Information processing system, information processing method, and program

Abstract

To enable a user to search for a product that is preferable to the user. [Solution] The information processing system acquires a first query, extracts at least one product from a plurality of pre-stored products based on the first query, acquires other products associated with the extracted product, acquires at least one query associated with the other products as a second query, and outputs information corresponding to the second query along with the products searched for based on the first query.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] The search results page of an e-commerce site displays advertisements based on the search query entered by the user, as well as products based on the search query. [Prior art documents] [Non-patent literature]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2010-165171 Summary of the Invention [Problem to be solved by the invention]

[0004] To suggest a wider variety of products, it is possible to display products that correspond to a search query and other products related to the searched product. However, to find other products related to a certain product, data indicating the relationship between the products is required in advance, and this data is not always sufficient. This makes it difficult to find a new product as another product, and the variety of other products found is limited, which does not necessarily result in useful results for users.

[0005] An object of the present disclosure is to provide a technology that enables a user to search for products that are desirable to the user, such as related products with a wide variety or new products, in a product search. [Means for solving the problem]

[0006] In order to solve the above problem, the information processing system according to the present disclosure includes a first acquisition means for acquiring a first query, a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query, an associated acquisition means for acquiring other products associated with the extracted product, a second acquisition means for acquiring at least one query associated with the other products as a second query, and an output means for outputting information corresponding to the second query together with the product searched for based on the first query.

[0007] The information processing method according to the present disclosure also includes the steps of acquiring a first query, extracting at least one product from a plurality of pre-stored products based on the first query, acquiring other products associated with the extracted product, acquiring at least one query associated with the other products as a second query, and outputting information corresponding to the second query together with the products searched for based on the first query.

[0008] The program according to the present disclosure also causes a computer to function as a first acquisition means for acquiring a first query, a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query, an associated acquisition means for acquiring other products associated with the extracted product, a second acquisition means for acquiring at least one query associated with the other products as a second query, and an output means for outputting information corresponding to the second query together with the products searched for based on the first query. [Effects of the Invention]

[0009] The present invention allows users to search for products that are more desirable than when searching with a simple query alone. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 2 is a diagram illustrating an example of elements related to a search system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing functions realized by the search system. [Figure 3] FIG. 10 is a flow chart illustrating an example of a process of the search system. [Figure 4] FIG. 10 is a diagram illustrating an example of a screen on which a query is input. [Figure 5] FIG. 10 is a diagram illustrating an example of a screen displayed based on the output of a display control unit. [Figure 6] FIG. 10 illustrates an example of processing by an additional query acquisition unit; [Figure 7] FIG. 10 is a diagram illustrating an example of data stored in a search history. [Figure 8] FIG. 10 is a diagram illustrating an example of data stored in a behavior history. [Figure 9] FIG. 10 is a diagram illustrating another example of the process of the additional query acquisition unit. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Duplicate descriptions of components with the same reference numerals will be omitted.

[0012] 1 is a diagram showing an example of elements related to a search system according to an embodiment of the present invention. The search system includes one or more servers 1, and transmits and receives information to a user terminal 2 via a network (not shown). The search system acquires a query entered by a user via the user terminal 2, and transmits information including products selected based on the query to the user terminal 2. The user terminal 2 is, for example, a computer such as a personal computer or a smartphone.

[0013] The search system includes one or more servers 1. The server 1 includes one or more processors 11, one or more storages 12, and one or more communication units 13. The search system may include multiple computers, each including one or more processors 11, storages 12, and communication units 13, or may include a single computer having one or more processors 11 and storages 12. The search system may be implemented on one or more virtual servers or container platforms.

[0014] The processor 11 operates according to a program (also referred to as an instruction code) stored in the storage 12. The processor 11 also controls the communication unit 13. The processor 11 includes, for example, a CPU (Central Processing Unit), and may further include a GPU (Graphic Processing Unit) and an NPU (Neural Processing Unit). The program may be provided via the Internet or the like, or may be provided by being stored in a computer-readable storage medium such as a flash memory or a DVD-ROM.

[0015] The storage 12 is composed of memory elements such as RAM and flash memory, and external storage devices such as a hard disk drive (HDD) and a solid state drive (SSD). The storage 12 stores the above programs. The storage 12 also stores information input from the processor 11 and the communication unit 13 and calculation results.

