JP6765262B2 - Judgment device, judgment method, and judgment program - Google Patents

Description

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

Conventionally, a technique for determining the similarity between products included as information in various contents has been provided. For example, a technique for determining the similarity of products on a product web page based on the characteristic words of each product web page is provided.

Japanese Unexamined Patent Publication No. 2013-101415

However, with the above-mentioned prior art, it may be difficult to appropriately determine the similarity of products corresponding to each content. For example, it is difficult to appropriately determine the similarity of products corresponding to each content simply by determining the similarity of products corresponding to each content based on the feature words included in each content. If similar keywords are accidentally used for each content corresponding to dissimilar products, dissimilar products may be determined to be similar. As described above, it is difficult to prevent dissimilar products from being determined to be similar only by determining the similarity of products corresponding to each content based on the character information contained in each content.

The present application has been made in view of the above, and provides a determination device, a determination method, and a determination program that suppresses determination of dissimilar products as similar and enables appropriate determination of product similarity. The purpose is.

The determination device according to the present application is each content corresponding to each of the products provided in the electronic commerce, and includes an acquisition unit for acquiring information regarding the user's click on each content displayed on the terminal device used by the user. It is characterized by including a determination unit for determining similar similar products among the products corresponding to the respective contents based on the information regarding the user's click on each content acquired by the acquisition unit.

According to one aspect of the embodiment, it is possible to suppress the determination of dissimilar products as similar and to appropriately determine the similarity of the products.

FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 2 is a diagram showing a configuration example of the determination device according to the embodiment. FIG. 3 is a diagram showing an example of the history information storage unit according to the embodiment. FIG. 4 is a diagram showing an example of a similar product information storage unit according to the embodiment. FIG. 5 is a flowchart showing an example of determination of similar products according to the embodiment. FIG. 6 is a diagram showing an example of determination of similar products based on the selection of the lowest price product according to the embodiment. FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the function of the determination device.

Hereinafter, a determination device according to the present application, a determination method, and a mode for carrying out the determination program (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. The determination device, determination method, and determination 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.

(Embodiment)
[1. Determination process〕
An example of the determination process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 1 shows a case where the determination device 100 determines a similar similar product based on the product information clicked by the user to whom the product information as the content is provided. In the example of FIG. 1, product information related to a predetermined product or service (hereinafter, also referred to as “product”) is shown as an example of the content, but the content is not limited to the product information but includes the content of the predetermined product. Any content may be provided as long as it is provided to the user.

As shown in FIG. 1, the determination system 1 includes a terminal device 10, an electronic commerce device 50, and a determination device 100. The terminal device 10, the electronic commerce device 50, and the determination device 100 are connected to each other so as to be communicable by wire or wirelessly via a predetermined communication network (network) (not shown). Further, the determination system 1 shown in FIG. 1 may include a plurality of terminal devices 10, a plurality of electronic commerce devices 50, and a plurality of determination devices 100.

The terminal device 10 is an information processing device used by the user. The terminal device 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. In the example shown in FIG. 1, a case where the terminal device 10 is a smartphone used by a user is shown. In the following, the terminal device 10 may be referred to as a user. That is, in the following, the user can be read as the terminal device 10. Specifically, FIG. 1 shows a case where the terminal device 10 is a smartphone used by a user identified by the user ID “U1” (hereinafter, may be referred to as “user U1”).

Further, in the example shown in FIG. 1, the terminal device 10 will be described as the terminal device 10-1 to 10-5 according to the time (timing) when the user U1 clicks each product information in the terminal device 10. The terminal devices 10-1 to 10-5 are the same terminal devices 10. Further, in the following, when the terminal devices 10-1 to 10-5 will be described without particular distinction, they will be referred to as the terminal device 10.

The electronic commerce device 50 is an information processing device used to provide an electronic commerce service. For example, the electronic commerce device 50 provides product information to the terminal device 10 used by the user. Further, the electronic commerce device 50 collects information on the product information clicked by the user, and provides the information on the user's click (hereinafter, also referred to as "click information") to the determination device 100. Further, for example, the electronic commerce device 50 performs a purchase process of a product according to the request in response to a purchase request from the user. The service provided by the provider using the electronic commerce device 50 may be any form of service as long as it can provide product information to the terminal device 10 used by the user and collect click information. .. Further, the electronic commerce device 50 may be integrated with the determination device 100. For example, when the electronic commerce device 50 is integrated with the determination device 100, the determination device 100 may provide the electronic commerce service.

The determination device 100 is an information processing device that determines similar similar products among the products corresponding to each content based on the information regarding the user's click on each content displayed on the terminal device 10 used by the user. For example, the determination device 100 determines similar products by using information on co-occurrence of clicks based on information on user clicks for each content.

