JP2019045982A - Recommendation device, recommendation method and recommendation program - Google Patents

Abstract

To make a recommendation for purchase of each of commodities timely for the commodity.SOLUTION: A recommendation device relating to this application has a specification unit and a notification unit. The specification unit specifies a commodity in which the sales increase within a prescribed period, on the basis of sales information indicative of sales transitions of commodities. The notification unit performs notification relating to the commodity prior by a prescribed period to a timing when the sales of the commodity specified by the specification unit increase.SELECTED DRAWING: Figure 1

Description

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

  Today, there is known a service for recommending related products related to a purchased product to a user based on the purchase history of the product purchased through a network or the like.

  For example, Patent Document 1 (Japanese Patent Laid-Open No. 2016-206794) discloses an information processing apparatus that recommends a transaction object based on information obtained from the history of the transaction of the user. In the case of this information processing apparatus, information of the history in which the user purchases or browses a product is divided into items included in the hierarchy based on hierarchy information in which products are divided into a plurality of hierarchies. Then, from the history information divided for each item, the purchase tendency is modeled based on the entropy calculated for each hierarchy, and the product corresponding to the modeled result is recommended to the user.

  Further, Patent Document 2 (Japanese Patent Laid-Open No. 2016-181196) discloses an information processing apparatus that recommends a product that matches the user's preference based on product information including the content of a product image or a product description sentence. There is. In the case of this information processing apparatus, product data including a product image and a product description are converted into feature amounts, machine learning is performed together with feature amounts of user data for purchasing a product, and feature amounts of user data and feature amounts of product data Create a correlation learning model that has learned the correlation with. Further, the feature amount of the user data and the feature amount of the product data corresponding to the user who has accessed the site purchasing the product is acquired, and the machine learning to which the correlation learning model is applied is executed to calculate the matching degree. Then, the recommendation order is determined based on the calculated matching degree, and the determined products are recommended to the user.

JP, 2016-206794, A JP, 2016-181196, A

  However, there is a timing that is suitable for recommendation, such as when the demand is high for products. For this reason, it is preferable to recommend a product at a timing suitable for each product.

  This application is made in view of the above, and an object of the present invention is to provide a recommendation device, a recommendation method, and a recommendation program which make a recommendation for purchase of a product etc. at a timing suitable for each product.

  The recommendation device according to the present invention is specified from the time when the sales of the product specified by the specifying unit increase and the specifying unit specifying the product whose sales increases within a predetermined period based on the sales information indicating the sales transition of the product. And a notification unit for notifying of a product before the period.

  According to one aspect of the embodiment, there is an effect that it is possible to make a recommendation for purchase or the like of a product at a timing suitable for each product.

FIG. 1 is a diagram for explaining an outline of the recommendation process performed in the first embodiment and the second embodiment. FIG. 2 is a system configuration diagram of the recommendation system according to the first embodiment. FIG. 3 is a block diagram of the main part of the recommendation device of the recommendation system of the first embodiment. FIG. 4 is a diagram showing an example of sales information stored in the recommendation device of the recommendation system of the first embodiment. FIG. 5 is a diagram showing an example of user information stored in the recommendation device of the recommendation system of the first embodiment. FIG. 6 is a flowchart for explaining the product recommendation operation in the recommendation device of the recommendation system of the first embodiment. FIG. 7 is a diagram for explaining transition of the number of sales of goods per month. FIG. 8 is a block diagram of the main part of the recommendation device of the recommendation system of the second embodiment. FIG. 9 is a diagram showing an example of purchase history information stored in the recommendation device of the recommendation system of the second embodiment. FIG. 10 is a diagram showing an example of search information stored in the recommendation device of the recommendation system of the second embodiment. FIG. 11 is a flowchart for explaining the product recommendation operation in the recommendation device of the recommendation system of the second embodiment. FIG. 12 is a hardware configuration diagram of a recommendation device provided in the recommendation system of the first embodiment and the second embodiment.