[0016] The communication unit 13 is a communication interface, such as a network interface card, that communicates with other devices. The communication unit 13 is configured with an integrated circuit, an antenna, a communication terminal, etc. that realize a wireless LAN or a wired LAN. Under the control of the processor 11, the communication unit 13 inputs information received from other devices via a network to the processor 11 or the storage 12, and transmits the information to other devices.

[0017] The hardware configuration of the search system is not limited to the above example. For example, the search system may include a device for reading a computer-readable information storage medium (e.g., an optical disk drive or a memory card slot) or a device for inputting and outputting data to and from an external device (e.g., a USB port). The external device may be an input device or an output device.

[0018] Next, the functions provided by the search system will be described. FIG. 2 is a block diagram showing the functions realized by the search system. The search system functionally includes a query acquisition unit 51, an additional query acquisition unit 52, a product search unit 53, an advertisement search unit 54, a display control unit 55, a search history 61, and a behavior history 62. The additional query acquisition unit 52 functionally includes a product extraction unit 56, a related product acquisition unit 57, and an additional acquisition unit 58. The query acquisition unit 51, the additional query acquisition unit 52, the product search unit 53, the advertisement search unit 54, and the display control unit 55 are realized by the processor 11 executing programs corresponding to each function stored in the storage 12 and controlling the communication unit 13, etc. The search history 61 and the behavior history 62 are stored in the storage 12.

[0019] The search history 61 stores at least one product that has been selected from the product database based on a plurality of queries previously input by a plurality of users, and on which a predetermined action (e.g., purchase or viewing) has been taken, in association with each of the queries. The products stored here are, strictly speaking, product identification information. In the following, products stored outside the product database strictly refer to product identification information. The search history 61 stores information on many users, not just the user who inputs the query. Using information on many users in the processing of the additional query acquisition unit 52, described below, improves the accuracy of the processing and makes it easier to ensure a variety of displayed products.

[0020] The search history 61 may be generated based on the input history of search queries and the browsing or purchase history of products in the same session. The search history 61 may also store queries previously input by multiple users and products extracted from a product database based on the queries, with the products being associated with the queries and having a suitability to the queries calculated by a known algorithm that is equal to or greater than a threshold.

[0021] The behavior history 62 stores a plurality of products for which a predetermined action was taken together in association with each other. More specifically, the behavior history 62 stores a plurality of products for which the action was taken in the same session in association with each other. The search history 61 and the behavior history 62 may be managed in a searchable manner by a database management system.

[0022] The query acquisition unit 51 acquires a main query from a user.

[0023] The additional query acquisition unit 52 acquires an additional query based on the main query. Here, the additional query acquisition unit 52 may acquire the additional query by executing the processes of the product extraction unit 56, the related product acquisition unit 57, and the additional acquisition unit 58 in real time based on the main query.

[0024] Instead of real-time processing, a plurality of sets of associated original queries (corresponding to the main query) and additional queries may be stored in advance in a database (not shown), and the additional query acquisition unit 52 may acquire the additional queries associated with the main query from the database. In this case, the additional query acquisition unit 52 has a function of acquiring in advance each of the plurality of original queries stored in the search history 61 as the original query to be processed, and the processes of the product extraction unit 56, the related product acquisition unit 57, and the additional acquisition unit 58 are executed in advance for the original query to be processed. The original query to be processed may be each of the plurality of queries from which duplicates have been eliminated.

[0025] The product extraction unit 56 extracts at least one product from a plurality of pre-stored products based on each of the original queries or the main query (hereinafter collectively referred to as a "first query"). The product extraction unit 56 may extract at least one product stored in association with the first query from the search history 61.

[0026] Here, the product extraction unit 56 extracts from the search history 61 products that have been selected based on the first query and for which a first action (e.g., purchase) has been taken, and if the number of products obtained is less than the first required number, the product extraction unit 56 may further extract from the search history 61 products that have been selected based on the first query and for which a second action (e.g., viewing) has been taken.

[0027] The related product acquisition unit 57 acquires other products associated with each of the extracted products. More specifically, the related product acquisition unit 57 may select other products stored in association with each of the at least one extracted product from the behavior history 62. The related product acquisition unit 57 may select other products for which a first action has been taken together with each of the at least one extracted product from the behavior history 62, and if the number of selected other products is less than the second required number, may further select other products for which a second action has been taken together with each of the at least one extracted product from the behavior history 62.