First, the electronic commerce device 50 provides list information to the terminal device 10 used by the user U1 (step S11). For example, the electronic commerce device 50 provides the terminal device 10 with product information such as products GD1 to GD6. Further, as shown in the terminal device 10-1, the terminal device 10 used by the user U1 displays list information including product information such as products GD1 to GD6. As described above, when "product GD * (* is an arbitrary numerical value)" is described, it means that the product is a product identified by the product ID "GD *". For example, when "Product GD1" is described, the product is a product identified by the product ID "GD1". In the following, the product information of "product GD * (* is an arbitrary numerical value)" may be referred to as "product GD * (* is an arbitrary numerical value)". For example, in the following, the product GD1 can be read as the product information of the product GD1.

After that, the electronic commerce device 50 acquires information indicating that the user U1 clicks the product information of the product GD1 displayed on the terminal device 10 at the date and time dt11 from the terminal device 10-1 (step S12-1). Further, the electronic commerce device 50 acquires information indicating that the user U1 clicks the product information of the product GD6 at the date and time dt12 from the terminal device 10-2 (step S12-2). Further, the electronic commerce device 50 acquires information indicating that the user U1 clicks the product information of the product GD3 at the date and time dt13 from the terminal device 10-3 (step S12-3). Further, the electronic commerce device 50 acquires information indicating that the user U1 clicks the product information of the product GD4 at the date and time dt 14 from the terminal device 10-4 (step S12-4). Further, the electronic commerce device 50 acquires information indicating that the user U1 clicks the product information of the product GD2 at the date and time dt21 from the terminal device 10-5 (step S12-5).

In FIG. 1, "* (* is an arbitrary numerical value)" following "dt" in the date and time "dt *" indicates an arbitrary date and time such as when the product information is clicked, and the date and time "dt *". The larger the value of "*", the newer the date. For example, the date and time "dt12" indicates that the date is newer because the numerical value following "dt" is larger than that of the date and time "dt11". That is, in the example shown in FIG. 1, it is shown that the product information of the product GD1, the product information of the product GD6, the product information of the product GD3, the product information of the product GD4, and the product information of the product GD2 are clicked in this order.

After that, the electronic commerce device 50 provides the collected click information of the user U1 to the determination device 100 (step S13). In the example shown in FIG. 1, the electronic commerce device 50 clicks the product GD1 on the date and time dt11, clicks the product GD6 on the date and time dt12, clicks the product GD3 on the date and time dt13, clicks the product GD4 on the date and time dt14, and clicks on the date and time. The determination device 100 is provided with click information indicating that the product GD2 has been clicked on the dt21. Further, the electronic commerce device 50 may provide the product information of the product GD1, the product information of the product GD6, the product information of the product GD3, the product information of the product GD4, and the product information of the product GD2 to the determination device 100.

The determination device 100 that has acquired the click information of the user U1 from the electronic commerce device 50 determines similar products based on the acquired click information and each product information. For example, the determination device 100 determines similar products based on the information shown in the history information storage unit 121 in FIG.

For example, the history information storage unit 121 in FIG. 1 indicates that the user U1 clicks on the content (product information) corresponding to the date and time dt11 to the date and time dt21 shown in the log IDs “LG1” to “LG5”. For example, the user U1 indicates that the product GD1 is clicked on the date and time dt11. Further, the image of the product GD1 indicates that the image is the image "IM1". Further, the title of the product GD1 indicates that the title is "TL1". Further, the description of the product GD1 indicates that the description is the description "DC1". Further, for example, the user U1 indicates that the product GD6 is clicked on the date and time dt12. Further, the image of the product GD6 indicates that the image is the image "IM6". Further, the title of the product GD6 indicates that the title is "TL6". Further, the description of the product GD6 indicates that the description is "DC6".

Here, the determination device 100 determines similar products based on the click co-occurrence of each product (step S14). For example, the determination device 100 uses information on the co-occurrence of clicks based on the click information of the user U1 whose time point when the user U1 clicks corresponds to a predetermined period among the click information of the user U1 for each product information. Judge the product. In the example of FIG. 1, a case where a session is used as a predetermined period is shown. For example, a session means a period during which a user performs an action with a predetermined purpose (intention). In the example of FIG. 1, a case where one session is set between the date and time dt10 and the date and time dt20 is shown. For example, the determination device 100 holds a session when the user has not operated on the product information displayed in the list information for a predetermined period since the user's operation on the product information displayed in the list information was last performed. It may be initialized. For example, when the search device 100 does not operate the product information displayed in the list information by the user for 30 minutes after the last operation of the product information displayed in the list information is performed during the continuation of the session. In addition, the session may be initialized. The term "initialization" as used herein means, for example, ending a session that has been continued until then and starting a new session. In this way, the search device 100 may continue the session while the user's behavior continues. Further, for example, the search device 100 may initialize the session at a timing when it is estimated that the user's intention has changed. For example, when the search device 100 changes the display of the list information and starts browsing other contents, it may presume that the user's intention has changed and initialize the session. In the example of FIG. 1, the determination device 100 determines the product information clicked between the date and time dt10 and the date and time dt20 as the product information in which the clicks co-occur. In this case, as shown in the click co-occurrence information IN11, the determination device 100 includes the product GD1 clicked on the date and time dt11, the product GD6 clicked on the date and time dt12, the product GD3 clicked on the date and time dt13, and the date and time dt14. It is determined as the product information in which the click is co-occurred with the product GD4 clicked on.

