JP7018905B2 - Grant device, grant method and grant program - Google Patents

Description

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

Conventionally, a technique for classifying transaction targets in an electronic market such as an EC (Electronic Commerce) site or an EC application has been proposed. For example, a technique for presenting an input screen for inputting a hash tag given to a transaction target in an electronic market has been proposed (Patent Document 1). In this technology, the user of the electronic market can attach an arbitrary hash tag to the transaction target in the electronic market via the presented input screen.

Japanese Unexamined Patent Publication No. 2018-136839

However, with the above-mentioned conventional technique, it is not always possible to give appropriate information to the transaction target. For example, in the above-mentioned prior art, the hashtag given to the transaction target by the user of the electronic market is not always appropriate information for this transaction target.

The present application has been made in view of the above, and an object of the present application is to provide a granting device, a granting method, and a granting program capable of granting appropriate information to a transaction target.

The granting device according to the present application is based on an estimation unit that estimates the similarity between a first transaction target in the electronic market and a second transaction target in the electronic market, and a similarity estimated by the estimation unit. It is characterized in that the information associated with the first transaction target is provided with a granting unit for imparting the information to the second transaction target.

According to one aspect of the embodiment, there is an effect that appropriate information can be given to the transaction target.

FIG. 1 is a diagram showing a configuration example of a network system according to an embodiment. FIG. 2 is a diagram showing an example of a grant process according to an embodiment. FIG. 3 is a diagram showing a configuration example of the granting device according to the embodiment. FIG. 4 is a diagram showing an example of a product information storage unit according to an embodiment. FIG. 5 is a flowchart showing a grant processing procedure by the grant device according to the embodiment. FIG. 6 is a diagram showing an example of a hardware configuration.

Hereinafter, the granting device, the granting method, and the embodiment for implementing the granting program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the granting device, granting method and granting program according to the present application. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description will be omitted.

[1. Network system configuration]
First, the configuration of the network system 1 according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing a configuration example of the network system 1 according to the embodiment. As shown in FIG. 1, the network system 1 according to the embodiment includes user devices 10 ₁ to 10 _n and granting devices 100 (n is an arbitrary natural number). In the present specification, when it is not necessary to distinguish between the user devices 10 ₁ to 10 _n , the user devices 10 ₁ to 10 _n are collectively referred to as "user device 10". The user device 10 and the granting device 100 are connected to the network N by wire or wirelessly, respectively. Although not shown in FIG. 1, the network system 1 may include a plurality of granting devices 100.

The user device 10 is an information processing device used by the user. The user device 10 may be any type of information processing device including a desktop PC (Personal Computer), a notebook PC, a smartphone, and a tablet PC.

The giving device 100 is an information processing device that provides various information to the user device 10. For example, the granting device 100 is a server device that provides various information to the user device 10. The granting device 100 provides, for example, the user device 10 with content related to the electronic market.

In one example, the granting device 100 provides the user device 10 with content related to the electronic market (for example, an EC site) via a browser. In another example, the granting device 100 provides the user device 10 with content about the electronic market via an application (eg, an EC application). The granting device 100 communicates with the user device 10 by wire or wirelessly via the network N.

[2. Grant process]
Next, an example of the granting process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing an example of a grant process according to an embodiment.

In the example of FIG. 2, the granting device 100 of FIG. 1 provides an electronic market in which the user of the user device 10 of FIG. 1 can purchase or sell a transaction object (eg, a commodity or service). For example, the granting device 100 provides the user device 10 with a service (not shown) related to an electronic shopping street such as an online shopping service. For example, the granting device 100 provides shopping content to the user device 10.

In the example of FIG. 2, the user of the user device 101 of FIG. ₁ is the seller of the store S1 in the electronic market provided by the granting device 100. Further, the user of the user apparatus 102 of _FIG . 1 is a seller of the store S2 in the electronic market provided by the granting apparatus 100.

In the example of FIG. 2, the granting device 100 receives the product information of the product M1 of the store S1 from the user device 10 ₂ . Further, the granting device 100 receives the product information of the product M2 of the store S2 from the user device ₁₀₂ .

The received product information includes information such as the store where the product is sold, the title of the product, the description of the product, the price of the product, the image of the product, and the tag of the product. Such product information is set by the seller of each store that sells each product.

The "product tag" included in the above-mentioned product information is used to search for the product associated with the tag. For example, when the tag "chocolate" is associated with a certain product, the granting device 100 presents a search result including this product in response to the search query "chocolate". In one example, the tag does not have to appear in the content about the electronic market. That is, the tag may be a metadata tag attached to the product. In another example, the tag may appear in content about the electronic market.

