of the commercial transaction on the network. Is a server device that performs generation processing using the generated model.

  Here, on the electronic commerce site such as the shopping site exemplified in the embodiment, it is assumed that a plurality of exhibitors exhibit various products (products) handled by each seller. For example, the electronic commerce site exemplified in the embodiment may be a shopping site imitating a shopping mall such that a plurality of exhibitors have their respective stores, or an auction site where a plurality of exhibitors arbitrarily present products. But you can.

  In such an electronic commerce site, a product title and description are usually created by an exhibitor and attached to the product. Then, the exhibitor uploads an image or the like obtained by capturing the product along with the product title and description. The electronic commerce site side generates a sales page of the product based on the information uploaded from the exhibitor. A user who uses the electronic commerce site accesses the electronic commerce site and makes a purchase with reference to the title and explanation posted on the sales page.

  Here, in such a commercial transaction site, creation of information to be given to a product (description of the product) may be entrusted to the exhibitor. For this reason, in a commercial transaction site, there is a problem that appropriate product information is not always provided to the user. That is, when an exhibitor gives an explanation arbitrarily, an excessively long explanation is given or an unrelated word or phrase is inserted into the explanation by, for example, applying SEO measures (Search Engine Optimization). Sometimes.

  In this case, when the user accesses the commercial transaction site and browses the sales page, it may be difficult to determine what characteristics the product has. Thereby, the usability of the whole commerce site may be reduced. Here, it is possible to obligate the exhibitor to give an appropriate explanation to the request from the commerce site, but for businesses that sell a large number of products, etc. Giving an appropriate description is a heavy workload. For this reason, a business operator may hesitate to exhibit on the commercial transaction site. In this case, since the commerce site side loses a large number of exhibitors, it is not desirable for the operation of the commerce site. In addition, it is not realistic that the commercial transaction site side artificially assigns explanatory texts to all the exhibited products when the number of exhibits is enormous.

  Therefore, the generation apparatus 100 according to the embodiment extracts feature information, which is information indicating the feature of the product, from the explanatory text associated with the product by the seller by the following method. Furthermore, the generation apparatus 100 newly generates a page that introduces a product and that is provided with advertisement information that is information for promoting the product, based on the extracted feature information. With this process, the generation device 100 can generate a sales page that is highly visible to the user without imposing a burden on the seller or the commercial transaction site. Thereby, the production | generation apparatus 100 can contribute to a user's purchasing activity. Hereinafter, an example of the generation process performed by the generation apparatus 100 will be described along the flow with reference to FIG.

  As illustrated in FIG. 1, the generation device 100 performs learning for performing processing for extracting feature information from an explanatory sentence as a learning phase. First, the generation device 100 acquires learning data to be used for the learning process (step S11).

  Specifically, the generation device 100 acquires learning data B01, B02, B03, and the like, which are existing product introduction pages uploaded to the commercial transaction site. The learning data B01 and the like are, for example, an introduction page (for example, a sales page for accepting purchase of a product from a user) that is exhibited by the seller, and includes text for explaining each product. For example, the learning data B01 includes an explanatory note F01. Similarly, the learning data B02 includes an explanatory text F02, and the learning data B03 includes an explanatory text F03.

  For example, the generation apparatus 100 acquires learning data B01 and the like by crawling on the network using a known method. Note that the generation apparatus 100 does not necessarily have to acquire the learning data B01 and the like from the same commercial transaction site. That is, the generation apparatus 100 may acquire any page as long as it is a page to which a product and text for explaining the product are assigned.

  Subsequently, the generation apparatus 100 performs a learning process regarding text (descriptive text) used for the acquired product introduction (step S12). That is, the generation device 100 generates a predetermined model (learning device) for extracting features included in the text (document).

  Although details will be described later, the generation apparatus 100 is not limited to one method, and may generate a model using various methods. For example, the generating apparatus 100 uses, as learning data, a summary sentence obtained by manually summarizing the explanation sentence F01 together with the explanation sentence F01. That is, the generation apparatus 100 performs machine learning on the summary sentence that summarizes the explanatory sentence F01 as correct data, and the words that are manually extracted when the explanatory sentence F01 is summarized as the feature information of the explanatory sentence F01. In this case, the generation apparatus 100 can learn the characteristics of the words and phrases extracted during manual summarization processing by using sufficient samples for learning. For this reason, when a new description is input to the model, the generation apparatus 100 can extract a word that is assumed to be important from the description by imitating a process in which a summary is manually created. . This extracted information can be characteristic information of the explanatory text.

  Further, the generation device 100 may generate a model by learning through statistical processing. For example, the generation device 100 performs learning for extracting words that are included in a certain explanatory text and that characterize the explanatory text. Such processing is performed, for example, by calculating the importance of each word in the document when the explanatory text is regarded as one document, and generating a rule for extracting a phrase from the document based on the importance. . For example, the generation device 100, when an explanation (document) is input based on an index value such as tf-idf (Term Frequency-Inverse Document Frequency), the phrase characterizing the explanation in the explanation A model that extracts (outputs) may be generated.

  Note that the generation apparatus 100 may generate a model using, for example, a deep learning technique. That is, the generation apparatus 100 performs learning for extracting a portion that can be a feature in the explanatory note F01 or the like using a deep learning method. For example, the model generated by the generation apparatus 100 is a model in which a plurality of nodes that output calculation results for input data are connected in multiple layers, and is a model for learning features included in text data. For example, the model is a neural network in which layers having a plurality of nodes are connected in multiple stages, and is a DNN (Deep Neural Network) realized by a so-called deep learning technique.