Then, the determination device 100 determines a similar product based on the content of each product information with respect to the product information included in the click co-occurrence information IN11 (step S15). For example, the determination device 100 determines similar products based on the similarity of the contents such as images, titles, and explanations of the four product information of the products GD1, GD3, GD4, and GD6. In the example of FIG. 1, the determination device 100 determines the product GD1 and the product GD3 as similar products, as shown in the similar product list SL1.

After that, the determination device 100 transmits the information of the similar product determined in step S15 to the electronic commerce device 50 (step S16). In the example of FIG. 1, the determination device 100 transmits a similar product list SL1 indicating that the product GD1 and the product GD3 are similar products to the electronic commerce device 50.

As described above, the determination device 100 suppresses the determination of dissimilar products as similar by determining the similarity of products by co-occurrence of clicks based on the click information of the user U1, and appropriately resembles the products. Gender can be determined. Further, the determination device 100 performs the similarity determination of the information regarding the click co-occurrence as the first step, and then performs the similarity determination based on the content for the product information satisfying the click co-occurrence condition as the second step. In this way, the determination device 100 can suppress an increase in the processing load for determining similar products by determining similar products in two steps.

The above-mentioned process is an example, and the determination device 100 may determine a similar product by appropriately using various information in addition to the information regarding the click. For example, the determination device 100 determines similar products by varying the processing according to the category of the products for which similar products are to be determined. For example, when the category of the product to be determined for the similar product is the first category, the determination device 100 determines the similar product based on the information about the user's click on each content, and determines the similar product. When the category of the product is a second category different from the first category, a similar product is determined based on information other than the information regarding the user's click for each content. For example, when the category such as products GD1 to GD6 is a "book" or the like included in the first category, the determination device 100 may determine similar products based on click co-occurrence.

For example, when the category of the product for which the similar product is to be determined is the second category, the determination device 100 determines the similar product based on the similarity of the images included in each content. For example, when the category such as products GD1 to GD6 is an "electrical appliance" included in the second category, the determination device 100 may determine similar products based on the similarity of images. The above is an example, and the determination device 100 may determine similar products by appropriately using various information according to the characteristics of the category.

Further, for example, the determination device 100 may determine a similar product by using a model generated based on information on clicks, product information, and the like. For example, the determination device 100 uses a model that is product information that is co-occurred and clicked within a predetermined time and is generated by using the product information of a similar product as correct answer information (correct example) to obtain a similar product. You may judge. Further, for example, the determination device 100 uses a model generated as incorrect answer information (negative example) of product information that is co-occurrence and clicked within a predetermined time and that is not similar to the product. Similar products may be determined. The above-mentioned process is an example, and the determination device 100 may determine a similar product using any information. For example, the determination device 100 may extract (determine) similar product candidates from the click co-occurrence in the above-mentioned session. Further, for example, the determination device 100 may further narrow down similar product candidates by using various similarity determinations. For example, the determination device 100 may determine the similarity of each product based on the product category information. Further, for example, the determination device 100 may determine the similarity of each product based on the title character string of the product. Further, for example, the determination device 100 may determine the similarity of each product based on the image of the product. Further, for example, the determination device 100 may generate a classification model using various information such as product categories, character strings, and images as described above, and determine the similarity using the generated classification model. Good.

[2. Judgment device configuration]
Next, the configuration of the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the determination device 100 according to the embodiment. As shown in FIG. 2, the determination device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The determination device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the determination device 100, and a display unit (for example, a 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. Then, the communication unit 110 is connected to the network by wire or wirelessly, and transmits / receives information to / from, for example, the electronic commerce device 50 and the terminal device 10 included in the determination system 1.

(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. 2, the storage unit 120 according to the embodiment includes a history information storage unit 121 and a similar product information storage unit 122.

(History information storage unit 121)
The history information storage unit 121 according to the embodiment stores various information related to the action history performed by the user. FIG. 3 shows an example of the history information storage unit 121 according to the embodiment. The history information storage unit 121 shown in FIG. 3 has items such as "user ID", "log ID", "date and time", and "product information".

The "user ID" indicates identification information for identifying the user. The "log ID" indicates identification information for identifying each log information. "Date and time" indicates the date and time when the user clicks the corresponding content. Further, the "product information" includes items such as "product ID", "image", "title", and "description".