[0028] The related product acquisition unit 57 may calculate a first score of the selected other products relative to the selected product. The first score is a value obtained by dividing the number of times a predetermined action was performed on the selected product and the other selected products together by the product of the number of times the predetermined action was performed on the selected product and the number of times the predetermined action was performed on the other selected products.

[0029] The additional acquisition unit 58 acquires at least one query associated with the other product as an additional query (second query). More specifically, the additional acquisition unit 58 may acquire, from the search history 61, a past query associated with the other selected product as the additional query.

[0030] The additional acquisition unit 58 may calculate a second score for the past search query in which the selected other product was searched for. The second score is a value obtained by dividing the number of times the other product was searched for using the past query and a predetermined action was taken on the other product by the product of the number of times the other product was searched for using the past query and the number of times a predetermined action was taken on the other product.

[0031] The product search unit 53 selects products based on the main query and also based on the additional query.

[0032] The advertisement search unit 54 selects an advertised product based on the main query, and also selects an advertised product based on the additional query.

[0033] The display control unit 55 outputs information corresponding to the additional query along with the product searched for based on the main query. The information may be output to the user terminal 2. The display control unit 55 may output information for displaying both the product selected based on the first query and the product selected based on the additional query. More specifically, the display control unit 55 may output information for displaying the product selected based on the first query in association with the first query, and for displaying the product selected based on the additional query in association with the additional query. Here, the display control unit 55 may display either of the above and output information for displaying the advertised product selected based on the additional query. The display control unit 55 may output information for displaying the advertised product selected based on the additional query in association with the additional query.

[0034] Next, the processing of the search system will be described in more detail with reference to Fig. 3, which is a flow chart showing an example of the processing of the search system.

[0035] First, the query acquisition unit 51 acquires a main query from a user (S101). More specifically, the query acquisition unit 51 acquires, from the user terminal 2, a query input by the user as the main query.

[0036] 4 is a diagram showing an example of a screen on which a query is input. In the example of FIG. 4, "protein" is input as the main query.

[0037] Here, the query acquisition unit 51 may correct variations in the expression of the query entered by the user and acquire the corrected query as the main query. More specifically, the query acquisition unit 51 may delete unnecessary characters, standardize the notation of katakana, hiragana, and kanji, and standardize parts of speech for the entered query.

[0038] When the main query is acquired, the product search unit 53 selects a product from the product database based on the main query (S102). The product database stores attribute information and description information for each product, and the product search unit 53 selects a product having attribute information or description information that satisfies the conditions specified by the main query.

[0039] The advertisement search unit 54 selects an advertisement product to be displayed from a plurality of advertisement products registered in the advertisement database based on the main query (S103). The advertisement database stores advertisement products associated with queries, and the advertisement search unit 54 selects an advertisement product associated with the main query. The advertisement product corresponding to the query (keyword) in the advertisement database may be determined or set by an advertiser who bids on the keyword and wins the bid.

[0040] Furthermore, the additional query acquisition unit 52 acquires additional queries based on the main query (S104). Details of the processing by the additional query acquisition unit 52 will be described later.

[0041] When the additional query is acquired, the product search unit 53 selects a product from the product database based on the additional query (S105). The advertisement search unit 54 selects an advertised product to be displayed from a plurality of advertised products registered in the advertisement database based on the additional query (S106).

[0042] Then, the display control unit 55 outputs control information (image data) for displaying a screen including the main query, the products and advertised products selected based on the main query, the additional query, and the products and advertised products selected based on the additional query (S107).

[0043] FIG. 5 is a diagram illustrating an example of a screen displayed based on the output of the display control unit 55. In the example of FIG. 5, the additional query acquisition unit 52 acquires "creatine" as an additional query for "protein" corresponding to the main query. The display control unit 55 generates data for displaying the advertised products Ad1 to Ad3 acquired based on the main query and the products Item1 to Item5 acquired based on the main query in association with each other, for example, by arranging them directly below the main query. The display control unit 55 generates data for displaying the advertised products Ad ex1 to Ad ex3 acquired based on the additional query and the products Item ex1 to Item ex5 acquired based on the additional query in association with each other, for example, by arranging them directly below the additional query. The display control unit 55 may display the additional query in an area shaped similar to a search window so that it is clear that the additional query is a query.

[0044] The display control unit 55 may also generate data so that only the additional query is placed on the screen in a visible state, and the advertised product acquired based on the additional query and the product acquired based on the additional query are displayed when an icon around the additional query is clicked.

