Item search system, item search method, and item search program

Abstract

This invention provides an item search system, an item search method, and an item search program for users to search for desired items. [Solution] The support device 20 includes a control unit 21 connected to the user device 10. The control unit 21 performs an item acquisition process to acquire the search target item from the user device 10, calculates the image features of the search target item, identifies a specified number of similar items from the item information storage unit 22 based on the image features, classifies the specified number of similar items into multiple groups, identifies a representative item among the similar items belonging to each group, outputs the representative item for each group, and outputs it to the user device 10. The user device 10 then repeats the item search process using the selected representative item as the search target item.

Description

Technical Field

[0001] The present disclosure relates to an item search system, an item search method, and an item search program for searching for items such as images according to user preferences.

Background Art

[0002] There are cases where information from a user is acquired and items according to the user's preferences are searched. For example, a technique has been studied for obtaining, from registered reference images in which an image of the same subject is captured in advance, an image in which the same subject is captured as an input image as a query (for example, Patent Document 1). In the technique described in this patent document, an index is created based on feature amounts extracted from reference images. Then, feature amounts are extracted from the input query image. For reference images having feature amounts belonging to the same cluster by referring to the index, a candidate image score is added, and an image with a high candidate image score is set as a candidate image. For each candidate image, a more detailed recognition process is performed based on the similarity to the feature amount of the query image by directly referring to the feature amount of the reference image, thereby calculating a detailed score. A reference image with a high total score obtained by weighted summation of the normalized values of the candidate image score and the detailed score is output as a similar image.

[0003] Also, an item search system for searching for an item desired by a user has been studied (for example, Patent Document 2). The support server described in this patent document includes a control unit connected to a user device. Then, the control unit outputs, to the user device, a first item composed of first component values and a plurality of item candidates composed of component values different from the first component values in a plurality of main components constituting the item. Then, a second item selected by the user device is specified from the item candidates. Next, in each main component, the positional relationship between the first component value and the second component value of the second item is calculated. Further, in each main component, a component value distribution is calculated according to the positional relationship. Then, a plurality of item candidates are newly generated for the second item based on the component value distribution and output to the user device. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2017-016501 [Patent Document 2] Japanese Patent Publication No. 2023-002325 [Overview of the project] [Problems that the invention aims to solve]

[0005] However, images contain a variety of elements, including shape, pattern, color, and atmosphere. Furthermore, when users select an image, the deciding factors are also diverse. Moreover, the elements a user desires may change during the selection process. Presenting appropriate item options to such users can be challenging. [Means for solving the problem]

[0006] An item search system that solves the above problems comprises a control unit connected to a user device and an item information storage unit that records multiple items. The control unit performs an item acquisition process to acquire a search target item from the user device, calculates the image feature quantities of the search target item, identifies a specified number of similar items from the item information storage unit based on the image feature quantities, classifies the specified number of similar items into multiple groups, identifies a representative item among the similar items belonging to each group, outputs the representative item for each group, and outputs it to the user device. The user device then repeats the item search process using the selected representative item as the search target item. [Effects of the Invention]

[0007] According to this disclosure, users can efficiently and accurately search for the items they desire. [Brief explanation of the drawing]

[0008] [Figure 1] This is an explanatory diagram of the item search system according to the first embodiment. [Figure 2] This is an explanatory diagram of the hardware configuration of the first embodiment. [Figure 3] This is an explanatory diagram of the processing procedure for the selection support process of the first embodiment. [Figure 4] This is an explanatory diagram of the method for selecting a representative item in the first embodiment. [Figure 5] This is an explanatory diagram of the processing procedure according to the second embodiment. [Figure 6] This is a diagram illustrating the processing procedure for a different example of selection support processing. [Figure 7] This is an explanatory diagram of the process for narrowing down the search range in a different example. [Figure 8] This is an explanatory diagram of a selection history in a different example. [Figure 9] This is an explanatory diagram of the extraction range based on the selection history in a different example. [Figure 10] This is an explanatory diagram showing how to select representative items in a different example. [Figure 11] This is an explanatory diagram of the processing procedure for another example, where (a) is an explanatory diagram of the attribute feature axis generation process and (b) is an explanatory diagram of the search range narrowing process. [Figure 12] The following are diagrams illustrating the search range in a different example; (a) shows the same color scheme, and (b) shows the color variations. [Modes for carrying out the invention]

[0009] (First Embodiment) An embodiment of the item search system, item search method, and item search program will be described with reference to Figures 1 to 4. In this embodiment, it is assumed that a user searches for items of their choice according to their preferences. Here, pre-prepared two-dimensional still images are used as items. In this embodiment, the two-dimensional still images include photographs of clothing that can be provided to the user. As shown in FIG. 1, the item search system of the present embodiment uses a user device 10 and a support device 20 connected via a network.

