JP6913596B2 - Information processing equipment, information processing methods and information processing programs - Google Patents

Description

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

Sites that display a plurality of contents related to products, such as product search sites, are known. In such sites, multiple contents may be ranked.

Japanese Unexamined Patent Publication No. 2012-203821

Content ranking is based on various factors. However, the ranking may not always be appropriate.

The present application has been made in view of the above, and an object of the present application is to provide an information processing device, an information processing method, and an information processing program capable of appropriately ranking.

The information processing apparatus according to the present application has a display order in which a plurality of contents are displayed, and the display order based on the first index value is changed based on the second index value related to the content, which is different from the first index value related to the content. The determination unit determines the order as the display order of the plurality of contents, and the determination is made when there is a content in which the first index value and the second index value satisfy a predetermined condition among the plurality of contents. It is characterized by having a changing part for changing the display order determined by the part.

According to one aspect of the embodiment, there is an effect that appropriate ranking can be performed.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the information processing device 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 showing an example of information processing according to the embodiment. FIG. 6 is a flowchart showing an information processing procedure according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, the information processing apparatus, the information processing method, and the mode for carrying out the information processing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. An 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 showing an example of information processing according to an embodiment. The information processing device 100 shown in FIG. 1 is a server device that provides a search service for products and the like. In FIG. 1, the information processing apparatus 100 has a plurality of information processing devices 100 based on the degree of relevance between a phrase related to product content, which is a first index value related to content related to a product or service (hereinafter, referred to as “product content”), and a search query. Calculate the score related to the display order, which is the order in which the product content is displayed as the search result. The information processing device 100 has a score regarding the display order, which is the order in which a plurality of product contents are displayed as search results, based on a plurality of index values related to the product contents, in addition to the degree of relevance between the words and phrases related to the product contents and the search query. Is calculated (step S1).

The information processing device 100 has a click rate (CTR: Click), which is a probability that the user selects the product content, for example, as a plurality of index values related to the product content, in addition to the degree of relevance between the phrase related to the product content and the search query. Corresponds to Through Rate (CVR), which is the probability that the user will take an action that is beneficial to the seller, such as purchasing a product or service or requesting materials, following the action of selecting the product content, and the product content. A score related to the display order, which is the order in which a plurality of product contents are displayed as search results, is calculated based on the price of the product or service to be used, the number of page views (PV: Page View) based on the actual results of the product contents, and the like.

In the example shown in the upper part of FIG. 1, when the information processing apparatus 100 receives the search queries "Polo shirt" and "3 sheets set", the words and phrases related to the product content and the search queries "Polo shirt" and "3 sheets set" are used. Calculate the degree of relevance. In the example shown in the upper part of FIG. 1, the information processing apparatus 100 has a product content C1 relevance degree of 85, a product content C2 relevance degree of 96, a product content C3 relevance degree of 90, and a product content C4 relevance degree of 70. , The relevance degree of the product content C5 is 50, the relevance degree of the product content C6 is 5, the relevance degree of the product content C7 is 1, and so on.

Subsequently, the information processing apparatus 100 calculates a score regarding the display order of the plurality of product contents based on the index values related to the plurality of product contents including the degree of relevance between the words and phrases related to the product contents and the search query. In the example shown in the upper part of FIG. 1, the information processing apparatus 100 has a score of product content C1 of 100, a score of product content C2 of 90, a score of product content C3 of 80, a score of product content C4 of 70, and a score of product content C5. The score of the product content C6 is 60, the score of the product content C6 is 50, the score of the product content C7 is 40, and so on.

Specifically, the information processing apparatus 100 uses a plurality of index values as feature quantities and calculates a score using a model in which the weights of each index value are learned. For example, the information processing apparatus 100 calculates a higher score as the degree of relevance between a phrase related to product content and a search query is greater. Further, the information processing apparatus 100 processes other index values in the same manner. For example, the information processing device 100 calculates a higher score as the click rate, which is the probability that the product content is selected by the user, is higher. Further, the information processing device 100 calculates a higher score as the conversion rate, which is the probability that the user takes an action of purchasing a product or the like following the action of selecting a product content, is higher.

Subsequently, the information processing apparatus 100 corrects the score regarding the display order of the plurality of product contents based on the sales promotion ratio which is the ratio of the sales promotion cost to the price of the product or service which is the second index value regarding the product content. The information processing device 100 corrects the score so that the higher the sales promotion ratio, the higher the score. Then, the information processing apparatus 100 determines the display order of the plurality of product contents based on the corrected score (hereinafter, referred to as “corrected score”) (step S2).

In the example shown in the middle of FIG. 1, the information processing apparatus 100 sets the score 100 of the product content C1 to the correction score 10 based on the sales promotion ratio 0.1 and the score 90 of the product content C2 based on the sales promotion ratio 0.4. In the correction score 36, the score 80 of the product content C3 is set to the correction score 8 based on the promotion ratio 0.1, the score 70 of the product content C4 is set to the correction score 3.5 based on the promotion ratio 0.05, and the sales promotion ratio is 0. The score 60 of the product content C5 is corrected to 1.8 based on .03, the score 50 of the product content C6 is corrected to 17.5 based on the promotion ratio of 0.35, and the product is based on the promotion ratio of 0.5. The score 40 of the content C7 is corrected to the correction score 20, and so on.

Then, in the information processing device 100, the product content C2 is ranked first, the product content C7 is ranked second, the product content C6 is ranked third, the product content C1 is ranked fourth, and the product content C3 is ranked fifth in order from the content having the largest correction score. , Product content C4 is ranked 6th, Product content C5 is ranked 7th, and so on, and the display order of a plurality of product contents is determined.

