Information processing device, learning device, information processing method, method for producing learning information, and program

Abstract

To solve the problem that it used to be difficult to propose merchandise group content such as an electronic catalog or a Web page carrying a plurality of pieces of merchandise information.SOLUTION: An information processing device includes: a learning information storage part for storing learning information acquired by learning information to be learnt having one or more merchandise attribute information having one or more attribute values of merchandise information associated with merchandise and one or more marketing information associated with marketing of the merchandise; a reception part for receiving one or more object merchandise information having one or more attribute values; a marketing information acquisition part for acquiring the marketing information by applying one or more attribute values owned by each of one or more object merchandise information; and an output part for outputting the marketing information. Thus, it is possible to propose merchandise group content carrying a plurality of pieces of merchandise information.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing apparatus and the like that perform information processing on product group content such as electronic catalogs and web pages. [Background Art]

[0002] In the prior art, there has been known an electronic catalog editing apparatus capable of freely creating a layout and generating a presentation sheet that maintains linkage with a product sales system, based on an electronic catalog linked to the product sales system (see, for example, Patent Document 1). [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2013-242634 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, in the prior art, it has been difficult to propose product group content that is estimated to have good sales performance or improved sales performance. Note that product group content refers to, for example, electronic catalogs, web pages, and the like on which multiple pieces of product information are posted. [Means for Solving the Problem]

[0005] An information processing apparatus according to a first aspect of the present invention comprises: a learning information storage unit that stores learned information obtained by learning learning target information including one or more pieces of product attribute information each having one or more attribute values for product information related to products, and sales information related to sales of one or more products; a reception unit that receives one or more pieces of target product information each having one or more attribute values; a sales information acquisition unit that applies the one or more attribute values of each of the one or more pieces of target product information to the learned information to acquire sales information; and an output unit that outputs the sales information.

[0006] This configuration makes it possible to predict product sales information, which is the effect of product group content consisting of product information for one or more products.

[0007] Furthermore, the information processing device of this second invention, in contrast to the first invention, is an information processing device in which the one or more attribute values ​​possessed by the target product information include one or more attribute values ​​from among the following: product itself attribute value, which is the attribute value of the product itself; image attribute value, which is the attribute value of the product image possessed by the product information; string attribute value, which is the attribute value of the product string, which is the attribute value of the string relating to the product possessed by the product information; placement attribute value, which is the attribute value of the arrangement of the product information; and attribute values ​​of product information arranged around the product information.

[0008] This configuration allows us to predict product sales information, which is the effect of product group content.

[0009] Furthermore, the information processing device of this third invention, compared to the second invention, comprises a receiving unit which receives one or more target product information having one or more attribute values ​​from among product itself attribute values ​​and image attribute values, and a placement pattern information acquisition unit which acquires two or more placement pattern information which is placement pattern information having one or more placement attribute values ​​for each of the one or more target product information; a sales information acquisition unit which applies the one or more attribute values ​​received by the receiving unit and the placement pattern information acquired by the placement pattern information acquisition unit to learning information and acquires sales information for each of the two or more placement pattern information; a judgment unit which determines whether the sales situation is good enough to satisfy predetermined conditions for the sales information for each of the two or more placement pattern information acquired by the sales information acquisition unit; and a configuration unit which arranges two or more target product information according to the placement pattern information when the judgment unit determines that the sales situation is good, thereby constituting a product group content; and an output unit which outputs the product group content configured by the configuration unit, or the product group content configured by the configuration unit and sales information.

[0010] This configuration allows us to propose an arrangement of product information that is estimated to be selling well.

[0011] Furthermore, the information processing device of the fourth invention, compared to the second invention, comprises: a receiving unit which receives one or more target product information having one or more attribute values ​​and further comprises an attribute value changing unit which changes some of the one or more attribute values ​​received by the receiving unit; a sales information acquisition unit which applies the attribute values ​​changed by the attribute value changing unit and the attribute values ​​among the one or more attribute values ​​received by the receiving unit that have not been changed by the attribute value changing unit to learning information to acquire sales information; a judgment unit which determines whether the sales situation is good enough to satisfy predetermined conditions based on the sales information acquired by the sales information acquisition unit; and a configuration unit which arranges one or more target product information using the attribute values ​​when the judgment unit determines that the sales situation is good to constitute a product group content; and an output unit which outputs the product group content configured by the configuration unit, or the product group content configured by the configuration unit and sales information.

[0012] This configuration allows us to propose changes to the attribute values ​​of product information for products that are estimated to be selling well.

