JP2019079131A - Information processing apparatus, information processing method, and information processing program - Google Patents

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program capable of outputting a search result desired by a user.SOLUTION: An information processing apparatus 100 includes an extraction unit 133 and an assignment unit 134. The extraction unit 133 extracts information on goods. The assignment unit 134 assigns information on the goods extracted by the extraction unit 133 to other goods identified by an identifier for identifying the goods as information to be compared with a search query during a search process. In addition, when the amount of information assigned to the other goods as information to be compared with the search query by a seller of the other goods during the search process falls below a predetermined threshold value, the assignment unit 134 assigns, to the other goods, information on the goods extracted by the extraction unit 133 as information to be compared with the search query during the search process.SELECTED DRAWING: Figure 3

Description

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

  There are known sites for displaying a plurality of contents related to a product etc., such as a product search site. In such a site, a plurality of contents may be output as a search result in the order in which the contents are ranked.

JP, 2012-203821, A

  Output of search results is performed based on various elements. However, the output search results may not necessarily be what the user desires.

  The present application has been made in view of the above, and an object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program capable of outputting a search result desired by a user.

  The information processing apparatus according to the present application searches for information on a product extracted by the extraction unit with respect to another product identified by an extraction unit that extracts information on a product and an identifier for identifying the product. The information processing apparatus is characterized by further comprising: an adding unit that adds information as information to be compared with the search query at the time of processing.

  According to an aspect of the embodiment, it is possible to output the search result desired by the user.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating an exemplary configuration of an information processing system according to the embodiment. FIG. 3 is a diagram illustrating an exemplary configuration of the information processing apparatus according to the embodiment. FIG. 4 is a diagram showing an example of the content information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the weight information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of search processing according to the embodiment. FIG. 7 is a flowchart showing an information processing procedure according to the embodiment. FIG. 8 is a flowchart showing a search processing procedure according to the embodiment. FIG. 9 is a diagram illustrating an example of information processing according to a modification. FIG. 10 is a hardware configuration diagram showing an example of a computer for realizing the function of the information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, and a mode for carrying out an information processing program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by the embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

[1. Example of information processing]
First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. The information processing apparatus 100 illustrated in FIG. 1 is a server apparatus that provides a search service for products and the like. In FIG. 1, the information processing apparatus 100 selects, from among the contents (hereinafter referred to as “merchandise contents”) related to a plurality of goods or services, the first goods to which the description of the goods explanation is not given by the seller. To do (step S1). In FIG. 1, the fact that the seller does not give the description of the item description corresponds to the fact that the item description is NULL. The first product is a product corresponding to the product content C1, and specifically, is a polo shirt. As for the first product, only the information of "Polo shirt" which is the product title is given by the seller.

  Subsequently, the information processing apparatus 100 is a product identified by the product ID “111122223333” which is the same as the product ID “111122223333” of the first product among the plurality of product contents, and the description of the product description by the seller A second product to which a sentence is assigned is selected (step S2). For example, the product ID is a JAN code (Japanese Article Number). The JAN code is a product identification number commonly assigned to the same product. That is, the JAN code does not identify an individual product. Further, the product ID may be identification information that a service side such as the information processing apparatus 100 uniquely assigns to each product. The second product is a product corresponding to the product content C2, specifically, a polo shirt. For the second product, in addition to the product title "polo shirt", the seller has given a sentence "a unisex short sleeve shirt. A polo shirt classic!"

  Subsequently, the information processing apparatus 100 extracts a predetermined keyword from the description of the item description of the selected second item (step S3). Specifically, the information processing apparatus 100 is an explanatory sentence of the product description given to the second product, and "man and woman" and "others" from the sentence "man and woman combined short sleeve shirt. Polo shirt classic!" Extract three keywords: short sleeve shirts and "standard".

  Subsequently, when the information processing apparatus 100 extracts a keyword from the item description of the second item, the information processing apparatus 100 assigns the first item as information to be compared with the search query (step S4). Specifically, the information processing apparatus 100 extracts the three items extracted into the item of “given item description” different from “item title” which is the item indicating the information given by the seller and “item description”. The keywords "unisex", "short sleeve shirt" and "standard" are stored.

  After this, it is assumed that the information processing apparatus 100 receives "unisex" and "short sleeve shirt" which are search queries inputted by the user U1 from the user terminal 10 (step S5).

  In this case, the information processing apparatus 100 calculates a score according to the degree of association between the search query and the product (step S6). Specifically, the information processing apparatus 100 calculates a score such that the degree of association between the search query and the product increases as the degree of matching between the information given to the product and the search query increases. For example, the information processing apparatus 100 determines whether the keywords “men and women combined” and “short sleeve shirt”, which are keywords stored in the “given item description” item of the first item, match the search query, etc. 1 Calculate the score of the product. For example, the information processing apparatus 100 performs a morphological analysis on "man and woman combined short sleeve shirts and polo shirts!" Which is a sentence stored in the item "item description" of the second item, and "men and women" Extract "shared", "short sleeve shirt" and "standard". Then, the information processing apparatus 100 calculates the score of the second product based on, for example, that the words “unisex” and “short sleeve shirt” that are words extracted from the product description match the search query. The detailed calculation method of the score will be described later.