Here, the plurality of product contents are displayed as search results in the search result contents. The search result content refers to content that displays a plurality of product contents as search results, and refers to content that displays a plurality of product contents in a display order determined by the information processing apparatus 100. Specifically, the search result content is content for a web page or an application. In the following, the search result content displayed on the initial screen will be referred to as the first search result content. The first search result content SR1 includes five product contents whose display order is determined by the information processing apparatus 100 from the first to the fifth. Then, as a result of switching the display screen by the user's operation, the search result content displayed on the next display screen includes five product contents whose display order determined by the information processing device 100 is from 6th to 10th. included. Further, as a result of switching the display screen by the user's operation, the search result contents displayed on the next and subsequent display screens include 5 product contents whose display order is 11th or lower as determined by the information processing device 100. Included one by one.

Subsequently, the information processing apparatus 100 has a sales promotion ratio in which the degree of relevance between the phrase related to the product content and the search query is an outlier among the plurality of product contents, and is the ratio of the sales promotion cost to the price of the product or service. When there is product content exceeding a predetermined threshold (hereinafter, referred to as “out-of-order content”), the display order of a plurality of product contents is changed so that the product content is not displayed in the first search result content SR1 (step S3). The outlier refers to a value that greatly deviates from other observed values in the distribution of data. For example, suppose there are 100 pieces of data that can take numbers from 0 to 100. Then, it is assumed that the numerical values of 99 data out of 100 data are distributed between 80 and 90, and only the numerical value of the remaining 1 data is 1. In this case, in the distribution of 100 data, the numerical value of the remaining 1 data is an outlier because it greatly deviates from the other 99 observed values.

In the example shown in the lower part of FIG. 1, the degree of relevance of the product content C6 and the other product contents other than the product content C7 is distributed between 50 and 96, whereas the degree of relevance between the product content C6 (relevance degree 5) and the product is distributed. The relevance degree of the content C7 (relevance degree 1) is smaller than the relevance degree of other product contents. Therefore, the information processing device 100 has the product content C6 and the product content C7 as the product content whose relevance is out of the plurality of product contents among the five product contents displayed in the first search result content SR1. Is detected.

Further, assuming that the predetermined threshold value is 0.35, the sales promotion ratios of the product content C2 (promotion ratio 0.4), the product content C6 (promotion ratio 0.35) and the product content C7 (promotion ratio 0.5) are predetermined. It exceeds the threshold value of 0.35. Therefore, the information processing device 100 detects the product content C2, the product content C6, and the product content C7 as the product content whose sales promotion ratio exceeds a predetermined threshold among the five product contents displayed in the first search result content SR1. do.

Subsequently, the information processing device 100 determines that the product content C2 does not satisfy the condition of the outlier content because the sales promotion ratio exceeds a predetermined threshold value but the relevance is not an outlier among the plurality of product contents. do. On the other hand, in the information processing device 100, with respect to the product content C6 and the product content C7, the degree of relevance is an outlier among the plurality of product contents, and the sales promotion ratio exceeds a predetermined threshold value. It is determined that the condition is satisfied. Therefore, the information processing device 100 detects the product content C6 and the product content C7 as out-of-order contents.

Subsequently, the information processing apparatus 100 lowers the display order of the product content C7 from the second place to the sixth place so that the product content C7, which is the out-of-order content, is not displayed in the first search result content SR1. Further, the information processing apparatus 100 lowers the display order of the product content C6 from the third place to the seventh place so that the product content C6, which is the out-of-order content, is not displayed in the first search result content SR1.

In the information processing apparatus 100, instead of lowering the display order of the product content C7 and the product content C6, the display order of the product content C3 is changed from 5th to 3rd, and the display order of the product content C4 is changed from 6th to 4th. In addition, the display order of the product content C5 is moved up from the 7th place to the 5th place.

Here, the information processing apparatus 100 may check again that the product content that moves up the ranking does not satisfy the condition of the content. For example, since the product content C3 has a relevance degree of 90, the relevance degree is not an outlier. Since the sales promotion ratio of the product content C3 is 0.1, the sales promotion ratio is lower than the predetermined threshold value of 0.35. Therefore, the information processing device 100 determines that the product content C3 is not the out-of-content content because it does not satisfy the condition of the out-of-content. Then, the information processing device 100 raises the order of the product content C3. Similarly, the information processing device 100 is disengaged because the product content C4 (relevance degree 70, sales promotion ratio 0.05) and the product content C5 (relevance degree 50, sales promotion ratio 0.03) do not satisfy the conditions of the disengaged content. Judge that it is not content. Then, the information processing device 100 raises the order of the product content C4 and the product content C5.

As described above, the information processing apparatus 100 searches for a plurality of product contents based on the index values related to the plurality of product contents including the degree of relevance between the words and phrases related to the product contents, which is the first index value related to the product contents, and the search query. Calculate the score for the display order, which is the order in which they are displayed as a result. As a result, the information processing apparatus 100 can rank the product contents in the order in which the user can easily purchase the product while matching the search intention of the user.

Further, the information processing device 100 is calculated based on a sales promotion ratio which is an index value different from the first index value and indicates the ratio of the sales promotion cost to the price of the product or service which is the second index value related to the product content. Correct the score. Thereby, the information processing apparatus 100 can rank the product contents so as to reflect the sales efforts of the seller of the product or service.

Then, in the information processing apparatus 100, the degree of relevance between the phrase related to the product content, which is the first index value, and the search query is an outlier among the plurality of product contents, and the product or service, which is the second index value, has a degree of relevance. When there is content whose sales promotion ratio indicating the ratio of sales promotion cost to the price exceeds a predetermined threshold, the display order of a plurality of product contents is changed so that the content is not displayed in the first search result content SR1. As a result, the information processing apparatus 100 can lower the display order of the product content that has risen to the top of the search result due to the high sales promotion ratio even though it does not match the user's search intention. Therefore, the information processing device 100 can be displayed in the display order desired by the user.