[0045] Many users are not clear about what they really want and are not experienced at searching. As a result, the primary query they enter is not necessarily optimal. Displaying products and advertisements based on other queries increases the variety of products, allowing users to find the product they want more quickly, for example. Furthermore, by clearly indicating additional queries and displaying the results in association with the additional queries, users can avoid confusion when they see images of the increased variety of products. Furthermore, by making products easier to find and reducing confusion, users are less likely to give up on their search, which makes it possible to operate the system efficiently while reducing wasted time.

[0046] Next, a description will be given of details of the processing of the additional query acquisition unit 52. Fig. 6 is a diagram showing an example of the processing of the additional query acquisition unit 52. In the processing shown in Fig. 6, after the main query is input, the additional query acquisition unit 52 acquires an additional query using the search history 61 and the behavior history 62.

[0047] The product extraction unit 56 included in the additional query acquisition unit 52 first extracts products associated with the main query (hereinafter also referred to as the “original query”) (S201). More specifically, the additional query acquisition unit 52 extracts products stored in association with the original query from the search history 61.

[0048] 7 is a diagram showing an example of data stored in the search history 61. The search history 61 stores information on at least one product that was selected based on a plurality of past queries and on which a predetermined action (e.g., viewing or purchase) was performed, in association with each of the queries. The search history 61 is data indicating a mapping between queries and products.

[0049] In the example of FIG. 7, the search history 61 stores a timestamp, a user, a query, a product, and a type of action. Specifically, the timestamp is the time when the action indicated by the type was performed, the user is the identification information of the user who input the query and performed the action, and the product is the identification information of the product that was displayed by the query and for which the action was performed. If the type is set to "purchase," the query that triggered the purchase, the timestamp of the purchase, and the identification information of the purchased product are set. If a search using a query and an action are performed in the same session, the query and the product for which the action was performed may be associated. In this search history 61, by associating only products that are linked to an action with the query, it is possible to prevent inappropriate products that were searched for by the query from being used in processing.

[0050] Here, the product extraction unit 56 may first extract products that have been searched for using a query and have been purchased from the search history 61, and if the number of extracted products is less than the required number of products to be extracted (a threshold), further extract products that have been searched for using a query and have been purchased. In other words, the product extraction unit 56 first extracts products for a first action (purchase in this case) that has a high degree of relevance but a small quantity, and if the number of extracted products is equal to or less than the threshold, further extracts products for a second action (browsing in this case) that has a low degree of relevance but a large quantity. This makes it possible to achieve a balance between the precision and quantity of additional queries that can ultimately be obtained.

[0051] The product extraction unit 56 may further generate a score Sc1 for each of the extracted products. When a query q and a product p are associated with each other, the score Sc1 for the combination of the query q and the product p may be calculated using the following formula:

[0052] Sc1=SQP(q,P) / (SQ(q)×SP(p))

[0053] Here, SQP(q,p) is the number of times a user searches using query q and takes one action (e.g., purchase) on product p, SQ(q) is the number of times a user searches using query q, and SP(p) is the number of times a user purchases product p. Each of SQP(q,p), SQ(q), and SP(p) is equivalent to the sum of the number of times counted for one or more users (e.g., all active users of the search system) who are the subject of score calculation.

[0054] The number of sessions in which a search or action was performed may be used as the number of times the search or action was performed. The score is calculated for the action used to retrieve the product. For example, if a product that was purchased after a query is retrieved, the score for the combination of the query and the product is calculated for the purchase action.

[0055] When a product is extracted in the process of S201, the related product acquisition unit 57 included in the additional query acquisition unit 52 acquires other products associated with the extracted product (S202). More specifically, the related product acquisition unit 57 selects other products stored in association with each of the at least one extracted product from the behavior history 62.

[0056] FIG. 8 is a diagram showing an example of data stored in the behavior history 62. In the behavior history 62, multiple products for which a predetermined action was taken together are stored in association with each other. The behavior history 62 is data showing the mapping of multiple products. In the example of FIG. 8, the products are associated with each other by session ID and type. More specifically, products indicated by product IDs written in multiple columns with the same session ID and type are associated with each other as multiple products for which a predetermined action was taken together.