[0013] Furthermore, the information processing device of the fifth invention, compared to the fourth invention, is an information processing device in which the attribute value changing unit changes one or more attribute values ​​received by the receiving unit, such as the product itself attribute value, image attribute value, or string attribute value.

[0014] This configuration allows us to propose changes to the attribute values ​​of product information for products that are estimated to be selling well.

[0015] Furthermore, the information processing device of the sixth invention, compared to the fourth invention, is an information processing device in which the attribute value changing unit changes the placement attribute value among one or more attribute values ​​received by the receiving unit.

[0016] This configuration allows us to propose changes to the placement of product information for products that are presumed to be selling well.

[0017] Further, the information processing apparatus according to the seventh aspect of the present invention is a learning apparatus that constitutes learning information used by the information processing apparatus according to any one of the first to sixth aspects of the present invention, comprising: a learning information storage unit that stores learning information obtained by learning learning target information including one or more pieces of product attribute information having one or more attribute values of product information related to products, and sales information related to sales of one or more products; a reception unit that receives the learning target information; and a learning unit that learns the learning target information by a machine learning algorithm, acquires the learning information, and accumulates the learning information in the learning information storage unit.

[0018] With this configuration, learning information can be easily acquired.

Effects of the Invention

[0019] According to the information processing apparatus of the present invention, product group content in which product information of one or more products is posted can be proposed.

Brief Description of Drawings

[0020] [Figure 1] Diagram showing a conceptual diagram of an information system A in Embodiment 1 [Figure 2] Block diagram of the information system A [Figure 3] Flowchart for explaining an operation example of the information processing apparatus 1 [Figure 4] Flowchart for explaining an example of the product group content acquisition process [Figure 5] Flowchart for explaining an example of the pattern information acquisition process [Figure 6] Flowchart for explaining an operation example of the terminal apparatus 2 [Figure 7] Diagram showing the attribute value condition management table [Figure 8] Diagram showing the layout information management table [Figure 9] Diagram showing the product information management table [Figure 10] Diagram showing the product information management table [Figure 11] Diagram showing an example of a web page of an automobile catalog [Figure 12] A diagram showing an example of the sales performance of the vehicle. [Figure 13] Diagram showing attribute value management table [Figure 14] A diagram showing an example of a webpage from the automobile catalog. [Figure 15] Figure showing an example of the same output. [Figure 16] Figure showing an example of the same output. [Figure 17] This diagram shows an example of a block diagram of the learning device 3. [Figure 18] Overview of the computer system [Figure 19] Block diagram of the computer system [Modes for carrying out the invention]

[0021] The embodiments of the information processing device, etc., will be described below with reference to the drawings. In the embodiments, components that are denoted by the same reference numerals perform the same operation, and therefore, further explanation may be omitted.

[0022] (Embodiment 1)

[0023] In this embodiment, we describe an information system that includes an information processing device capable of predicting the sales status of products listed in product group content, which consists of one or more product information items such as electronic catalogs and web pages. More specifically, in this embodiment, we describe an information system that includes an information processing device that stores learning information obtained by learning target information having one or more product attribute information and sales information, receives one or more target product information items having one or more attribute values, and outputs sales information. Here, "product" means an item for sale and is interpreted broadly to include services as well.

[0024] Furthermore, in this embodiment, we will describe an information system that includes an information processing device capable of suggesting changes to the arrangement of product information, changes to the attribute values ​​of product information, etc., for products that are selling well or are estimated to be selling well.

[0025] Furthermore, in this embodiment, we will describe an information system that includes an information processing device capable of suggesting product group content that is selling well or is estimated to be selling well.

[0026] Figure 1 is a conceptual diagram of information system A in this embodiment. Information system A comprises an information processing device 1 and one or more terminal devices 2. The information processing device 1 is, in this case, a so-called server device. The information processing device 1 may be, for example, a cloud server or an ASP server, but its type and installation location are not specified. The terminal devices 2 may be mobile terminals such as smartphones, tablet terminals or mobile phones, or so-called personal computers, and their type is not specified.

[0027] Figure 2 is a block diagram of information system A in this embodiment.

[0028] The information processing device 1 comprises a storage unit 11, a receiving unit 12, a processing unit 13, and an output unit 14. The storage unit 11 comprises a learning information storage unit 111 and an attribute value condition storage unit 112. The processing unit 13 comprises a learning unit 131, an arrangement pattern information acquisition unit 132, an attribute value modification unit 133, a sales information acquisition unit 134, a judgment unit 135, and a configuration unit 136. The sales information acquisition unit 134 comprises an attribute value set acquisition means 1341 and a sales information acquisition means 1342.