The "product ID" indicates identification information for identifying the product. The "product ID" referred to here is information that distinguishes the product included in the product information from others, and is not information that identifies a specific product such as a product name. The "image" indicates an image of product information which is a content. Although FIG. 3 shows an example in which conceptual information such as “IM1” is stored in the “image”, the image information or a file path name indicating the storage location thereof is actually stored.

The "title" indicates a title included in the product information of the product identified by the product ID. Further, the "description" indicates a description included in the product information of the product identified by the product ID. In the history information storage unit 121 shown in FIG. 3, the title is indicated by an abstract symbol such as the title "TL1" or the title "TL2". For example, "new bag A ..." or "free shipping ..." etc. As such, each title shall be a specific title of the corresponding product. Further, in the history information storage unit 121 shown in FIG. 3, the explanatory text is indicated by abstract symbols such as the explanatory text "DC1" and the explanatory text "DC2". For example, "It is a new work of a popular brand ..." or " Each description shall be a specific description of the corresponding product, such as "We will deliver it with free shipping ...".

For example, in the example shown in FIG. 3, the user (user U1) identified by the user ID "U1" is the content (product information) corresponding to the date and time dt11 to the date and time dt21 shown in the log IDs "LG1" to "LG5". Indicates that you have clicked.

For example, in the example shown in FIG. 3, it is shown that the user U1 clicks the product information of the product (product GD1) identified by the product ID “GD1” at the date and time dt11. Further, the image of the product GD1 indicates that the image is the image "IM1". Further, the title of the product GD1 indicates that the title is "TL1". Further, the description of the product GD1 indicates that the description is the description "DC1".

Further, for example, in the example shown in FIG. 3, it is shown that the user U1 clicks the product information of the product (product GD6) identified by the product ID "GD6" at the date and time dt12. Further, the image of the product GD6 indicates that the image is the image "IM6". Further, the title of the product GD6 indicates that the title is "TL6". Further, the description of the product GD6 indicates that the description is "DC6".

The history information storage unit 121 is not limited to the above, and various information may be stored depending on the purpose. For example, the history information storage unit 121 may store user attribute information such as the gender and age of the user.

(Similar product information storage unit 122)
The similar product information storage unit 122 according to the embodiment stores information about similar products. In the example of FIG. 4, the similar product information storage unit 122 stores information regarding the association of products determined to be similar products. FIG. 4 is a diagram showing an example of a similar product information storage unit according to the embodiment. The similar product information storage unit 122 shown in FIG. 4 has items such as "similar ID" and "similar product". The "similar product" has items such as "# 1" and "# 2".

The "similar ID" indicates identification information for identifying a similar product group associated as a similar product. That is, the "similar ID" indicates identification information for identifying a similar product group determined to be a similar product. Further, "# 1" and "# 2" in the "similar product" indicate information for identifying a product included in the similar product group identified by the similar ID. In the example of FIG. 4, only "# 1" and "# 2" are shown for the sake of simplicity, but "similar products" correspond to the number of products included in one similar product group. It may have items such as "# 3" and "# 4".

For example, in the example shown in FIG. 4, it is shown that the similar product group identified by the similar ID “SM11” includes the product GD1 and the product GD3. Further, for example, in the example shown in FIG. 4, it is shown that the similar product group identified by the similar ID "SM12" includes the product GD2, the product GD9, and the like.

The similar product information storage unit 122 is not limited to the above, and various information may be stored depending on the purpose. For example, the name of the similar product group may be stored in the similar product information storage unit 122.

(Control unit 130)
Returning to the description of FIG. 2, the control unit 130 is a controller, and is stored in a storage device inside the determination 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 determination 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).

As shown in FIG. 2, the control unit 130 includes an acquisition unit 131, a determination unit 132, and a transmission unit 133, and realizes or executes an information processing function or operation described below.

(Acquisition unit 131)
For example, the acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various information from the history information storage unit 121 and the similar product information storage unit 122. Further, the acquisition unit 131 may acquire various information from an external information processing device.

For example, the acquisition unit 131 acquires information regarding the user's click on each content displayed on the terminal device 10 used by the user, which is each content corresponding to each of the products provided in the electronic commerce. Further, for example, the acquisition unit 131 acquires information regarding the user's click for each content listed on the terminal device 10.

In the example of FIG. 1, the acquisition unit 131 acquires the click information of the user U1 from the electronic commerce device 50. In the example shown in FIG. 1, the acquisition unit 131 clicks the product GD1 on the date and time dt11, clicks the product GD6 on the date and time dt12, clicks the product GD3 on the date and time dt13, and clicks the product GD4 on the date and time dt14 from the electronic commerce device 50. Click to acquire click information indicating that the product GD2 was clicked at the date and time dt21. Further, the acquisition unit 131 acquires the product information of the product GD1, the product information of the product GD6, the product information of the product GD3, the product information of the product GD4, and the product information of the product GD2 from the electronic commerce device 50.