  Subsequently, the information processing apparatus 100 selects, as a search result, a predetermined number of product contents in descending order of the calculated product score (step S7). Further, the information processing apparatus 100 determines the display order of the product content so as to be displayed in descending order of the score.

  Here, the plurality of item contents selected by the information processing apparatus 100 are displayed as search results in the search result contents. The search result content is content for displaying a plurality of product contents as a search result, and refers to content for displaying a plurality of product contents in the display order determined by the information processing apparatus 100. Specifically, the search result content is content for a web page or an application.

  Subsequently, the information processing apparatus 100 distributes the search result to the user terminal 10 of the request source (step S8).

  As described above, the information processing apparatus 100 extracts information on a product from the second product identified by the same identifier as the identifier for identifying the first product to which the description text of the product description is not attached. Then, the information processing apparatus 100 adds information related to the extracted product to the first product identified by the same identifier as the second product as information to be compared with the search query at the time of the search processing.

  As a result, although the information processing apparatus 100 is the same product as the product desired by the user as the search result, the information attached to the product is scarce, so the word matching the search query is not included, and the search result is Products that were not output as can be output as search results. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  In the example shown in FIG. 1, the information processing apparatus 100 shows an example in which information to be compared with the search query at the time of search processing is given to the first product to which the description sentence of the item description is not attached. Information to be compared with the search query may be added to the first item to which the description of the item description is attached at the time of search processing. Specifically, the information processing apparatus 100 may assign information to be collated with the search query at the time of the search processing to the product for which the information amount of the product description given by the seller falls below a predetermined threshold.

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

  The user terminal 10 is a terminal device used by a user. The user terminal 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 10 transmits, to the information processing apparatus 100, the search query input to the search service for a product or the like according to the operation of the user. The user terminal 10 displays the search result content distributed by the information processing apparatus 100 on the display screen.

  Specifically, when the user terminal 10 is a smartphone, a predetermined application is installed on the user terminal 10, and the search result content distributed by the information processing apparatus 100 is displayed on the display screen of the user terminal 10 by the application. indicate. The application referred to here means, for example, a dedicated application for displaying search result content distributed by a browser or the information processing apparatus 100.

  The store terminal 20 is a terminal device used by a seller of goods or services. For example, the shop terminal 20 is a tablet type terminal, a PC, a mobile phone, a PDA, or the like. Further, the shop terminal 20 transmits the product content to the information processing apparatus 100 together with the document (the product title, the text of the product description, etc.) related to the product content according to the operation of the seller.

  For example, the shop terminal 20 transmits product information corresponding to a still image, a moving image, text data, and the like to the information processing apparatus 100. Also, for example, when the product content is selected (for example, clicked or tapped), the shop terminal 20 transmits, to the information processing apparatus 100, the product content corresponding to the URL (Uniform Resource Locator) of the transition destination content to be transitioned. You may

  The information processing apparatus 100 is a server apparatus that performs the information processing described in FIG. 1. The information processing apparatus 100 is a server apparatus that provides a shopping service that accepts exhibitions of a plurality of products from a plurality of stores and sells the products through the Internet. Here, the shopping service provided by the information processing apparatus 100 is a shopping mall type service that handles products exhibited from a plurality of different stores. The information processing apparatus 100 acquires product content such as a product image from the shop terminal 20 together with a document (product title, product description text, etc.) related to product content.

  Further, the information processing apparatus 100 is a server apparatus that provides a search service for products and the like. The information processing apparatus 100 receives a search query from the user terminal 10. When the information processing apparatus 100 receives the search query, the information processing apparatus 100 calculates, for each product, a score based on the degree of association between the search query and the product. The information processing apparatus 100 selects a predetermined number of product contents from the one with the highest calculated score. The information processing apparatus 100 determines the display order of the selected product content. Then, the information processing apparatus 100 distributes, to the user terminal 10, search result content in which a plurality of product contents are displayed in the determined display order.

[3. Configuration of information processing apparatus]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating an exemplary configuration of the information processing apparatus 100 according to the embodiment. As shown in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(Communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to the network N in a wired or wireless manner, and transmits and receives information to and from, for example, the user terminal 10 and the shop terminal 20.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device 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 illustrated in FIG. 3, the storage unit 120 includes a content storage unit 122, a content information storage unit 121, and a weight information storage unit 123.

(Content information storage unit 121)
The content information storage unit 121 stores various types of information related to product content received from the shop terminal 20. Further, the content information storage unit 121 stores the information given to the product by the information processing apparatus 100. FIG. 4 shows an example of the content information storage unit 121 according to the embodiment. In the example illustrated in FIG. 4, the content information storage unit 121 has items such as “content ID”, “product ID”, “product title”, “product description”, and “provided product description”. Besides the content shown in FIG. 4, the content information storage unit 121 may have an item such as “store ID” which is identification information for identifying the store terminal 20 that is the transmission source of the product content.

  The “content ID” indicates identification information for identifying the item content received from the shop terminal 20.