  For example, the model is generated by the following learning method using the deep learning technique. In the model, the connection coefficient between each node is initialized, and text having various words is input. Then, the model is generated by processing such as backpropagation (Backpropagation (error back propagation method)) for correcting a parameter (connection coefficient) so that an error between an output in the model and an input is reduced. For example, the model only needs to be learned so that when text data constituting the explanatory text is input, the feature information included in the explanatory text is output. Note that adjustments such as returning appropriate feedback manually may be performed on the output of the model.

  Note that the model learning method and the generated model are not limited to the method described above, and any known technique can be applied. That is, the generation apparatus 100 can use any model as long as it can output feature information indicating features abstracted from text data. The generation device 100 stores the model generated in the learning phase in a predetermined storage unit. The above is the learning phase according to the embodiment.

  Thereafter, the generation apparatus 100 executes a generation phase according to the embodiment. First, when the exhibitor intends to sell a product or to add a description to the product, the generating apparatus 100 uses the feature in the description based on the description associated with the product. The process which extracts is performed. Then, the generation device 100 generates a new product page based on the extracted features.

  For example, on the commercial transaction site, a seller who intends to newly sell a product uploads product information via the seller terminal 20 (step S21). The product information includes a product name of the product, price information of the product, image data of the product, and a description F10 that is a description of the product.

  Here, the generating apparatus 100 acquires the explanatory note F10 uploaded from the exhibitor (step S22). And the production | generation apparatus 100 extracts the characteristic information which is the information which shows the characteristic of goods from the acquired description sentence F10 (text data). Specifically, the generation device 100 inputs the acquired explanatory sentence F10 into the model and causes the feature information in the explanatory sentence F10 to be output. More specifically, the generation device 100 generates a summary sentence A10 of the description sentence F10 that is generated by extracting only feature information from the redundant description sentence F10 (step S23).

  Then, the generation apparatus 100 selects a page that introduces a product based on the extracted feature information and that is provided with advertisement information (here, summary sentence A10) that is information for promoting the product. Generate. Specifically, the generation device 100 generates a product page W10, which is a new page in which the summary sentence A10 is added to the original product page generated based on the information uploaded by the seller (step). S24).

  FIG. 1 shows an aspect when the product page W10 generated by the generation device 100 is displayed on the browser of the terminal device used by the user. As shown in FIG. 1, on the product page W10, a summary sentence A10 is displayed immediately below the title “Wine: Product XXX”. That is, when browsing the product page W10, the user can grasp the characteristics of the product introduced on the product page W10 by browsing only the summary sentence A10 without reading the redundant explanation F10. it can.

  As described above, the generation apparatus 100 according to the embodiment acquires text data (description) associated with a commercial material that is a target of a commercial transaction on the network. And the production | generation apparatus 100 extracts the characteristic information which is the information which shows the characteristic of merchandise from the acquired text data. Furthermore, the generating apparatus 100 generates a page that introduces a commercial material based on the extracted feature information and that is provided with advertisement information that is information for promoting the commercial material.

  For example, the generation apparatus 100 extracts product features from descriptions set by various exhibitors on a product introduction page on a commercial transaction site, and generates advertisement information such as summary sentences based on the extracted features. To do. And the production | generation apparatus 100 produces | generates the goods page which provided the produced | generated advertisement information newly. Thereby, the production | generation apparatus 100 can produce | generate the goods page excellent in visibility, maintaining the characteristic of the appeal point of the goods provided by the exhibitor. Further, according to the generating apparatus 100, instead of simply summarizing the explanatory text, the feature information of the explanatory text is learned and extracted, thereby generating advertisement information using words or the like important for appealing as a product. be able to. As a result, the generating device 100 can improve the usability in the commercial transaction site and can exert an effect that it can contribute to the user's purchasing activities.

  Note that the generation apparatus 100 may use various types of information to supplement the learning process. For example, in the learning phase described above, the generation device 100 may acquire result information (user reaction) such as whether or not the user has performed a purchase activity via a page generated by the generation device 100. And the production | generation apparatus 100 may feed back to the learning process the advertisement information provided to the page with which the user's reaction was good, such as a high purchase rate, for example as correct answer data. Thereby, the generation apparatus 100 can proceed with learning so as to optimize the process of extracting points that appeal to the user from the explanatory text. Hereinafter, the configuration of the generation apparatus 100 that performs such processing and the generation processing system 1 including the generation apparatus 100 will be described in detail.

[2. Configuration of generation processing system]
Next, the configuration of the generation processing system 1 including the generation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the generation processing system 1 according to the embodiment. As illustrated in FIG. 2, the generation processing system 1 according to the embodiment includes a user terminal 10, an exhibitor terminal 20, and a generation device 100. These various devices are communicably connected via a network N by wire or wireless. The generation processing system 1 shown in FIG. 2 may include a plurality of user terminals 10 and a plurality of exhibitor terminals 20.

  The user terminal 10 is, for example, an information processing apparatus such as a smartphone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or a wearable device. It is. The user terminal 10 accesses the commercial transaction site in accordance with an operation by the user, and performs processing for the user to browse information or purchase a product on the commercial transaction site.

  The exhibitor terminal 20 is an information processing terminal used by an exhibitor who sells products on a commercial transaction site. The exhibitor terminal 20 is, for example, an information processing apparatus such as a smartphone, a desktop PC, a notebook PC, a tablet terminal, a mobile phone, a PDA, or a wearable device.

