Information processing apparatus, information processing method, and information processing program

Abstract

To present search results close to the intention of a user.SOLUTION: An information processing device comprises an estimation unit and a determination unit. When a plurality of categories to which a search target where relevance to a query exceeds a prescribed threshold value belongs exist, the estimation unit estimates a category relationship on the basis of an action history of a user for the search target corresponding to the query. The determination unit determines a search target provided as search results corresponding to the query on the basis of the relationship estimated by the estimation unit.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, techniques for estimating the intention of a user have been known. As an example of such a technique, there is known a technique of generating intention information of a user at the time of performing an action from the action information of the user and learning the characteristics of the intention in a model.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional technology, there has been room for further improvement in presenting search results closer to the intention of the user.

[0005] The present application has been made in view of the above, and an object thereof is to present search results closer to the intention of the user.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application, based on the behavior history of the user with respect to the search target corresponding to the query, when there are a plurality of categories to which the search target whose relevance to the query exceeds a predetermined threshold belongs, an estimation unit that estimates the relevance of the categories, and a determination unit that determines a search target to be provided as a search result corresponding to the query based on the relevance estimated by the estimation unit.

Effects of the Invention

[0007] According to one aspect of the embodiment, there is an effect that search results close to the user's intention can be presented.

Brief Description of Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and redundant explanations are omitted.

[0010] (Embodiment) The category of the search query (query) intended by the user (i.e., category intention) can be estimated by operation information (e.g., number of clicks) on the products presented as search results based on the degree of match of the query string. Also, the estimated category is used for narrowing down search results. For example, it becomes possible to present only the products belonging to the estimated category as search results. To give a specific example, when the query is "melon soda", there are multiple categories such as carbonated beverages and toothpaste. However, if the total number of clicks on the products of carbonated beverages is overwhelmingly more than the total number of clicks on the products of toothpaste, it becomes possible to present only the products of carbonated beverages. For example, when the total number of clicks on the products of carbonated beverages is "99" and the total number of clicks on the products of toothpaste is "1", the click probability of the category of carbonated beverages is "0.99" and the click probability of the category of toothpaste is "0.01". Therefore, by performing thresholding based on the click probability, it becomes possible to estimate that the category intention of the query "melon soda" is carbonated beverages.

[0011] However, for example, products in the relationship between a main body and parts such as smartphones and smartphone cases (smartphones or smartphone cases) are likely to appear in search results at the same time because their product names are similar, and since they are not unrelated to the query (query of "smartphone"), both are often clicked. For example, there may be a case where the click probability of the category of smartphone bodies is "0.5" and the click probability of the category of smartphone cases is "0.5", and it is estimated that the category intention of the query "smartphone" is both smartphone bodies and smartphone cases. Therefore, there are cases where the user's category intention cannot be appropriately estimated only from search behavior (e.g., click logs).

[0012] The present application has been made in view of the above, and an object thereof is to present search results closer to the user's intention.

[0013] Specifically, in the following embodiments, when there are a plurality of categories estimated from past search behaviors (for example, when there is a pair having a predetermined relationship with the category intention), a category close to the intention of the query is specified using text information.

[0014] 〔1. Configuration of Information Processing System〕 The information processing system 1 shown in FIG. 1 will be described. As shown in FIG. 1, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are communicably connected by wire or wirelessly via a predetermined communication network (network N). FIG. 1 is a diagram showing a configuration example of the information processing system 1 according to the embodiment.

[0015] The terminal device 10 is an information processing device used by a user who performs a search action. The terminal device 10 may be any device as long as it can realize the processing in the embodiment. Also, the terminal device 10 may be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 2 shows the case where the terminal device 10 is a smartphone.

[0016] The terminal device 10 is, for example, a smart device such as a smartphone or a tablet, and is a portable terminal device that can communicate with an arbitrary server device via a wireless communication network such as 3G to 5G (Generation) or LTE (Long Term Evolution). Also, the terminal device 10 has a screen such as a liquid crystal display and has a screen having a touch panel function, and may receive various operations on display data such as content, such as a tap operation, a slide operation, and a scroll operation, from the user using a finger or a stylus. In FIG. 2, the terminal device 10 is used by the user U1.