[0029] The terminal device 2 comprises a terminal storage unit 21, a terminal receiving unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal receiving unit 25, and a terminal output unit 26.

[0030] The storage unit 11, which constitutes the information processing device 1, stores various types of information. These various types of information include, for example, learning information (described later), attribute value conditions (described later), one or more layout information, one or more target product information, or product group content having one or more target product information. The target product information is the product information that the information processing device 1 processes.

[0031] Layout information is information used to determine the placement of one or more product information items. Layout information includes, for example, placement attribute values ​​indicating the placement position of product information (e.g., the coordinate value of the top-left corner of an area), and a set of one or more attribute values ​​for product information that can be placed in the area determined by the placement attribute values. Product information is information about a product and is placed in product group content such as an electronic catalog or a web page. Product group content may be information containing a single product information item. Product group content may be content that has the concept of a page, or content that does not have the concept of a page. Product information may include, for example, a product image, product string, product video, and product audio. The product image is an image of the product. The product string is a string describing the product. The product video is a video describing the product. The product audio is audio describing the product. Furthermore, one or more attribute values ​​of the product information may be stored in association with that product information.

[0032] Product information attribute values ​​include, for example, product itself attribute values, image attribute values, string attribute values, video attribute values, audio attribute values, and placement attribute values. Product itself attribute values ​​are attribute values ​​of the product itself, such as product color, product shape, product weight, product type, and product category. Image attribute values ​​are attribute values ​​of the product image contained in the product information, such as product image size, product image color, product image resolution, product image brightness, and product image shape. Product image color is, for example, the average value of the color components of the pixel values ​​that make up the product image. Product image brightness is, for example, the average value of the brightness of the pixels that make up the product image. String attribute values ​​are attribute values ​​of the string that describes the product, such as font, font size, and length. Video attribute values ​​are attribute values ​​of the product video contained in the product information, such as including one or more features of the product video. Features include, for example, the length of the product video, the resolution of the product video, information indicating whether or not the product video has subtitles, information indicating whether or not the product video has commercials, information indicating the number of times the product video has been viewed, information indicating whether or not the product video has comments, information indicating whether or not the product video is divided, various other features of the product video, and features of still images that make up the product video. Note that there can be various types of video features and still image features, and the techniques for acquiring these features are publicly known. Audio attribute values ​​are attribute values ​​of audio information contained in the product information, and for example, include one or more features of the product audio. Features include, for example, the length of the product audio, the volume of the product audio, the sound quality of the product audio, the key of the product audio, the gender of the speaker of the product audio, information indicating whether or not the product audio has background music, the insertion point of the background music, information indicating whether or not the product audio has sound effects, the insertion point of sound effects, and other audio features. Note that there can be various types of audio features, and the techniques for acquiring these features are publicly known. Placement attribute values ​​are attribute values ​​related to the placement of product information, and include absolute placement attribute values ​​or attribute values ​​of surrounding product information. Absolute placement attribute values ​​are attribute values ​​related to the placement of the product information itself, such as its position on the page (e.g., top, middle, bottom, left, center, right), coordinate values, and page number. Surrounding product information refers to product information adjacent to the product information, or product information located on the same page as the product information. Sales information refers to information related to the sale of the product.Sales information may include, for example, the number of items sold or the total sales amount. While the total sales amount or total number of items sold for two or more products is preferable, the sales amount or number of items sold for each of the two or more products is also acceptable.

[0033] The learning information storage unit 111 stores the learning information.

[0034] Learning information is, for example, information acquired by the learning unit 131 through learning. Details of the learning unit 131 will be described later. Learning information is, for example, information acquired by learning target information. Learning target information has one or more product attribute information and sales information. Product attribute information has one or more attribute values ​​corresponding to product information. One or more attribute values ​​corresponding to product information may be one or more attribute values ​​that the product information has, one or more attribute values ​​linked to the product information, or one or more attribute values ​​that can be obtained from the product information. Learning target information may also be information that has product group content and sales information. Learning target information may also be information that has two or more product attribute information and sales information obtained from product group content.

[0035] The learning information may also consist of multiple sets of sales information, each containing one or more attribute values ​​for one or more product pieces.