[0010] (Hardware configuration example) FIG. 2 is a hardware configuration example of an information processing device H10 that functions as the user device 10, the support device 20, and the like.

[0011] The information processing device H10 includes a communication device H11, an input device H12, a display device H13, a storage device H14, and a processor H15. Note that this hardware configuration is an example, and it may have other hardware.

[0012] The communication device H11 is an interface that establishes a communication path with other devices and executes data transmission and reception, and is, for example, a network interface or a wireless interface.

[0013] The input device H12 is a device that receives input from a user or the like, and is, for example, a mouse or a keyboard. The display device H13 is a display, a touch panel, or the like that displays various information.

[0014] The storage device H14 is a storage device that stores data and various programs for executing various functions of the user device 10 and the support device 20. Examples of the storage device H14 include a ROM, a RAM, and a hard disk.

[0015] The processor H15 controls each process in the user device 10 and the support device 20 (for example, the process in the control unit 21 described later) using the programs and data stored in the storage device H14. Examples of the processor H15 include a CPU and an MPU. This processor H15 expands the program stored in the ROM or the like into the RAM and executes various processes corresponding to various processes. For example, when the application program of the user device 10 and the support device 20 is started, the processor H15 operates a process that executes each process described later.

[0016] The processor H15 is not limited to performing all of its operations through software processing. For example, the processor H15 may include dedicated hardware circuits (e.g., application-specific integrated circuits: ASICs) that perform hardware processing for at least some of the operations it performs. In other words, the processor H15 may be configured as follows:

[0017] (1) One or more processors that operate according to a computer program (2) One or more dedicated hardware circuits that perform at least some of the various processes, (3) Circuits including combinations of those A processor includes a CPU and memory such as RAM and ROM, where memory stores program code or instructions configured to cause the CPU to perform processing. Memory, or computer-readable media, includes any available media that can be accessed by a general-purpose or dedicated computer.

[0018] (Functions of each information processing device) The functions of the user device 10 and the support device 20 will be explained using Figure 1. User device 10 is a computer terminal used by users of this system.

[0019] The support device 20 is a computer system for assisting the user in searching for desired items. This support device 20 comprises a control unit 21, an item information storage unit 22, and a history information storage unit 23.

[0020] The control unit 21 performs the processing described later (including the management stage, extraction stage, candidate output stage, etc.). By executing the item search program for this purpose, the control unit 21 functions as the management unit 211, extraction unit 212, candidate output unit 213, etc.

[0021] The management unit 211 performs the process of acquiring and managing information about items. The extraction unit 212 performs a process to identify similar items based on the items identified in the user device 10. The candidate output unit 213 performs a process to output the item candidates identified from among similar items to the user device 10.

[0022] The item information storage unit 22 stores item management information related to an item. This item management information is recorded when an item that can be provided to the user device 10 is registered. This item management information includes data related to the item identifier, item image, item attributes, and image features. For example, an image of clothing is used as the item.

[0023] An item identifier is an identifier used to identify each item. Item images are photographs of the item (clothing). Item attributes are the elements that make up this item (material, color, pattern, shape, size, style, brand, price, function, etc.).

[0024] Image features are the features of this item image. For example, a multidimensional vector calculated from the item image using deep learning with a convolutional neural network (CNN) can be used as the image features. Alternatively, principal component analysis of the pixels of the item image can be performed, and a multidimensional vector consisting of the principal components of each element can be used as the image features.

[0025] The history information storage unit 23 records history management information about the items selected by the user. This history management information is recorded each time the user selects an item. This history information includes data about the initial item and the item identifier for each selection.

[0026] The number of selections is the number of times the selection process has been repeated (n times). The initial item is an image (search target item) obtained from user device 10. The item identifier is the identifier of the item selected by the user during the selection process.