(Judgment unit 132)
The determination unit 132 determines various information. For example, the determination unit 132 determines similar similar products among the products corresponding to each content based on the information regarding the user's click on each content acquired by the acquisition unit 131.

For example, the determination unit 132 determines similar products by using information on co-occurrence of clicks based on information on user clicks for each content. For example, the determination unit 132 uses information on the co-occurrence of clicks based on the information on the user's click corresponding to a predetermined period when the user clicks, among the information on the user's click for each content, to obtain a similar product. judge.

Further, for example, the determination unit 132 determines a similar product by varying the processing according to the category of the product for which the similar product is determined. For example, when the category of the product to be determined for the similar product is the first category, the determination unit 132 determines the similar product based on the information regarding the user's click on each content, and determines the similar product. When the category of the product is a second category different from the first category, a similar product is determined based on information other than the information regarding the user's click for each content. For example, when the category of the product for which the similar product is determined is the second category, the determination unit 132 determines the similar product based on the similarity of the images included in each content.

In the example of FIG. 1, the determination unit 132 determines similar products based on the click information of the user U1 acquired from the electronic commerce device 50 by the acquisition unit 131 and each product information. For example, the determination unit 132 determines similar products based on various information stored in the history information storage unit 121 (see FIG. 3).

In the example of FIG. 1, the determination unit 132 determines similar products based on the click co-occurrence of each product. For example, the determination unit 132 uses information on the co-occurrence of clicks based on the click information of the user U1 whose time point when the user U1 clicks corresponds to a predetermined period among the click information of the user U1 for each product information. Judge the product. For example, the determination unit 132 determines the product information clicked between the date and time dt10 and the date and time dt20 as the product information in which the clicks co-occur. For example, as shown in the click co-occurrence information IN11, the determination unit 132 sets the product GD1 clicked on the date and time dt11, the product GD6 clicked on the date and time dt12, the product GD3 clicked on the date and time dt13, and the date and time dt14. It is determined as the product information in which the clicked product GD4 and the click co-occur.

Further, for example, the determination unit 132 determines similar products based on the contents of each product information. For example, the determination unit 132 determines similar products based on the similarity of character information included in each product information and the similarity of images. In the example of FIG. 1, the determination unit 132 determines similar products based on the contents of each product information for the product information included in the click co-occurrence information IN11. For example, the determination unit 132 determines similar products based on the similarity of the contents such as images, titles, and explanations of the four product information of the products GD1, GD3, GD4, and GD6. In the example of FIG. 1, the determination unit 132 determines that the product GD1 and the product GD3 are similar products, as shown in the similar product list SL1.

Further, for example, when the determination unit 132 clicks only the content including the lowest priced product, which is the cheapest product among the contents listed on the terminal device 10, the lowest priced product is selected. The product included in the content other than the included content and the lowest priced product are determined as similar products. For example, when the price of the lowest priced product is equal to or higher than a predetermined threshold value, the determination unit 132 determines that the product included in the content other than the content including the lowest priced product and the lowest priced product are similar products. For example, when the difference between the price of the highest priced product and the price of the lowest priced product among the contents listed on the terminal device 10 is equal to or less than a predetermined threshold value, the determination unit 132 selects the lowest priced product. The product included in the content other than the included content and the lowest priced product are determined as similar products. For example, when the ratio of the price of the lowest priced product to the price of the highest priced product among the contents listed on the terminal device 10 is equal to or higher than a predetermined threshold value, the determination unit 132 includes the lowest priced product. A product included in other contents other than the above and the lowest priced product are determined as similar products. Details on this point will be described later.

(Transmission unit 133)
The transmission unit 133 transmits various information to an external information processing device. For example, the transmission unit 133 transmits the information of the similar product determined by the determination unit 132 to an external information processing device. For example, the transmission unit 133 transmits information about a similar product determined by the determination unit 132 to the electronic commerce device 50. Further, for example, the transmission unit 133 transmits various information acquired by the acquisition unit 131 from the history information storage unit 121 and the similar product information storage unit 122 to an external information processing device.

For example, the transmission unit 133 transmits information about a similar product determined by the determination unit 132 to the electronic commerce device 50. For example, the transmission unit 133 transmits the information of the similar product determined by the determination unit 132 to the electronic commerce device 50. In the example of FIG. 1, the transmission unit 133 transmits a similar product list SL1 indicating that the product GD1 and the product GD3 are similar products to the electronic commerce device 50.

[3. Judgment processing flow]
Here, the procedure of the determination process by the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a flowchart showing an example of determination of similar products according to the embodiment.