[0036] The attribute value condition storage unit 112 stores one or more attribute value conditions relating to the conditions under which an attribute value can take place. Each attribute value condition includes an attribute identifier that identifies the attribute value and an attribute value modification condition.

[0037] Attribute identifiers include, for example, attribute names and IDs. Attribute names include, for example, "Color" indicating the color of a product, "Shape" indicating the shape of a product, "Weight" indicating the weight of a product, "Type" indicating the type of product, "Image Size" indicating the size of a product image, "Image Color" indicating the color of a product image, "Resolution" indicating the resolution of a product image, "Brightness" indicating the brightness of a product image, "Image Shape" indicating the shape of a product image, "Font" and "Font Size" indicating the font of the text describing the product, "String Length" indicating the length of the text describing the product, "Video Duration" indicating the playback time of a video describing the product, "Audio Type" indicating the type of audio describing the product, "Page Position" indicating the position on the page, "Coordinate Value" indicating the coordinate value on the page, "Page Number" indicating the page number on which the product information is placed, "Surrounding Image Size" indicating the size of product images in surrounding product information, "Surrounding Image Resolution" indicating the resolution of product images in surrounding product information, "Surrounding Product Font Size" indicating the font size of surrounding product information, and "Surrounding Product String Length" indicating the length of the strings in surrounding product information. "Surrounding image size" refers to, for example, the size of the adjacent upper product image ("upper product image size"), the size of the adjacent horizontal product image ("horizontal product image size"), the size of the adjacent lower product image ("lower product image size"), etc. "Surrounding image resolution" refers to, for example, the resolution of the adjacent upper product image ("upper product image resolution"), the resolution of the adjacent horizontal product image ("horizontal product image resolution"), the resolution of the adjacent lower product image ("lower product image resolution"), etc. "Surrounding product text size" refers to, for example, the text size of the adjacent upper product text ("upper product text size"), the text size of the adjacent horizontal product text ("horizontal product text size"), the text size of the adjacent lower product text ("lower product text size"), etc. "Surrounding product text length" refers to, for example, the length of the adjacent upper product text ("upper product text length"), the length of the adjacent horizontal product text ("horizontal product text length"), the length of the adjacent lower product text ("lower product text length"), etc.

[0038] The conditions for changing attribute values ​​include, for example, a set of information on possible values ​​for the attribute value and information on the range of values ​​the attribute value can take. The set of information on possible values ​​for the attribute value is, for example, "Font = Gothic, Mincho,...", "Font size = 10pt, 12pt, 14pt,...", "Page position = (1st, left), (1st, right), (2nd, left), (3rd, right), (3rd, left), (3rd, right),...". Information on the range of values ​​the attribute value can take is, for example, "(x1, y1) <= Image size <= (x2, y2) (x1, x2 are width, y1, y2 are height)", "1 <= Page number <= 10", "10pt <= Surrounding product font size <= 16pt".

[0039] The reception unit 12 receives one or more target product information items having one or more attribute values. The target product information is usually the product information that makes up the output product group content. The target product information may also be, for example, one or more attribute values ​​that the product information that makes up the output product group content has.

[0040] Here, it is preferable that the attribute values ​​of 1 or more are one or more attribute values ​​from among the product itself attribute values ​​and image attribute values.

[0041] The reception unit 12 may, for example, accept learning instructions, proposal instructions, and sales forecast instructions.

[0042] A learning instruction contains learning target information. Learning target information is the information to be learned. Learning target information is the information used by the sales information acquisition unit 134 to acquire sales information. Learning target information contains product attribute information for one or more products and sales information. Product attribute information contains one or more attribute values ​​of the product information.

[0043] A proposal instruction is an instruction to propose product group content. A proposal instruction may output product group content that is estimated to have good sales performance, or it may output product group content that is estimated to have improved sales performance. A proposal instruction may, for example, have one or more target product information. A proposal instruction may, for example, have product group content. If a proposal instruction has product group content, for example, the receiving unit 12 obtains one or more attribute values ​​for each of the one or more product information items that the product group content has. Such one or more attribute values ​​are target product information.

[0044] A sales forecast instruction is an instruction to output a sales forecast. A sales forecast instruction has, for example, information on one or more target products. A sales forecast instruction has, for example, product group content. If a sales forecast instruction has product group content, for example, the receiving unit 12 obtains one or more attribute values ​​for each of the one or more product information contained in the product group content. Such one or more attribute values ​​are the target product information.

[0045] Here, "reception" usually refers to receiving information from terminal device 2, but it is a concept that also includes receiving information input from input devices such as keyboards, mice, and touch panels, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory. Reception is any process that can acquire the target information or instructions.