  The exhibitor terminal 20 executes various processes for listing products on the commercial transaction site in accordance with operations by the exhibitor. For example, the exhibitor terminal 20 uploads text data such as a product title and a description to a server (in the embodiment, the generation device 100) that provides a commercial transaction site.

  The generation device 100 is a server device that extracts feature information from text data associated with a product and generates a product page to which advertisement information of a product generated based on the feature information is added.

  And the production | generation apparatus 100 provides the produced | generated goods page to the user terminal 10, when access is received from a user. As described above, the generation device 100 according to the embodiment also serves as a configuration as a web server that provides a commercial transaction site or provides a generated product page. Actually, in the generation processing system 1, the generation device 100 and the web server may be configured as separate devices.

[3. Configuration of the generator
Next, the configuration of the generation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus 100 according to the embodiment. As illustrated in FIG. 3, the generation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The generation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the generation device 100, and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits / receives information to / from the user terminal 10 and the exhibitor terminal 20 via the network N.

(About the 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. The storage unit 120 includes a learning information storage unit 121, an exhibition information storage unit 122, and a product information storage unit 123.

(About the learning information storage unit 121)
The learning information storage unit 121 stores information related to learning for generating a model for use in the extraction process. Here, FIG. 4 shows an example of the learning information storage unit 121 according to the embodiment. FIG. 4 is a diagram illustrating an example of the learning information storage unit 121 according to the embodiment. In the example illustrated in FIG. 4, the learning information storage unit 121 includes items such as “learning data ID”, “category”, “product”, and “learning data”.

  “Learning data ID” indicates identification information for identifying learning data. In the following description, identification information such as a learning data ID may be indicated by a reference symbol. For example, the learning data whose learning data ID is “B01” may be referred to as “learning data B01”.

  “Category” indicates the category to which the product on the commercial transaction site belongs. “Product” indicates the type of product on the commercial transaction site.

  “Learning data” indicates the content of learning data actually used in the learning process. For example, the learning data according to the embodiment is text data associated with a product, that is, an explanatory text given to explain the product.

  Although illustration in FIG. 4 is omitted, the items of learning data include not only explanatory texts used for learning but also correct data such as summary sentences manually created based on the explanatory texts, for example. Also good. Further, in the case of using a deep learning method in learning, it is not always necessary to use only learning data for which a correct example (correct answer data) is clearly identified. For example, the generation apparatus 100 does not necessarily need correct data as long as it can learn the feature of text data (document) and recognize the feature information included in the text data.

  That is, the example of the data illustrated in FIG. 4 indicates that the product category in the learning data B01 identified by the learning data ID “B01” is “food” and the product is “wine”. In addition, the learning data in the learning data B01 indicates “description F01”.

  Note that the learning information storage unit 121 may store a model learned based on the learning data. Further, the generation apparatus 100 may update the learning data stored in the learning information storage unit 121 as appropriate, and may continue learning the generated model.

(About the exhibition information storage unit 122)
The exhibition information storage unit 122 stores information related to exhibits (products) uploaded from the exhibitor terminal 20. Here, FIG. 5 shows an example of the exhibition information storage unit 122 according to the embodiment. FIG. 5 is a diagram illustrating an example of the exhibition information storage unit 122 according to the embodiment. In the example illustrated in FIG. 5, the exhibition information storage unit 122 includes items such as “exhibitor ID”, “exhibition page ID”, “category”, “product”, “description”, and “image”.

  “Exhibitor ID” indicates identification information for identifying the exhibitor or the exhibitor terminal 20. “Exhibition page ID” indicates identification information for identifying an exhibition page corresponding to a product exhibited by an exhibitor.

  “Category” and “Product” correspond to the same items shown in FIG. “Description” indicates the description given to the product by the seller. The “image” indicates an image (for example, an image obtained by capturing a product) that is associated with the exhibition page by the exhibitor.

  That is, the example of the data shown in FIG. 5 indicates that the seller identified by the seller ID “20” has an exhibition page identified by the exhibition page ID “B10” on the commercial transaction site. ing. Further, the category of the product on the exhibition page B10 is “food”, and the product is “wine”. Further, it is indicated that the explanation given to the exhibition page B10 is “description F10” and the image is “image P10”.

(About the product information storage unit 123)
The merchandise information storage unit 123 stores information related to the merchandise page generated by the generating device 100 among the pages on the commercial transaction site. Here, FIG. 6 shows an example of the product information storage unit 123 according to the embodiment. FIG. 6 is a diagram illustrating an example of the product information storage unit 123 according to the embodiment. In the example illustrated in FIG. 6, the product information storage unit 123 includes items such as “product page ID”, “exhibition page ID”, “description”, “advertisement information”, “effect measurement information”, and “review information”. Have.

  “Product page ID” indicates identification information for identifying a product page generated by the generation apparatus 100. “Exhibition page ID” and “description” correspond to the same items shown in FIG.

  The “advertisement information” is advertisement information generated by the generation device 100 and indicates information added (added) to the original exhibition page. For example, the advertising information is a summary sentence that summarizes the explanatory text.

  “Effect measurement information” indicates result information indicating that the product page exerts an effect among the information related to the user's reaction to the product page. “Review information” indicates information related to a review posted by a user on a product page among information related to a user's reaction to the product page. In the example shown in FIG. 6, “effect measurement information” and “review information” are represented by concepts such as “G01” and “H01”, but actually, various specific information is stored. The

  For example, the “effect measurement information” may store the number of times that the product page has been accessed by the user, and the number and rate of users who have reached conversion on the product page. Examples of conversion include purchase of a product on a product page, access to a product introduction page (for example, a product manufacturer's web page), and the like. Further, the effect measurement information may store, for example, the number of items selected by the user (the number of clicks or touches, the number of items in the cart, or the like) or the rate, even if the purchase is not completed. . Further, the effect measurement information may store the frequency with which the user accesses the product page, the time spent on the product page, and the like. In other words, any information may be stored in the effect measurement information as long as it is information relating to the product page or the user's reaction to the product.