By the way, in the example of FIG. 2, five tags (that is, tag T1, tag T2, tag T3, tag T4, and tag T5) are associated with the product M1 of the store S1. That is, the seller of the store S1 attaches the keywords "ice I1", "chocolate", "company C1", "ice confectionery" and "summer" to the product M1 as tags.

On the other hand, in the example of FIG. 2, one tag (that is, the tag T1) is associated with the product M2 of the store S2. That is, the seller of the store S2 attaches only the keyword "ice I1" to the product M2 as a tag. However, when the product is not associated with a sufficient number of tags, such as the product M2 in FIG. 2, the product suitable for the user may not be searched with high accuracy.

Therefore, as an example, the granting device 100 executes the granting process described below in order to associate additional tags with products that are not associated with a sufficient number of tags. In an example of the granting process described below, when the first product is the same as or similar to the second product, the tag associated with the first product is assigned to the second product.

First, the granting device 100 calculates the product similarity indicating the similarity between the first product and the second product based on the product information of the first product and the product information of the second product. do.

More specifically, the granting device 100 identifies an image of the first product from the product information of the first product. Further, the granting device 100 identifies an image of the second product from the product information of the second product. Then, the granting device 100 has an image feature corresponding to the image of the specified first product (for example, BoVW (Bag of Visual Words)) and an image feature corresponding to the image of the specified second product. Based on the similarity between the image of the first product and the image of the second product (similarity calculated using a predetermined similarity function, such as similarity based on the inner product of BoVW). , Calculated as the degree of product similarity indicating the similarity between the first product and the second product.

The above-mentioned product similarity is, for example, the similarity between images of products, but is not limited to this. The above-mentioned product similarity may be the similarity between texts relating to the product.

For example, the granting device 100 may specify the first text regarding the title of the first product or the description of the first product from the product information of the first product. Further, the granting device 100 may specify a second text regarding the title of the second product or the description of the second product from the product information of the second product. Then, the granting device 100 is based on a text feature corresponding to the specified first text (for example, a Bow ((Bag of Words))) and a text feature corresponding to the specified second text. The similarity between the first text and the second text (for example, the similarity calculated using a predetermined similarity function such as the similarity based on the inner product of BoW) is determined by the first product and the second. It may be calculated as a product similarity indicating similarity with the product of.

Further, the above-mentioned product similarity may be the degree of similarity between numerical data related to the product.

For example, the granting device 100 may specify the price of the first product from the product information of the first product. Further, the granting device 100 may specify the price of the second product from the product information of the second product. Then, the granting device 100 uses the similarity based on the difference between the price of the first product and the price of the second product as the product similarity indicating the similarity between the first product and the second product. It may be calculated. Further, the granting device 100 includes an average selling price of a product belonging to the product category to which the first product belongs, an average selling price of a product belonging to the product category to which the second product belongs, a price of the first product, and a second product. A predetermined similarity function including the price of the first product may be used to calculate the product similarity indicating the similarity between the first product and the second product.

For illustration purposes, in the example of FIG. 2, it is assumed that the image of the product M2 is the same image as the image of the product M1. Further, it is assumed that the image feature corresponding to the image of the product M1 and the image feature corresponding to the image of the product M2 are normalized. In this example, the granting device 100 identifies an image of the product M1 (that is, an image of a popsicle) from the product information of the product M1. Further, the granting device 100 identifies an image of the product M2 (that is, an image of a stick ice cream) from the product information of the product M2. Then, the granting device 100 resembles the image of the product M1 and the image of the product M2 based on the image feature corresponding to the image of the specified product M1 and the image feature corresponding to the image of the specified product M2. The degree value "1" is calculated as a product similarity indicating the similarity between the product M1 and the product M2.

Next, the granting device 100 attaches the tag associated with the first product to the second product based on the calculated product similarity.

More specifically, the granting device 100 determines whether or not the calculated product similarity satisfies the granting condition for granting the tag associated with the first product to the second product. The granting device 100 sets a tag that is not associated with the second product among the tags associated with the first product according to the determination that the calculated product similarity satisfies the granting condition. It is given to 2 products. In other words, the granting device 100 is a tag associated with the first product but not associated with the second product according to the determination that the calculated product similarity satisfies the granting condition. Is associated with the second product. On the other hand, when it is determined that the calculated product similarity does not satisfy the granting condition, the granting device 100 does not grant the tag associated with the first product to the second product.