Further, the information processing device 100 can prevent the product content having an extremely low relevance to the search query from being displayed in the first search result content. That is, the information processing device 100 can prevent the product content that greatly deviates from the user's search intention from being first seen by the user as a search result. Therefore, the information processing device 100 can be displayed in the display order desired by the user.

Further, in the information processing device 100, since the sales promotion ratio is high, the product content that has been added to the search result of the product unrelated to the product sold by the seller against the intention of the seller is displayed as the first search result. Can be prevented. That is, the information processing device 100 can prevent the product content from being displayed as a search result of an irrelevant product, contrary to the seller's sales intention. As a result, the information processing apparatus 100 can be displayed in the order desired by the seller.

Further, the information processing apparatus 100 displays other product contents at a higher level instead of the product contents that greatly deviate from the user's search intention. As a result, the information processing apparatus 100 can make the user see the product content that matches the user's search intention and that the user can easily purchase the product. Further, the information processing apparatus 100 displays other product contents at a higher level instead of the product contents that greatly deviate from the seller's sales intention. As a result, the information processing apparatus 100 can display the product content that matches the seller's sales intention at the top as the product search result. Therefore, the information processing apparatus 100 can be displayed in the display order desired by the user and in the display order desired by the seller. That is, the information processing apparatus 100 can perform appropriate ranking.

[2. Information processing system configuration]
Next, the configuration of the information processing system 1 including the information processing device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As illustrated in FIG. 2, the information processing system 1 according to the embodiment includes a user terminal 10, a store terminal 20, and an information processing device 100. These various devices are connected so as to be communicable by wire or wirelessly via a network N (for example, the Internet). The information processing system 1 shown in FIG. 2 may include a plurality of user terminals 10 and a plurality of store terminals 20.

The user terminal 10 is a terminal device used by the 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 the search query input to the search service for products and the like to the information processing device 100 according to the user's operation. The user terminal 10 displays the search result content delivered by the information processing device 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 application displays the search result content distributed by the information processing device 100 on the display screen of the user terminal 10. indicate. The application referred to here means, for example, a dedicated application for displaying search result contents distributed by a browser or an information processing device 100.

The store terminal 20 is a terminal device used by a seller of goods or services. For example, the store terminal 20 is a tablet terminal, a PC, a mobile phone, a PDA, or the like. Further, the store terminal 20 transmits the product content to the information processing apparatus 100 together with the sales promotion ratio indicating the ratio of the sales promotion cost to the price of the product or service and the text information regarding the product content according to the operation of the seller.

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

The information processing device 100 is a server device that performs information processing described with reference to FIG. The information processing device 100 is a server device that receives listings of a plurality of products from a plurality of stores and provides a shopping service for selling the products via the Internet. Here, the shopping service provided by the information processing device 100 is a shopping mall type service that handles products exhibited from a plurality of different stores. Further, the information processing device 100 is a server device that provides a search service for products and the like.

The information processing device 100 acquires the product content from the store terminal 20 together with the sales promotion ratio indicating the ratio of the sales promotion cost to the price of the product or service and the text information regarding the product content. When the information processing device 100 acquires the product content together with the sales promotion ratio and the text information regarding the product content, the information processing device 100 collects log data of various users regarding the acquired product content. Then, the information processing device 100 calculates various index values related to the product content based on the collected log data of various users.

The information processing device 100 receives a search query from the user terminal 10. When the information processing device 100 receives the search query, the information processing device 100 determines the display order of the plurality of product contents based on the calculated index value. Further, the information processing apparatus 100 changes the display order of the plurality of product contents when the out-of-order contents exist. Then, the information processing device 100 delivers the search result content in which a plurality of product contents are displayed in the determined display order or, if there is the out-of-order content, in the changed display order to the user terminal 10.

[3. Information processing device configuration]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing device 100 according to the embodiment. As shown in FIG. 3, the information processing device 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 NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and transmits / receives information to / from, for example, the user terminal 10 and the store terminal 20.

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

(Content information storage unit 121)
The content information storage unit 121 stores various information related to the product content received from the store terminal 20. FIG. 4 shows an example of the content information storage unit 121 according to the embodiment. In the example shown in FIG. 4, the content information storage unit 121 has items such as "content ID", "product name", "product description", "CTR", "CVR", "price", and "number of PVs". In addition to the items 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 which is the transmission source of the product content.

The "content ID" indicates identification information for identifying the product content received from the store terminal 20.

The "product name" indicates the name of the product or service corresponding to the product content. The product name is the most commonly used phrase as a search query entered when a user searches for a product or the like. In the example shown in FIG. 4, the product name 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 product description is information provided by the store so that the user can use it as a clue when considering the purchase of the product or the like. Therefore, the product description often includes words and phrases that match the search query that the user inputs when searching for the product or the like. For example, the product description includes words and phrases such as categories of products and features of products and the like. In the example shown in FIG. 4, the product description of the product corresponding to the product content identified by the content ID "C1" is "short sleeve, men's".

“CTR” indicates the click rate, which is the probability that the user selects the product content. The click rate is calculated by dividing the number of times the product content is selected (the number of clicks) by the number of times the product content is displayed (the number of impressions). In the example shown in FIG. 4, the CTR of the product content identified by the content ID "C1" is "0.2".

“CVR” indicates the conversion rate, which is the probability that the user takes an action that is profitable for the seller, such as purchasing a product or service or requesting materials, following the action of selecting the product content. For the conversion rate, the number of actions (conversions) that lead to profitable actions for the seller, such as purchasing a product or service or requesting materials, following the action of the user selecting the product content, has been selected so far. It is calculated by dividing by the number of times. In the example shown in FIG. 4, the CVR of the product content identified by the content ID "C1" is "0.2".