  “Product ID” indicates identification information for identifying a product or service corresponding to product content. In the example shown in the first record of FIG. 4, the product ID of the product corresponding to the product content identified by the content ID “C1” is a number “111122223333”. As the product ID, any information may be used as long as it is information that can identify the same product. For example, the product ID may be a JAN code (Japanese Article Number). The JAN code is a universal product identification number capable of identifying "which product is created by which company". The JAN code is a product identification number commonly assigned to the same product. That is, the JAN code does not identify an individual product. Further, the product ID may be identification information that a service side such as the information processing apparatus 100 uniquely assigns to each product. The identification information may be the name of the product itself.

  "Product title" indicates the name of a product or service corresponding to the product content. The product title is a term that is most commonly used as a search query that the user inputs when searching for a product or the like. In the example shown in the first record of FIG. 4, the product title of the product corresponding to the product content identified by the content ID “C1” is “Polo shirt”.

  "Product description" indicates a description of a product or service corresponding to the product content. The item description is information provided by the store so as to be a clue when the user considers the purchase of the item or the like. Therefore, the item description often includes a phrase that matches the search query that the user inputs when searching for an item or the like. For example, the item description includes a term such as a category such as an item or a feature such as an item. In the example shown in the first record of FIG. 4, the item description of the item corresponding to the item content identified by the content ID “C1” is “NULL”. That is, the product corresponding to the product content identified by the content ID “C1” is a product to which the product description is not given by the seller. In other words, the product corresponding to the product content identified by the content ID “C1” is a product whose information provided by the seller is only the product title. Further, in the example shown in the second record of FIG. 4, the item description of the item corresponding to the item content identified by the content ID “C2” is a sentence “man and woman short sleeve shirt. Polo shirt classic!”. Further, in the example shown in the third record of FIG. 4, the item description of the item corresponding to the item content identified by the content ID “C3” is a word “unisex”.

  The information processing apparatus 100 may morphologically analyze the text of the product description and store the decomposed words. For example, the information processing apparatus 100 morphologically analyzes "Product for unisex short sleeve shirt. Standard polo shirt!" And analyzes the words "unisex" and "short sleeve shirt" and "Standard". May be stored in the item description.

  The “given item description” is an explanation about the item or service corresponding to the item content, and indicates the item description given by the information processing apparatus 100. The given item description is given by the information processing apparatus 100 when the amount of information of the item for which the item description has not been given by the seller or the item description given by the seller falls below a predetermined threshold. In the example shown in the first record of FIG. 4, the item description of the item corresponding to the item content identified by the content ID “C1” is “NULL”. That is, the product corresponding to the product content identified by the content ID “C1” is a product to which the product description is not given by the seller. Then, the item description provided with the item corresponding to the item content identified by the content ID "C1" is the three words "unisex", "short sleeve shirt" and "standard". Further, in the example shown in the third record of FIG. 4, the item description of the item corresponding to the item content identified by the content ID "C3" is only the word "unisex". That is, the product corresponding to the product content identified by the content ID “C3” is a product whose amount of information provided by the seller falls below a predetermined threshold. Then, the item description provided with the item corresponding to the item content identified by the content ID “C3” is the two words “short sleeve shirt” and “standard”.

(Content storage unit 122)
The content storage unit 122 stores various product content. The content storage unit 122 stores data of content corresponding to the content ID of the content information storage unit 121. The content storage unit 122 stores data of product content such as audio data, image data, text data, game data, data in a game format, etc. in association with a content ID. In addition, the content storage unit 122 may store a URL where each item content is located, a file path name indicating a storage location of these, or the like in association with the content ID.

(Weight information storage unit 123)
The weight information storage unit 123 stores weight information on the score based on the degree of association between the search query and the product. FIG. 5 shows an example of the weight information storage unit 123 according to the embodiment. In the example illustrated in FIG. 5, the weight information storage unit 123 has items such as “item” and “weight”.

  "Item" indicates an item of the content information storage unit 121. Specifically, the item "product title" is an item of the product title in the content information storage unit 121. Further, the item “product description” is an item of the product description in the content information storage unit 121. Further, the item “delivered item description” is an item of the item description attached to the content information storage unit 121.

  “Weight” indicates a weight corresponding to each item of the content information storage unit 121. Specifically, the weight "1.0" corresponding to the search query item "product title" received from the user is the product when the search query received from the user matches the word stored in the item of the product title. It indicates that the weight applied to the score given to the product corresponding to the title is 1.0.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device in the information processing apparatus 100 by, for example, a central processing unit (CPU) or a micro processing unit (MPU). Various programs (corresponding to an example of a generation program) are realized by executing the RAM as a work area. The control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As shown in FIG. 3, the control unit 130 includes a paper receiving unit 131, a selecting unit 132, an extracting unit 133, an applying unit 134, a receiving unit 135, a searching unit 136, and a distributing unit 137. , Realize or execute the action of the 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 it performs the information processing described later.

(Draft Section 131)
The submission unit 131 accepts submission of product content. Specifically, the submission unit 131 receives submission of product content from a plurality of shop terminals desiring to open a shopping service provided by the information processing apparatus 100, and acquires a plurality of product content.