For illustration purposes, in the example of FIG. 2, the condition for attaching the tag associated with the first product to the second product is that the calculated product similarity is greater than 0.95. Suppose that In this example, the granting device 100 gives the second product a tag associated with the first product with a product similarity "1" indicating similarity between the product M1 and the product M2. It is determined that the condition is satisfied. The granting device 100 determines that the product similarity indicating the similarity between the product M1 and the product M2 satisfies the granting condition, and the five tags associated with the product M1 (that is, the tag T1, Of the tags T2, tag T3, tag T4, and tag T5), tags not associated with the product M2 (that is, tag T2, tag T3, tag T4, and tag T5) are attached to the product M2.

As shown in FIG. 2, when the four tags associated with the product M1 (that is, the tag T2, the tag T3, the tag T4, and the tag T5) are attached to the product M2, the attached four tags are attached. , Associated with the product M2 of the store S2.

As described above, the granting device 100 according to the embodiment attaches a tag associated with the first product to the second product when the first product is the same as or similar to the second product. .. As a result, the granting device 100 can reattach the tag associated with the product to another product that is the same as or similar to this product. Therefore, the granting device 100 can prevent a decrease in the accuracy of the product search due to a shortage of tags associated with the product. Hereinafter, the granting device 100 that realizes such a granting process will be described in detail.

[3. Configuration of granting device]
Next, a configuration example of the granting device 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the granting device 100 according to the embodiment. As shown in FIG. 3, the granting device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The granting device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from an administrator or the like who uses the granting device 100, and a display unit (liquid crystal display, etc.) for displaying various information. You may.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network network by wire or wirelessly, and transmits / receives information to / from the user device 10 via the network network.

(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 product information storage unit 121.

(Product information storage unit 121)
FIG. 4 is a diagram showing an example of the product information storage unit 121 according to the embodiment. The product information storage unit 121 stores the product information of the product, which is the product information posted on the electronic market. For example, the product information storage unit 121 stores the product information received by the reception unit 131. In the example of FIG. 4, "product information" is stored in the product information storage unit 121 for each "product ID". By way of example, "product information" includes items "store", "title", "description", "price", "image" and "tag".

The "product ID" indicates an identifier for identifying the product. "Store" indicates a store that sells products. "Title" indicates the title of the product. "Description" indicates a description of the product. "Price" indicates the price of a product. "Image" indicates an image of a product. "Tag" indicates a tag of a product.

For example, FIG. 4 shows that the store that sells the product identified by the product ID “M1” is the “store S1”. The store S1 corresponds to information such as an identifier for identifying a store in the electronic market and a store name of the store in the electronic market.

Further, for example, FIG. 4 shows that the title of the product identified by the product ID “M1” is “Ice I1 (chocolate) 30 company C1”. Company C1 corresponds to information such as the company name of the company that manufactures ice I1 and the brand that manufactures ice I1.

Further, for example, FIG. 4 shows that the description of the product identified by the product ID “M1” is “Explanation MD1”. Description MD1 includes, for example, information such as a name (that is, ice I1), a content, a raw material name, a best-by date, a storage method, and the like.

Further, for example, FIG. 4 shows that the image of the product identified by the product ID “M1” is “image MI1”. The image MI1 corresponds to, for example, an image of a bag of ice I1, a box of ice I1, and the like.

Further, for example, FIG. 4 shows that the tag of the product identified by the product ID “M1” is “ice I1, chocolate, company C1, ice cream, summer”. As mentioned above, the product tag is used to search for the product associated with the tag. For example, the providing unit 135 of the granting device 100 presents a search result including a product identified by the product ID “M1” in the content related to the electronic market in response to the search query “Ice I1”.

(Control unit 130)
The control unit 130 is a controller, and for example, various programs (of the grant program) stored in the storage device inside the grant device 100 by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). (Corresponding to one example) is realized by executing RAM or the like as a work area. Further, the control unit 130 is a controller, and may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes a reception unit 131, an acquisition unit 132, an estimation unit 133, an addition unit 134, and a provision unit 135, and has functions and operations of information processing described below. To realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it is configured to perform information processing described later.

(Receiver 131)
The receiving unit 131 receives the product information of the product, which is the product information posted on the electronic market. For example, the receiving unit 131 receives product information from a predetermined server device. The receiving unit 131 may receive the product information via the electronic market provided by the providing unit 135. The receiving unit 131 may store the received product information in the product information storage unit 121.

The receiving unit 131 may receive product information from the user of the granting device 100 via the user interface. The receiving unit 131 may store the received product information in the product information storage unit 121.

The receiving unit 131 may receive the product information from the user device 10 via the content provided by the providing unit 135 that enables posting of the product information. That is, the receiving unit 131 may receive the product information via the content that enables the posting of the product information.

In one example, the receiving unit 131 receives the product information of the product (for example, the product information of the product in the store), which is the product information posted on the electronic market, from the user device 10.