  Hereinafter, as an example, a recommendation system, a recommendation method, and a recommendation system to which a recommendation program according to the present invention is applied are modes for implementing the recommendation device, the recommendation method, and the recommendation program according to the present application (hereinafter referred to as “embodiment”) It will be described in detail with reference to the drawings. Note that the recommendation device, the recommendation method, and the recommendation program according to the present application are not limited by the embodiment. Moreover, it is possible to combine each embodiment suitably in the range which does not make process contents contradictory. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

[Example of recommendation process]
First, an example of the recommendation process according to the first embodiment and the second embodiment will be described with reference to FIG. In the recommendation process of the first embodiment, the recommendation device 1 detects a product whose sales increases from the current time within a predetermined period. The term "goods" is a concept that includes intangible services and the like, such as services given to people and the like, as well as tangible articles.

  The example shown in FIG. 1 shows the transition of sales of school bags, socks and athletic shoes. In the case of this example, the school bag shows an increase in sales in December, the sock shows almost uniform sales throughout the year, and the sports shoes show an increase in sales in April and September. The recommendation device 1 detects such sales transition of each product.

  In addition, when the current date (the present time) is October 1st, the recommendation device 1 detects the presence or absence of a product whose sales will increase within a predetermined period, for example, within two months from October 1st. In the case of the example shown in FIG. 1, the product whose sales increase within two months from October 1 which is the present is a parcel. For this reason, the recommendation device 1 notifies the user that a sold out is expected to occur, for example, before a predetermined period such as one month or two months before the time when sales increase due to increased demand. Recommend the purchase of goods.

  Thus, it is possible to recommend the user to purchase the product at a timing suitable for each product. In addition, it is possible for the user to recommend the purchase of a product that is likely to be needed in the future, before the product is sold out and the purchase of the product becomes difficult due to the timely increase in sales.

  The above is the outline of the recommendation process of the first embodiment, but in addition to the above, in the recommendation process of the second embodiment, the recommendation device 1 applies to the user specified based on the user's purchase history, search information, etc. Recommend the purchase of products at the above-mentioned timing suitable for each product. Also, for example, for users who have purchased baby products six years ago, instead of simply identifying users based on purchase history etc., it is recommended to purchase school bags for elementary school children when six years have passed, etc. As described above, the product that the user needs with the passage of time is estimated, and the user is recommended to purchase the product at a timing appropriate for each of the products described above. Thereby, it is possible to provide the user who really needs the recommendation of the purchase of the product that is truly necessary.

Hereinafter, the configuration and the like of the recommendation device 1 that performs such recommendation processing and the recommendation system including the recommendation device 1 will be described in detail for each embodiment.
First Embodiment
(System configuration)
FIG. 2 shows a system configuration diagram of the recommendation system according to the first embodiment. As shown in FIG. 1, the recommendation system includes one or more recommendation devices 1 and one or more user terminals 2. The recommendation device 1 and the user terminal 2 are mutually connected via a predetermined network 3 such as the Internet or a LAN (Local Area Network).

  As the user terminal 2, in addition to a desktop type or laptop type personal computer device, a wearable terminal such as a glasses type or a watch type other than a cellular phone, a smartphone terminal, a tablet type terminal or the like can be used.

(Configuration of Recommendation Device of First Embodiment)
The control unit 6 is a controller, and is realized by, for example, a recommendation program 22 being executed by using a RAM as a work area by a central processing unit (CPU), a micro processing unit (MPU) or the like. Further, the control unit 6 is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 6 shown in FIG. 3 performs communication control with the user terminal 2 and executes the recommendation program 22 to realize the identification unit 31 and the notification unit 32. Although described later, the control unit 6 functions as the specifying unit 31 to detect a product whose sales increase in a predetermined period. In addition, the control unit 6 functions as the notification unit 32 to notify the user of the presence of a product whose sales increase in a predetermined period, and recommends the purchase.

  In addition, the recommendation program 22 for realizing each function is provided as a file in an installable format or an executable format, recorded on a recording medium readable by a computer device such as a CD-ROM, a flexible disk (FD), etc. It is also good. Further, the recommendation program 22 may be provided by being recorded on a recording medium readable by a computer device such as a CD-R, a DVD (Digital Versatile Disk), a Blu-ray Disc (registered trademark), and a semiconductor memory. The recommendation program 22 may also be provided in the form of installation via a network such as the Internet. Further, the recommendation program 22 may be provided by being incorporated in advance in a ROM or the like in the portable terminal.