[0046] If the reception is the reception of information entered from an input device, the input means can be anything, such as a touch panel, keyboard, mouse, or menu screen. In such cases, the reception unit 12 can be implemented using device drivers for input means such as touch panels or keyboards, or control software for menu screens.

[0047] The processing unit 13 performs various processes. These various processes include, for example, those performed by the learning unit 131, the arrangement pattern information acquisition unit 132, the attribute value modification unit 133, the sales information acquisition unit 134, the judgment unit 135, and the configuration unit 136.

[0048] The learning unit 131 learns the target information using a machine learning algorithm and acquires the learned information. Here, machine learning refers to, for example, SVR, deep learning, decision trees, random forests, SVM, etc. However, the machine learning algorithm is not limited.

[0049] The learning target information includes one or more product attribute information and sales information. The product attribute information has one or more attribute values ​​for the product information. The sales information is usually information about the sale of one or more products corresponding to one or more product attribute information. Preferably, the sales information held by the learning target information is information about sales made using a product group content that includes one or more product information corresponding to each of the one or more product attribute information held by the learning target information.

[0050] The information to be learned may be product group content and sales information. In this case, the learning unit 131 obtains one or more product attribute information from the product group content. The learning unit 131 then learns the obtained product attribute information and the sales information contained in the information to be learned using a machine learning algorithm, and obtains the learned information.

[0051] The learning information only needs to be information that allows sales information to be obtained when one or more attribute values ​​of a product are applied.

[0052] Since the processing of the learning unit 131 is based on publicly known technology, a detailed explanation will be omitted. Furthermore, the learning information may also consist of multiple pairs of product attribute information (one or more) and sales information. Alternatively, the learning information may also consist of multiple correspondence pieces of information, such as one or more product attribute information and sales information.

[0053] The arrangement pattern information acquisition unit 132 acquires two or more arrangement pattern information units. The arrangement pattern information is information that has one or more arrangement attribute values ​​for each of the one or more target product information units, and is information about an arrangement pattern.

[0054] The placement pattern information acquisition unit 132, for example, adds the placement order of each of the two or more target product information received by the reception unit 12 to each of the target product information. In this case, the placement pattern information acquisition unit 132 may, for example, randomly add the placement order starting from 1 to arbitrarily selected target product information. The placement pattern information acquisition unit 132 also determines the placement order of each target product information (sorts the product information) based on predetermined conditions (conditions using one or more attribute values) and adds the said placement order to each of the target product information. Furthermore, the placement pattern information acquisition unit 132 places one or more of the target product information according to two or more predetermined layout information and acquires the placement attribute values ​​of one or more of the target product information. The placement pattern information is information for placing one or more product information within the product group content. Once the placement pattern information is determined, the placement of one or more of the product information is usually determined.

[0055] The attribute value modification unit 133 modifies some of the attribute values ​​among the one or more attribute values ​​that each of the one or more target product information received by the reception unit 12 possesses. It is not specified how the attribute value modification unit 133 modifies the attribute values. However, it is preferable for the attribute value modification unit 133 to modify the attribute values ​​to match the attribute value conditions. If the attribute value conditions are, for example, a set of candidate information for the attribute value, the attribute value modification unit 133 selects one candidate from the candidate values ​​and determines that candidate as the modified attribute value. Alternatively, if the attribute value conditions are, for example, information for a range of values ​​that the attribute value can take, the attribute value modification unit 133 randomly selects one value from that range and determines that value as the modified attribute value.

[0056] The attribute value modification unit 133 may modify one or more attribute values ​​from the one or more target product information received by the reception unit 12, including the product itself attribute value, image attribute value, and string attribute value.

[0057] The attribute value modification unit 133 may change the placement attribute value among the one or more attribute values ​​that each of the one or more target product information received by the reception unit 12 has.

[0058] The sales information acquisition unit 134 applies one or more attribute values ​​from the one or more target product information received by the reception unit 12 to the learning information to acquire sales information. It should be noted that the sales information here is sales forecast information.

[0059] The process of applying one or more attribute values ​​to training information is, for example, a process that uses a machine learning algorithm. Alternatively, the process of applying one or more attribute values ​​to training information is, for example, a process that selects one or more attribute values ​​from the training information that are closest to one or more attribute values, and then retrieves the sales information contained in the selected training information.