  Further, the submission unit 131 receives documents (for example, a title of a product and a text of a product description) related to the product content from the shop terminal 20 together with the submission of the product content.

  Specifically, upon receiving a document related to product content, the import unit 131 extracts a term corresponding to the product title from among the received documents, and stores the word / phrase in the content information storage unit 121. Similarly, the submission unit 131 extracts a term corresponding to the item description from the received document and stores the term in the content information storage unit 121. In addition, the submission unit 131 stores the received product content in the content storage unit 122.

  In the example shown in the second record of FIG. 4, when the document input unit 131 receives a document related to the product content C2, the document input unit 131 extracts the word “polo shirt” from the received document as the word or phrase corresponding to the product title. Subsequently, the submission unit 131 stores the extracted word “polo shirt” in the item of the product title of the content information storage unit 121. Further, upon receiving the document related to the product content C2, the submission unit 131 extracts a sentence “unisex short sleeve shirt. Polo shirt classic!” As a sentence corresponding to the item description from the received document. In addition, the submission unit 131 stores the extracted sentence “unisex short sleeve shirt. Polo shirt classic!” In the item description of the content information storage unit 121.

  The submission unit 131 may morphologically analyze the text of the received item description, and store the decomposed word in the item description of the item in the content information storage unit 121. For example, the information processing apparatus 100 morphologically analyzes "Product for unisex short sleeve shirt. Standard polo shirt!" And analyzes the words "unisex" and "short sleeve shirt" and "Standard". May be stored in the item of the item description of the content information storage unit 121.

  The submission unit 131 may extract keywords from the document related to the product content using various known methods. For example, the submission unit 131 may extract a keyword related to product content from a document related to product content using a weight value such as tf-idf (Term Frequency, Inverse Document Frequency). For example, the submission unit 131 may not extract words that are widely used words and that are determined not to be useful for searching for product content as keywords related to the product content. For example, using the weight value such as tf-idf, the submission unit 131 uses the weight value such as tf-idf to extract the keyword extracted as the term relating to the product content, such as the product title or the product description. The items may be classified and stored.

(Selection unit 132)
The selection unit 132 selects a first product for which the amount of information provided to the product as information to be compared with the search query at the time of search processing falls below a predetermined threshold. Specifically, the selection unit 132 selects, from among the plurality of item contents received from the store terminal 20, the first item in which the information given to the item by the seller is only the item title of the item.

  Subsequently, the selection unit 132 selects the second item identified by the identifier for identifying the first item. Specifically, the selection unit 132 is a product identified by the same product ID as the product ID for identifying the selected first product among the plurality of product contents received from the shop terminal 20, The second commodity to which the description of the commodity description is given by the seller is selected.

(Extraction unit 133)
The extraction unit 133 extracts information on the second product selected by the selection unit 132. Specifically, the extraction unit 133 refers to the content information storage unit 121, and is an explanatory note of the item description of the second product for the selected second product. From the text, we will extract three keywords: "unisex", "short sleeve shirt" and "standard".

(Grant unit 134)
For the second product identified by the identifier for identifying the first product selected by the selection unit 132, the assignment unit 134 uses information on the product extracted by the extraction unit 133 as a search query at the time of search processing. Give as information to be collated. Specifically, the adding unit 134 stores the information on the product extracted by the extracting unit 133 in the item of “added product description” corresponding to the content ID “C2” of the content information storage unit 121.

  For example, when the amount of information provided to the first product as information to be compared with the search query by the seller of the first product by the seller of the first product falls below a predetermined threshold, The information on the second product extracted by the extraction unit 133 is added as information to be compared with the search query at the time of search processing.

  For example, when the information given to the first product as information to be compared with the search query by the seller of the first product by the seller of the first product is only the product title of the first product, Then, the information on the second product extracted by the extraction unit 133 is added as information to be compared with the search query at the time of search processing.

  The assigning unit 134 classifies the information given to the first item by the seller of the first item among the items for classifying the information given to the first item as the information to be compared with the search query at the time of the search processing. The information regarding the 2nd goods extracted by extraction part 133 is given to the item different from an item.

  Specifically, the adding unit 134 adds “a product title”, which is an item for classifying the information provided to the first product by the seller of the first product, and “a product description”, which are different from each other. By storing the keywords “sex sharing”, “short sleeve shirt”, and “standard” regarding the second product extracted by the extraction unit 133 in the item of “product description”, the keyword regarding the second product extracted by the extraction unit 133 is Give.

(Reception unit 135)
The receiving unit 135 receives a search query from the user terminal 10. For example, the reception unit 135 receives “unisex” and “short sleeve shirt”, which are search queries input by the user U1 from the user terminal 10.

(Search unit 136)
When the reception unit 135 receives a search query, the search unit 136 searches for a product based on the received search query. Specifically, when the receiving unit 135 receives a search query, the search unit 136 refers to the content information storage unit 121 to calculate a score based on the degree of association between the search query and the product. Specifically, the search unit 136 calculates a score such that the degree of association between the search query and the product increases as the degree of matching between the information given to the product and the search query increases.