(Style of sales information)
FIG. 4 is an example of the format of the sales information 23 stored in the storage unit 7. The sales information 23 and user information 24 described later are, for example, aggregated and distributed by the shopping server device on the network 3. The recommendation device 1 acquires the sales information 23 and the user information 24 from the shopping server device, and stores the sales information 23 and the user information 24 in the storage unit 7. In this example, although the sales information 23 and the user information 24 are acquired from the shopping server device, the sales information and the user information may be acquired from a computer device or the like of an actual store.

  As exemplified in FIG. 4, the user identification number (user ID), sales date, product name, sales quantity, sales store name, product price etc. be delivered. The control unit 6 of the recommendation device 1 stores and controls the sales information 23 acquired from the shopping server device in the storage unit 7.

  The example illustrated in FIG. 4 illustrates the sales information 23 when the user with the user ID “A123” purchases five pairs of socks for infants from the AB clothes store on August 10, 2011 for 1,500 yen. In this case, the user ID of "A123", the sales date of "August 10, 2011", the product name of "Socks (for infants)", the number of sales of "five pairs", and sales of "AB clothes store" Information indicating the store name and the price of the product of “1500 yen” is distributed as sales information 23 from the shopping server device. Similarly, the example illustrated in FIG. 4 illustrates the sales information 23 in the case where the user with the user ID “B911” has purchased one school bag from the F department store web shop on December 1, 2011 for 51,000 yen. . In this case, the user ID of "B 911", the sales date of "December 1, 2011", the product name of "Randel", the number of sales of "one", the sales store name of "F department store web store", , And information indicating the price of the “5100 yen” item is distributed as sales information 23 from the shopping server device. The control unit 6 stores and controls such sales information 23 in the storage unit 7.

(Style of user information)
FIG. 5 is an example of the form of the user information 24 stored in the storage unit 7. As exemplified in FIG. 5, the control unit of the recommendation device 1 in which the user ID, the user name, the e-mail address (mobile phone address), the address, the telephone number and the like are distributed from the shopping server device as the user information 24. 6 stores the user information 24 acquired from the shopping server device in the storage unit 7. In the example of FIG. 5, the user ID of "A123", the user name of "○○○○", the e-mail address of "A@B.com", the address of "Hokkaido Sapporo city ○○", "011- ○ An example is shown in which a telephone number or the like of “○○ ×××××” is distributed as the user information 24 from the shopping server device. Similarly, in the example of FIG. 5, the user ID of “A127”, the user name of “○ ×××”, the electronic mail address of “C@D.co.jp”, the address of “Yokohama City, Kanagawa Prefecture ××” An example is shown in which the telephone number or the like of "090-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------xxx-xxx, has been distributed as user information 24 from the shopping server device. The control unit 6 stores and controls such user information 24 in the storage unit 7.

(Product recommending operation according to the first embodiment)
Next, the product recommendation operation in the recommendation system of the first embodiment will be described. FIG. 6 is a flowchart showing the flow of the product recommendation operation in the recommendation system of the first embodiment. This flowchart is executed by the control unit 6 shown in FIG. 3 based on the recommendation program 22 stored in the storage unit 7 every predetermined time, for example, every three hours, every day, every month, etc. . In this example, the processing of the flowchart in FIG. 6 is performed at predetermined time intervals, but may be performed at any timing such as a timing designated by the administrator or the like.

  In step S1, based on the sales information 23 shown in FIG. 4, the identification unit 31 identifies a product whose number of sales increases in a predetermined period. For example, FIG. 7 shows the transition of the sales number of school bags. School bags require new students to become elementary school students in April of the following year, and because they are expensive, sales tend to increase in December of the previous year, which is the bonus period. Then, when sales of this school bag will increase within a predetermined period of time from the current date and time, it is expected to be sold out, so the identifying unit 31 designates the "song bag" as a product whose sales will increase within the predetermined period. Identify.