[0060] The process of applying one or more attribute values ​​to the learning information is, for example, the process of selecting one or more attribute values ​​from the learning information that are closest to the one or more attribute values ​​that each of the one or more target product information received by the reception unit 12 has, and then obtaining the sales information that corresponds to the selected one or more attribute values ​​from the learning information.

[0061] The sales information acquisition unit 134 acquires sales information by applying target product information to training data, for example, using a machine learning algorithm. Examples of machine learning algorithms include SVR, deep learning, decision trees, random forests, and SVM. Furthermore, it is preferable that the two or more target product information entries received by the reception unit 12 do not include sales information.

[0062] It is preferable for the sales information acquisition unit 134 to apply one or more attribute values ​​received by the reception unit 12 and the arrangement pattern information acquired by the arrangement pattern information acquisition unit 132 to the learning information and acquire sales information, for each of the two or more arrangement pattern information. The two or more arrangement pattern information refers to the arrangement pattern information acquired by the arrangement pattern information acquisition unit 132.

[0063] It is preferable for the sales information acquisition unit 134 to acquire sales information by applying the attribute values ​​changed by the attribute value modification unit 133 and the attribute values ​​among the one or more attribute values ​​received by the reception unit 12 that have not been changed by the attribute value modification unit 133 to the learning information.

[0064] It is preferable for the sales information acquisition unit 134 to acquire sales information by applying, for each combination of attribute value changes made by the attribute value change unit 133, the attribute values ​​changed by the attribute value change unit 133 and the one or more attribute values ​​received by the reception unit 12 that have not been changed by the attribute value change unit 133, to the learning information.

[0065] The attribute value set acquisition means 1341 acquires one or more attribute value sets. The attribute value set may be a set of attribute values ​​acquired only from one or more attribute values ​​possessed by each of the one or more target product information received by the reception unit 12. Alternatively, the attribute value set may be a set of attribute values ​​acquired from one or more attribute values ​​possessed by each of the one or more target product information received by the reception unit 12, in addition to one or more placement attribute values ​​acquired by the placement pattern information acquisition unit 132. Furthermore, the attribute value set may be a set of attribute values ​​acquired from one or more attribute values ​​possessed by each of the one or more target product information received by the reception unit 12, specifically from attribute values ​​that have not been changed by the attribute value modification unit 133 and attribute values ​​that have been changed by the attribute value modification unit 133. Furthermore, the attribute value set may also be a set of attribute values ​​obtained from the one or more attribute values ​​that each of the one or more target product information received by the reception unit 12 has, including attribute values ​​that have not been changed by the attribute value modification unit 133, attribute values ​​that have been changed by the attribute value modification unit 133, and one or more placement attribute values ​​obtained by the placement pattern information acquisition unit 132. The structure of the attribute value set acquired by the attribute value set acquisition means 1341 and the one or more attribute values ​​that each of the one or more target product information received by the reception unit 12 has have may be the same or different.

[0066] The attribute value set acquisition means 1341 preferably acquires possible values ​​for each of one or more attributes so as to satisfy the attribute value change conditions corresponding to each attribute, and then acquires possible combinations of attribute values ​​from the set of possible values ​​for that attribute value. The combination of attribute values ​​may also be called an attribute value set.

[0067] The sales information acquisition means 1342 applies the attribute value set acquired by the attribute value set acquisition means 1341 to the learning information and acquires sales information. For example, the sales information acquisition means 1342 applies the attribute value set acquired by the attribute value set acquisition means 1341 to the learning information and acquires sales information using a machine learning algorithm. Alternatively, the sales information acquisition means 1342 searches the learning information for one or more attribute values ​​that have a similarity to the attribute value set acquired by the attribute value set acquisition means 1341 that satisfies predetermined conditions, and acquires one or more sales information corresponding to that one or more attribute values ​​from the learning information.

[0068] The judgment unit 135 determines whether the sales situation is good enough to satisfy predetermined conditions for the sales information for each of the two or more arrangement pattern information acquired by the sales information acquisition unit 134. These predetermined conditions include, for example, that the sales information, specifically the total sales amount, is equal to or greater than a threshold. Another predetermined condition is that the sales information, specifically the total number of units sold, is equal to or greater than a threshold. Furthermore, another predetermined condition is that the sales situation has improved compared to the received sales information. This means, for example, that the acquired total sales amount is greater than the received total sales amount, or that the acquired total number of units sold is greater than the received total number of units sold. The received total sales amount and received total number of units sold are typically sales performance information for the product group content being improved.