"Price" indicates the selling price of a product or service corresponding to the product content. In the example shown in FIG. 4, the price of the product corresponding to the product content identified by the content ID "C1" is "3000" (yen).

The “PV number” indicates the number of page views, which is the total number of times the product content has been viewed. In the example shown in FIG. 4, the number of PVs of the product content identified by the content ID "C1" is "10000".

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

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). It is realized by executing various programs (corresponding to an example of a generation program) using the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

Further, the control unit 130 sets each element belonging to each layer other than the output layer as the first element with respect to the index value related to the predetermined product content input to the input layer by information processing according to the product content model described later. Whether or not the predetermined product content is selected by the user by performing the calculation based on the first element and the weight of the first element, and whether or not the product or the like is purchased following the action selected by the user. Make the computer function to output the score regarding whether or not from the output layer.

As shown in FIG. 3, the control unit 130 includes a submission unit 131, a reception unit 132, a selection unit 133, a determination unit 134 having a calculation unit 134A and a correction unit 134B, a change unit 135, and a distribution unit. It has 136 and realizes or executes the action of information processing described below. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it is a configuration for performing information processing described later.

(Drafting Department 131)
The trafficking unit 131 accepts trafficking of product contents. Specifically, the trafficking unit 131 receives the trafficking of the product content from the store terminal 20 together with the sales promotion ratio indicating the ratio of the sales promotion cost to the price of the product or service and the text information regarding the product content. Here, the text information about the product content refers to the character information included in the product name and the product description displayed together with the product content when the product content is displayed as a search result. For example, the submission unit 131 accepts submissions of product contents from a plurality of store terminals wishing to open a store in the shopping service provided by the information processing device 100, and acquires a plurality of product contents. When the trafficking unit 131 receives the trafficking of the product content, the trafficking unit 131 extracts words and phrases related to the product content from the text information related to the product content and stores them in the content information storage unit 121. In addition, the trafficking unit 131 stores the product content in the content storage unit 122.

In the example shown in the first record of FIG. 4, when the trafficking unit 131 accepts the trafficking of the product content C1, the words such as "polo shirt", "short sleeve", and "men's" are used as the words related to the product content C1. Extract from the text information about C1. Subsequently, the trafficking unit 131 stores the extracted word "polo shirt" in the item of the product name of the content information storage unit 121. In addition, the trafficking unit 131 stores the extracted words "short sleeve" and "men's" in the item of the product description of the content information storage unit 121.

The trafficking unit 131 uses weight values such as tf-idf (Term Frequency, Inverse Document Frequency) to extract words and phrases related to the product content from the text information related to the product content received from the store terminal 20. You may. For example, the trafficking unit 131 may not extract a word that is widely used and is determined not to be useful for searching the product content as a phrase related to the product content. For example, the trafficking unit 131 uses a weight value such as tf-idf to extract words extracted as words and phrases related to the product content according to the weight of each word, and each of the content information storage units 121 such as the product name and the product description. It may be classified into items.

(Reception Department 132)
The reception unit 132 receives a search query from the user terminal 10. Specifically, the reception unit 132 provides the user terminal 10 with a search query input screen. Then, the reception unit 132 receives the search query input to the provided input screen from the user terminal 10. For example, the reception unit 132 receives the search queries "polo shirt" and "three-sheet set" input by the user who uses the shopping service provided by the information processing device 100 from the user terminal 10. Further, the reception unit 132 receives a search result acquisition request for the search query from the user terminal 10 together with the search query. For example, the reception unit 132 receives a search result acquisition request for the search queries "polo shirt" and "three-sheet set" input by the user who uses the shopping service provided by the information processing device 100 from the user terminal 10.

(Selection unit 133)
The selection unit 133 selects a predetermined number of product contents based on the degree of relevance between the phrase related to the product content, which is the first index value related to the product content, and the search query.

Specifically, when the reception unit 132 receives the search query, the selection unit 133 refers to the content information storage unit 121, and the degree of relevance between the word and phrase related to the product content acquired by the submission unit 131 and the search query. Is calculated. For example, when the reception unit 132 receives the search queries "polo shirt" and "three-sheet set", the selection unit 133 refers to the first record of the content information storage unit 121 and stores it in the product name. Words such as "polo shirt" and "short sleeves" and "men's" stored in the product description are extracted as words and phrases related to the product content C1. Next, the selection unit 133 has a higher degree of relevance as the degree of matching between the words "polo shirt", "short sleeve", and "men's" extracted as words and phrases related to the product content C1 and the search query "polo shirt" and "set of 3" is higher. The degree of relevance between the phrase related to the product content C1 and the search query is calculated so as to be high.

In the example shown in the upper part of FIG. 1, when the reception unit 132 receives the search queries "Polo shirt" and "3 sheets set", the selection unit 133 determines the degree of relevance between the words and phrases related to the product content and the search query. The relevance of C1 is 85, the relevance of product content C2 is 96, the relevance of product content C3 is 90, the relevance of product content C4 is 70, the relevance of product content C5 is 50, and the relevance of product content C6 is 50. 5. The degree of relevance of the product content C7 is calculated as 1, ...

Subsequently, the selection unit 133 selects the product contents from the first place to the predetermined order in order from the one having the highest degree of relevance between the calculated words and phrases related to the product contents and the search query. Specifically, the selection unit 133 ranks the product contents acquired by the trafficking unit 131 in order from the one with the highest relevance, based on the calculated relevance between the words and phrases related to the product content and the search query. Then, the selection unit 133 selects, for example, 1000 product contents whose ranked order is from 1st to 1000th.