  Further, “review information” stores information related to user reviews for the product page. For example, in a product page, when a system in which a user evaluates a product with a numerical value in five stages is adopted, the score evaluated by the user is stored in the review information. For example, the review information stores an average value of numerical values from “0” to “5” transmitted from the user. The review information may store the number and rate of user reviews transmitted from the user, or specific user review comments (text data). That is, any information may be stored in the effect measurement information as long as it is information relating to a product page or a user review for a product.

  That is, the example of the data illustrated in FIG. 6 indicates that the product page W10 identified by the product page ID “W10” is originally an exhibition page identified by the exhibition page ID “B10”. Further, the explanatory text associated with the product page W10 is “explanatory text F10”, and the newly added advertisement information is “summary text A10”. Further, the effect measurement information of the product page W10 is “G01”, and the review information is “H01”.

(About the control unit 130)
The control unit 130 is, for example, a controller, and includes various programs (an example of a generation program) stored in a storage device inside the generation device 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. This is realized by executing the RAM as a work area. The control unit 130 is, for example, a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, an extraction unit 132, a reception unit 133, a generation unit 134, a storage unit 135, a reception unit 136, and a provision unit 137. Implements or executes the functions and operations of information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as the information processing described below is performed. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship illustrated in FIG. 3, and may be another connection relationship.

(About the acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires information related to an exhibition page on a commercial transaction site on the network N. In addition, the acquisition unit 131 acquires text data (description) associated with a product that is a target of a commercial transaction on the network N.

  For example, the acquisition unit 131 performs morphological analysis on the explanatory text associated with the product, and acquires words included in the explanatory text. Furthermore, the acquisition part 131 acquires the word which shows the attribute of goods. More specifically, the acquisition unit 131 acquires, for example, a word indicating the size, weight, date of manufacture, date of sale, or manufacturer name as a word indicating the attribute of the product. In addition, the acquisition part 131 may acquire not only an explanatory note but any information, if it is text data matched with goods, such as a title.

  In addition, when the morphological analysis is performed on the title or the explanatory text, the acquiring unit 131 may generate an appearance frequency of words or a plurality of words based on the number of appearances of words (phrases) included in the document (here, the title or the explanatory text). You may calculate the importance of each word in the description sentence. For example, the acquisition unit 131 may calculate a DF value of a word related to the acquired explanatory text. Moreover, the acquisition part 131 may acquire not only DF value but index values, such as tf-idf. Then, the acquisition unit 131 may acquire only words that exceed a predetermined threshold. Thereby, the acquisition part 131 can acquire only the word assumed to characterize goods, without acquiring a very general word etc.

  Moreover, the acquisition part 131 may acquire the information regarding the reaction with respect to the said product page from the user who actually browsed the product page. For example, the acquisition unit 131 may acquire at least one of the number or rate at which a product is selected from the user or the number or rate of conversions related to the product as a user's response to the product page or the product. Moreover, the acquisition part 131 may acquire the information regarding the review transmitted from a user. Then, the extraction unit 132 and the generation unit 134 to be described later may appropriately tune the generated model and the generated advertisement information based on the information about the user response acquired by the acquisition unit 131.

  Note that the acquisition unit 131 may acquire information related to a user who has browsed the product page generated by the generation unit 134. The information about the user is, for example, user attribute information (gender, age, place of residence, occupation, etc.) or user behavior information (past browsing history, purchase history, etc. on the network). For example, the acquisition unit 131 specifies a user based on a cookie transmitted from the user terminal 10 and acquires information regarding the specified user.

  The acquisition unit 131 stores the acquired information in each unit of the storage unit 120 as appropriate. The acquisition unit 131 may appropriately acquire information used by each processing unit described later from each unit of the storage unit 120.

(About the extraction unit 132)
The extraction unit 132 extracts feature information that is information indicating the feature of the product from the text data acquired by the acquisition unit 131.

  For example, the extraction unit 132 extracts feature information based on learning processing (for example, supervised machine learning) using correct data set for text data. Alternatively, the extraction unit 132 may extract feature information using a model learned to extract information characterizing text data (for example, a model learned by deep learning).

  That is, the extraction unit 132 generates a model through the learning process as described above, and extracts feature information using the model. The feature information extracted by the extraction unit 132 may be a word that characterizes the product in the text data, a combination of a plurality of words, or a sentence.

  Note that the extraction unit 132 may perform processing for adjusting feature information to be extracted based on information related to a user's reaction. For example, the extraction unit 132 may extract the product page in which the reaction from the user has exceeded a predetermined threshold (for example, a page having a conversion exceeding a predetermined number or a page having a user review score exceeding a predetermined score). Information is determined as correct data, and the model is updated. That is, the extraction unit 132 treats the product page that has a relatively good response from the user as correct data in model generation, assuming that the feature information has been properly extracted. Thereby, the extraction unit 132 can optimize the extraction process.