[0057] In the example of FIG. 8, the behavior history 62 stores a timestamp, a user, a type, and multiple products in association with each other. Specifically, in the behavior history 62, the timestamp indicates the time when the action indicated by the type was performed, the user is the identification information of the user who performed that action, and each product stores the identification information of the product for which the action indicated by the type was performed. If the type is "purchase," the timestamp of the purchase and the identification information of products purchased in the same cart are set. If the type is "view," for example, the timestamp indicates the time when the product was viewed, and the product column stores the identification information of a certain product and products viewed before or after that product.

[0058] Here, the related product acquisition unit 57 may select other products for which a purchase action was performed together with each of the at least one extracted product from the behavior history 62, and if the number of selected other products is less than the required number of selections (threshold), may further select other products for which a browsing action was performed together with each of the at least one extracted product from the behavior history 62. In other words, the related product acquisition unit 57 first selects other products for a first action (purchase in this case) with high relevance accuracy but a small quantity, and if the number of selected products is equal to or less than the threshold, further selects products for a second action (viewing in this case) with low relevance accuracy but a large quantity. This makes it possible to balance the accuracy and quantity of additional queries that can ultimately be acquired.

[0059] The related product acquisition unit 57 may further generate a score Sc2 for each combination of a product and another product. When a product x is combined with another product y, if SXY(x, y) is the number of times a user has taken one action (e.g., purchase) for the product x and the product y together, SX(x) is the number of times a user has taken one action for the product x, and SY(y) is the number of times a user has taken that action for the product y, the score Sc2 for the combination of the product x and the product y may be calculated using the following formula:

[0060] Sc2=SXY(x,y) / (SX(x)×SY(y))

[0061] The score is calculated for the action used to select other products. For example, if another product is selected that was purchased together with a certain product, the score for the combination of those products is calculated for the purchase action. As with the calculation of score Sc1, each of SXY(x, y), SX(x), and SY(y) is equivalent to the sum of the counts for each of one or more users that are the subject of the score calculation.

[0062] When another product is acquired in the process of S202, the additional acquisition unit 58 included in the additional query acquisition unit 52 acquires at least one query associated with the other product as a candidate for the additional query (S203). More specifically, the additional acquisition unit 58 acquires, from the search history 61, past queries associated with the other product as candidates for the additional query (S203).

[0063] Here, the additional acquisition unit 58 may acquire queries that search for other products for which a purchase action has been performed from the search history 61, and if the number of acquired queries is smaller than the required number to acquire (threshold), may further extract queries that search for other products for which a browsing action has been performed. This makes it possible to strike a balance between the accuracy and quantity of additional queries that can ultimately be acquired.

[0064] The additional acquisition unit 58 may further generate a score Sc3 for each combination of another product and query. The method of calculating the score Sc3 is the same as that for the score Sc1. When a query q is associated with another product p, if SQP(q, p) is the number of times a user has searched using the query q and taken one action (e.g., purchased) on the product p, SQ(q) is the number of times a user has searched using the query q, and SP(p) is the number of times a user has purchased the product p, the score Sc3 for the combination of the query q and the product p may be calculated using the following formula:

[0065] Sc3=SQP(q,P) / (SQ(q)×SP(p))

[0066] The score Sc3 is calculated for the action used to obtain the query. For example, if a query is obtained that searches for another purchased product p, the score Sc3 for the combination of that query and product is calculated for the purchase action. As with the calculation of the score Sc1, each of SQP(q, p), SQ(q), and SP(p) is equivalent to the sum of the counts for each of one or more users that are the subject of the score calculation.

[0067] When the additional query candidates are acquired, the additional acquisition unit 58 acquires, from the at least one acquired query, some that are different from the original query as additional queries (S204). The additional acquisition unit 58 may acquire, from the at least one acquired query that is different from the original query, additional queries based on the score. The additional acquisition unit 58 may acquire, from the at least one acquired query, some that are different from the original query as additional queries based on at least a part of the scores Sc1 to Sc3.

[0068] To acquire an additional query, all of the scores Sc1 to Sc3 may be used, or some of the scores, such as scores Sc1 and Sc3 or scores Sc1 and Sc2, may be used. When multiple scores are used, the additional acquisition unit 58 may acquire the product of the scores and acquire the query with the largest product as the additional query, or may acquire the query with the largest value obtained by weighting and adding the scores as the additional query. Instead of calculating a value from multiple scores, the additional acquisition unit 58 may sort by one score, and when there are multiple queries with the same score, sort by the next score, and acquire the query with the highest ranking as a result of these sorts as the additional query.

[0069] By the processing from S201 to S204, an additional query is obtained from the original query.