[0027] (Selection support processing) Next, we will explain the selection support process using Figure 3. First, the item acquisition process is performed. Here, the control unit 21 of the support device 20 executes the sample image acquisition process (step S11). Specifically, the management unit 211 of the control unit 21 acquires a sample image from the user device 10 as a preceding item. Then, the management unit 211 records the sample image in the history information storage unit 23 as the initial item (item to be searched).

[0028] Next, the item search process is performed. Here, the control unit 21 of the support device 20 performs the extraction process of a specified number of similar images (step S12). Specifically, the extraction unit 212 of the control unit 21 calculates the image features of the sample image. Then, the extraction unit 212 extracts the specified number of item management information from the item information storage unit 22 using the features of the sample image. In this case, the extraction unit 212 extracts item management information in which the image features of the item management information are within a similar range within a predetermined distance from the image features of the sample image.

[0029] Next, the control unit 21 of the support device 20 performs similar image clustering processing (step S13). Specifically, the extraction unit 212 of the control unit 21 uses the image features of the specified number of extracted item management information to perform clustering, classifying them into multiple groups (clusters) through cluster analysis processing.

[0030] Next, the control unit 21 of the support device 20 performs the process of identifying candidate items that represent each cluster (step S14). Specifically, the extraction unit 212 of the control unit 21 identifies a representative item in each cluster according to the positional relationship of similar items. In this case, the method of identifying the representative item is changed according to the positional relationship between the cluster and the preceding item.

[0031] As shown in Figure 4, for the nearest cluster C12, which is close to the preceding item, the similar item 501 belonging to cluster C12 that has the shortest distance to the preceding item is identified as the representative item (candidate item). For the other clusters C11, C13, and C14, the center position of each cluster C11, C13, and C14 is identified, and the similar item 502 with features close to this center position is identified as the representative item (candidate item). In this way, the extraction unit 212 identifies item candidates equal to the number of clusters.

[0032] Next, the control unit 21 of the support device 20 performs the output processing of candidate items (step S15). Specifically, the candidate output unit 213 of the control unit 21 outputs an item selection screen to the display device H13 of the user device 10. This item selection screen includes selection buttons for the item image and sample image (preceding item image) of the identified item candidate, as well as a selection button to indicate termination.

[0033] Next, the control unit 21 of the support device 20 executes the item selection process (step S16). Specifically, on the item selection screen, if the user has a desired item candidate, they press the selection button for the desired item candidate. If the user wants to end the process, they press the end button. If there is no desired item, the user presses the selection button for a previous item (e.g., a sample image). In this case, the candidate output unit 213 of the control unit 21 identifies the pressed selection button. If an item candidate is selected, the item identifier of this item candidate is obtained from the user device 10. In this case, the candidate output unit 213 adds "1" to the selection count in the history management information recorded in the history information storage unit 23.

[0034] Next, the control unit 21 of the support device 20 performs a determination process to determine whether the process has ended (step S17). Specifically, the candidate output unit 213 of the control unit 21 determines that the process has ended if it detects that the end button has been pressed on the item selection screen.

[0035] If it is determined that the process is complete (i.e., "YES" in step S17), the control unit 21 of the support device 20 terminates the selection support process. If it is determined that the process is not complete (i.e., "NO" in step S17), the control unit 21 of the support device 20 performs a determination process to determine whether it is a new item (step S18). Specifically, the candidate output unit 213 of the control unit 21 determines whether the selected item is a preceding item or a new item candidate.

[0036] If it is determined that a new item candidate has been selected (if the answer is "YES" in step S18), the control unit 21 of the support device 20 performs a process to reduce the specified number (step S19). Specifically, the extraction unit 212 of the control unit 21 reduces the specified number according to the number of times the item search process is repeated. In this case, for example, the reduced specified number is calculated according to the number of repetitions.

[0037] On the other hand, if it is determined that a preceding item has been selected (if the answer is "NO" in step S18), the control unit 21 of the support device 20 performs a process to increase the specified number (step S20). Specifically, the extraction unit 212 of the control unit 21 increases the specified number. In this case, for example, the increased specified number is calculated according to the number of times the item search process has been repeated.

[0038] Then, the control unit 21 of the support device 20 repeats the item search process after the extraction process of a specified number of similar images (step S12). In this case, it extracts similar images to the selected item candidate or preceding item.