[0017] The information processing apparatus 100 is an information processing apparatus aimed at presenting search results close to the user's intention, and it can be any apparatus as long as it can realize the processing in the embodiment. For example, when there are a plurality of categories estimated from past search behaviors, the information processing apparatus 100 estimates the relationship between the categories of the plurality of categories, and determines a search target to be provided as a search result by identifying a category close to the intention of the query. The information processing apparatus 100 is realized, for example, by a server apparatus such as an administrator who provides an electronic shopping street, a cloud system, or the like.

[0018] [2. An Example of Information Processing] FIG. 2 is a diagram showing an example of information processing of the information processing system 1 according to the embodiment. In the following embodiments, the search target does not have to be limited to a product having physical characteristics. For example, the search target may be a product having no physical characteristics. Also, for example, the search target does not have to be limited to a product. For example, the search target may be content such as news, travel, or insurance. Also, in the following embodiments, the case where the search target has a complementary product relationship such as a smartphone and a smartphone case, or travel and insurance will be described as an example, but it does not have to be particularly limited. For example, the search target may have a relationship used in a set. For example, the search target may have a relationship used in a set, such as a remote control and a battery, or a product and a consumable of the product.

[0019] Hereinafter, as a method for determining the category intention, two determination methods will be described: a determination method using unsupervised learning by comparing the similarity between the query and the category name, and a determination method using supervised learning using the label assigned to the category corresponding to the query in which the category pair appears.

[0020] (Processing Based on the Determination Method Using Unsupervised Learning) When the user U1 searches using "smartphone 13" as a query, the terminal device 10 transmits information indicating that the user U1 has searched for "smartphone 13" to the information processing device 100 (step S101). When the information processing device 100 obtains information indicating that the user U1 has searched for "smartphone 13", it obtains the user U1's action history (e.g., click log) for the search target corresponding to the query "smartphone 13" (step S102).

[0021] The information processing device 100 identifies a search target whose relevance to the query of "smartphone 13" exceeds a predetermined threshold based on the acquired behavior history of the user U1 (step S103). For example, the information processing device 100 identifies the smartphone body and the smartphone case as search targets whose relevance to the query of "smartphone 13" exceeds a predetermined threshold. Then, when there are a plurality of categories to which the identified search target belongs, the information processing device 100 identifies the plurality of categories (step S104). For example, the information processing device 100 uses a category pair list (information indicating the relationship between categories) listing pairs of categories to identify the plurality of categories. For example, the information processing device 100 identifies a plurality of categories by collating the pair of the smartphone body and the smartphone case with the category pair list. For example, when the pair of the smartphone body and the smartphone case is included in the category pair list, the information processing device 100 identifies the plurality of categories corresponding to the pair. Also, for example, the information processing device 100 may end the information processing when the pair of the smartphone body and the smartphone case is not included in the category pair list. Then, the information processing device 100 estimates the relationship between the plurality of categories using the category pair list (step S105). For example, the information processing device 100 estimates the relationship between the smartphone body and the smartphone case using the category pair list. For example, the information processing device 100 estimates that the smartphone body and the smartphone case have a relationship of a main body and a component. At this time, the information processing device 100 may perform labeling such as attaching the label "main body" to the smartphone body and "component" to the smartphone case. Note that the information processing device 100 may determine whether there are a plurality of categories to which the search target belongs in step S104. For example, the information processing device 100 may determine whether there are a plurality of categories by collating the pair of the smartphone body and the smartphone case with the category pair list. For example, when the pair of the smartphone body and the smartphone case is included in the category pair list, the information processing device 100 may determine that there are a plurality of categories. Also, for example, when the pair of the smartphone body and the smartphone case is not included in the category pair list, the information processing device 100 may determine that there are not a plurality of categories and end the information processing.

[0022] Based on the estimated relationship between the "main body" and "parts", the information processing apparatus 100 determines a search target to be provided as a search result corresponding to the query of the "smartphone 13" (step S106). For example, the information processing apparatus 100 determines whether to propose a smartphone main body or a smartphone case.