[0070] In this embodiment, instead of finding products related to the product selected by the original query as related products, additional queries that find related products are searched for. This allows related products to be found on a query-by-query basis, and even when there is little data on the relationship between products, such as a new product, the new product can be displayed as a related product. This allows a more diverse and useful product to be displayed. Furthermore, users can easily infer the relationship by comparing the main query and the additional query, reducing the burden of searching for displayed products. Furthermore, advertisements are also displayed for related queries, which increases the opportunities for products to be advertised, and is also beneficial for advertisers.

[0071] Here, the main query and the additional query may be associated with each other and stored in advance in the database. In this case, in the process of S104 in Fig. 3, the additional query acquisition unit 52 acquires the additional query associated with the main query from the database.

[0072] Fig. 9 is a diagram showing another example of the processing of the additional query acquisition unit 52. Fig. 9 shows processing for previously storing the original query and the additional query in association with each other in the database.

[0073] First, the additional query acquisition unit 52 selects one of the unprocessed queries stored in the search history 61 as an original query (S301). The original query corresponds to the main query in the processing of FIG.

[0074] Here, the additional query acquisition unit 52 may correct variations in the expression of the selected query and acquire the corrected query as the original query. More specifically, the additional query acquisition unit 52 may delete unnecessary characters, standardize the notation of katakana, hiragana, and kanji, and standardize parts of speech for the selected query.

[0075] Next, the product extraction unit 56 extracts products associated with the original query (S302). This process is similar to the process of S201 in FIG. 6, so detailed description will be omitted. The product extraction unit 56 may first extract products for a first action (here, purchase) with high relevance accuracy but a small quantity, and if the number of extracted products is equal to or less than a threshold, may further extract products for a second action (here, browsing) with low relevance accuracy but a large quantity. The product extraction unit 56 may generate a score Sc1 for each extracted product.

[0076] Once a product is extracted based on the original query, the related product acquisition unit 57 acquires other products associated with the extracted product (S303). This process is similar to the process of S202 in FIG. 6, so detailed description will be omitted. The related product acquisition unit 57 may first select other products for a first action (purchase in this case) with high relevance accuracy but a small quantity, and if the number of selected products is equal to or less than a threshold, may further select products for a second action (viewing in this case) with low relevance accuracy but a large quantity. The related product acquisition unit 57 may further generate a score Sc2 for each combination of the product and other products.

[0077] When the other product is acquired, the additional acquisition unit 58 included in the additional query acquisition unit 52 acquires at least one query associated with the other product as a candidate for an additional query (S304). This process is similar to the process of S203 in FIG. 6, and therefore detailed description will be omitted. The additional acquisition unit 58 may acquire queries that search for other products for which a purchase action has been performed from the search history 61, and if the number of acquired queries is smaller than the required number of acquisitions (threshold), may further extract queries that search for other products for which a browsing action has been performed. The additional acquisition unit 58 may also generate a score Sc3 for each combination of the other product and the query.

[0078] When the candidates for the additional query are acquired, the additional acquisition unit 58 acquires, from among the acquired at least one query, some that are different from the original query as additional queries (S305). This process is similar to the process of S204 in FIG. 6, and therefore a detailed description thereof will be omitted.

[0079] When the additional query is acquired, the additional query acquisition unit 52 associates the acquired additional query with the original query and stores the associated additional query in the database (S306). If an unprocessed query exists in the search history 61 (Y in S307), the additional query acquisition unit 52 repeats the processing from S301 onwards. On the other hand, if an unprocessed query does not exist in the search history 61 (N in S307), the processing in FIG. 9 ends.

[0080] The same effect can be achieved by first obtaining an original query from the search history 61 and then obtaining an additional query corresponding to the original query. The scope of the present invention is not limited to the above-described embodiment. For example, the selection of products and advertised products in S102 and S103 in FIG. 3 may be performed after obtaining the additional query, and the order of other processes may be changed as long as the dependencies between them are not disrupted.

[0081] [Note] This specification discloses various technical ideas, including the following: (1) An information processing system including: a first acquisition means for acquiring a first query; a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query; an associated acquisition means for acquiring other products associated with the extracted product; a second acquisition means for acquiring at least one query associated with the other products as a second query; and an output means for outputting information corresponding to the second query together with the products searched for based on the first query.