[0039] (Operation of the first embodiment) Since representative items from each cluster, which classifies similar items, are used as candidate items, the features of the candidate items are distributed.

[0040] (Effects of the first embodiment) (1-1) In this embodiment, the control unit 21 of the support device 20 performs the process of acquiring a sample image (step S11) and the process of extracting a specified number of similar images (step S12). This makes it possible to extract item candidates that are similar to the sample image. (1-2) In this embodiment, the control unit 21 of the support device 20 performs similar image clustering processing (step S13) and processing to identify candidate items that represent each cluster (step S14). Since the sample image contains various elements such as color, pattern, and shape, it may not be possible to determine what elements the user desires in the sample image. In this case as well, it is possible to extract dispersed item candidates in clusters classified by feature quantities. Furthermore, by identifying item candidates that are close to the sample image in the nearest cluster, it is possible to extract item candidates that are generally similar to the sample image.

[0041] (1-3) In this embodiment, the control unit 21 of the support device 20 performs candidate item output processing (step S15) and item selection processing (step S16). This makes it possible to identify the desired item candidate from the existing items.

[0042] (1-4) In this embodiment, if it is determined that a new item candidate has been selected (if the answer is "YES" in step S18), the control unit 21 of the support device 20 performs a process to reduce the specified number (step S19). This makes it possible to identify item candidates within a narrowed range of similar items.

[0043] (1-5) In this embodiment, if it is determined that a prior item has been selected (if the answer is "NO" in step S18), the control unit 21 of the support device 20 performs a process to increase the specified number (step S20). This allows for the identification of item candidates within a broadened range of similar items if the item candidate desired by the user cannot be found.

[0044] (Second Embodiment) In the first embodiment, items are classified by clustering. The method of classifying items is not limited to clustering. In the second embodiment, a case in which items are classified using principal component analysis instead of clustering is described.

[0045] The selection support process in this case will be explained using Figure 5. First, the control unit 21 of the support device 20 performs the same steps as in steps S11 and S12: the acquisition of sample images (step S21) and the extraction of a specified number of similar images (step S22).

[0046] Next, the control unit 21 of the support device 20 performs principal component analysis processing of similar images (step S23). Specifically, the extraction unit 212 of the control unit 21 calculates image feature components by performing principal component analysis of similar images.

[0047] Next, the control unit 21 of the support device 20 performs a process to identify feature components with large variability (step S24). Specifically, the extraction unit 212 of the control unit 21 identifies multiple feature component axes in principal component analysis in order of the variability of the image feature components.

[0048] Next, the control unit 21 of the support device 20 performs the process of identifying candidate items using feature components (step S25). Specifically, the management unit 211 of the control unit 21 identifies candidate items on multiple feature component axes with large variability. Here, among similar images grouped by these component axes, the similar items with the maximum and minimum values ​​are identified as candidate items. Next, the control unit 21 of the support device 20 executes the output processing of candidate items (step S15) to the incrementing of the specified number (step S20).

[0049] (Effects of the second embodiment) According to this embodiment, in addition to the effects of (1-1), (1-3) to (1-5), the following effects can be obtained.

[0050] (2-1) In this embodiment, the control unit 21 of the support device 20 performs principal component analysis processing of similar images (step S23), processing to identify feature components with large variability (step S24), and processing to identify candidate items using feature components (step S25). This makes it possible to identify candidate items consisting of representative items according to the variability of similar images.

[0051] This embodiment can be implemented with the following modifications. This embodiment and the following modifications can be combined with each other to the extent that they do not contradict each other technically. • In each of the above embodiments, we assume that the search is conducted using a two-dimensional still image as the item. However, the search target is not limited to two-dimensional still images. It can be applied to anything whose constituent elements can be quantified in multiple dimensions. For example, it can be applied to three-dimensional images, videos, audio, and text.

[0052] In each of the above embodiments, the control unit 21 of the support device 20 performs output processing of candidate items (step S15). Here, item candidates that are close in distance to each other are displayed closer together in terms of the feature quantities of each item candidate. This makes it easier for the user to compare the item candidates.

[0053] In each of the above embodiments, item candidates are identified in the classified groups using clustering or principal component analysis. In addition, the user may be allowed to narrow down the search range.