  Although this example is an example of specifying the presence or absence of sales increase on a monthly basis, if the sales fluctuate on an hourly basis per day, the presence or absence of the increase on sales may be specified on an hourly basis. If the sales fluctuate on a daily basis in January, the presence or absence of the sales increase may be specified on a daily basis.

  Next, in step S2 of the flowchart of FIG. 6, the identifying unit 31 determines whether a product (recommended product) whose sales increase within a predetermined period is present. For example, in the case of the school bag described with reference to FIG. Therefore, the identification unit 31 determines whether or not the current date is a date within a predetermined period, such as two months, from the beginning of December (December 1) when sales of school bags increase. Do.

  Also, for example, when “Oct. 1” is the current date (the current time), this current date is a date within two months (within a predetermined period) from the beginning of December when sales of school bags increase. (Step S2: Yes). In this case, the process proceeds to step S3, and the notification unit 32 illustrated in FIG. 3 notifies each user that the time to increase sales of school bags is near, based on the user information 24 described with reference to FIG. We will notify you of the impending month when there is a risk of being sold out.

  In addition, the notification unit 32 performs the above-described notification including information indicating the time when the recommended product is required. Specifically, in the case of a school bag, it will be necessary when entering the school in April of the following year. For this reason, the notification unit 32 performs the above-described notification including information indicating the time when the recommended product is required, such as “A school bag is required due to admission next April.” As a result, it is possible to notify each user that the recommended product is a highly necessary product, and it is possible to further increase the possibility that the user purchases the recommended product.

  In step S3, for example, if you have a child who goes on to elementary school, you will need a school bag in April next year. If you have a school bag, sales will peak in December each year, and it will be sold out. To create an e-mail that announces the sale of goods etc., such as “we recommend the early purchase”, and send it to each user based on the user information 24 described above, the communication unit 15 Communication control. As a result, each user registered with the user information 24 can consider the purchase of a product that is likely to be needed in the future, before the product is sold out.

  In this example, the user is notified by e-mail, but each user may be notified by displaying the text or the like of the above content as an advertisement of the portal site. You may make a push notification.

  Further, in step S2 described above, when it is determined by the specifying unit 31 that there is no item whose sales increases within a predetermined period such as two months, for example (step S2: No), the notification to the above user is given. Since it is not the timing to perform, the processing of the flowchart of FIG.

(Effects of the first embodiment)
As is clear from the above description, the recommendation system according to the first embodiment detects a product at the time when sales increase within a predetermined period, and notifies each user. By this, it is possible to prompt each user to consider the purchase of the product and to recommend the purchase of the product meeting the user's potential needs before sales increase and being sold out. In addition, it is possible to make a recommendation for purchase of a product or the like at a timing suitable for each product.

  In addition, the recommendation system of the first embodiment can enable sales of a number of items or more before the peak of sales. In addition, although it is an example, even if it is a seller who performs product management by the minimax system that places an order for products so as to maximize the product inventory when the product inventory is minimized. It is possible to improve the sales of products by preventing the occurrence of stock as much as possible.

Second Embodiment
Next, the recommendation system of the second embodiment will be described. The example of the first embodiment described above is an example in which each user is notified of a product at the time when sales increase. On the other hand, the recommendation system according to the second embodiment described below is an example of specifying a user who is likely to be required in the future among the users who recommend a product, and recommending the product. The first embodiment described above and the second embodiment described below are different only in this point. Therefore, hereinafter, only the difference between the two will be described, and the redundant description will be omitted.

(Configuration of Recommendation Device of Second Embodiment)
FIG. 8 is a block diagram of the main part of the recommendation device 1 in the recommendation system of the second embodiment. As shown in FIG. 8, in the case of the second embodiment, the recommendation device 1 includes a communication unit 5, a control unit 6, and a storage unit 7 as in the above-described first embodiment. The storage unit 7 includes the above-described operation system (OS) 21, sales information 23, and user information 24, as well as a recommendation program 51 for the recommendation device 1 of the second embodiment, purchase history information 52, and search information 53 (log An example of the information is stored.