  In addition to the degree of association between the search query and the product, the search unit 136 may, for example, click rate (CTR: Click Through Rate), which is a probability that the user selects the product content, and an action in which the user selects the product content. Subsequently, based on the conversion rate (CVR: Conversion Rate), which is the probability of taking action leading to profit for the seller such as purchase of a product or service or material request, the price of the product or service corresponding to the product content, and the performance of the product content. The score may be calculated based on the number of page views (PV: Page View) or the like. In addition, the search unit 136 may calculate the score based on the sales promotion ratio which is the ratio of the sales promotion cost to the price of the product or service.

  Further, the search unit 136 performs the search process based on the weight added to the information to be compared with the search query at the time of the search process. Specifically, the search unit 136 performs the search process based on the weight to which a different weight is added according to the item for classifying the information given to the other product as the information to be compared with the search query at the time of the search process. In addition, the search unit 136 adds a smaller weight to the item for classifying the information provided to the other item by the giving unit 134 than the item for classifying the information provided to the other item by the seller of the other item. Search processing is performed based on the weight. In addition, the search unit 136 is a weight that adds a greater weight to the product title than the product description among the product title and the product description, which are items for classifying information provided to the other product by the seller of the other product. Perform search processing based on. Further, the search unit 136 performs a search process based on the weight in which the maximum weight is added to the product title, which is an item for classifying the information given to the other product by the seller of the other product.

  Here, the search processing performed by the search unit 136 will be described with reference to FIG. FIG. 6 is a diagram illustrating an example of search processing according to the embodiment. In FIG. 6, keywords included in the item content C1 and the item content attached to the item content C2 shown in the example of FIG. 1 are “Q1”, “Q2”, “in order to easily understand the score calculation method. We will use symbols such as “Q3” and “Q4”.

  In the example illustrated in FIG. 6, the receiving unit 135 receives “Q1”, “Q2”, “Q3”, and “Q4” as search queries from the user terminal 10 (step S11).

  Subsequently, when the receiving unit 135 receives the search query, the search unit 136 calculates, for each product content, a score based on the degree of association between the search query and the product (step S12).

  Specifically, first, the search unit 136 refers to the content information storage unit 121, and searches for product content including a keyword matching the search query in the information attached to the product content. The search unit 136 detects a plurality of item contents including the item content C1 and the item content C2 as a result of the search.

  Subsequently, the search unit 136 sets the weight according to the item to which the information attached to the item content belongs to 100 points each time one keyword matching the search query is included in the information attached to the item content. Calculate the multiplied score. In other words, when the search unit 136 finds a keyword that matches the search query in the information given to the product content, it refers to the weight information storage unit 123 and responds to the item to which the information given to the product content belongs. The score is calculated by multiplying the weight by 100 points.

  In the example illustrated in FIG. 5, when the keyword matching the search query belongs to the “product title” which is an item, the search unit 136 calculates a score obtained by multiplying 100 points by the weight “1.0”. In addition, when the keyword matching the search query belongs to the item “item description”, the search unit 136 calculates a score obtained by multiplying 100 points by the weight “0.7”. In addition, when the keyword matching the search query belongs to the item “given item description”, the search unit 136 calculates a score obtained by multiplying 100 points by the weight “0.4”.

  For example, with regard to the product content C1, since the search unit 136 belongs to the “product title”, which is the item “keyword“ Q1 ”that matches the search query, the search unit 136 has a score of“ 100 points ” To calculate Further, the search unit 136 calculates the score “40 points” obtained by multiplying 100 points by the weight “0.4” because the keyword “Q2” matching the search query belongs to the item “added item description”. Do. Further, the search unit 136 calculates the score "40 points" obtained by multiplying 100 points by the weight "0.4" because the keyword "Q3" matching the search query belongs to the item "given item description". Do. Further, the search unit 136 calculates the score "40 points" obtained by multiplying 100 points by the weight "0.4" because the keyword "Q4" matching the search query belongs to the item "given item description". Do. Then, the search unit 136 calculates the total score as 220 points for the product content C1.

  For example, for the product content C2, the search unit 136 has a score of "100 points" obtained by multiplying 100 points by the weight "1.0" because the keyword "Q1" matching the search query belongs to the "item title" which is an item To calculate Further, the search unit 136 calculates the score “70 points” obtained by multiplying 100 points by the weight “0.7” because the keyword “Q2” matching the search query belongs to the item “item description”. Further, the search unit 136 calculates the score “70 points” obtained by multiplying 100 points by the weight “0.7” because the keyword “Q3” matching the search query belongs to the item “product description”. Then, the search unit 136 calculates the total score as 240 points for the product content C2.

  Subsequently, when the search unit 136 calculates a score for each product content, the search unit 136 selects a predetermined number of product content from the one with the highest score (step S13).

  Subsequently, when a predetermined number of product contents are selected, the search unit 136 determines the display order in which the selected product contents are displayed. Then, the distribution unit 137 arranges the product content in the display order determined by the search unit 136, and distributes the search result to the user terminal 10 (step S14). Specifically, the search unit 136 selects a predetermined number of product contents in descending order of the calculated score, and determines the display order so as to display the selected product contents in the order of the calculated high score. For example, in the product content C1 and the product content C2, since the product content C2 has a higher total score calculated for the product content C1, the search unit 136 displays the product content C2 in the display order for the product content C1. Determine the display order to be higher than that.