  Further, the extraction unit 132 may extract different feature information for each user. For example, in the advertisement information given to the product, there is a possibility that there is advertisement information that is highly effective depending on the attribute of the user. For example, even for the same product page, the conversion rate is high for female users, whereas the conversion rate may be low for male users. In such a case, the extraction unit 132 separately extracts feature information for female users and feature information for male users in the feature information extraction process that is the source of the advertisement information. And the production | generation part 134 mentioned later produces | generates a different goods page for every user's attribute information. Thereby, even if it is a page corresponding to the same goods, the production | generation apparatus 100 can produce | generate the different goods page to which the advertising information assumed that an effect becomes high with respect to each user was provided. As a result, the generation device 100 can increase the purchase rate of each product and contribute to the user's purchasing activities and the operation of the commercial transaction site.

  The extraction unit 132 may adjust the feature information to be extracted for each product category or product type. For example, it is assumed that the term indicating the feature in the description changes depending on the category of the product and the type of the product. As an example, if the product is “wine”, it is assumed that the phrase that follows “château” in the description indicates a characteristic, but if the product is other than “wine”, the phrase that follows “château” is the product. It is not assumed to show the characteristics of In this manner, the extraction unit 132 can extract feature information suitable for a product by performing learning for each product category or product type.

(About the reception unit 133)
The accepting unit 133 accepts information related to listing in electronic commerce from the exhibitor terminal 20. For example, the reception unit 133 receives an image obtained by capturing a product that the exhibitor intends to exhibit. In addition, the reception unit 133 receives text data such as a title and an explanation given to the product.

  When accepting an exhibition, the accepting unit 133 assigns an exhibition page ID for each exhibition and stores the information in the exhibition information storage unit 122.

(About the generator 134)
Based on the feature information extracted by the extraction unit 132, the generation unit 134 generates a product page that is a page that introduces a product and that is provided with advertisement information that is information for promoting the product.

  For example, the production | generation part 134 produces | generates the goods page which contains the summary sentence of the explanatory text matched with the goods as advertisement information. In this case, the production | generation part 134 may produce | generate the goods page of the aspect by which a summary sentence is arrange | positioned prior to the original description sentence matched with goods. Thereby, the production | generation part 134 can produce | generate the goods page of the aspect which can grasp | ascertain the characteristic of goods, even if a user does not read a redundant explanatory note.

  Further, the generation unit 134 may generate a product page to which advertising information is given based on a reaction from the user. That is, similar to the extraction unit 132 described above, the generation unit 134 generates the advertisement information generated based on the user's reaction as correct data (or as incorrect data if the user's response is relatively bad). Processing learning may be performed to optimize the product page to be generated.

  As a specific example, a case where a product is converted will be described. In the product page, if the content of information presented as advertisement information (for example, summary text) is incorrect or the product characteristics are not well reflected, the user is willing to purchase the product. Is done. On the other hand, when the product is purchased from the user (converted), it is assumed that the advertisement information given to the product page was correct.

  Therefore, the generation unit 134 estimates the propriety of the advertisement information associated with the product based on such user reaction. For example, the generation unit 134 sets a predetermined threshold value in advance. For example, the generation unit 134 sets a conversion rate threshold for a certain product. And the production | generation part 134 determines whether the conversion rate exceeding a threshold value was achieved within the predetermined period or during a fixed number of browsing.

  When the conversion rate exceeds the threshold value, the generation unit 134 assumes that the advertisement information associated with the product is correct, and the description of the product and the advertisement information (or feature information) As one, it feeds back to the extraction unit 132 and the learning information storage unit 121. In addition, when the conversion rate does not exceed the threshold, the generation unit 134 determines that the advertisement information associated with the product is incorrect and provides the description of the product and the advertisement information (or feature information). As one of negative examples, feedback is made to the extraction unit 132 and the learning information storage unit 121. As described above, the generation unit 134 can improve the accuracy of estimation by continuing the learning using the reaction of the user. In addition, as a method of obtaining such user reaction, for example, manual determination using crowdsourcing may be performed. By performing learning using human hands, the generation unit 134 can generate advertisement information that is not unnatural when viewed by a person.

  Moreover, the production | generation part 134 is a goods page to which advertising information was provided based on the information regarding a user, Comprising: You may produce | generate a different page for every user. That is, like the extraction unit 132 described above, the generation unit 134 also generates advertisement information that is expected to be more effective for the user based on the user's attribute information, action history, and the like, and adds the advertisement information. A product page may be generated.

  Note that the generation unit 134 may maintain the original exhibition page when the feature information is not extracted by the extraction unit 132 due to, for example, insufficient learning. In this case, the original listing page to which the explanation given by the seller is added is provided to the user. Then, the generation unit 134 may generate a product page corresponding to the exhibition page when the learning process proceeds and feature information is extracted from the information related to the exhibition page. Note that when the generation process is suspended as described above, the generation unit 134 may transmit an alert to, for example, an administrator of the generation apparatus 100 (that is, an administrator of the commercial transaction site). In this case, the administrator of the generation apparatus 100 can take measures such as artificially adding advertisement information.

(About the storage unit 135)
The storage unit 135 stores the product and the advertisement information corresponding to the product estimated by the generation unit 134 in the product information storage unit 123 in association with each other. That is, the storage unit 135 constructs a database related to product pages on the commercial transaction site.

(Receiving unit 136)
The receiving unit 136 receives various requests. For example, the receiving unit 136 receives a search query for searching for a product from the user terminal 10 that has accessed the commercial transaction site. And the receiving part 136 receives the acquisition request of the goods page which a user desires from the user who browsed the search result page. That is, the receiving unit 136 receives an access request to the product page desired by the user. The receiving unit 136 sends the received various requests to the providing unit 137 and the like.