[0023] The information processing apparatus 100 determines a search target to be provided as a search result based on the proximity of the string between the query of the "smartphone 13" and the category name of the "main body", and the proximity of the string between the query of the "smartphone 13" and the category name of the "parts". For example, the information processing apparatus 100 converts the strings of "smartphone 13", "main body", and "parts" into vectors, and uses the proximity of the vectors as the similarity to determine which intention of the "main body" and "parts" the query of the "smartphone 13" is closer to, thereby determining the search target to be provided as a search result. For example, the information processing apparatus 100 may determine the search target to be provided as a search result using a model trained with word2vec or the like for the similarity between the query and the category name.

[0024] The information processing apparatus 100 transmits information proposing the purchase of the determined search target to the terminal device 10 (step S107). For example, the information processing apparatus 100 transmits information proposing only the determined search target as a search result. For example, when it is determined that the query of the "smartphone 13" is closer to the intention of the "main body", the information processing apparatus 100 transmits information proposing the purchase of a product belonging to the category of the "main body". At this time, the information processing apparatus 100 may transmit information that does not include products belonging to the category of the "parts". Further, the information processing apparatus 100 may transmit information that proposes the purchase of a product belonging to the category of the "main body" and also proposes the purchase of a product belonging to the category of the "parts" as a product for combined purchase with the product belonging to the category of the "main body". Further, the information processing apparatus 100 may transmit information that proposes the purchase of a product belonging to the category of the "parts" after proposing the purchase of a product belonging to the category of the "main body".

[0025] (Processing Based on a Determination Method Using Supervised Learning) The processing from steps S101 to S105 is the same as the processing based on the determination method using unsupervised learning. In step S106, when the information processing apparatus 100 inputs a query and a plurality of category names, it determines a search target to be provided as a search result using a model that outputs a category name corresponding to the query. Specifically, the information processing apparatus 100 determines the category name output by inputting the query "Smartphone 13", the category name "Main Body", and the category name "Parts" into the model as the search target to be provided as the search result. Here, the model is, for example, a model that has been trained using information input manually as teacher data. For example, the model is a model that has been trained using response data obtained through crowdsourcing or the like (for example, response data in which the intention of a query is answered for a predetermined query). Therefore, the information processing apparatus 100 may determine the search target to be provided as the search result using a model that has been trained using response data obtained through crowdsourcing or the like. Also, the model is, for example, a model that has been trained using output information output by a classification model for classifying categories (for example, BERT: Bidirectional Encoder Representations from Transformers) as teacher data. Therefore, the information processing apparatus 100 may determine the search target to be provided as the search result using a model that has been trained using output information output by a classification model for classifying categories or the like. Also, the processing in step S107 is the same as the processing based on the determination method using unsupervised learning.

[0026] [3. Variations of Processing] In the above embodiment, when the information processing apparatus 100 inputs a query, a plurality of category names, and the order relationship (e.g., order) between the categories of the plurality of categories, it may determine a search target to be provided as a search result using a model that outputs a category name corresponding to the query. Specifically, the information processing apparatus 100 may determine, as a search target to be provided as a search result, the category name output by inputting into the model the query "Smartphone 13", the category name "Main body", the category name "Parts", and information indicating that the category of "Main body" is higher in order than the category of "Parts". Further, the model is a model learned by including the order relationship between categories as an explanatory variable. Also, the model may be a model based on unsupervised learning or a model based on supervised learning.

[0027] In the above embodiment, the case where the information processing apparatus 100 identifies a plurality of categories to which the search target belongs by referring to the category pair list has been shown, but a plurality of categories to which the search target belongs may be identified from the action history. For example, the information processing apparatus 100 may identify four categories, namely, "Smartphone 13A Main body", "Smartphone 13B Main body", "Smartphone 13A Case", and "Smartphone 13B Case", as categories for the query "Smartphone 13" based on the action history. Then, when the category pair list includes a category pair for extracting categories having a main body / parts relationship, the information processing apparatus 100 may use that category pair to extract categories having a main body / parts relationship from the four categories of "Smartphone 13A Main body", "Smartphone 13B Main body", "Smartphone 13A Case", and "Smartphone 13B Case". For example, the information processing apparatus 100 may extract two pairs, namely, "Smartphone 13A Main body" and "Smartphone 13A Case" and "Smartphone 13B Main body" and "Smartphone 13B Case". Note that the information processing apparatus 100 may perform the pair extraction process the number of times equal to the number of category pairs included in the category pair list, and when there is no discrepancy in the extraction results, determine the final pair.