The receiving unit 131 receives the transmission request of the content related to the electronic market from the user device 10.

(Acquisition unit 132)
The acquisition unit 132 acquires the product information of the product, which is the product information posted on the electronic market. The acquisition unit 132 acquires, for example, the product information received by the reception unit 131. The acquisition unit 132 may acquire product information from a predetermined storage device. For example, the acquisition unit 132 may acquire product information from the product information storage unit 121. The acquisition unit 132 may store the acquired product information in the product information storage unit 121.

(Estimation unit 133)
The estimation unit 133 estimates the similarity between the first transaction target in the electronic market and the second transaction target in the electronic market.

For example, the estimation unit 133 determines the relationship between the information posted on the electronic market and related to the first transaction target and the information posted on the electronic market and related to the second transaction target. Based on this, the similarity between the first transaction target and the second transaction target is estimated.

Further, for example, the estimation unit 133 is an image included in the information regarding the first transaction target, and is an image included in the image of the first transaction target and the information regarding the second transaction target, and is the second image. The image of the transaction target is compared with the image of the transaction target, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

Further, for example, the estimation unit 133 is a text included in the information regarding the first transaction target, and is a text describing the explanation of the first transaction target and a text included in the information regarding the second transaction target. Then, the text describing the explanation of the second transaction target is compared, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

Further, for example, the estimation unit 133 is a price included in the information regarding the first transaction target, which is a price included in the price of the first transaction target and the price included in the information regarding the second transaction target, and is the second. Compare with the price of the transaction target of, and estimate the similarity between the first transaction target and the second transaction target based on the comparison result.

In order to estimate the similarity between the first transaction target in the electronic market and the second transaction target in the electronic market, the estimation unit 133 may, for example, use the first transaction target in the electronic market and the second transaction target in the electronic market. Calculate the degree of similarity that indicates the similarity with the trading target of.

In one example, the estimation unit 133 determines the degree of product similarity indicating the similarity between the first product and the second product based on the product information of the first product and the product information of the second product. , Calculated as a degree of similarity indicating the similarity between the first transaction target in the electronic market and the second transaction target in the electronic market.

For example, the estimation unit 133 identifies an image of the first product from the product information of the first product. Further, the estimation unit 133 identifies an image of the second product from the product information of the second product. Then, the estimation unit 133 is based on the image feature corresponding to the image of the specified first product (for example, BoVW) and the image feature corresponding to the image of the specified second product. The similarity between the image of the product and the image of the second product (for example, the similarity calculated using a predetermined similarity function such as the similarity based on the inner product of BoVW) is defined as that of the first product. It is calculated as a product similarity indicating similarity with the second product. For example, the estimation unit 133 calculates the product similarity based on the image feature corresponding to the image of the specified first product and the image feature corresponding to the image of the specified second product. That is, the estimation unit 133 calculates the product similarity based on the comparison between the image feature corresponding to the image of the specified first product and the image feature corresponding to the image of the specified second product. May be good.

The estimation unit 133 may output the product name of the first product and the product name of the second product by executing image recognition of the image of the first product and the image of the second product. .. Then, when the output product name of the first product and the product name of the second product match each other, the estimation unit 133 sets a predetermined product similarity (for example, "1") to the first. It may be determined as a product similarity indicating the similarity between the product and the second product.

The estimation unit 133 may specify the first text regarding the title of the first product or the description of the first product from the product information of the first product. Further, the estimation unit 133 may specify a second text regarding the title of the second product or the description of the second product from the product information of the second product. Then, the estimation unit 133 determines the first text and the second text based on the text feature corresponding to the specified first text (for example, Function) and the text feature corresponding to the specified second text. The similarity with the text of the text (for example, the similarity calculated using a predetermined similarity function, such as the similarity based on the DoW product) between the first product and the second product. It may be calculated as a product similarity indicating similarity. For example, the estimation unit 133 calculates the product similarity based on the text feature corresponding to the specified first text and the text feature corresponding to the specified second text. That is, the estimation unit 133 may calculate the product similarity based on the comparison between the text feature corresponding to the specified first text and the text feature corresponding to the specified second text.

The estimation unit 133 may specify the price of the first product from the product information of the first product. Further, the estimation unit 133 may specify the price of the second product from the product information of the second product. Then, the estimation unit 133 sets the similarity based on the difference between the price of the first product and the price of the second product as the product similarity indicating the similarity between the first product and the second product. It may be calculated. In addition, the estimation unit 133 includes an average selling price of a product belonging to the product category to which the first product belongs, an average selling price of a product belonging to the product category to which the second product belongs, a price of the first product, and a second product. A predetermined similarity function including the price of the first product may be used to calculate the product similarity indicating the similarity between the first product and the second product. For example, the estimation unit 133 may use the average selling price of the product belonging to the product category to which the first product belongs, the average selling price of the product belonging to the product category to which the second product belongs, the price of the first product, and the second product. Calculate the product similarity based on the price of.