(Decision unit 134)
The determination unit 134 determines the display order of the plurality of product contents selected by the selection unit 133. Specifically, the determination unit 134 sets the second index value for the product content, which is the display order of the plurality of product contents and is different from the relevance between the word and the search query, which is the first index value for the product content. Based on the sales promotion ratio indicating the ratio of the sales promotion cost to the price of the product or service, the display order in which the display order based on the first index value is changed is determined as the display order of the plurality of product contents.

For example, the determination unit 134 is a product that is the first index value based on the sales promotion ratio that indicates the ratio of the sales promotion cost to the price of the product or service that is the second index value in the display order of the plurality of product contents. The display order in which the display order is changed based on the degree of relevance between the word related to the content and the search query and other index values different from both the first index value and the second index value is determined as the display order of multiple product contents. do. For example, the determination unit 134 sets the display order of the plurality of product contents selected by the selection unit 133, and the product content calculated by the selection unit 133 and the search query based on the sales promotion ratio acquired by the submission unit 131. The display order is based on the degree of relevance and other index values that differ from both the degree of relevance and the promotion ratio, such as click rate, conversion rate, price of the product or service, and the number of page views based on actual results. The changed display order is determined as the display order of a plurality of contents.

The determination unit 134 has a calculation unit 134A and a correction unit 134B, and determines the display order of a plurality of product contents, and the display order based on the score corrected by the correction unit 134B is determined as the display order of the plurality of product contents. do.

(Calculation unit 134A)
The calculation unit 134A calculates a score regarding the display order of a plurality of product contents based on the degree of relevance between the phrase related to the product content, which is the first index value, and the search query. The calculation unit 134A calculates the scores related to the display order of the plurality of product contents based on the plurality of index values related to the product contents in addition to the first index value. Specifically, the calculation unit 134A has a plurality of product contents selected by the selection unit 133 based on a plurality of index values related to the product content in addition to the degree of relevance between the product content selected by the selection unit 133 and the search query. Calculate the score for the display order of.

First, first, the calculation unit 134A has a plurality of index values related to the product content in addition to the degree of relevance between the product content and the search query, based on the information of the user who uses the shopping service provided by the information processing device 100. The click rate, which is the probability that the user selects the product content, and the conversion rate, which is the probability that the user takes an action that is beneficial to the seller, such as purchasing a product or service or requesting materials, following the action of selecting the product content. , Calculate the number of page views, etc. based on the actual results of the product content.

Next, secondly, the calculation unit 134A generates a product content model (product content model) based on various index values related to the calculated product content. Specifically, the calculation unit 134A calculates a higher score for product content that has a higher probability of being selected by the user and has a higher probability of taking an action of purchasing a product or the like following the action of the user selecting the product content. Generate a product content model that has been trained to be. For example, the calculation unit 134A uses a plurality of index values as feature quantities and generates a product content model in which the weights of each index value are learned. For example, the calculation unit 134A generates a product content model learned to calculate a higher score as the degree of relevance between the product content and the search query is greater. In addition, the calculation unit 134A generates a product content model learned to process other index values in the same manner. For example, the calculation unit 134A generates a product content model learned to calculate a higher score as the click rate, which is the probability that the product content is selected by the user, is higher. Further, the calculation unit 134A generates a product content model learned to calculate a higher score as the conversion rate is higher, which is the probability that the user takes an action of purchasing a product or the like following the action of selecting the product content.

Next, the calculation unit 134A calculates the score of each product content using the generated product content model. In the example shown in the upper part of FIG. 1, the calculation unit 134A sets the score of the product content C1 to 100 and the score of the product content C2 based on the index values related to a plurality of product contents including the degree of relevance between the product content and the search query. 90, the score of the product content C3 is 80, the score of the product content C4 is 70, the score of the product content C5 is 60, the score of the product content C6 is 50, the score of the product content C7 is 40, and so on. ..

Next, fourth, the calculation unit 134A uses the calculated score as a score related to the display order of the plurality of product contents.

The calculation unit 134A may generate a product content model using any learning algorithm. For example, the calculation unit 134A generates a product content model using learning algorithms such as a neural network, a support vector machine, clustering, and reinforcement learning. As an example, when the calculation unit 134A uses a neural network to generate a product content model, the product content model includes an input layer containing one or more neurons, an intermediate layer containing one or more neurons, and one or more neurons. It has an output layer including.

(Correction unit 134B)
The correction unit 134B corrects the score calculated by the calculation unit 134A based on the sales promotion ratio, which is the ratio of the sales promotion cost to the price of the product or service, which is the second index value. Specifically, the correction unit 134B corrects the score so that the higher the sales promotion ratio, the higher the score. For example, the correction unit 134B corrects the score calculated by the calculation unit 134A by multiplying the score of each product content calculated by the calculation unit 134A by a numerical value proportional to the sales promotion ratio of each product content acquired by the submission unit 131. do.

In the example shown in the middle of FIG. 1, the correction unit 134B corrects the score 100 of the product content C1 to the correction score 10 based on the sales promotion ratio 0.1, and corrects the score 90 of the product content C2 based on the sales promotion ratio 0.4. The score 36, the score 80 of the product content C3 based on the sales promotion ratio 0.1 is corrected to the score 8, the score 70 of the product content C4 is corrected to the correction score 3.5 based on the sales promotion ratio 0.05, and the sales promotion ratio is 0. The score 60 of the product content C5 is corrected to 1.8 based on 03, the score 50 of the product content C6 is corrected to 17.5 based on the sales promotion ratio of 0.35, and the product content is based on the sales promotion ratio of 0.5. The score 40 of C7 is corrected to the correction score 20, and so on.

Then, the determination unit 134 determines the display order based on the score corrected by the correction unit 134B as the display order of the plurality of product contents. In the example shown in the middle of FIG. 1, the determination unit 134 places the product content C2 in the first place, the product content C7 in the second place, the product content C6 in the third place, and the product content C1 in the fourth place in order from the content having the largest correction score. The display order of a plurality of product contents is determined, such as product content C3 in 5th place, product content C4 in 6th place, product content C5 in 7th place, and so on.