  The control unit 6 realizes the estimation unit 41 and the detection unit 42 in addition to the identification unit 31 and the notification unit 32 by executing the recommendation program 51. Although described later, the control unit 6 functions as the specifying unit 31 to detect a product whose sales increase in a predetermined period. Further, the control unit 6 functions as the detection unit 42 to detect a user who has purchased a product (recommended product) whose sales is increased within a predetermined period. Further, the control unit 6 functions as the estimation unit 41. A user with a search history that is the same as or similar to the search history of the user who purchased the recommended product is estimated as a user who is highly likely to purchase the recommended product. Then, the control unit 6 functions as the notification unit 32, thereby notifying the user who has detected the presence of the recommended product based on the above-described search history and recommending the purchase.

(Style of purchase history information)
FIG. 9 is an example of the format of the purchase history information 52 stored in the storage unit 7. The purchase history information 52 and the search information 53 to be described later are aggregated and distributed by the shopping server apparatus on the network 3 together with the sales information 23 and the user information 24 described above. The recommendation device 1 acquires the purchase history information 52 and the search information 53 together with the sales information 23 and the user information 24 from the shopping server device, and stores the information in the storage unit 7. In this example, the purchase history information 52 and the search information 53 are acquired from the shopping server device, but the purchase history information 52 and the search information 53 may be acquired from a computer device or the like of an actual store , As described above.

  As exemplified in FIG. 9, as the purchase history information 52, the shopping server device distributes a user ID, a user name, a purchase date, a product name, a purchase quantity, a purchase store name, a purchase price, and the like. The example illustrated in FIG. 9 indicates that the user whose user ID is A123 purchases five pairs of socks for infants from the AB clothes store on August 10, 2011, and the purchase price is 1,500 yen. An example in which the history information 52 is distributed is shown. Similarly, the example illustrated in FIG. 9 indicates that a user whose user ID is B911 purchases one pair of athletic shoes from J shoes store on September 4, 2016, and the purchase price is 3,500 yen. An example in which the history information 52 is distributed is shown. The control unit 6 stores and controls such purchase history information 52 in the storage unit 7.

(Style of search information)
FIG. 10 is an example of the format of the search information 53 stored in the storage unit 7. As exemplified in FIG. 10, as the search information 53, a user ID, a user name, a search time (search date, hour, minute, and second), a search word and the like are distributed from the shopping server device. In the example illustrated in FIG. 10, search information indicates that the user with the user ID A123 performed the network search using the search word (query) of “Below, baby, cotton” on August 10, 2011. 53 indicates that it has been delivered. Similarly, in the example illustrated in FIG. 10, the search information 53 indicating that the user whose user ID is B911 has performed the network search on June 10, 2011 using the search word of “Hail String, Price” is Indicates that it was delivered.

  In the following, an example will be described in which another user performing network search identical or similar to a user who has purchased a recommended product is detected using a search word (query) input by a user (purchaser). However, instead of the search word or together with the search word, browsing history information which is information on the content browsed by the purchaser and / or purchase history information which is information on the product purchased by the purchaser is used May be

(Product recommending operation according to the second embodiment)
Next, the product recommendation operation in the recommendation system of the second embodiment will be described. FIG. 11 is a flowchart showing the flow of the product recommendation operation in the recommendation system of the second embodiment. Each process of step S1 and step S2 of this flowchart is the same process as each process of step S1 and step S2 of the flowchart of FIG. That is, in step S1 and step S2, the specification unit 31 specifies a recommended product whose sales increases in a predetermined period. The process then proceeds to step S11. For the detailed operations of step S1 and step S2, refer to the description of the first embodiment described above.

  Next, in step S11, the detection unit 42 shown in FIG. 8 purchases the recommended product (the product specified in step S2) in the past by referring to the purchase history information 52 of each user described with reference to FIG. Detect the user who has Specifically, when, for example, a "song bag" is specified as a recommended product by the specifying unit 31, the detecting unit 42 detects the user who has purchased the package by referring to the purchase history information 52. In the case of the example shown in FIG. 9, the user whose user ID is A123 purchases the parcel on December 1, 2017. Therefore, the detection unit 42 detects a user whose user ID is A123 as a user who has purchased a recommended product in the past.