[0028] [4. Configuration of Terminal Device] Next, with reference to FIG. 3, the configuration of the terminal device 10 according to the embodiment will be described. FIG. 3 is a diagram showing a configuration example of the terminal device 10 according to the embodiment. As shown in FIG. 3, the terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0029] (Communication Unit 11) The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 11 is connected to a predetermined network N by wire or wirelessly, and information is transmitted and received between the communication unit 11 and an information processing device 100 or the like via the predetermined network N.

[0030] (Input Unit 12) The input unit 12 receives various operations from the user. In FIG. 2, various operations from the user U1 are received. For example, the input unit 12 may receive various operations from the user via the display surface by a touch panel function. Further, the input unit 12 may receive various operations from buttons provided on the terminal device 10 or from a keyboard or mouse connected to the terminal device 10.

[0031] (Output Unit 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays the content received from the information processing device 100. For example, the output unit 13 displays the search result of the query.

[0032] (Control Unit 14) The control unit 14 is, for example, a controller, and is realized by various programs stored in the storage device inside the terminal device 10 being executed with the RAM (Random Access Memory) as the working area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. For example, these various programs include the programs of applications installed in the terminal device 10. For example, these various programs include the programs of applications for displaying the content (for example, the search results of a query) received from the information processing device 100. Further, the control unit 14 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0033] As shown in FIG. 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the operations of information processing described below.

[0034] (Receiving Unit 141) The receiving unit 141 receives various information from other information processing devices such as the information processing device 100. For example, the receiving unit 141 receives the content transmitted from the information processing device 100. For example, the receiving unit 141 receives the search results of a query. To give a specific example, the receiving unit 141 receives information indicating a list of products (smartphone bodies) belonging to the category of "body" as the search results for the query of "smartphone 13".

[0035] (Transmitting Unit 142) The transmitting unit 142 transmits various information to other information processing devices such as the information processing device 100. For example, the transmitting unit 142 transmits the input information of the user's query. To give a specific example, the transmitting unit 142 transmits information indicating that the user has performed a search with "smartphone 13" as the query.

[0036] [5. Configuration of Information Processing Device] Next, with reference to FIG. 4, the configuration of the information processing apparatus 100 according to the embodiment will be described. FIG. 4 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 4, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing apparatus 100 may include an input unit (e.g., a keyboard, a mouse, etc.) for receiving various operations from the administrator of the information processing apparatus 100 and a display unit (e.g., a liquid crystal display, etc.) for displaying various information.

[0037] (Communication Unit 110) The communication unit 110 is realized by, for example, a NIC or the like. Then, the communication unit 110 is connected to the network N by wire or wirelessly, and information is transmitted and received between the communication unit 110 and the terminal device 10 or the like via the network N.

[0038] (Storage Unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4, the storage unit 120 includes a category pair information storage unit 121 and a model information storage unit 122.

[0039] The category pair information storage unit 121 stores information listing pairs of categories (that is, information indicating the relationship between categories). Here, FIG. 5 shows an example of the category pair information storage unit 121 according to the embodiment. As shown in FIG. 5, the category pair information storage unit 121 has items such as "pair ID", "category pair", and "relationship".

[0040] The "pair ID" indicates identification information for identifying a pair of categories. The "category pair" indicates a pair of categories. The "relationship" indicates the relationship between categories.

[0041] The model information storage unit 122 stores model information for determining the category intention. Here, FIG. 6 shows an example of the model information storage unit 122 according to the embodiment. As shown in FIG. 6, the model information storage unit 122 has items such as "model ID" and "model information".

[0042] "Model ID" indicates identification information for identifying a model for determining the category intention. "Model information" indicates model information for determining the category intention. In the example shown in FIG. 6, an example in which conceptual information such as "model information #1" and "model information #2" is stored in "model information" is shown, but actually, teacher data such as target variables and explanatory variables is stored.

[0043] (Control unit 130) The control unit 130 is a controller, and is realized, for example, by various programs stored in a storage device inside the information processing apparatus 100 being executed with the RAM as a work area by a CPU, MPU, etc. Further, the control unit 130 is realized by an integrated circuit such as an ASIC or an FPGA, for example.