(Change 135)
The change unit 135 changes the display order of the determined plurality of product contents. Specifically, the change unit 135 describes the degree of relevance between the phrase related to the product content, which is the first index value, and the search query, and the sales promotion cost for the price of the product or service, which is the second index value, among the plurality of product contents. When there is product content whose sales promotion ratio indicating the ratio of the above satisfies a predetermined condition, the display order determined by the determination unit 134 is changed.

Specifically, in the change unit 135, among the plurality of product contents, the degree of relevance between the phrase related to the product content, which is the first index value, and the search query is an outlier among the plurality of product contents, and the first index value. 2 Change the display order of a plurality of product contents determined by the determination unit 134 when there is product content in which the sales promotion ratio indicating the ratio of the sales promotion cost to the price of the product or service which is the index value exceeds a predetermined threshold. do. For example, the changing unit 135 detects outliers in which the first index value is an outlier among the plurality of product contents and the second index value exceeds a predetermined threshold value among the plurality of product contents. Subsequently, the changing unit 135 changes the display order determined by the determining unit 134 by lowering the display order of the detected out-of-order content and raising the display order of the other product content.

Here, the outlier refers to a value that greatly deviates from other observed values in the distribution of data. For example, the changing unit 135 detects a product content whose first index value is an outlier among a plurality of product contents, with 1.5 times the interquartile range (IQR) as the upper and lower limits. Then, the change unit 135 sets "first interquartile range-1.5 x IQR" as the lower limit of the first index value and "third interquartile range + 1.5 x IQR" as the upper limit of the first index value. , The product content whose first index value is smaller than the lower limit and the product content whose first index value is larger than the upper limit are detected as product contents whose first index value is an outlier among a plurality of product contents. In general, it is rare that the first index value, which is the degree of relevance between a phrase related to product content and a search query, deviates significantly from the upper limit. Therefore, the change unit 135 may detect only the product content whose first index value is smaller than the lower limit as the out-of-order content.

The interquartile range (IQR) is one of the scales indicating the degree of data dispersion in the data distribution. The interquartile range (IQR) is determined as "third interquartile range (75th percentile) -1st interquartile range (25th percentile)". Here, the third quartile is a number that is 75% of the data counted from the beginning when the data are arranged in ascending order. The first quartile is a number that is 25% of the data counted from the beginning when the data are arranged in ascending order.

In the example shown in the lower part of FIG. 1, the change unit 135 sets "first interquartile range-1.5 x IQR" as the lower limit of the first index value and "third interquartile range + 1.5 x IQR". As the upper limit of the first index value, product content C6 (relevance degree 5) and product content C7 (relevance degree 1) are the first as product content whose first index value is smaller than the lower limit and product content whose first index value is larger than the upper limit. 1 Detect as product content whose index value is an outlier among a plurality of product contents. In addition, the change unit 135 sets "first quartile -1.5 x IQR" as the lower limit of the first index value, and sets the first index value as the product content smaller than the lower limit, and sets the product content C6 (relevance degree 5). And product content C7 (relevance degree 1) may be detected as product content whose first index value is an outlier among a plurality of product contents.

Further, when the predetermined threshold value is set to 0.35, the change unit 135 sets the product content C2 (sales promotion ratio 0.4) and the product content C6 (sales promotion ratio 0.35) as product contents whose sales promotion ratio exceeds the predetermined threshold value. And product content C7 (promotion ratio 0.5) is detected.

Subsequently, in the change unit 135, among the detected product contents, the product content C2 has a sales promotion ratio exceeding a predetermined threshold value, but the degree of relevance is not an outlier among the plurality of product contents. Is not satisfied. On the other hand, the change unit 135 satisfies the condition of the outlier content because the product content C6 and the product content C7 have an outlier value among the plurality of product contents and the sales promotion ratio exceeds a predetermined threshold value. Is determined. Therefore, the change unit 135 detects the product content C6 and the product content C7 as out-of-order contents.

Further, in the changing unit 135, among a plurality of search result contents in which a plurality of product contents are displayed in a display order based on the score corrected by the correction unit 134B, the first index value and the second index value are predetermined conditions. The display order of the plurality of product contents determined by the determination unit 134 is changed so that the product contents satisfying the conditions are displayed in the search result contents other than the first search result contents.

Specifically, the changing unit 135 detects outlier content in which the first index value is an outlier among the plurality of product contents and the second index value exceeds a predetermined threshold value among the plurality of product contents. do. Subsequently, the change unit 135 displays the detected out-of-order content in the display order based on the score corrected by the correction unit 134B, and if it exists within the display order displayed in the first search result content, the change unit 135 Lower the display order so that the display order of the out-of-order content is displayed in the search result content. Subsequently, the changing unit 135 changes the display order determined by the determining unit 134 by moving up the display order of the other product content instead of the out-of-order content whose order is lowered.

In the example shown in the lower part of FIG. 1, the change unit 135 lowers the display order of the product content C7 from the second place to the sixth place so that the product content C7 detected as the out-of-content content is not displayed in the first search result content SR1. Further, the change unit 135 lowers the display order of the product content C6 from the third place to the seventh place so that the product content C6, which is the out-of-order content, is not displayed in the first search result content SR1.

Subsequently, the change unit 135 lowers the display order of the product content C6 and the product content C7, but instead changes the display order of the product content C3 from 5th to 3rd and the display order of the product content C4 from 6th to 4th. In addition, the display order of the product content C5 is moved up from the 7th place to the 5th place.

(Distribution Department 136)
The distribution unit 136 distributes the search result content to the user terminal 10. Specifically, the distribution unit 136 distributes a plurality of search result contents in which a plurality of product contents are displayed in the display order determined by the determination unit 134 to the user terminal 10.