[0069] The judgment unit 135 determines whether the sales information acquired by the sales information acquisition unit 134 is good enough to meet predetermined conditions.

[0070] For example, the component 136 arranges one or more target product information according to the arrangement pattern information when the judgment unit 135 determines that the sales situation is good, thereby composing the product group content.

[0071] For example, the component 136 uses attribute values ​​determined by the judgment unit 135 to indicate that sales are favorable, and arranges one or more target product information to constitute product group content.

[0072] If two or more sales information items are obtained, the component 136 may select the sales information that satisfies predetermined conditions. Then, the component 136 uses the attribute values ​​corresponding to the selected sales information to arrange one or more target product information items and construct the product group content.

[0073] The output unit 14 outputs, for example, sales information acquired by the sales information acquisition unit 134. The output unit 14 also outputs, for example, product group content configured by the configuration unit 136. Furthermore, the output unit 14 outputs, for example, the product group content configured by the configuration unit 136 and the sales information acquired by the sales information acquisition unit 134. Note that the product group content output by the output unit 14 may be information for a single product.

[0074] Here, output usually refers to transmission to an external device (usually terminal device 2), but it can also be considered a concept that includes display on a screen, projection using a projector, printing with a printer, sound output, storage on a recording medium, and transfer of processing results to other processing devices or other programs.

[0075] If the output is the transfer of sales information, for example, it is the transfer of sales information to the determination unit 135.

[0076] The terminal storage unit 21, which constitutes the terminal device 2, stores various types of information. These various types of information include, for example, a user identifier that identifies a user. Other types of information include, for example, information received by the terminal receiving unit 25. The user identifier may also be information that identifies the terminal device 2.

[0077] The terminal reception unit 22 receives various instructions and information. These instructions and information include, for example, learning instructions, suggestion instructions, sales forecast instructions, learning target information, and information on one or more target products. Here, "reception" is a concept that includes receiving information entered from input devices such as keyboards, mice, and touch panels, receiving information transmitted via wired or wireless communication lines, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory.

[0078] The input methods for various instructions and information can be anything, such as a touch panel, keyboard, mouse, or menu screen. The terminal reception unit 22 can be implemented using device drivers for input methods such as touch panels and keyboards, or control software for menu screens.

[0079] The terminal processing unit 23 performs various processes, such as structuring the information received by the terminal receiving unit 25 into data to be displayed. Other various processes include structuring instructions received by the terminal reception unit 22 into instructions to be transmitted.

[0080] The terminal transmission unit 24 transmits various instructions and information to the information processing device 1. These instructions and information include, for example, instructions configured by the terminal processing unit 23 and instructions and information received by the terminal reception unit 22.

[0081] The terminal receiving unit 25 receives various types of information from the information processing device 1. These types of information include, for example, sales information and product group content.

[0082] The terminal output unit 26 acquires various types of information. These types of information include, for example, information received by the terminal reception unit 22, information received by the terminal receiving unit 25, and information configured by the terminal processing unit 23. These types of information include, for example, sales information and product group content.

[0083] Here, "output" is a concept that includes display on a screen, projection using a projector, printing with a printer, sound output, transmission to an external device, storage on a recording medium, and transfer of processing results to other processing devices or other programs.

[0084] The storage unit 11, the learning information storage unit 111, the attribute value condition storage unit 112, and the terminal storage unit 21 are preferably made of non-volatile recording media, but can also be made of volatile recording media.

[0085] The process by which information is stored in the storage unit 11, etc. is not relevant. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information input via an input device may be stored in the storage unit 11, etc.

[0086] The processing unit 13, learning unit 131, arrangement pattern information acquisition unit 132, attribute value modification unit 133, sales information acquisition unit 134, determination unit 135, configuration unit 136, and terminal processing unit 23 can typically be implemented using an MPU, memory, etc. The processing procedures of the processing unit 13, etc., are typically implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry).

[0087] The output unit 14 and the terminal transmission unit 24 are usually implemented by wireless or wired communication means, but may also be implemented by broadcasting means.

[0088] The output unit 14 may be implemented using driver software for an output device, or by using driver software for an output device and an output device, etc.

[0089] The terminal output unit 26 may or may not be considered to include output devices such as a display or speakers. The terminal output unit 26 can be implemented using driver software for an output device, or a driver software for an output device and an output device.

[0090] Next, we will explain the operation of information system A. First, we will explain an example of the operation of information processing device 1 using the flowchart in Figure 3.