[0054] The selection support process will be explained using Figure 6. First, the control unit 21 of the support device 20 performs the process of acquiring a sample image (step S11). Next, the control unit 21 of the support device 20 performs a search range narrowing process (step S31). Specifically, the management unit 211 of the control unit 21 obtains the attributes specified by the user from the user device 10. Then, the extraction unit 212 extracts the item management information in which the specified attributes are recorded from the item information storage unit 22. Then, the control unit 21 of the support device 20 uses the extracted item management information to perform the processing from step S12 onward, which involves extracting a specified number of similar images.

[0055] In the above embodiment, similar images are searched based on the sample image. Here, the search range may be narrowed based on the selection history.

[0056] Figure 7 will be used to explain the process of narrowing down the search range. First, the control unit 21 of the support device 20 executes the process of acquiring the selection history (step S41). Specifically, the extraction unit 212 of the control unit 21 identifies the item selected by the user from the history information storage unit 23. As shown in Figure 8, we assume that item candidates P2, P3, and P4 are selected in order for the sample image P1.

[0057] Next, the control unit 21 of the support device 20 performs principal component analysis processing of the historical images (step S42). Specifically, the extraction unit 212 of the control unit 21 calculates the image features of the identified items. Next, the extraction unit 212 performs principal component analysis of the calculated image features. Then, the extraction unit 212 identifies the component axes of each feature. Here, we perform principal component analysis on the image features of candidate items P1 to P4.

[0058] Next, the control unit 21 of the support device 20 performs a variability evaluation process for each component axis (step S43). Specifically, the extraction unit 212 of the control unit 21 evaluates the variance of the feature quantities of the selected history image in the identified component axis. The variance can be, for example, the variance (eigenvalue) of the data in that axis direction or the contribution rate.

[0059] Next, the control unit 21 of the support device 20 performs weighting processing of the component axes according to the variability (step S44). Specifically, the extraction unit 212 of the control unit 21 compares the variability of the feature quantities of similar images for each component axis and weights the component axes. Here, the weight is increased for component axes with large variability.

[0060] Next, the control unit 21 of the support device 20 performs a range narrowing process that takes weighting into account (step S45). Specifically, the extraction unit 212 of the control unit 21 calculates the distance between similar ranges on the component axis according to the weighting.

[0061] As shown in Figure 9, if the items included in the selection history are dispersed along a predetermined component axis AX1, weighting is applied to expand the similarity range RG1 along this component axis AX1. Furthermore, the method for selecting representative items may be changed depending on the component axis AX1.

[0062] As shown in Figure 10, let's assume that clusters C21 to C23 are generated during the similar image clustering process (step S13). In this case, for similar items included in cluster C22, which intersects with the component axis AX1 which has a large variation, the nearest similar item 511 is identified as the representative item. On the other hand, for clusters C21 and C23 which do not intersect with the component axis which has a large variation, the similar item 512, which is close to the center of clusters C21 and C23, is identified as the representative item. This means that if there is variation along the component axis, it indicates that the user's preferences are not stable, allowing for the extraction of similar items by broadening the range.

[0063] In the above embodiment, similar images are searched based on the sample image. Here, attributes may be narrowed down based on image features.

[0064] Next, we will explain the attribute feature axis generation process using Figure 11(a). This process is performed prior to the item selection process (pre-processing). First, the control unit 21 of the support device 20 performs the image feature calculation process (step S51). Specifically, the management unit 211 of the control unit 21 calculates the image feature of each item image.

[0065] Next, the control unit 21 of the support device 20 performs the attribute value acquisition process (step S52). Specifically, the management unit 211 of the control unit 21 acquires the attribute values ​​of each item. Attributes can include, for example, color, shape, pattern, etc.

[0066] Next, the control unit 21 of the support device 20 performs the attribute feature axis setting process (step S53). Specifically, the management unit 211 of the control unit 21 associates image features with attributes. Here, PLS-DA (Partial Least Squares Discriminant Analysis) is used as the discriminant analysis for the attribute feature axis. Note that the method is not limited to PLS-DA, as long as it can perform discriminant analysis to associate image features with attributes.

[0067] Next, we will explain the selection support process using Figure 11(b). First, the control unit 21 of the support device 20 executes the process of specifying attribute conditions by the user (step S61). Specifically, the extraction unit 212 of the control unit 21 obtains the attribute conditions specified by the user from the user device 10. For example, it obtains attribute conditions specified by the user (same hue, color variations, etc.).