(About the providing unit 137)
The providing unit 137 provides various types of information. For example, when the receiving unit 136 receives a product page acquisition request, the providing unit 137 provides (transmits) the product page to the user terminal 10. In addition, when the receiving unit 136 receives a search query for searching for a product, the providing unit 137 provides the user terminal 10 with a search result corresponding to the search query.

  That is, the providing unit 137 provides the user with a purchase opportunity related to the product associated with the product page to which the advertisement information generated by the generating unit 134 is provided by providing the product page and the search result.

[4. Processing procedure)
Next, a processing procedure performed by the generation apparatus 100 according to the embodiment will be described with reference to FIGS. 7, 8, and 9. First, a processing procedure related to model generation will be described with reference to FIG. FIG. 7 is a flowchart (1) illustrating a processing procedure according to the embodiment.

  As illustrated in FIG. 7, the generation device 100 acquires learning data for generating a model (Step S101). For example, the generation device 100 acquires an explanatory text associated with a product as learning data.

  And the production | generation apparatus 100 produces | generates a model based on the acquired information (step S102). The generation device 100 stores the generated model in the storage unit 120 (step S103). With the above flow, the learning phase by the generation apparatus 100 ends.

  Next, a processing procedure regarding generation processing using a model will be described with reference to FIG. FIG. 8 is a flowchart (2) illustrating a processing procedure according to the embodiment.

  As illustrated in FIG. 8, the generation apparatus 100 determines whether or not an exhibition page including information on an article (product) uploaded from the exhibitor terminal 20 has been received (step S201). The production | generation apparatus 100 waits until it receives, when the exhibition page is not received (step S201; No).

  On the other hand, when the exhibition page is received (step S201; Yes), the generation apparatus 100 inputs text data included in the received exhibition page into the model (step S202). Then, the generation device 100 determines whether or not feature information is output from the model (step S203).

  When the feature information is output (step S203; Yes), the generation device 100 generates a product page including advertisement information based on the feature information (step S204). On the other hand, when the characteristic information is not output (step S203; No), the generation device 100 temporarily holds the generation process and maintains the original exhibition page (step S205). With the above flow, the generation phase by the generation apparatus 100 ends.

  Next, a feedback procedure regarding the generation process will be described with reference to FIG. FIG. 9 is a flowchart (3) illustrating the processing procedure according to the embodiment.

  As illustrated in FIG. 9, the generation device 100 determines whether a response to the product page has been received from the user terminal 10 (Step S <b> 301). The production | generation apparatus 100 waits until it receives, when reaction is not received (step S301; No).

  On the other hand, when a reaction is received (step S301; Yes), the generation device 100 acquires a reaction from the user (step S302). And the production | generation apparatus 100 determines whether the reaction from a user exceeded the predetermined threshold value (step S303).

  When the reaction from the user exceeds a predetermined threshold (step S303; Yes), the generation apparatus 100 determines that the advertisement information (or extracted feature information) given to the product is correct ( Step S304). On the other hand, when the reaction from the user does not exceed the predetermined threshold (step S303; No), the generating apparatus 100 determines that the advertisement information given to the product is incorrect (step S305).

  Then, the generation apparatus 100 updates the model by obtaining learning data in which the data obtained in steps S304 and S305 is a positive example or a negative example (step S306). In other words, the generation device 100 learns the model more strongly based on the user's reaction. By repeating the above flow, the generation device 100 optimizes the model.

[5. (Modification)
The generation apparatus 100 described above may be implemented in various different forms other than the above embodiment. Therefore, in the following, another embodiment of the generation apparatus 100 will be described.

[5-1. (Use for search results)
The generation apparatus 100 may not only generate the product page using the generated advertisement information but also use the advertisement information for various processes. For example, the generation apparatus 100 may display advertisement information together with a search result in a search for a product performed on a commercial transaction site or the like.

  That is, the generation device 100 may generate a search result page including advertisement information of a product when the product is displayed as a result of a predetermined search process. In this case, on the search result page, for example, advertisement information (for example, summary text) related to the product is displayed in the vicinity of the product searched based on the search query. For this reason, when searching for a product, the user can grasp the characteristics of the product without displaying the product page. As described above, the generation device 100 can improve the convenience of the user who uses the commercial transaction site.

[5-2. Advertising information)
In the above embodiment, the generation apparatus 100 has shown an example in which a summary sentence is generated as advertisement information. Here, the advertisement information is not limited to the summary sentence, but is information for promoting the product, and any information may be used as long as the information characterizing the product is transmitted to the user.

  For example, the generation apparatus 100 may extract a word included in text data as feature information and generate a product page in a form in which the extracted word is highlighted in the text data associated with the product. Good.

  As an example, the generation apparatus 100 highlights a word extracted as a characterizing item in the original description. In this case, the advertising information means a highlight display added to the text data. Then, the generation device 100 generates a product page including the highlighted word. That is, the generating apparatus 100 generates a product page in which the characteristic words included in the explanatory text are highlighted while the layout of the original exhibition page is maintained. Thereby, the production | generation apparatus 100 can produce | generate the goods page to which the information which wants to appeal to a user was provided, maintaining the aspect of the page which the exhibitor intended. In other words, the content generated by the generation device 100 includes not only new content generated from scratch, but also highlights existing content and highlights it to enhance text visibility. Content generated by the adding process and the conversion process is also included.

[5-3. (Use for recommendation)
The generation apparatus 100 displays advertisement information not only on a commercial transaction site but also on, for example, a recommendation of a product displayed together with a web page or the like (for example, information displayed on an advertisement frame or recommendation frame of a web page). Also good.