In another example, the estimation unit 133 uses the service information of the first service (not shown) and the service information of the second service (not shown) to provide the first service and the second service. The service similarity indicating the similarity between and may be calculated as the similarity indicating the similarity between the first transaction target in the electronic market and the second transaction target in the electronic market.

For example, the estimation unit 133 may specify the address of the hotel H1 from the service information of the service "hotel H1 (that is, the reservation of the hotel H1)". Further, the estimation unit 133 may specify the address of the hotel H2 from the service information of the service "hotel H2". Then, when the specified address of the hotel H1 and the address of the hotel H2 match each other, a predetermined service similarity (for example, "1") is set between the service "hotel H1" and the service "hotel H2". It may be calculated as a service similarity indicating the similarity of. That is, the estimation unit 133 shows the similarity between the service "Hotel H1" and the service "Hotel H2" based on whether or not the specified address of the hotel H1 and the address of the hotel H2 match each other. The degree of similarity may be determined.

Further, for example, the estimation unit 133 may specify the menu of the restaurant R1 from the service information of the service "restaurant R1 (that is, the reservation of the restaurant R1)". Further, the estimation unit 133 may specify the menu of the restaurant R2 from the service information of the service "restaurant R2". Then, when the menu of the specified restaurant R1 and the menu of the restaurant R2 match each other, a predetermined service similarity (for example, "1") is set between the service "restaurant R1" and the service "restaurant R2". It may be calculated as a service similarity indicating the similarity of. That is, the estimation unit 133 shows the similarity between the service "restaurant R1" and the service "restaurant R2" based on whether or not the menu of the specified restaurant R1 and the menu of the restaurant R2 match each other. The degree of similarity may be determined.

(Granting unit 134)
The granting unit 134 assigns the information associated with the first transaction target to the second transaction target based on the similarity estimated by the estimation unit 133.

For example, the granting unit 134 sets the tag attached to the first transaction target as the information associated with the first transaction target to the second transaction target based on the similarity estimated by the estimation unit 133. Give.

In one example, the granting unit 134 assigns a tag associated with the first product to the second product based on the calculated product similarity.

For example, the granting unit 134 determines whether or not the calculated product similarity satisfies the granting condition for granting the tag associated with the first product to the second product. The granting unit 134 sets the tags associated with the first product, which are not associated with the second product, according to the determination that the calculated product similarity satisfies the granting condition. It is given to 2 products. In other words, the granting unit 134 is a tag associated with the first product but not associated with the second product according to the determination that the calculated product similarity satisfies the granting condition. Is associated with the second product. On the other hand, when it is determined that the calculated product similarity does not satisfy the granting condition, the granting unit 134 does not grant the tag associated with the first product to the second product.

In another example, the granting unit 134 may grant the tag associated with the first service to the second service based on the calculated service similarity.

Regarding the granting of information associated with the transaction target, "giving the information associated with the first transaction target to the second transaction target" means that the information associated with the first transaction target is given to the second transaction target. It may include associating with a transaction target. Further, "giving the information associated with the first transaction target to the second transaction target" includes propagating the rough information related to the first transaction target to the second transaction target. obtain. In other words, the granting unit 134 may associate the information associated with the first transaction object with the second transaction object based on the similarity estimated by the estimation unit 133. Further, the granting unit 134 may propagate the information associated with the first transaction target to the second transaction target based on the similarity estimated by the estimation unit 133.

For example, the granting unit 134 may store information associated with the first transaction target in association with the second transaction target based on the similarity estimated by the estimation unit 133. In this case, the predetermined storage device (for example, the product information storage unit 121) sets the information corresponding to the second transaction target (for example, an identifier for identifying the second transaction target) and the first transaction target. It may be stored in association with the associated information (for example, a tag).

Further, for example, the granting unit 134 transfers the information (for example, a tag) associated with the first transaction target to the information corresponding to the second transaction target (for example, based on the similarity estimated by the estimation unit 133). , An identifier for identifying a second transaction target) may be allocated.

Further, for example, the granting unit 134 corresponds to the information associated with the first transaction target (for example, a metadata tag) to the second transaction target based on the similarity estimated by the estimation unit 133. It may be added to the information (for example, the content related to the second transaction target). More specifically, the granting unit 134 includes the metadata tag contained in the content related to the first transaction target in the content related to the second transaction target based on the similarity estimated by the estimation unit 133. You may. That is, even if the granting unit 134 embeds the metadata tag contained in the content related to the first transaction target in the component included in the content related to the second transaction target based on the similarity estimated by the estimation unit 133. good.