[0068] Next, the control unit 21 of the support device 20 performs a filtering process on the attribute feature axis according to the attribute conditions specified by the user (step S62). Specifically, the extraction unit 212 of the control unit 21 calculates image features corresponding to the attributes on the attribute feature axis for the attribute conditions specified by the user. If the user desires attributes common to preceding items, the variation in attribute features is adjusted so that a similarity range is set in a direction orthogonal to the attribute axis of this attribute. On the other hand, if the user desires a change in attribute conditions for preceding items, the variation in attribute features is adjusted so that a similarity range is set in a direction along the attribute axis of this attribute.

[0069] As shown in Figure 12(a), for example, if you want the same hue (if you want common attributes) for color attributes, you set the extraction range orthogonal to the color component axis AX2. On the other hand, as shown in Figure 12(b), if you want color variations (changes) for the color attributes, you set the extraction range along the color component axis AX2. This allows you to set the extraction range for image features using component axes that evaluate item attributes. [Explanation of Symbols]

[0070] 10...User device, 20...Support device, 21...Control unit, 211...Management unit, 212...Extraction unit, 213...Candidate output unit, 22...Item information storage unit, 23...History information storage unit.

Claims

1. An item search system comprising a control unit connected to a user device and an item information storage unit that records multiple items, The control unit, The item acquisition process involves acquiring the item to be searched from the user device, The image features of the item to be searched are calculated, and a specified number of similar items are identified from the item information storage unit based on the image features. The specified number of similar items are classified into multiple groups, From among the similar items belonging to each of the aforementioned groups, identify a representative item. The representative items for each group are output, and an item search process is executed to output to the user device. An item search system characterized by repeating the item search process using the representative item selected in the user device as the item to be searched.

2. The control unit, In the above classification, multiple clusters are generated by cluster analysis, The item search system according to claim 1, characterized in that it identifies the representative item among a plurality of similar items included in the cluster.

3. The control unit, The positional relationship between each of the aforementioned clusters and the item to be searched is identified, The item search system according to claim 2, characterized in that the method for identifying the representative item is changed according to the aforementioned positional relationship.

4. The item search system according to claim 3, characterized in that, as the identification method, a similar item close to the center of the cluster is identified as the representative item.

5. The item search system according to claim 3, characterized in that, as the identification method, in the cluster close to the item to be searched, the nearest similar item to the item to be searched is identified as the representative item.

6. The control unit, In the above classification, the image feature components are calculated by principal component analysis. The item search system according to claim 1, characterized in that similar items dispersed in the image feature components are identified as the representative item.

7. The item search system according to claim 1, characterized in that the control unit changes the specified number according to the number of times the item search process is repeated.

8. The control unit calculates attribute feature axes by performing discriminant analysis using the attributes of each item and the image features, The item search system according to claim 1, characterized in that it searches for similar items by adjusting the variation of attribute features on the attribute feature axis according to the user's specified attributes.

9. The control unit, Get the item selection history, Principal component analysis is performed on the image features of the selected items. The item search system according to claim 1, characterized in that the search range is narrowed by weighting the component axes calculated by the principal component analysis.

10. A method for searching for items according to a user's preferences using an item search system comprising a control unit connected to a user device and an item information storage unit that records multiple items, The control unit, The item acquisition process involves acquiring the item to be searched from the user device, The image features of the item to be searched are calculated, and a specified number of similar items are identified from the item information storage unit based on the image features. The specified number of similar items are classified into multiple groups, From among the similar items belonging to each of the aforementioned groups, identify a representative item. The representative items for each group are output, and an item search process is executed to output to the user device. An item search method characterized by repeating the item search process using the representative item selected in the user device as the item to be searched.

11. An item search program that searches for items according to the user's preferences using an item search system comprising a control unit connected to a user device and an item information storage unit that records multiple items, The control unit, The item acquisition process involves acquiring the item to be searched from the user device, The image features of the item to be searched are calculated, and a specified number of similar items are identified from the item information storage unit based on the image features. The specified number of similar items are classified into multiple groups, From among the similar items belonging to each of the aforementioned groups, identify a representative item. The representative items for each group are output, and an item search process is executed to output to the user device. An item search program that functions as a means for repeating the item search process, using the representative item selected in the user device as the item to be searched.

Images