As shown in FIG. 5, the determination device 100 acquires information regarding the user's click on each product information (step S101). In FIG. 1, the determination device 100 acquires information regarding the click of the user U1 from the electronic commerce device 50.

After that, the determination device 100 determines the product information in which the clicks co-occur, among the product information, based on the information regarding the user's click (step S102). In FIG. 1, the determination device 100 determines that the product information clicked by the user U1 is co-occurring product information between the date and time dt10 and the date and time dt20.

In addition, the determination device 100 determines product information related to similar products based on the content of each product information among the product information in which clicks co-occur (step S103). In FIG. 1, the determination device 100 determines that the product information of the product GD1 and the product information of the product GD3 are product information related to similar products based on the contents of each product information.

[4. Cheapest product]
Here, using FIG. 6, only the content including the cheapest product (hereinafter, also referred to as “lowest price product”) is clicked among the contents listed by the determination device 100 according to the embodiment. The determination of similar products in the case will be described. FIG. 6 is a diagram showing an example of determination of similar products based on the selection of the lowest price product according to the embodiment. For example, when only the product information of the lowest priced product, which is the cheapest product, is clicked among the product information listed on the terminal device 10, the determination device 100 other than the product information of the lowest priced product. The product of the product information of the above and the lowest priced product may be determined as similar products. Note that FIG. 6 is an example, and the determination device 100 has a significant tendency to easily click the cheaper product among the product groups that are frequently displayed in the list for determining similar products based on the lowest price product. You may go only to the product group.

As shown in FIG. 6, it is assumed that the terminal device 10 displays a list of product information (product list) of the products GD11 to GD14. Further, it is assumed that the price of the product GD11 is 1 million yen, the price of the product GD12 is 980,000 yen, the price of the product GD13 is 970,000 yen, and the price of the product GD14 is 950,000 yen.

In the example of FIG. 6, the determination device 100 acquires click information indicating that only the product information of the product GD14 has been selected from the terminal device 10 (step S21). That is, the determination device 100 acquires click information indicating that only the product information of the lowest priced product GD14 is selected from the product GD11 to GD14 from the terminal device 10. Then, the determination device 100 determines a similar product based on the acquired click information (step S22). In this case, for example, the determination device 100 is displayed in a list because the user who uses the terminal device 10 selects only the product information of the lowest priced product GD14 among the listed products GD11 to GD14. Products GD11 to GD14 are determined to be similar products.

In the example of FIG. 6, for the sake of simplicity, when only the product information of the product GD14, which is the lowest price product, is clicked, the determination device 100 determines the other product without considering other conditions. Although the GD11 to GD13 and the product GD14 are determined as similar products, the determination device 100 may determine the similar products in consideration of other conditions.

For example, when the price of the lowest priced product is equal to or higher than a predetermined threshold value, the determination device 100 may determine that the product included in the content other than the content including the lowest priced product and the lowest priced product are similar products. Good. For example, when the price of the lowest priced product is 500,000 yen or more, the determination device 100 may determine that the product included in the content other than the content including the lowest priced product and the lowest priced product are similar products. Good.

In the example of FIG. 6, since the price of the lowest priced product GD14 is 500,000 yen or more in the determination device 100, when the user selects only the product information of the lowest priced product GD14, the listed products GD11 to 1 GD14 is determined to be a similar product.

Further, for example, the determination device 100 is the difference between the price of the highest priced product (hereinafter, also referred to as “highest price product”) and the price of the lowest priced product among the contents listed on the terminal device 10. When is not more than a predetermined threshold value, a product included in the content other than the content including the lowest price product and the lowest price product may be determined as similar products. For example, the determination device 100 includes the content including the lowest price product when the difference between the price of the highest price product and the price of the lowest price product is 100,000 yen or less among the contents listed on the terminal device 10. A product included in other contents other than the above and the lowest priced product may be determined as similar products.

In the example of FIG. 6, in the determination device 100, the difference between the highest price product GD11 price "1 million yen" and the lowest price product GD14 price "950,000 yen" is 100,000 yen or less, so that the user When only the product information of the lowest priced product GD14 is selected, the listed products GD11 to GD14 are determined to be similar products. Further, the determination device 100 may change the threshold value according to the price of the highest priced product or the price of the lowest priced product. For example, the determination device 100 may change the threshold value so that the higher the price of the highest priced product or the price of the lowest priced product, the larger the threshold value. For example, when the price of the highest priced product is "100,000 yen", the determination device 100 may set the threshold value to 10,000 yen.

Further, for example, the determination device 100 includes the content including the lowest price product when the ratio of the price of the lowest price product to the price of the highest price product is equal to or higher than a predetermined threshold among the contents listed on the terminal device 10. A product included in other contents other than the above and the lowest priced product may be determined as similar products. For example, when the ratio of the price of the lowest priced product to the price of the highest priced product is 90% or more among the contents listed on the terminal device 10, the determination device 100 is other than the contents including the lowest priced product. The product included in the content of the above and the lowest priced product are judged as similar products.