  For example, a product that is exhibited on a commercial transaction site may be displayed as a recommendation on a product page other than the product. In this case, the generating apparatus 100 displays the advertisement information together with the recommended product. Thus, the user can grasp the characteristics of the product without accessing the product page of the recommended product (without changing the display from the currently viewed page to the product page).

  Note that the generation apparatus 100 may acquire information indicating whether a recommendation for the product has been clicked or whether the user has converted. For example, when the advertisement information displayed as a recommendation is inappropriate or when the appeal effect is low, it is assumed that the user does not return a click or conversion response. On the other hand, when the user returns a response that the user clicks or converts, the advertising information displayed together with the recommendation is assumed to be information that appropriately indicates the feature of the product (correct answer).

  Then, as described in the above embodiment, the generation apparatus 100 determines whether the processing of the advertisement information or the feature information is correct according to the reaction to the recommendation. Thereby, the production | generation apparatus 100 can improve the precision of an extraction process or a production | generation process (learning) using the reaction from users other than a goods page.

[5-4. commodity〕
In the above-described embodiment, the merchandise such as wine handled at the shopping site is taken as an example, but the merchandise is not limited to these. In other words, the generation apparatus 100 is a product handled at a commercial transaction site, and can perform the generation process according to the embodiment for any product such as a product or a service as long as the product can acquire information on the product. It can be carried out.

[5-5. content〕
In the said embodiment, although the web page was mentioned as an example as content, a content is not restricted to this example. For example, the content may be advertising content, an information page provided via an application, or content related to a recommendation. That is, the content generated by the generation device 100 may be any content as long as it is information content provided via a network.

  For example, the generating apparatus 100 may generate advertisement information for a predetermined product and reflect the advertisement information in advertisement content for promoting the product. Specifically, the generation device 100 generates advertisement information about a product corresponding to the advertisement content submitted by the advertiser (product provider). And the production | generation apparatus 100 provides the produced | generated advertisement information (for example, summary sentence) to advertisement content, and produces | generates a new advertisement content. Specifically, the generation apparatus 100 adds a summary sentence that is advertisement information to a place where text data for promoting a product is inserted in the advertisement content. Thereby, the production | generation apparatus 100 can produce | generate the advertising content which can transmit the characteristic of goods to a user succinctly, for example.

[6. Hardware configuration)
The generation apparatus 100, the user terminal 10, and the exhibitor terminal 20 according to the above-described embodiment are realized by a computer 1000 having a configuration as shown in FIG. Hereinafter, the generation apparatus 100 will be described as an example. FIG. 10 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the generation apparatus 100. The computer 1000 includes a CPU 1100, RAM 1200, ROM 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 a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from other devices via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100. Send to device.

  The CPU 1100 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 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the data generated via the input / output interface 1600 to the output device.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the 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 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.

  For example, when the computer 1000 functions as the generation apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from other devices via the communication network 500.

[7. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the acquisition unit 131 and the reception unit 133 illustrated in FIG. 3 may be integrated. Further, for example, information stored in the storage unit 120 may be stored in a predetermined storage device provided outside via the network N.

  Moreover, in the said embodiment, the production | generation apparatus 100 showed the example which performs the acquisition process which acquires text data, the extraction process which extracts feature information, and the production | generation process which produces | generates a goods page, for example. However, the generation apparatus 100 described above may be separated into an acquisition apparatus that performs an acquisition process, an extraction apparatus that performs an extraction process, and a generation apparatus that performs a generation process. In this case, the acquisition device includes at least the acquisition unit 131. The extraction device has at least an extraction unit 132. The generation device has at least a generation unit 134. And the process by said production | generation apparatus 100 is implement | achieved by the production | generation processing system 1 which has each apparatus of an acquisition apparatus, an extraction apparatus, and a production | generation apparatus.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

[8. effect〕
As described above, the generation device 100 according to the embodiment includes the acquisition unit 131, the extraction unit 132, and the generation unit 134. The acquisition unit 131 acquires text data associated with a commercial material that is a target of a commercial transaction on the network. The extraction unit 132 extracts feature information that is information indicating the feature of the product from the text data acquired by the acquisition unit 131. Based on the feature information extracted by the extraction unit 132, the generation unit 134 generates a page (an example of content) to which advertising information that is information for advertising a product is given.

  As described above, the generating apparatus 100 according to the embodiment extracts product features from explanatory texts set by various exhibitors on, for example, a product introduction page on a commercial transaction site, and summarizes based on the extracted features. Generate advertising information such as sentences. Thereby, the production | generation apparatus 100 can produce | generate the goods page excellent in visibility, maintaining the characteristic of the appeal point of the goods provided by the exhibitor. For this reason, the production | generation apparatus 100 can improve the usability in a commercial transaction site, and can contribute to a user's purchasing activity.

  Further, the extraction unit 132 extracts feature information based on a learning process using correct data set for text data.

  As described above, the generation apparatus 100 according to the embodiment can extract feature information similar to a summary generated manually by performing learning based on preset correct answer data. For this reason, the production | generation apparatus 100 can extract the information which shows the characteristic of goods exactly.

  The extraction unit 132 extracts feature information using a model (learning device) learned to extract information that characterizes text data.

  As described above, the generation apparatus 100 according to the embodiment may perform learning by a method of extracting a feature amount characterizing text data by a method such as deep learning. By such processing, the generation apparatus 100 can extract the feature information of the product with high accuracy and efficiency.