  Next, in step S12, the estimation unit 41 detects a user having the same or similar log information based on the user's log information detected in step S11. Specifically, in the example of the purchase history information 52 shown in FIG. 9, the user whose user ID is A123 purchases the parcel on December 1, 2017. Referring to the search information 53 shown in FIG. 10 and searching the search information 53 of the user whose user ID is A123, August 10, 2011, which is six years before December 1, 2017, when the parcel was purchased During September 3, 2011, search is performed using search words such as "socks", "baby", and "hug straps". This is the preparation of the elementary school entrance ceremony to be held in April 2018 on December 1, 2017, six years after the birth of a newborn baby to a user (or relatives etc.) whose user ID is A123 It means that you are going.

  Therefore, in step S12, the estimation unit 41 performs a search using a search word for newborns, such as "socks", "baby", and "hug cord" 6 years ago, similarly to the user whose user ID is A123. Other users are detected from the search information 53. In the case of the example of FIG. 10, the user whose user ID is B911 is six years ago, and the user ID performs a search with search words of “hail string” and “price” at about the same time as the user whose user ID is A123. There is. Therefore, it is highly possible that a user (or a relative or the like) whose user ID is B 911 is born in 2011 and is preparing for the entrance ceremony for the elementary school to be held in April 2018. Therefore, the estimation unit 41 detects a user whose user ID is B911 as a user of log information that is the same as or similar to the user who purchased the recommended product (user whose user ID is A123).

  By detecting another user who is performing a search based on the search information 53 similar to the search information 53 of the user who purchased the recommended product, the other user in the living environment similar to the living environment of the user who purchased the recommended product It can be detected. That is, it is possible to identify and detect (estimate) a user who is highly likely to need a recommended product in the future, and is highly likely to purchase the recommended product.

  Thus, when another user of the living environment similar to the living environment of the user who purchased the recommended product is detected, the notification unit 32 searches in step S13 for the same search information 53 as the search information 53 of the user who purchased the recommended product. As described above, notification control such as e-mail is performed to other users who are searching for information 53. This makes it possible to identify a user who is more likely to purchase and a user who will need to purchase in the future, and to make a notification that recommends the purchase of a product.

(Effect of the second embodiment)
As is clear from the above description, the recommendation system of the second embodiment can obtain the following effects in addition to the same effects as the recommendation system of the first embodiment described above.

  In order to recommend the purchase of the recommended product to other users who are searching with the same search information 53 as the search information 53 of the user who purchased the recommended product, in the same living environment as the user who purchased the recommended product It is possible to recommend the purchase of a recommended product to a user who is highly likely to live. For this reason, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

[Hardware configuration]
The recommendation device 1 and the user terminal 2 of the above-described embodiments are realized by, for example, a computer device having a configuration shown in FIG. Hereinafter, the recommendation device 1 will be described as an example. FIG. 12 is a hardware configuration diagram showing an example of a computer device that implements the function of the recommendation device 1. The computer device includes a CPU 11, a RAM 12, a ROM 13, an HDD 14, a communication unit 15, an input / output interface (I / F) 16, and a media interface (I / F) 17.

  The CPU 11 corresponds to the control unit 6 shown in FIGS. 3 and 8. The CPU 11 operates based on a program stored in the ROM 13 or the HDD 14 to control each part. The ROM 13 stores a boot program executed by the CPU 11 when the computer device is started, a program depending on the hardware of the computer device, and the like.

  The RAM 12 to the HDD 14 correspond to the storage unit 7 shown in FIGS. 3 and 8. The HDD 14 stores programs executed by the CPU 11, data used in these programs, and the like. The communication unit 15 corresponds to the communication unit 5 shown in FIGS. 3 and 8. The communication unit 15 receives data from another device via the network 3 shown in FIG. 2 and transfers the data to the CPU 11, and transmits the data generated by the CPU 11 to the other device via the network 3.

  The CPU 11 controls an output device such as a display device and a printer device, and an input device such as a keyboard device and a mouse device via the input / output interface 16. The CPU 11 acquires data from the input device via the input / output interface 16. The CPU 11 also outputs the data generated through the input / output interface 16 to the output device.