In the example of FIG. 6, in the determination device 100, the ratio of the lowest price product GD14 price "950,000 yen" to the highest price product GD11 price "1 million yen" is "95% (= 95/100 * 100). ) ”Is 90% or more, so when the user selects only the product information of the lowest priced product GD14, the listed products GD11 to GD14 are determined to be similar products. Further, the determination device 100 may change the threshold value according to the price of the highest priced product or the price of the lowest priced product. For example, the determination device 100 may change the threshold value so that the value of the threshold value becomes smaller as the price of the lowest priced product increases. For example, the determination device 100 may set the threshold value to 98% when the price of the highest priced product is "100,000 yen".

[5. effect〕
As described above, the determination device 100 according to the embodiment includes an acquisition unit 131 and a determination unit 132. The acquisition unit 131 acquires information regarding the user's click on each content displayed on the terminal device 10 used by the user, which is each content corresponding to each of the products provided in the electronic commerce. The determination unit 132 determines similar similar products among the products corresponding to each content based on the information regarding the user's click on each content acquired by the acquisition unit 131.

As a result, the determination device 100 according to the embodiment determines that the dissimilar products are similar by determining similar similar products among the products corresponding to each content based on the information regarding the user's click on each content. It is possible to suppress this and appropriately determine the similarity of products.

Further, in the determination device 100 according to the embodiment, the determination unit 132 determines similar products by using the information regarding the co-occurrence of clicks based on the information regarding the user's clicks for each content.

As a result, the determination device 100 according to the embodiment determines that dissimilar products are similar by determining similar products using information on co-occurrence of clicks based on information on user clicks for each content. It can be suppressed and the similarity of products can be appropriately determined.

Further, in the determination device 100 according to the embodiment, the determination unit 132 co-occurs clicks based on the information regarding the user's click corresponding to a predetermined period when the user clicks among the information regarding the user's click for each content. Use the information about to determine similar products.

As a result, the determination device 100 according to the embodiment uses the information on the co-occurrence of clicks based on the information on the user's click corresponding to the predetermined period when the user clicks, among the information on the user's click for each content. Therefore, by determining similar products, it is possible to suppress the determination of dissimilar products as similar and make it possible to appropriately determine the similarity of products.

Further, in the determination device 100 according to the embodiment, for example, the determination unit 132 determines a similar product by varying the process according to the category of the product for which the similar product is determined.

As a result, the determination device 100 according to the embodiment is appropriate according to the category of the product by, for example, varying the processing according to the category of the product for which the similar product is determined and determining the similar product. Judgment processing can be performed. Therefore, it is possible to suppress the determination of dissimilar products as similar in the determination device 100 and appropriately determine the similarity of the products.

Further, in the determination device 100 according to the embodiment, for example, when the category of the product for which the similar product is determined is the first category, the determination unit 132 is similar based on the information regarding the user's click on each content. When a product is determined and the category of the product for which the similar product is determined is a second category different from the first category, the similar product is determined based on information other than the information regarding the user's click on each content.

As a result, the determination device 100 according to the embodiment determines similar products based on the information regarding the user's click on each content, for example, when the category of the product for which the similar product is determined is the first category. , When the category of the target product for determining the similar product is the second category different from the first category, the similar product is determined by determining the similar product based on the information other than the information about the user's click for each content. Appropriate judgment processing can be performed according to the category. Therefore, it is possible to suppress the determination of dissimilar products as similar in the determination device 100 and appropriately determine the similarity of the products.

Further, in the determination device 100 according to the embodiment, the determination unit 132 determines, for example, when the category of the product for which the similar product is determined is the second category, the determination unit 132 is based on the similarity of the images included in each content. Judge similar products.

As a result, the determination device 100 according to the embodiment determines similar products based on the similarity of the images included in each content, for example, when the category of the product for which the similar products are determined is the second category. By doing so, it is possible to perform an appropriate determination process according to the product category. Therefore, it is possible to suppress the determination of dissimilar products as similar in the determination device 100 and appropriately determine the similarity of the products.

[6. Hardware configuration]
The determination device 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 function of the determination device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 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 that depends 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 the network N and sends it to the CPU 1100, and provides the data generated by the CPU 1100 to the other device via the network N.

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 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 determination device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

The embodiments of the present application have been described in detail with reference to the drawings, but these are examples, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure line of the invention. It is possible to carry out the present invention in other forms described above.