  In addition, the acquisition unit 131 acquires a response to the product associated with the page of the user who has viewed the page generated by the generation unit 134. The generation unit 134 generates a page to which advertisement information is given based on a reaction from the user.

  As described above, the generation apparatus 100 according to the embodiment can perform the generation process by feeding back the user's reaction. Thereby, the generating apparatus 100 can optimize the page to be generated.

  In addition, the acquisition unit 131 acquires information related to a user who has viewed the page generated by the generation unit 134. The generation unit 134 generates a page corresponding to the information related to the user, based on the information related to the user, to which the advertisement information is given.

  Thus, the generation apparatus 100 according to the embodiment may generate a different page for each user. Thereby, since the production | generation apparatus 100 can provide the advertisement information according to the characteristic of each user, it can improve the appeal effect of the produced | generated page.

  Moreover, the production | generation part 134 produces | generates the page which contains the summary sentence of the text data matched with the commercial material as advertisement information.

  As described above, the generation apparatus 100 according to the embodiment may generate a summary sentence that summarizes the features of the product as the advertisement information. Thereby, since the production | generation apparatus 100 can show the characteristic of goods to a user with a short sentence instead of a redundant description, it can produce | generate the page which can convey information efficiently.

  Further, the generation unit 134 generates a page in a form in which a summary sentence is arranged prior to text data associated with a product.

  As described above, the generating apparatus 100 according to the embodiment can transmit the feature of the product to the user more quickly and accurately by generating the page that presents the summary sentence prior to the original explanatory text. Thereby, the production | generation apparatus 100 can improve the usability of the user who uses a commercial transaction site.

  Further, the extraction unit 132 extracts words included in the text data as feature information. The generation unit 134 generates a page in which the word extracted by the extraction unit 132 is highlighted in the text data associated with the product.

  As described above, the generation apparatus 100 according to the embodiment may generate a page in such a manner that only features are highlighted with respect to the original explanatory text. Thereby, the production | generation apparatus 100 can transmit the characteristic of goods to a user, without destroying layout, such as a display of the original exhibitor's explanatory note.

  In addition, when the product is displayed as a result of the predetermined search process, the generation unit 134 generates a search result page including the advertisement information of the product as an example of the content.

  As described above, the generating apparatus 100 according to the embodiment may present the advertisement information as information displayed together with the search result. Thereby, the production | generation apparatus 100 can tell the user the characteristic of goods, even if a user does not bother to access a goods page.

  The embodiment of the present application has been described in detail with reference to the drawings. However, this is an exemplification, and various modifications and improvements are made based on the knowledge of those skilled in the art including the aspects described in the column of the disclosure of the invention. The present invention can be implemented in other forms.

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

DESCRIPTION OF SYMBOLS 1 Generation processing system 10 User terminal 20 Exhibitor terminal 100 Generating device 110 Communication part 120 Storage part 121 Learning information storage part 122 Exhibition information storage part 123 Merchandise information storage part 130 Control part 131 Acquisition part 132 Extraction part 133 Reception part 134 Generation part 135 Storage Unit 136 Receiving Unit 137 Providing Unit

Claims (11)

An acquisition unit that acquires text data associated with a commercial product that is a target of a commercial transaction on the network;
An extraction unit that extracts feature information that is information indicating the characteristics of the product from the text data acquired by the acquisition unit;
Based on the feature information extracted by the extraction unit, a generation unit that generates content to which advertising information that is information for advertising the product is provided;
A generating apparatus comprising: The extraction unit includes:
Extracting the feature information based on a learning process using correct data set for the text data;
The generating apparatus according to claim 1, wherein: The extraction unit includes:
Extracting the feature information using a learning device trained to extract information characterizing the text data;
The generating apparatus according to claim 1 or 2, wherein The acquisition unit
Obtaining a response to the product associated with the content of the user who has browsed the content generated by the generation unit,
The generator is
Based on the reaction from the user, the content with the advertising information is generated.
The generating apparatus according to claim 1, wherein The acquisition unit
Obtain information about the user who viewed the content generated by the generation unit,
The generator is
Based on the information on the user, the content is provided with the advertisement information, and the content corresponding to the information on the user is generated.
The generating apparatus according to claim 1, wherein The generator is
Generating the content including a summary sentence of text data associated with the product as the advertisement information;
The generating apparatus according to claim 1, wherein The generator is
Prior to the text data associated with the product, the content of the aspect in which the summary sentence is arranged is generated.
The generating apparatus according to claim 6. The extraction unit includes:
As the feature information, a word included in the text data is extracted,
The generator is
Generating the content in a form in which the word extracted by the extraction unit is highlighted among the text data associated with the product;
The generating apparatus according to claim 1, wherein The generator is
When the product is displayed as a result of a predetermined search process, a search result page including advertisement information of the product is generated as the content.
The generation device according to claim 1, wherein the generation device is a device. A generation method executed by a computer,
An acquisition step of acquiring text data associated with the merchandise that is the object of the commercial transaction on the network;
An extraction step of extracting feature information, which is information indicating the characteristics of the product, from the text data acquired by the acquisition step;
Based on the feature information extracted by the extraction step, a generation step of generating content to which advertising information that is information for advertising the product is provided;
The generation method characterized by including. An acquisition procedure for acquiring text data associated with the merchandise that is the object of the commercial transaction on the network;
An extraction procedure for extracting feature information, which is information indicating the characteristics of the product, from the text data acquired by the acquisition procedure;
Based on the feature information extracted by the extraction procedure, a generation procedure for generating content provided with advertisement information, which is information for promoting the product,
A program for causing a computer to execute.

Images