Here, an outline of a processing example of each of the above-mentioned processing units will be described with reference to FIG. FIG. 5 shows an example of information processing according to the embodiment. In the example shown in FIG. 5, the information processing apparatus 100 selects a predetermined number of product contents in order from the one having the highest degree of relevance between the product contents and the search query (step S11).

Subsequently, the information processing apparatus 100 calculates a score regarding the display order of the plurality of product contents based on the plurality of index values including the degree of relevance between the product contents and the search query (step S12).

Subsequently, the information processing apparatus 100 corrects the score based on the sales promotion ratio, and determines the display order of the plurality of product contents based on the corrected score (corrected score) (step S13).

Subsequently, the information processing apparatus 100 changes the display order so that the content is not displayed in the first search result content when there is an outlier content whose relevance is outlier and the sales promotion ratio exceeds a predetermined threshold value (step S14).

[4. Information processing flow]
Next, the procedure of information processing according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an information processing procedure according to the embodiment.

As shown in FIG. 6, the information processing apparatus 100 determines whether or not the search query has been received from the user terminal 10 (step S101). When the information processing apparatus 100 has not received the search query from the user terminal 10 (step S101; No), the information processing device 100 waits until the search query is received from the user terminal 10.

When the information processing apparatus 100 receives the search query from the user terminal 10 (step S101; Yes), the information processing apparatus 100 calculates the degree of relevance between the phrase related to the product content and the search query (step S102).

Subsequently, the information processing apparatus 100 selects a predetermined number of product contents in order from the one having the highest degree of relevance between the product contents and the search query (step S103).

Subsequently, the information processing apparatus 100 calculates a score regarding the display order of the plurality of product contents based on the plurality of index values including the degree of relevance between the product contents and the search query (step S104).

Subsequently, the information processing apparatus 100 corrects the score regarding the display order based on the sales promotion ratio (step S105).

Subsequently, the information processing apparatus 100 determines the display order of the plurality of product contents based on the corrected score (step S106).

Subsequently, the information processing apparatus 100 determines whether or not there is outlier content whose relevance is outlier and whose sales promotion ratio exceeds a predetermined threshold value (step S107). When the relevance value is outlier and there is no outlier content whose sales promotion ratio exceeds a predetermined threshold value (step S107; No), the information processing apparatus 100 delivers the search result content including the product content to the user terminal 10 (step). S109).

The information processing apparatus 100 changes the display order so that the outlier content is not displayed in the first search result content when there is outlier content whose relevance is outlier and the sales promotion ratio exceeds a predetermined threshold value (step S107; Yes). (Step S108).

Subsequently, the information processing device 100 distributes the search result content including the product content to the user terminal 10 (step S109).

[5. effect〕
As described above, the information processing apparatus 100 according to the embodiment has a determination unit 134 and a change unit 135. The determination unit 134 sets a display order in which the display order based on the first index value is changed based on the second index value related to the content different from the first index value related to the content, which is the display order of the plurality of contents. Is determined as the display order of. The changing unit 135 changes the display order determined by the determining unit 134 when there is content in which the first index value and the second index value satisfy a predetermined condition among the plurality of contents.

As a result, in the information processing apparatus 100 according to the embodiment, even if the display order based on the predetermined index value related to the content is changed based on the other index value, the display order is changed to an inappropriate display order. , If there is content in which the first index value and the second index value satisfy a predetermined condition, the display order can be changed. Therefore, the information processing apparatus 100 can perform appropriate ranking.

Further, the change unit 135 determines when, among the plurality of contents, the first index value is an outlier among the plurality of contents and the second index value exceeds a predetermined threshold value. The display order of the plurality of contents determined by 134 is changed.

As a result, in the information processing apparatus 100, even if the display order based on the predetermined index value related to the content is changed based on the other index value and the display order is changed to an inappropriate display order, the display order is changed. You can identify inappropriate content and change its display order. Therefore, the information processing apparatus 100 can perform appropriate ranking.

Further, the determination unit 134 is a calculation unit 134A that calculates a score related to the display order of a plurality of contents based on the first index value, and a correction unit 134B that corrects the score calculated by the calculation unit 134A based on the second index value. And, which is the display order of the plurality of contents, the display order based on the score corrected by the correction unit 134B is determined as the display order of the plurality of contents.

Thereby, the information processing apparatus 100 can objectively determine whether or not each content is desired by the user by using a numerical value called a score regarding the display order of the contents. As a result, the information processing device 100 can rank the contents in the order desired by the user. Therefore, the information processing apparatus 100 can perform appropriate ranking.

Further, in the changing unit 135, among the plurality of search result contents in which a plurality of contents are displayed in the display order based on the score corrected by the correction unit 134B, the first index value and the second index value satisfy predetermined conditions. The display order of the plurality of contents determined by the determination unit 134 is changed so that the satisfied contents are displayed in the search result contents other than the first search result contents.

As a result, the information processing apparatus 100 can display the content desired by the user in the first search result content by not displaying the content not desired by the user in the first search result content. As a result, the information processing device 100 can rank the contents in the order desired by the user. Therefore, the information processing apparatus 100 can perform appropriate ranking.

Further, the determination unit 134 sets the first index value and another index value different from both the first index value and the second index value based on the second index value in the display order of the plurality of contents. The display order in which the display order is changed is determined as the display order of a plurality of contents.

As a result, the information processing apparatus 100 can comprehensively determine whether or not each content is desired by the user by using the score calculated based on a plurality of index values related to the content. As a result, the information processing device 100 can rank the contents in the order desired by the user. Therefore, the information processing apparatus 100 can perform appropriate ranking.