(Distribution unit 137)
The distribution unit 137 distributes information other than the information provided to the second product by the giving unit 134 as a search result for the second product. Specifically, the delivery unit 137 delivers information other than the information belonging to the given item description given to the second item by the giving unit 134 as a search result for the second item. That is, the distribution unit 137 distributes the product title and the product description given to the second product by the seller of the second product, and the product content C2 as a search result for the second product.

[4. Flow of information processing]
Next, the procedure of the information processing according to the embodiment will be described with reference to FIG. FIG. 7 is a flowchart showing an information processing procedure according to the embodiment.

  As shown in FIG. 7, the information processing apparatus 100 selects a first product whose amount of information included in the product description falls below a predetermined threshold (step S101).

  Subsequently, the information processing apparatus 100 selects a second product having the same product ID as the first product (step S102).

  Subsequently, the information processing apparatus 100 determines whether a keyword not included in the item description of the first item is included in the item description of the second item (step S103). The information processing apparatus 100 ends the process when the keyword not included in the item description of the first item is not included in the item description of the second item (step S103; No).

  When the information processing apparatus 100 includes a keyword not included in the item description of the first item in the item description of the second item (step S103; Yes), a keyword not included in the item description of the first item Are extracted from the item description of the second item (step S104).

  Subsequently, the information processing apparatus 100 assigns, to the first product, the keyword extracted as the information to be matched with the search query (step S105).

[5. Flow of search processing]
Next, the procedure of the search process according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart showing a search processing procedure according to the embodiment.

  As shown in FIG. 8, the information processing apparatus 100 determines whether a search query has been received (step S201). When the information processing apparatus 100 does not receive the search query (step S201; No), the information processing apparatus 100 stands by until the search query is received.

  Subsequently, when the information processing apparatus 100 receives the search query (step S201; Yes), the information processing apparatus 100 determines whether the keyword included in the product title matches the search query (step S202). When the keyword included in the product title matches the search query (step S202; Yes), the information processing apparatus 100 multiplies the score given to the product when the search query matches the weight by the weight according to the item of the product title. The calculated score is calculated (step S203).

  If the keyword included in the product title does not match the search query (step S202; No), the information processing apparatus 100 determines whether the keyword included in the product description matches the search query (step S204). When the keyword included in the item description matches the search query (step S 204; Yes), the information processing apparatus 100 multiplies the score given to the item when the search query matches the weight by the weight according to the item of the item description. The calculated score is calculated (step S205).

  Subsequently, in the information processing apparatus 100, when the keyword included in the item description does not match the search query (step S204; No), the keyword included in the provided item description matches the search query. It is determined whether or not (step S206). When the keyword included in the given item description matches the search query (step S206; Yes), the information processing apparatus 100 responds to the item of the item description according to the score given to the item when it matches the search query. A score multiplied by the weight is calculated (step S207).

  In the information processing apparatus 100, when the keyword included in the provided item description does not match the search query (step S206; No), the item content is displayed in the order of the highest calculated score. Thus, the search results are distributed (step S208).

[6. Modified example]
The information processing system 1 according to the above-described embodiment may be implemented in various different forms other than the above-described embodiment. So, below, other embodiments of the information processing system 1 are described.

  In the embodiment described above, the second product identified by the information processing apparatus 100 using the same identifier as the identifier for identifying the first product for the first product to which the description of the product description is not attached. Although the case where the information related to the product extracted from the item is added is described as an example, the same as the identifier for identifying the first product for the first product whose amount of information included in the product description falls below a predetermined threshold value Information on a product extracted from the second product identified by the identifier may be added. This point will be described with reference to FIG. FIG. 9 is a diagram illustrating an example of information processing according to a modification. The same parts as those of the embodiment are given the same reference numerals and the description thereof is omitted.

  In FIG. 9, the information processing apparatus 100 selects, from among the product content, a product whose amount of information included in the product description given to the product by the seller falls below a predetermined threshold (step S21). In FIG. 9, the fact that the amount of information included in the item description given to the item by the seller falls below a predetermined threshold value corresponds to the fact that the item description is only one word. The third product is a product corresponding to the product content C3, specifically, a polo shirt. For the third product, information on the product title "polo shirt" and information on the product description "unisex" are given by the seller.

  Subsequently, the information processing apparatus 100 is a product identified by the product ID “111122223333” which is the same as the product ID “111122223333” of the third product from among the plurality of product contents, and is a product provided by the seller. A second product whose information amount of explanation exceeds a predetermined threshold value is selected (step S22). The second product is a product corresponding to the product content C2, specifically, a polo shirt. For the second product, in addition to the product title "polo shirt", the seller has given a sentence "a unisex short sleeve shirt. A polo shirt classic!"

  Subsequently, the information processing apparatus 100 extracts a predetermined keyword from the description of the item description of the selected second item (step S23). Specifically, the information processing apparatus 100 is a description of the third product from among the sentences “a unisex short sleeve shirt, a standard polo shirt!” Which is an explanatory text of the product description given to the second product. Extract two keywords, "short sleeve shirt" and "standard", which are not included in.