[7. Others]
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically 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 them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

In addition, the processes described in the above-described embodiments 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 acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Judgment system 100 Judgment device 121 History information storage unit 122 Similar product information storage unit 130 Control unit 131 Acquisition unit 132 Judgment unit 133 Transmission unit 10 Terminal device 50 Electronic commerce device N network

Claims (10)

An acquisition unit that acquires information about a user's click on each content displayed on a terminal device used by the user, which is each content corresponding to each of the products provided in electronic commerce.
Using the information on the co-occurrence of clicks based on the information on the user's clicks for each content acquired by the acquisition unit, among the products corresponding to the respective contents, a similar product group based on the co-occurrence of clicks is determined, and the above-mentioned Among the similar product groups determined based on click co-occurrence, similar similar products are determined based on the content of the content, and the lowest priced product among the listed content groups is included. If only the content is clicked, a determining section for determining the of the content group with products other than Great product wherein the lowest price product as a similar product,
A determination device comprising. Of the information regarding the user's click on each content displayed on the terminal device used by the user, which is the content corresponding to each of the products provided in the electronic commerce, the time when the user clicks is the time when the user clicks. An acquisition unit that acquires information about the user's click corresponding to one session, which is a period during which an action with a predetermined purpose is performed, and an acquisition unit.
Using the information about the co-occurrence of clicks based on the information about the user's click for each content corresponding to the one session, similar similar products are determined among the products corresponding to each of the contents, and the listed contents are displayed. of the group, and most if only Price low content including rates for products is clicked, the determination unit for determining the said content group with products other than Great products and the lowest price products to be similar products ,
A determination device comprising. The determination unit
Among the information regarding the user's click for each content, the information regarding the co-occurrence of clicks based on the information regarding the user's click corresponding to a predetermined period at the time when the user clicks is used to determine the similar product. The determination device according to claim 1. The determination unit
The determination device according to any one of claims 1 to 3, wherein the processing is varied according to the category of the product to be determined to determine the similar product, and the similar product is determined. The determination unit
When the category of the product for which the similar product is determined is the first category, the similar product is determined based on the information regarding the user's click on each content, and the product for which the similar product is determined is determined. The determination according to claim 4, wherein when the category is a second category different from the first category, the similar product is determined based on information other than the information regarding the user's click for each content. apparatus. The determination unit
The fifth aspect of the present invention is that when the category of the product for which the similar product is to be determined is the second category, the similar product is determined based on the similarity of the images included in the respective contents. The determination device described. It is a judgment method executed by a computer.
An acquisition process for acquiring information about a user's click on each content displayed on a terminal device used by the user, which is each content corresponding to each of the products provided in electronic commerce.
Using the information on the co-occurrence of clicks based on the information on the user's clicks for each content acquired in the acquisition process, a group of similar products based on the co-occurrence of clicks is determined among the products corresponding to the respective contents, and the above-mentioned Among the similar product groups determined based on click co-occurrence, similar similar products are determined based on the content of the content, and the lowest priced product among the listed content groups is included. If only the content is clicked, a determination step of determining the said content group with products other than Great product wherein the lowest price product as a similar product,
A determination method characterized by including. An acquisition procedure for acquiring information on a user's click on each content displayed on a terminal device used by the user, which is each content corresponding to each of the products provided in electronic commerce.
Using the information on the co-occurrence of clicks based on the information on the user's clicks for each content acquired by the acquisition procedure, a group of similar products based on the co-occurrence of clicks is determined among the products corresponding to the respective contents, and the above-mentioned Among the similar product groups determined based on click co-occurrence, similar similar products are determined based on the content of the content, and the lowest priced product among the listed content groups is included. If only the content is clicked, a determining step of determining the said content group with products other than Great product wherein the lowest price product as a similar product,
A judgment program characterized by having a computer execute. It is a judgment method executed by a computer.
Of the information regarding the user's click on each content displayed on the terminal device used by the user, which is the content corresponding to each of the products provided in the electronic commerce, the time when the user clicks is the time when the user clicks. An acquisition process for acquiring information about the user's click corresponding to one session, which is a period for performing an action with a predetermined purpose, and
Using the information about the co-occurrence of clicks based on the information about the user's click for each content corresponding to the one session, similar similar products are determined among the products corresponding to each of the contents, and the listed contents are displayed. of the group, and most if only Price low content including rates for products is clicked, the determination step of determining the said content group with products other than Great products and the lowest price products to be similar products ,
A determination method characterized by including. Of the information regarding the user's click on each content displayed on the terminal device used by the user, which is the content corresponding to each of the products provided in the electronic commerce, the time when the user clicks is the time when the user clicks. An acquisition procedure for acquiring information about the user's click corresponding to one session, which is a period for performing an action with a predetermined purpose, and an acquisition procedure.
Using the information about the co-occurrence of clicks based on the information about the user's click for each content corresponding to the one session, similar similar products are determined among the products corresponding to each of the contents, and the listed contents of the group, and most if only Price low content including rates for products is clicked, the determination procedure of determining the said content group with products other than Great products and the lowest price products to be similar products ,
A judgment program characterized by having a computer execute.

Images