(Providing section 135)
The providing unit 135 provides the content related to the electronic market to the user device 10. For example, the providing unit 135 transmits the content related to the electronic market to the user apparatus 10 when the receiving unit 131 receives the transmission request of the content related to the electronic market.

As an example, the provider 135 provides an electronic market in which the user of the user apparatus 10 can purchase or sell a transaction object (eg, a commodity or service). For example, the providing unit 135 provides the user device 10 with a service related to an electronic shopping district such as an online shopping service. For example, the providing unit 135 provides shopping content to the user device 10.

The transaction target in the above-mentioned electronic market may be a product or a service (for example, reservation of a restaurant or a hotel, travel). When the transaction target is a product, the provider 135 may provide an electronic market in which the user of the user device 10 can purchase or sell the product. On the other hand, when the transaction target is a service, the providing unit 135 may provide an electronic market in which the user of the user apparatus 10 can use or provide the service. For example, the provider 135 may provide an electronic market where the user can reserve a restaurant. More generally, "purchase" and "use" can be read as "conversion".

The providing unit 135 may provide the user device 10 with content that enables posting of product information. For example, the providing unit 135 may provide the user device 10 with content including a content item for receiving product information. For example, the providing unit 135 may provide the user device 10 with content including a content item for inputting product information (for example, a management screen of a store in an electronic market).

The providing unit 135 may provide the user device 10 with contents such as search, portal, shopping, and travel. The providing unit 135 may present the search result to the user device 10 in response to the search query entered in the search box of the provided content. In one example, if the tag "chocolate" is associated with a product, the provider 135 presents a search result containing this product to the user device 10 in response to the search query "chocolate".

As an example, the tag may be associated with the product ID and stored in the product information storage unit 121. In this example, the providing unit 135 identifies the tag corresponding to the search query entered in the search box of the provided content from the tags stored in the product information storage unit 121, and associates it with the specified tag. The user apparatus 10 may be presented with a search result including the product identified by the product ID. As another example, the tag (eg, a metadata tag) may be included in the content about the product. In this example, the provider 135 identifies the tag corresponding to the search query entered in the search box of the provided content from the tags included in the content, and the search result including the content including the specified tag. May be presented to the user device 10.

[4. Flow of grant processing]
Next, the procedure of the granting process by the granting device 100 according to the embodiment will be described. FIG. 5 is a flowchart showing a grant processing procedure by the granting device 100 according to the embodiment.

As shown in FIG. 5, first, the granting device 100 estimates the similarity between the first trading object in the electronic market and the second trading object in the electronic market (step S101).

For example, the granting device 100 is related to the information posted on the electronic market and related to the first transaction target and the information posted on the electronic market and related to the second transaction target. Based on this, the similarity between the first transaction target and the second transaction target is estimated.

For example, the granting device 100 is an image included in the information regarding the first transaction target, and is an image included in the image of the first transaction target and the information regarding the second transaction target, and is the second transaction. The image of the target is compared, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

Further, for example, the granting device 100 is a text included in the information regarding the first transaction target, and is a text describing a description of the first transaction target and a text included in the information regarding the second transaction target. Then, the text describing the explanation of the second transaction target is compared, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

Further, for example, the granting device 100 is a price included in the information regarding the first transaction target, which is a price included in the price of the first transaction target and the price included in the information regarding the second transaction target, and is a second. Compare with the price of the transaction target of, and estimate the similarity between the first transaction target and the second transaction target based on the comparison result.

The granting device 100 then grants the information associated with the first transaction target to the second transaction target based on the estimated similarity (step S102).

For example, the granting device 100 assigns a tag attached to the first transaction target to the second transaction target as information associated with the first transaction target based on the estimated similarity.

[5. Modification example]
The applying device 100 according to the above-described embodiment may be implemented in various different forms other than the above-mentioned embodiment. Therefore, in the following, another embodiment of the above-mentioned granting device 100 will be described.

[5-1. Granting evaluation]
The granting unit 134 may assign an evaluation to the first transaction target to the second transaction target as information associated with the first transaction target based on the similarity estimated by the estimation unit 133. .. For example, the granting unit 134 may associate the evaluation for the first trading object with the second trading object based on the similarity estimated by the estimation unit 133. The evaluation (ie, review) of the first transaction object is, for example, a reputation or impression of the first transaction object. The evaluation of such a transaction target is included in the evaluation information (for example, reputation information) displayed in the content related to the electronic market, for example.