  Subsequently, when the information processing apparatus 100 extracts a keyword from the item description of the second item, the information processing apparatus 100 adds the keyword to the third item as information to be compared with the search query (step S24). Specifically, the information processing apparatus 100 extracts two items of “product description given” different from “product title” and “product description” which are items indicating information given by the seller. The keywords "short sleeve shirt" and "standard" are stored.

  Thereafter, it is assumed that the information processing apparatus 100 receives the “standard” and the “short sleeve shirt” which are search queries input by the user U1 from the user terminal 10 (step S25).

  In this case, the information processing apparatus 100 calculates a score according to the degree of association between the search query and the product (step S26). Specifically, the information processing apparatus 100 calculates a score such that the degree of association between the search query and the product increases as the degree of matching between the information given to the product and the search query increases. For example, the information processing apparatus 100 may execute the third information processing based on the match between the “standard” and the “short sleeve shirt”, which are the keywords stored in the “given item description” item of the third item, and the search query. Calculate the product score. For example, the information processing apparatus 100 performs a morphological analysis on "man and woman combined short sleeve shirts and polo shirts!" Which is a sentence stored in the item "item description" of the second item, and "men and women" Extract "shared", "short sleeve shirt" and "standard". Then, the information processing apparatus 100 calculates the score of the second product based on, for example, that the words “standard” and “short sleeve shirt” extracted from the product description match the search query.

  Subsequently, the information processing apparatus 100 selects, as a search result, a predetermined number of product contents in descending order of the calculated product score (step S27). Further, the information processing apparatus 100 determines the display order of the product content so as to be displayed in descending order of the score.

  Subsequently, the information processing apparatus 100 distributes the search result to the user terminal 10 of the request source (step S28).

  Thus, the information processing apparatus 100 extracts the information on the item from the second item identified by the same identifier as the identifier for identifying the third item whose amount of information included in the item description falls below the predetermined threshold. Do. Then, the information processing apparatus 100 adds information related to the extracted product to the third product identified by the same identifier as the second product as information to be compared with the search query at the time of the search processing.

  As a result, although the information processing apparatus 100 is the same product as the product desired by the user as the search result, the information attached to the product is scarce, so the word matching the search query is not included, and the search result is Products that were not output as can be output as search results. Therefore, the information processing apparatus 100 can output the search result desired by the user.

[7. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the extraction unit 133 and the application unit 134. The extraction unit 133 extracts information on a product. The assigning unit 134 assigns information on the item extracted by the extracting unit 133 to the other item identified by the identifier for identifying the item as information to be compared with the search query during the search process.

  As a result, the information processing apparatus 100 does not include the word matching the search query although it is the same product as the product desired by the user as the search result, and the product which is not output as the search result is obtained as the search result Output can be made possible. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  In addition, when the amount of information provided to the other product as information to be matched with the search query by the seller of the other product at the time of the search processing falls below a predetermined threshold value, the giving unit 134 applies to the other product. Information on the product extracted by the extraction unit 133 is added as information to be compared with the search query at the time of search processing.

  Thus, although the information processing apparatus 100 is the same product as the product desired by the user as the search result, the information given to the product by the seller is scarce, so the word matching the search query is not included. It is possible to make it possible to output a product that has not been output as a search result as a search result. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  In addition, when the information given to the other product as the information to be matched with the search query by the seller of the other product at the time of the search processing is only the product title of the other product, the giving unit 134 The information on the product extracted by the extraction unit 133 is added as information to be compared with the search query at the time of search processing.

  Thus, although the information processing apparatus 100 is the same product as the product desired by the user as the search result, the information attached to the product by the seller is only the product title, and thus the information processing apparatus 100 searches for the product description etc. It is possible to output products that are not output as search results without including a word that matches the query. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  Further, the assignment unit 134 classifies the information assigned to the other commodity by the seller of the other commodity among the items for classifying the information imparted to the other commodity as the information to be compared with the search query at the time of the search processing. Information on the product extracted by the extraction unit 133 is added to an item different from the item.

  Thereby, the information processing apparatus 100 can distinguish the information which the seller intended and attached to the goods, and the information which the information processing apparatus 100 extracts and gives from the other goods.

  Further, the information processing apparatus 100 according to the embodiment further includes a search unit 136 which performs a search process based on the weight added to the information to be compared with the search query at the time of the search process.

  Thereby, the information processing apparatus 100 can output the search result according to the priority of the information given to the product. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  Further, the search unit 136 performs the search process based on the weight to which a different weight is added according to the item for classifying the information given to the other product as the information to be collated with the search query at the time of the search process.

  Thereby, the information processing apparatus 100 can output the search result according to the priority of the item to which the information given to the product belongs.

  In addition, the search unit 136 adds a smaller weight to the item for classifying the information provided to the other item by the giving unit 134 than the item for classifying the information provided to the other item by the seller of the other item. Search processing is performed based on the weight.