In addition, the determination unit 134 has a display order of a plurality of contents, and as a first index value, a display order based on an index value indicating the degree of relevance between a phrase related to the content and a search query is set based on the second index value. The changed display order is determined as the display order of a plurality of contents. Further, the determination unit 134 sets the display order of the plurality of contents, and as the second index value, the display order in which the display order based on the first index value is changed based on the information related to the sales promotion of the product or service. Determined as the display order of multiple contents.

As a result, the information processing apparatus 100 can rank the product contents in the order in which the user can easily purchase the product while matching the search intention of the user. In addition, the information processing device 100 can rank the product contents so as to reflect the sales efforts of the seller of the product or service. Further, the information processing device 100 can prevent the product content having an extremely low relevance to the search query from being displayed in the first search result content. That is, the information processing device 100 can prevent the product content that greatly deviates from the user's search intention from being first seen by the user as a search result. As a result, the information processing apparatus 100 can be displayed in the display order desired by the user. Further, in the information processing device 100, since the sales promotion ratio is high, the product content that has been added to the search result of the product unrelated to the product sold by the seller against the intention of the seller is displayed as the first search result. Can be prevented. That is, the information processing device 100 can prevent the product content from being displayed as a search result of an irrelevant product, contrary to the seller's sales intention. As a result, the information processing apparatus 100 can be displayed in the order desired by the seller. Therefore, the information processing apparatus 100 can perform appropriate ranking.

Further, since the information processing device 100 displays other product contents at a higher level instead of the product contents that greatly deviate from the user's search intention, the product purchase or the like can be performed by the user while more matching the user's search intention. It is possible to make the product content that is easy to perform visible to the user. As a result, the information processing apparatus 100 can be displayed in the display order desired by the user. Further, since the information processing apparatus 100 displays other product contents at a higher level instead of the product contents that greatly deviate from the seller's sales intention, the product contents that more closely match the seller's sales intention are used as the product search result. It can be displayed at the top. As a result, the information processing apparatus 100 can be displayed in the order desired by the seller. Therefore, the information processing apparatus 100 can be displayed in the display order desired by the user and in the display order desired by the seller. That is, the information processing apparatus 100 can perform appropriate ranking.

[6. Hardware configuration]
Further, the information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 7. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has 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, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, 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 such a program, and the like. The communication interface 1500 receives data from another device via a predetermined communication network and sends it to the CPU 1100, and transmits the 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 the input device via the input / output interface 1600. Further, the CPU 1100 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 program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the 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. And so on.

For example, when the computer 1000 functions as the information processing device 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, so that the control unit 130 Realize the function. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, a product content model) from the recording medium 1800, but as another example, these programs or data from another device via a predetermined communication network. (For example, a product content model) may be acquired.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to practice the present invention in other improved forms.

[7. others〕
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed may be manually performed, or may be described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document 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 of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the changing unit can be read as a changing means or a changing circuit.

1 Information processing system 10 User terminal 20 Store terminal 100 Information processing device 121 Content information storage unit 122 Content storage unit 131 Submission unit 132 Reception unit 133 Selection unit 134 Decision unit 134A Calculation unit 134B Correction unit 135 Change unit 136 Distribution unit

Claims (8)

Display of the plurality of contents in a display order in which the display order based on the first index value is changed based on the second index value related to the content, which is different from the first index value related to the content. The decision section that decides in order, and
When the first index value is an outlier among the plurality of contents and the second index value exceeds a predetermined threshold value among the plurality of contents, the determination unit determines the content. An information processing device characterized by having a changing unit for changing the displayed display order. The decision unit
A calculation unit that calculates a score related to the display order of the plurality of contents based on the first index value, and a calculation unit.
It has a correction unit that corrects the score calculated by the calculation unit based on the second index value.
The information processing apparatus according to claim 1, wherein the display order of the plurality of contents is determined based on the score corrected by the correction unit as the display order of the plurality of contents. The changed part
Among the plurality of search result contents in which the plurality of contents are displayed in the display order based on the score corrected by the correction unit, the first index value is an outlier among the plurality of contents, and the said It is characterized in that the display order of a plurality of contents determined by the determination unit is changed so that the contents whose second index value exceeds a predetermined threshold are displayed in the search result contents other than the first search result contents. The information processing device according to claim 2. The decision unit
Display order of a plurality of contents, based on the second index value, and the display order based on the first index value and other index values different from both the first index value and the second index value. The information processing apparatus according to any one of claims 1 to 3, wherein the changed display order is determined as the display order of the plurality of contents. The decision unit
A display in which the display order of a plurality of contents is changed based on the index value indicating the degree of relevance between the phrase related to the content and the search query as the first index value based on the second index value. The information processing apparatus according to any one of claims 1 to 4, wherein the order is determined as a display order of the plurality of contents. The decision unit
In the display order of a plurality of contents, as the second index value, the display order in which the display order based on the first index value is changed based on the information on the sales promotion of the product or service is the display order of the plurality of contents. The information processing apparatus according to any one of claims 1 to 5, wherein the display order is determined. It is an information processing method executed by a computer.
Display of the plurality of contents in a display order in which the display order based on the first index value is changed based on the second index value related to the content, which is different from the first index value related to the content. The decision process to decide in order and
When the first index value is an outlier among the plurality of contents and the second index value exceeds a predetermined threshold value among the plurality of contents, the content is determined by the determination step. An information processing method including a change process for changing the displayed display order. Display of the plurality of contents in a display order in which the display order based on the first index value is changed based on the second index value related to the content, which is different from the first index value related to the content. The decision procedure to decide in order and
When the first index value is an outlier among the plurality of contents and the second index value exceeds a predetermined threshold value among the plurality of contents, the content is determined by the determination procedure. An information processing program characterized by having a computer execute a change procedure for changing the displayed order.

Images