  The media interface 17 reads a program or data stored in the recording medium 18 and provides the CPU 11 with the program via the RAM 12. The CPU 11 loads such a program from the recording medium 18 via the media interface 17 onto the RAM 12 and executes the loaded program. The recording medium 18 is, for example, an optical recording medium such as a digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer device operates as the recommendation device 1 according to the embodiment, the CPU 11 of the computer device implements the function of the control unit 6 by executing the above-described recommendation program loaded on the RAM 12. Further, data in the storage unit 7 is stored in the HDD 14. The CPU 11 of the computer device reads these programs from the recording medium 18 and executes them, but as another example, these programs may be acquired from another device via the network 3.

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

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured. Moreover, it is possible to combine suitably the above-mentioned each embodiment and modification in the range which does not make process content contradictory.

〔effect〕
As described above, the recommendation device 1 of the recommendation system according to each embodiment identifies the identification unit 31 that identifies the product whose sales increase in a predetermined period, based on the sales information indicating the sales transition of the product, and the identification unit 31 And a notification unit 32 for notifying of a product before a predetermined period from the time when the sales of the product specified by the item increase.

  By this, it is possible to prompt each user to consider the purchase of the product and to recommend the purchase of the product meeting the user's potential needs before sales increase and being sold out. In addition, it is possible to make a recommendation for purchase of a product or the like at a timing suitable for each product.

  Further, sales information including at least information indicating the date of sale of the product and information indicating the number of sales is used. This makes it possible to more clearly identify the product whose sales increase in a predetermined period.

  The information processing apparatus further includes an estimation unit 41 for estimating a user who is expected to purchase a product based on purchaser information on a purchaser of the product, and the notification unit 32 transmits the product for the user estimated by the estimation unit 41. Make a notification about

  In this manner, the same as the user who has purchased the recommended product because the recommendation of purchasing the recommended product is recommended to other users who are searching with the search information 53 similar to the search information 53 of the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to live in a living environment. For this reason, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

  In addition, the estimation unit 41 uses a product having a user whose living environment is the same as or similar to the living environment of the purchaser based on the purchaser information including information on the living environment of the purchaser when the purchaser purchases the product. Estimate as a user who is expected to purchase.

  As a result, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

  In addition, the estimation unit 41 is at least one of a search query input by the purchaser, a browsing history that is information related to content browsed by the purchaser, and a purchase history that is information related to a product purchased by the purchaser. Information on the purchaser's living environment based on the

  As a result, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

  Further, the specifying unit 31 specifies a product expected to be sold out in the future as a product whose sales increase in a predetermined period.

  This enables the user to proceed with the purchase of a more highly necessary product.

  Further, the notification unit 32 performs notification including information indicating when the product specified by the specifying unit 31 is required.

  This makes it possible to clearly indicate to the user when the product is needed.

  Further, in the recommendation method applied to the recommendation device 1 of the recommendation system according to each embodiment, the identification unit 31 identifies the product whose sales increase within a predetermined period based on the sales information indicating the sales transition of the product. In the identification step, the notification unit 32 performs notification on the product a predetermined period before the time when sales of the product specified by the identification unit 31 increase.

  By this, it is possible to prompt each user to consider the purchase of the product and to recommend the purchase of the product meeting the user's potential needs before sales increase and being sold out. In addition, it is possible to make a recommendation for purchase of a product or the like at a timing suitable for each product.

  Further, in the recommendation method applied to the recommendation device 1 of the recommendation system of each embodiment, the estimation unit 41 estimates a user who is expected to purchase a product based on purchaser information on a purchaser of the product. In the notification step, the notification unit 32 notifies the user estimated by the estimation unit 41 of the product.

  In this way, the same living environment as the user who has purchased the recommended product can be recommended because the recommendation of purchasing the recommended product is recommended to other users who are searching with the same search information as the search information of the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to be living in Japan. For this reason, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

  Further, the recommendation program executed by the recommendation device 1 of the recommendation system according to each embodiment identifies the product whose sales increase in a predetermined period based on the sales information 23 indicating the sales transition of the product. 31 and the notification unit 32 that notifies of a product about a predetermined period before the time when sales of the product specified by the specification unit 31 increase.