[0082] (2) In (1), an information processing system in which at least one product selected based on a past query and a predetermined action taken is stored in a search history in association with each of a plurality of past queries, and a plurality of products together with which the predetermined action was taken are stored in association with each other in a behavior history, a product extraction means extracts at least one product stored in association with the first query from the search history, an associated acquisition means selects other products stored in association with each of the extracted at least one product from the behavior history, and a second acquisition means acquires from the search history a past query associated with the other selected product as the second query.

[0083] (3) In (2), the search history stores information on at least one product that was selected based on a past query and subjected to a first or second action, in association with each of a plurality of past queries; the behavior history stores a plurality of products that were subjected to a first or second action together, in association with each other; the product extraction means extracts from the search history the products that were selected based on the first query and subjected to the first action; and if the number of products obtained is less than a first required number, further extracts from the search history the products that were selected based on the first query and subjected to the second action; the related acquisition means selects from the behavior history other products that were subjected to the first action together with each of the extracted at least one product; and if the number of selected other products is less than a second required number, further selects from the behavior history other products that were subjected to the second action together with each of the extracted at least one product.

[0084] (4) In the information processing system of (2) or (3), the second acquisition means acquires a portion of past queries associated with the selected other products as the second query based on at least a portion of the first score of the product extracted from the first query, the second score of the selected other products relative to the selected product, and the third score of past search queries in which the selected other products were searched.

[0085] (5) In (4), the information processing system, wherein the first score is the number of times the specified action is performed on the product extracted by the first query divided by the product of the number of times the product is extracted by the first query and the number of times the specified action is performed on the product.

[0086] (6) In (4) or (5), the information processing system, wherein the second score is the number of times the specified action is performed on the selected product and the other selected products together divided by the product of the number of times the specified action is performed on the selected product and the number of times the specified action is performed on the other selected products.

[0087] (7) In any of (4) to (6), the information processing system, wherein the third score is the number of times the product was searched for using a past query and the specified action was taken on another product, divided by the product of the number of times the product was searched for using the past query and the number of times the specified action was taken on another product.

[0088] (8) In any one of (1) to (7), the output means displays both the product selected based on the first query and the product selected based on the second query.

[0089] (9) In (8), the output means displays the product selected by the first query in association with the first query, and displays the product selected by the second query in association with the second query.

[0090] (10) In any one of (1) to (9), the output means displays the advertisement product selected based on the second query.

[0091] (11) In the information processing system according to (10), the output means displays the advertising product selected based on the second query in association with the second query.

[0092] (12) In any one of (1) to (11), the information processing system is configured such that the first acquisition means acquires a first query from a user.

[0093] (13) In any of (1) to (11), the information processing system further includes a corresponding query acquisition means that acquires each of previously executed queries as a first query, the second acquisition means that stores at least one of the acquired queries associated with other products as a second query in a database in association with the first query, and acquires the second query from the database based on an input query acquired from a user, and the output means that outputs information corresponding to the second query together with the products searched for based on the input query.

[0094] (14) An information processing method including the steps of: acquiring a first query; extracting at least one product from a plurality of pre-stored products based on the first query; acquiring other products associated with the extracted product; acquiring at least one query associated with the other products as a second query; and outputting information corresponding to the second query together with the products searched for based on the first query.

[0095] (15) A program for causing a computer to function as a first acquisition means for acquiring a first query, a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query, an associated acquisition means for acquiring other products associated with the extracted product, a second acquisition means for acquiring at least one query associated with the other products as a second query, and an output means for outputting information corresponding to the second query together with the products searched based on the first query. [Explanation of symbols]

[0096] 1 Server, 2 User terminal, 11 Processor, 12 Storage, 13 Communication unit, 51 Query acquisition unit, 52 Additional query acquisition unit, 53 Product search unit, 54 Advertisement search unit, 55 Display control unit, 56 Product extraction unit, 57 Related product acquisition unit, 58 Additional acquisition unit, 61 Search history, 62 Behavioral history.

Claims

1. a first obtaining means for obtaining a first query; a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query; related acquisition means for acquiring other products related to the extracted product; a second acquiring means for acquiring at least one query associated with the other product as a second query; an output means for outputting information corresponding to the second query together with the products searched for based on the first query; Including, At least one product that has been selected based on a plurality of past queries and for which a predetermined action has been taken is stored in a search history in association with each of the past queries; the product extraction means extracts, from the search history, at least one product stored in association with the first query; the second acquisition means acquires, from the search history, a past query associated with the acquired other product as the second query; Information processing system.