[0044] As shown in FIG. 4, the control unit 130 has an acquisition unit 131, a specification unit 132, an estimation unit 133, a determination unit 134, and a proposal unit 135, and realizes or executes the operations of information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and any other configuration may be used as long as it can perform the information processing described later.

[0045] (Acquisition unit 131) The acquisition unit 131 acquires various information from the storage unit 120. Further, the acquisition unit 131 stores the acquired various information in the storage unit 120.

[0046] The acquisition unit 131 acquires various types of information from an external information processing device. The acquisition unit 131 acquires various types of information from another information processing device such as the terminal device 10. For example, the acquisition unit 131 acquires input information of a user's query. To give a specific example, the acquisition unit 131 acquires information indicating that the user has performed a search with "smartphone 13" as a query.

[0047] Also, for example, the acquisition unit 131 acquires the user's behavior history regarding the search target corresponding to the query. To give a specific example, the acquisition unit 131 acquires the user's behavior history regarding the search target (such as a smartphone body or a smartphone case) corresponding to the query "smartphone 13".

[0048] (Specification unit 132) Based on the behavior history acquired by the acquisition unit 131, the specification unit 132 specifies a plurality of categories to which search targets whose relevance to the query exceeds a predetermined threshold belong. For example, the specification unit 132 specifies a plurality of categories by collating search targets whose relevance to the query exceeds a predetermined threshold with a category pair list. For example, the specification unit 132 specifies a plurality of categories by collating a smartphone body and a smartphone case, which are search targets whose relevance to the query "smartphone 13" exceeds a predetermined threshold, with a category pair list.

[0049] (Estimation unit 133) The estimation unit 133 estimates the relationship between categories of a plurality of categories. For example, the estimation unit 133 estimates the relationship between categories of a plurality of categories by collating search targets whose relevance to the query exceeds a predetermined threshold with a category pair list. For example, the estimation unit 133 estimates that the relationship between the categories to which a smartphone body and a smartphone case, which are search targets for the query "smartphone 13", belong is a relationship of "body" and "parts".

[0050] (Decision unit 134) The determination unit 134 determines a search target to be provided as a search result corresponding to the query based on the relationship estimated by the estimation unit 133. For example, the determination unit 134 uses a model that determines the category intention to determine a search target to be provided as a search result corresponding to the query. For example, when the category intention of the query "Smartphone 13" is "main body", the determination unit 134 determines that the product of the smartphone main body is the search target to be provided as the search result corresponding to the query "Smartphone 13".

[0051] (Proposal unit 135) The proposal unit 135 transmits information for proposing the purchase of the search target determined by the determination unit 134. Further, the proposal unit 135 may transmit information for proposing the purchase of a search target not determined by the determination unit 134. For example, the proposal unit 135 may transmit information for proposing the purchase of a product belonging to the category of the search target not determined by the determination unit 134 as a product for grouped purchase with a product belonging to the category of the search target determined by the determination unit 134. Also, for example, the proposal unit 135 may transmit information for subsequently proposing the purchase of a product belonging to the category of the search target not determined by the determination unit 134 after proposing the purchase of a product belonging to the category of the search target determined by the determination unit 134.

[0052] [[6. Information processing flow]] Next, with reference to FIG. 7, the information processing procedure by the information processing system 1 according to the embodiment will be described. FIG. 7 is a flowchart showing the information processing procedure by the information processing system 1 according to the embodiment.

[0053] As shown in FIG. 7, the information processing apparatus 100 acquires the usage history of the user with respect to the search target corresponding to the query (step S201).

[0054] Based on the acquired usage history, the information processing apparatus 100 identifies a plurality of categories to which the search targets whose relevance to the query exceeds a predetermined threshold belong (step S202).

[0055] The information processing apparatus 100 estimates the relationship between a plurality of specified categories (step S203).

[0056] The information processing apparatus 100 determines a search target to be provided as a search result corresponding to the query based on the estimated relationship (step S204).

[0057] [7. Effect] As described above, the information processing apparatus 100 according to the embodiment includes an estimation unit 133 and a determination unit 134. The estimation unit 133 estimates the relationship between a plurality of categories to which a search target having a relevance to the query exceeding a predetermined threshold belongs based on the user's action history with respect to the search target corresponding to the query. The determination unit 134 determines a search target to be provided as a search result corresponding to the query based on the relationship estimated by the estimation unit 133.