  As a result, the information processing apparatus 100 can output the search result by giving higher priority to the information that the seller intends to give to the product than the information that the information processing apparatus 100 extracts and gives from the other products. It can be done. Therefore, the information processing apparatus 100 can output the search result reflecting the intention of the seller.

  In addition, the search unit 136 is a weight that adds a greater weight to the product title than the product description among the product title and the product description, which are items for classifying information provided to the other product by the seller of the other product. Perform search processing based on.

  As a result, the information processing apparatus 100 can set the priority of the product title higher than the product description and output the search result. In general, a product title is a search query that is most frequently used when a user searches for the product. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  Further, the search unit 136 performs a search process based on the weight in which the maximum weight is added to the product title, which is an item for classifying the information given to the other product by the seller of the other product.

  In general, a product title is a search query that is most frequently used when a user searches for the product. Therefore, the information processing apparatus 100 can output the search result desired by the user.

  Further, the information processing apparatus 100 according to the embodiment further includes a distribution unit 137 that distributes information other than the information provided to the other product by the giving unit 134 as a search result for the other product.

  As a result, the information processing apparatus 100 can output the search result by giving higher priority to the information that the seller intends to give to the product than the information that the information processing apparatus 100 extracts and gives from the other products. It can be done. Therefore, the information processing apparatus 100 can output the search result reflecting the intention of the seller.

[8. Hardware configuration]
The information processing apparatus 100 according to the embodiment described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 10 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 to control each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts 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 another device via a predetermined communication network, sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the predetermined communication network.

  The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the CPU 1100 with the program 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 digital versatile disc (DVD) or a phase change rewritable disc (PD), an optical magnetic recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium Etc.

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a program or data (for example, a product content model) loaded on the RAM 1200 to allow the control unit 130 to To realize the function. 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 another device via a predetermined communication network.

  Although some of the embodiments of the present application have been described above in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the section of the description of the invention. It is possible to implement the invention in other improved forms.

[9. Other]
Further, among the processes described in the embodiment and the modification, all or part of the process described as being automatically performed can be manually performed, or it is described as manually performed. All or part of the treatment may be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  Moreover, it is possible to combine suitably the embodiment and modification which were mentioned above in the range which does not make process content contradictory.

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

DESCRIPTION OF SYMBOLS 1 information processing system 10 user terminal 20 store terminal 100 information processing apparatus 121 content information storage unit 122 content storage unit 123 weight information storage unit 131 entry unit 132 selection unit 133 extraction unit 134 addition unit 135 reception unit 136 search unit 137 distribution unit

Claims (12)

An extraction unit that extracts information on a product;
And an adding unit for adding information related to the product extracted by the extraction unit to the other product identified by the identifier for identifying the product as information to be compared with the search query at the time of the search processing. Information processing apparatus characterized by the above. The giving unit
When the amount of information given to the other item as information to be matched with the search query at the time of search processing by the seller of the other item falls below a predetermined threshold value, the extraction unit The information processing apparatus according to claim 1, wherein the information on the extracted product is added as information to be compared with the search query at the time of search processing. The giving unit
When the information given to the other product as information to be compared with the search query by the seller of the other product is only the product title of the other product, the information for the other product may be The information processing apparatus according to claim 1, wherein the information on the product extracted by the extraction unit is added as information to be compared with the search query at the time of search processing. The giving unit
It is different from the item for classifying the information given to the other goods by the seller of the other goods among the items for classifying the information given to the other goods as the information to be collated with the search query at the time of the search processing. The information processing apparatus according to any one of claims 1 to 3, wherein information on the product extracted by the extraction unit is added to an item. The information processing apparatus according to any one of claims 1 to 4, further comprising: a search unit that performs a search process based on the weight added to the information to be compared with the search query at the time of the search process. The search unit is
The search processing is performed based on a weight to which a different weight is added according to an item for classifying information attached to the other product as information to be matched with a search query at the time of search processing. Information processing equipment. The search unit is
The weight to which a smaller weight is added to the item for classifying the information given to the other goods by the giving unit than the item for classifying the information given to the other goods by the seller of the other goods The information processing apparatus according to claim 5, wherein a search process is performed based on the information. The search unit is
Of the product title and the product description, which are items for classifying the information given to the other product by the seller of the other product, based on the weight by which a greater weight is added to the product title than the product description. The information processing apparatus according to any one of claims 5 to 7, wherein a search process is performed. The search unit is
The search processing is performed based on a weight by which a maximum weight is added to a product title, which is an item for classifying information provided to the other product by the seller of the other product. The information processing apparatus according to any one of 8. The distribution unit according to any one of claims 1 to 9, further comprising: a distribution unit that distributes information other than the information provided to the other product by the giving unit as a search result related to the other product. Information processing device. An information processing method executed by a computer,
An extraction step of extracting information on the product;
And adding the information related to the product extracted by the extraction step to the other product identified by the identifier for identifying the product as information to be compared with the search query at the time of the search process. Characteristic information processing method. An extraction procedure for extracting information about a product;
An assignment procedure for assigning information on the commodity extracted by the extraction procedure to information on the other commodity identified by the identifier for identifying the commodity as information to be compared with the search query at the time of the search processing An information processing program characterized by causing it to

Images