In one example, the estimation unit 133 may calculate the product similarity indicating the similarity between the product “bag B1” and the product “bag B2”. In this example, the granting unit 134 determines whether or not the product similarity estimated and calculated by the estimation unit 133 satisfies the granting condition for granting the evaluation associated with the product “bag B1” to the product “bag B2”. You may judge. The granting unit 134 determines that the calculated product similarity satisfies the granting condition for granting the evaluation associated with the product “bag B1” to the product “bag B2”, and the product “bag B1”. The evaluation associated with "" may be associated with the product "bag B2".

For illustration purposes, it is assumed that the rating "this bag is very easy to use" is associated with the product "bag B1". In this example, when the evaluation associated with the product "bag B1" is given to the product "bag B2", the evaluation "this bag is very easy to use" is associated with the product "bag B2".

In another example, the estimation unit 133 calculates a service similarity indicating the similarity between the service "Hotel H1" and the service "Hotel H2". In this example, the granting unit 134 determines whether or not the service similarity calculated by the estimation unit 133 satisfies the granting condition for granting the evaluation associated with the service "hotel H1" to the service "hotel H2". do. The granting unit 134 determines that the calculated service similarity satisfies the granting condition for granting the evaluation associated with the service "Hotel H1" to the service "Hotel H2", and the service "Hotel H1" Is associated with the service "Hotel H2".

For illustration purposes, it is assumed that the rating "scenic" is associated with the service "Hotel H1". In this example, when the rating associated with the service "Hotel H1" is given to the service "Hotel H2", the rating "scenic" is associated with the service "Hotel H2".

[5-2. Giving information between multiple transaction targets]
The granting unit 134 associates with one of the plurality of trading objects by solving the information optimization problem associated with each of the plurality of trading objects based on the similarity estimated by the estimation unit 133. The obtained information may be given to the other one of the plurality of transaction targets.

For example, the granting unit 134 may use a label propagation method to propagate information associated with one of a plurality of transaction targets among a plurality of transaction targets.

More specifically, the granting unit 134 is a similarity calculated by the estimation unit 133, and is a graph having a plurality of trading targets as elements from the similarity showing the similarity between a plurality of trading targets in the electronic market. You may generate an example of adjacent rows of (ie, examples of similarity). However, the off-diagonal component of the adjacent bank example indicates the degree of similarity indicating the similarity between a plurality of transaction targets. In this example, the granting unit 134 sets the information associated with the second transaction object that is not associated with the predetermined information (ie, the label) to the first transaction object so that the predetermined objective function is minimized. By calculating the probability of being the associated information, the information associated with the first transaction target may be given to the second transaction target.

Further, for example, the granting unit 134 may use a label spreading method to propagate information associated with one of a plurality of transaction targets among a plurality of transaction targets. In this case, the granting unit 134 calculates the probability that the information associated with the second transaction target associated with the predetermined information (that is, the label) is the information associated with the first transaction target. Information associated with the first transaction target may be given to the second transaction target.

[5-3. others〕
Further, among the processes described in the above-described embodiment, a part of the processes described as being automatically performed can also be performed manually. Alternatively, all or part of the process described as being performed manually can be automatically performed by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown in the figure.

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 them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured.

For example, a part or all of the storage unit 120 shown in FIG. 3 may not be held by the granting device 100, but may be held by a storage server or the like. In this case, the granting device 100 acquires various information such as product information by accessing the storage server.

[5-4. Hardware configuration]
Further, the granting device 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 6 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to the output device 1010 and the input device 1020, and the arithmetic unit 1030, the primary storage device 1040, the secondary storage device 1050, the output IF (Interface) 1060, the input IF 1070, and the network IF 1080 are connected by the bus 1090. Have.

The arithmetic unit 1030 operates based on a program stored in the primary storage device 1040 or the secondary storage device 1050, a program read from the input device 1020, or the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic unit 1030 for various operations. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD, a flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a monitor and a printer. For example, USB (Universal Serial Bus), DVI (Digital Visual Interface), and the like. It is realized by a connector of a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, a scanner, and the like, and is realized by, for example, USB.

The input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Further, the input device 1020 may be an external storage medium such as a USB memory.

The network IF 1080 receives data from another device via the network N and sends it to the arithmetic unit 1030, and also transmits the data generated by the arithmetic unit 1030 to the other device via the network N.

The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

For example, when the computer 1000 functions as the granting device 100, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the primary storage device 1040.

[6. effect〕
As described above, the granting device 100 according to the embodiment has an estimation unit 133 and a granting unit 134. The estimation unit 133 estimates the similarity between the first transaction target in the electronic market and the second transaction target in the electronic market. The granting unit 134 assigns the information associated with the first transaction target to the second transaction target based on the similarity estimated by the estimation unit 133.