[0058] Thereby, even when there are a plurality of categories estimated from the search behavior, the information processing apparatus 100 according to the embodiment can present a search result close to the user's intention.

[0059] Further, the estimation unit 133 estimates the relationship between a plurality of categories by collating a plurality of categories to which a search target having a relevance to the query exceeding a predetermined threshold belongs with information indicating the relationship between the categories.

[0060] Thereby, when there are a plurality of categories estimated from the search behavior, the information processing apparatus 100 according to the embodiment can appropriately estimate the relationship between the plurality of categories.

[0061] Further, the determination unit 134 determines a search target to be provided as a search result based on the proximity of the character strings of the queries to the search targets having a relevance to the queries exceeding a predetermined threshold.

[0062] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target based on the proximity of character strings without performing supervised learning.

[0063] Further, the determination unit 134 determines a search target to be provided as a search result based on the proximity of the intention indicated by the character string of the character string.

[0064] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target based on the proximity of the intention indicated by the character string without performing supervised learning.

[0065] Further, when the determination unit 134 inputs a plurality of categories to which search targets whose relevance between queries exceeds a predetermined threshold belong, the determination unit 134 uses a model trained to output a category corresponding to the query, and determines a search target to be provided as a search result corresponding to the query.

[0066] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target based on a model trained by supervised learning.

[0067] Further, when the determination unit 134 inputs a plurality of categories to which search targets whose relevance between queries exceeds a predetermined threshold belong and the order relationship between the categories of the plurality of categories, the determination unit 134 uses a model trained to output a category corresponding to the query, and determines a search target to be provided as a search result corresponding to the query.

[0068] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target in consideration of the order relationship between the categories of the plurality of categories.

[0069] Further, the determination unit 134 determines a search target to be provided as a search result corresponding to the query by using a model trained with information input manually as teacher data.

[0070] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target based on a model trained based on teacher data input manually.

[0071] Also, the determination unit 134 determines a search target to be provided as a search result corresponding to a query using a model trained with the information output by the classification model for classifying categories as teacher data.

[0072] Thereby, the information processing apparatus 100 according to the embodiment can appropriately determine a search target based on a model trained based on the teacher data output by the classification model.

[0073] Also, the information processing apparatus 100 according to the embodiment further includes a proposal unit 135 that proposes the purchase of a search target determined by the determination unit 134.

[0074] Thereby, the information processing apparatus 100 according to the embodiment can propose the purchase of a product that is a search target close to the intention of the user.

[0075] Also, the proposal unit 135 proposes the purchase of a search target that has not been determined as a search target to be provided as a search result.

[0076] Thereby, the information processing apparatus 100 according to the embodiment can propose the purchase of products having a relationship such as products used in a set or complementary goods.

[0077] Also, the search target is a product used in a set.

[0078] Thereby, even when there is a product used in a set for the search target corresponding to the query (for example, a battery if the search target is a remote control), the information processing apparatus 100 according to the embodiment can present a search result close to the intention of the user.

[0079] Also, the search target is a product having a relationship of complementary goods.

[0080] As a result, even when there is a product having a relationship with complementary goods in the search target corresponding to the query (for example, if the search target is a smartphone, a case for the smartphone, etc.), the information processing apparatus 100 according to the embodiment can present search results closer to the intention of the user.

[0081] 〔8. Hardware Configuration〕 In addition, the information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. 9. FIG. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing apparatus 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0082] The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program dependent on the hardware of the computer 1000, and the like.

[0083] The HDD 1400 stores a program executed by the CPU 1100 and data used by such a program. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and sends data generated by the CPU 1100 to other devices via a predetermined communication network.

[0084] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

[0085] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0086] For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing the program loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800. As another example, these programs may be acquired from another device via a predetermined communication network.

[0087] 〔9. Others〕 Also, among the respective processes described in the above embodiment, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0088] Moreover, each component of each illustrated device is functionally conceptual and does not necessarily have to be physically configured as shown in the drawings. That is, the specific form of distribution and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc.

[0089] Also, the above-described embodiments can be appropriately combined within a range that does not conflict with the processing content.