2. 2. The information processing system according to claim 1, A plurality of products for which the predetermined action was taken together are stored in association with each other in a behavior history, the association acquisition means selects other products to be stored in association with each of the at least one extracted product from the behavior history; Information processing system.

3. 3. The information processing system according to claim 2, The search history stores information on at least one product that was selected based on a plurality of past queries and for which a first or second action was taken, in association with each of the past queries, and the behavior history stores a plurality of products that were selected together with the first or second action in association with each other, the product extraction means extracts, from the search history, products that have been selected based on the first query and for which the first action has been taken, and if the number of acquired products is less than a first required number, further extracts, from the search history, products that have been selected based on the first query and for which the second action has been taken; the association acquisition means selects, from the behavior history, other products for which the first action has been taken together with each of the at least one extracted product, and when the number of the selected other products is less than a second required number, further selects, from the behavior history, other products for which the second action has been taken together with each of the at least one extracted product; Information processing system.

4. 3. The information processing system according to claim 2, the second acquiring means acquires, as a second query, a portion of past queries associated with the selected other product based on at least a portion of a first score of the product extracted from the first query, a second score of the selected other product relative to the selected product, and a third score of a past search query in which the selected other product was searched; Information processing system.

5. 5. The information processing system according to claim 4, the first score is a value obtained by dividing the number of times the predetermined action has been performed on the product extracted by the first query by the product of the number of times the product has been extracted by the first query and the number of times the predetermined action has been performed on the product; Information processing system.

6. 5. The information processing system according to claim 4, the second score is a value obtained by dividing the number of times the predetermined action was performed on the selected product and the other selected products together by the product of the number of times the predetermined action was performed on the selected product and the number of times the predetermined action was performed on the other selected products; Information processing system.

7. 5. The information processing system according to claim 4, The third score is a value obtained by dividing the number of times the product was searched for using a past query and the predetermined action was performed on another product by the product of the number of times the product was searched for using the past query and the number of times the predetermined action was performed on the other product. Information processing system.

8. 2. The information processing system according to claim 1, the output means displays both the product selected based on the first query and the product selected based on the second query; Information processing system.

9. 9. The information processing system according to claim 8, the output means displays the product selected by the first query in association with the first query, and displays the product selected by the second query in association with the second query; Information processing system.

10. 2. The information processing system according to claim 1, the output means displays the advertisement product selected based on the second query; Information processing system.

11. 11. The information processing system according to claim 10, the output means displays the advertisement product selected based on the second query in association with the second query; Information processing system.

12. 2. The information processing system according to claim 1, the first acquisition means acquires a first query from a user; Information processing system.

13. 2. The information processing system according to claim 1, the first acquisition means acquires each of the queries executed in the past as a first query; the second acquisition means stores the acquired at least one query associated with the other product as a second query in a database in association with the first query; The method further includes a corresponding query acquisition means for acquiring a second query from the database based on an input query acquired from a user, the output means outputs information corresponding to the second query together with the products searched for based on the input query. Information processing system.

14. An information processing system comprising a first acquisition means, a product extraction means, a related acquisition means, a second acquisition means, and an output means, The first obtaining means obtains a first query; extracting at least one product from a plurality of products stored in advance by the product extracting means based on the first query; a step in which the related acquisition means acquires other products related to the extracted product; The second acquiring means acquires at least one query associated with the other product as a second query; outputting information corresponding to the second query together with the products searched for based on the first query by the output means; Including, At least one product that has been selected based on a plurality of past queries and for which a predetermined action has been taken is stored in a search history in association with each of the past queries; the product extraction means extracts, from the search history, at least one product stored in association with the first query; the second acquisition means acquires, from the search history, a past query associated with the acquired other product as the second query; Information processing methods.

15. a first obtaining means for obtaining a first query; a product extraction means for extracting at least one product from a plurality of pre-stored products based on the first query; a related acquisition means for acquiring other products related to the extracted product; a second acquiring means for acquiring at least one query associated with the other product as a second query; and an output means for outputting information corresponding to the second query together with the products searched for based on the first query; Make the computer function as At least one product that has been selected based on a plurality of past queries and for which a predetermined action has been taken is stored in a search history in association with each of the past queries; the product extraction means extracts, from the search history, at least one product stored in association with the first query; the second acquisition means acquires, from the search history, a past query associated with the acquired other product as the second query; program.

Images