Further, in the granting device 100 according to the embodiment, the granting unit 134 is assigned to the first transaction target as information associated with the first transaction target based on the similarity estimated by the estimation unit 133. The tag is attached to the second transaction target.

Further, in the granting device 100 according to the embodiment, the granting unit 134 evaluates the first transaction target as information associated with the first transaction target based on the similarity estimated by the estimation unit 133. Granted to the second transaction target.

Further, in the granting device 100 according to the embodiment, the estimation unit 133 is information posted on the electronic market, information on the first transaction target, and information posted on the electronic market, and is the second information. Estimate the similarity between the first transaction target and the second transaction target based on the relevance to the information about the transaction target.

Further, in the granting device 100 according to the embodiment, the estimation unit 133 is an image included in the information regarding the first transaction target, and is included in the image of the first transaction target and the information regarding the second transaction target. The image is compared with the image of the second transaction target, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

Further, in the granting device 100 according to the embodiment, the estimation unit 133 is a text included in the information regarding the first transaction target, the text describing the explanation of the first transaction target, and the second transaction target. Compare the text contained in the information with the text describing the description of the second transaction target, and estimate the similarity between the first transaction target and the second transaction target based on the comparison result. do.

Further, in the granting device 100 according to the embodiment, the estimation unit 133 is a price included in the information regarding the first transaction target, and is included in the price of the first transaction target and the information regarding the second transaction target. The price is compared with the price of the second transaction target, and the similarity between the first transaction target and the second transaction target is estimated based on the comparison result.

By each of the above-mentioned processes, the giving device 100 can give appropriate information to the transaction target.

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 carry out the present invention in other modified forms.

Further, the above-mentioned granting device 100 may be realized by a plurality of server computers, and depending on the function, it may be realized by calling an external platform or the like by API (Application Programming Interface), network computing, or the like. It can be changed flexibly.

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

1 Network system 10 User device 100 Grant device 110 Communication section 120 Storage section 121 Product information storage section 130 Control section 131 Reception section 132 Acquisition section 133 Estimating section 134 Grant section 135 Providing section

Claims (7)

The information posted to the electronic market, which is the price of the first transaction target included in the information regarding the first transaction target in the electronic market, and the information posted to the electronic market, the electronic The price of the second trading object contained in the information about the second trading object in the market is compared with the price of the second trading object, and based on the comparison result, the similarity between the first trading object and the second trading object is made. An estimation unit that estimates sex, and
Based on the similarity estimated by the estimation unit, the granting unit that assigns the information associated with the first transaction target to the second transaction target, and the granting unit.
A granting device characterized by comprising. The granting part is
Based on the similarity estimated by the estimation unit, the tag attached to the first transaction target is given to the second transaction target as the information associated with the first transaction target. The granting device according to claim 1. The granting part is
Based on the similarity estimated by the estimation unit, the second transaction target is given an evaluation for the first transaction target as information associated with the first transaction target. The granting device according to claim 1 or 2. The estimation unit
An image included in the information regarding the first transaction target, the image included in the first transaction target image, and the image included in the information regarding the second transaction target, and the image of the second transaction target. To any one of claims 1 to 3, characterized in that the similarity between the first transaction target and the second transaction target is estimated based on the comparison result. The described granting device. The estimation unit
The text included in the information regarding the first transaction target, the text describing the description of the first transaction target, and the text included in the information regarding the second transaction target, the second one. Claims 1 to 1 , characterized in that the similarity between the first transaction target and the second transaction target is estimated based on the comparison result with the text describing the description of the transaction target. The granting device according to any one of 4 . It ’s a computer-executed granting method.
The information posted to the electronic market, which is the price of the first transaction target included in the information regarding the first transaction target in the electronic market, and the information posted to the electronic market, the electronic The price of the second trading object contained in the information about the second trading object in the market is compared with the price of the second trading object, and based on the comparison result, the similarity between the first trading object and the second trading object is made. The estimation process for estimating sex and
Based on the similarity estimated by the estimation step, the granting step of imparting the information associated with the first transaction target to the second transaction target, and the granting step.
A granting method characterized by including. The information posted to the electronic market, which is the price of the first transaction target included in the information regarding the first transaction target in the electronic market, and the information posted to the electronic market, the electronic The price of the second trading object contained in the information about the second trading object in the market is compared with the price of the second trading object, and based on the comparison result, the similarity between the first trading object and the second trading object is made. Estimating procedure for estimating sex and
An grant procedure for imparting information associated with the first transaction target to the second transaction target based on the similarity estimated by the estimation procedure, and a grant procedure.
A grant program characterized by having a computer execute.

Images