[0090] As described above, some of the embodiments of the present application have been described in detail based on the drawings. However, these are examples, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, starting from the aspects described in the column of the disclosure of the invention.

[0091] Also, the "section (section, module, unit)" described above can be read as "means", "circuit", etc. For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

Explanation of Reference Numerals

[0092] 1 Information Processing System 10 Terminal Device 11 Communication Unit 12 Input Unit 13 Output Unit 14 Control Unit 100 Information Processing Apparatus 110 Communication Unit 120 Storage Unit 121 Category Repair Information Storage Unit 122 Model Information Storage Unit 130 Control Unit 131 Acquisition Unit 132 Identification Unit 133 Estimation Unit 134 Decision Unit 135 Proposal Unit 141 Reception Unit 142 Transmission Unit N Network

Claims

1. A search target specified based on the past behavior history of an individual user with respect to a search target corresponding to a query, where there are a plurality of search targets whose relevance to the query exceeds a predetermined threshold, and when there are a plurality of categories to which the plurality of search targets belong, an estimation unit that estimates the relationship between the categories of the plurality of categories; A determination unit that determines a search target to be provided to the user as a search result corresponding to the query based on the relationship estimated by the estimation unit; An information processing apparatus characterized by comprising the above.

2. The estimation unit: Estimates the relationship between the categories of the plurality of categories by collating the plurality of categories to which search targets whose relevance to the query exceeds a predetermined threshold belong with information indicating the relationship between the categories. The information processing apparatus according to claim 1, characterized by the above.

3. The determination unit: Determines a search target to be provided as the search result based on the proximity of the character strings between the query and the search targets whose relevance to the query exceeds a predetermined threshold. The information processing apparatus according to claim 1, characterized by the above.

4. The determination unit: Determines a search target to be provided as the search result based on the proximity of the intentions indicated by the character strings. The information processing apparatus according to claim 3, characterized by the above.

5. The determination unit: When inputting a query and a plurality of categories to which search targets whose relevance to the query exceeds a predetermined threshold belong, uses a model trained to output a category corresponding to the query to determine a search target to be provided as a search result corresponding to the query. The information processing apparatus according to claim 1, characterized by the above.

6. The determination unit: When inputting a query, a plurality of categories to which search targets whose relevance to the query exceeds a predetermined threshold belong, and the order relationship between the categories of the plurality of categories, uses a model trained to output a category corresponding to the query to determine a search target to be provided as a search result corresponding to the query. The information processing apparatus according to claim 1, characterized by the above.

7. The determination unit: Uses the model trained with information manually input as teacher data to determine a search target to be provided as a search result corresponding to the query. The information processing apparatus according to claim 5 or 6, characterized by the above.

8. The determination unit: Determine a search target to be provided as a search result corresponding to the query using the model that has been learned with the information output by the classification model for classifying categories as teacher data. The information processing apparatus according to claim 5 or 6, characterized in that.

9. A proposal unit that proposes the purchase of a search target determined by the determination unit. The information processing apparatus according to claim 1, further comprising:

10. The proposal unit is Propose the purchase of search targets that have not been determined as search targets to be provided as the search results. The information processing apparatus according to claim 9, characterized in that.

11. The search target is a product used in a set. The information processing apparatus according to claim 1, characterized in that.

12. The search target is a product having a complementary goods relationship. The information processing apparatus according to claim 1, characterized in that.

13. An information processing method executed by a computer, comprising: An estimation step of estimating the relationship between categories of a plurality of categories when there are a plurality of search targets identified based on the past behavior history of the user individual for the search target corresponding to the query, the relevance of which to the query exceeds a predetermined threshold, and there are a plurality of categories to which the plurality of search targets belong; A determination step of determining a search target to be provided to the user as a search result corresponding to the query based on the relationship estimated in the estimation step; An information processing method characterized by including.

14. An estimation procedure for estimating the relationship between categories of a plurality of categories when there are a plurality of search targets identified based on the past behavior history of the user individual for the search target corresponding to the query, the relevance of which to the query exceeds a predetermined threshold, and there are a plurality of categories to which the plurality of search targets belong; A determination procedure for determining a search target to be provided to the user as a search result corresponding to the query based on the relationship estimated in the estimation procedure; An information processing program characterized by causing a computer to execute.

Images