  By this, it is possible to prompt each user to consider the purchase of the product and to recommend the purchase of the product meeting the user's potential needs before sales increase and being sold out. In addition, it is possible to make a recommendation for purchase of a product or the like at a timing suitable for each product.

  Further, the recommendation program executed by the recommendation device 1 of the recommendation system of each embodiment is a computer as the estimation unit 41 that estimates a user who is expected to purchase a product based on purchaser information on a purchaser of the product. Further, the notification unit notifies the user estimated by the estimation unit 41 about the product.

  As a result, since the recommendation product purchase is recommended to other users who are searching based on the search information 23 similar to the search information 23 of the user who purchased the recommended product, the same as the user who purchased the recommended product It is possible to recommend the purchase of recommended products to users who are likely to live in a living environment. For this reason, it is possible to recommend the purchase of a product by identifying users who are more likely to purchase and users who will need to purchase in the future.

  As mentioned above, although each embodiment of this application was described in detail based on a drawing, this is an illustration and various modifications and improvements are based on the knowledge of those skilled in the art including the aspect described in the column of the disclosure of the invention. It is possible to practice the invention in other forms which have been applied.

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

DESCRIPTION OF SYMBOLS 1 recommendation apparatus 2 user terminal 3 network 5 communication part 6 control part 7 memory part 11 CPU
12 RAM
13 ROM
14 HDD
15 Communication Unit 21 Operation System (OS)
22 recommendation program corresponding to the first embodiment 23 sales information 24 user information 31 identification unit 32 notification unit 41 estimation unit 42 detection unit 51 recommendation program corresponding to the second embodiment 52 purchase history information 53 search information

Claims (11)

A specific unit that specifies a product whose sales increase within a predetermined period based on sales information indicating a sales transition of the product;
And a notification unit for notifying of the product a predetermined period before the time when sales of the product specified by the specifying unit increase. The recommendation device according to claim 1, wherein the sales information includes at least information indicating a date of sale of a product and information indicating the number of sales. The information processing apparatus further includes an estimation unit configured to estimate a user who is expected to purchase the product based on purchaser information on a purchaser of the product,
The recommendation device according to claim 1 or 2, wherein the notification unit notifies the user estimated by the estimation unit regarding the product. The estimation unit is a user having a living environment identical or similar to the living environment of the purchaser based on the purchaser information including information on the living environment of the purchaser when the purchaser purchases the item. The recommendation device according to claim 3, wherein the recommendation device is estimated as a user who is expected to purchase the product. The estimation unit is at least one of a search query input by the purchaser, a browsing history that is information related to content browsed by the purchaser, and a purchase history that is information related to a product purchased by the purchaser. The recommendation device according to claim 3 or 4, wherein information on the living environment of the purchaser is estimated based on one. The said specific part specifies the goods which are expected to be sold out in the future as said goods in which sales increase in a predetermined period. It is characterized by the above-mentioned. Recommendation device. 7. The notification unit according to any one of claims 1 to 6, wherein the notification unit performs the notification including information indicating a time when the product specified by the identification unit is required. Recommendation device. A specific step of specifying a product whose sales increases within a predetermined period based on sales information indicating a sales transition of the product;
A notifying step of notifying the product of a predetermined period before a time when sales of the product specified by the specifying unit increase. The estimating unit further includes an estimating step of estimating a user who is expected to purchase the product based on purchaser information on a purchaser of the product,
The recommendation method according to claim 8, wherein, in the notification step, the notification unit notifies the user estimated by the estimation unit regarding the product. Computer,
A specific unit that specifies a product whose sales increase within a predetermined period based on sales information indicating a sales transition of the product;
A recommendation program characterized in that it functions as a notification unit that notifies of the product about a predetermined period before a time when sales of the product specified by the specification unit increase. The computer,
It further functions as an estimation unit that estimates users who are expected to purchase the product based on the purchaser information on the purchaser of the product,
The recommendation program according to claim 10, wherein the notification unit notifies the user estimated by the estimation unit regarding the product.

Images