[0091] (Step S301) The reception unit 12 determines whether or not it has received a learning instruction. If it has received a learning instruction, it proceeds to step S302; if it has not received a learning instruction, it proceeds to step S304.

[0092] (Step S302) The learning unit 131 acquires the learning target information contained in the learning instruction received in step S301. The learning unit 131 then acquires one or more attribute values ​​for each of the two or more product information contained in the learning target information. The learning unit 131 also acquires sales information contained in the learning target information. The learning unit 131 then performs machine learning processing on the acquired two or more attribute values ​​and the sales information to acquire learning information. Note that sales information is obtained by applying the two or more attribute values ​​to this learning information.

[0093] The learning unit 131 may also acquire the product group content and sales information contained in the learning instruction received in step S301. In this case, the learning unit 131 acquires one or more attribute values ​​for each of the one or more product information contained in the product group content. The learning unit 131 then performs machine learning processing on the one or more attribute values ​​for each of the one or more product information and the sales information in pairs to acquire learning information. Sales information is obtained by applying one or more attribute values ​​to this learning information.

[0094] (Step S303) The learning unit 131 stores the learning information acquired in step S302 in the learning information storage unit 111. Return to step S301.

[0095] (Step S304) The reception unit 12 determines whether or not it has received a suggestion instruction from the terminal device 2. If a suggestion instruction is received, it proceeds to step S305; if no suggestion instruction is received, it proceeds to step S307.

[0096] (Step S305) The processing unit 13 acquires product group content using one or more target product information contained in the proposed instruction. This product group content acquisition process will be explained using the flowchart in Figure 4.

[0097] (Step S306) The output unit 14 transmits the product group content acquired in step S305 to the terminal device 2. Return to step S301.

[0098] (Step S307) The reception unit 12 determines whether or not it has received a sales forecast instruction from the terminal device 2. If a sales forecast instruction has been received, the process proceeds to step S308; otherwise, the process returns to step S301.

[0099] (Step S308) The sales information acquisition unit 134 acquires one or more target product information contained in the sales forecast instruction received in step S307. If the sales forecast instruction has a product group content, the sales information acquisition unit 134 acquires target product information corresponding to one or more individual product information from the product group content.

[0100] (Step S309) The sales information acquisition unit 134 applies the one or more target product information acquired in step S308 to the learning information to acquire sales information. Applying the one or more target product information to the learning information means, for example, applying the one or more attribute values ​​that each of the one or more target product pieces has to the learning information.

[0101] (Step S310) The output unit 14 transmits the sales information acquired in step S309 to the terminal device 2. Return to step S301.

[0102] In the flowchart in Figure 3, processing is terminated by power-off or processing termination interrupts.

[0103] Next, an example of the product group content acquisition process in step S305 will be explained using the flowchart in Figure 4.

[0104] (Step S401) The arrangement pattern information acquisition unit 132, etc., acquires pattern information. This pattern information acquisition process will be explained using the flowchart in Figure 5. Pattern information is usually a combination of two or more attribute values. It can also be said that pattern information is a set of two or more attribute values. The pattern information acquisition process acquires a set of two or more attribute values. Each set of two or more attribute values ​​has at least some different attribute values. It can also be considered that pattern information may consist of just one attribute value.

[0105] (Step S402) The sales information acquisition unit 134 assigns 1 to counter i.

[0106] (Step S403) The sales information acquisition unit 134 attempts to acquire the i-th combination of attribute values ​​from the set of attribute values ​​acquired in step S401. Note that the i-th combination of attribute values ​​is the set of the i-th attribute value. It can also be considered that the combination of attribute values ​​may consist of just one attribute value.

[0107] (Step S404) The sales information acquisition unit 134 proceeds to step S405 if it can acquire the combination of the i-th attribute value, and to step S407 if it cannot acquire it.

[0108] (Step S405) The sales information acquisition unit 134 applies the combination of the i-th attribute value to the learning information in the learning information storage unit 111 and acquires sales information. The sales information acquisition unit 134 then associates the acquired sales information with the combination of the i-th attribute value and temporarily stores it in a buffer (not shown).

[0109] (Step S406) The sales information acquisition unit 134 increments counter i by 1. Return to step S403.

[0110] (Step S407) The determination unit 135 selects sales information that satisfies predetermined conditions from among the one or more sales information obtained in step S405. The determination unit 135 then obtains combinations of attribute values ​​corresponding to each of the one or more sales information selected from a buffer (not shown). Sales information that satisfies predetermined conditions is usually sales information where the sales situation is good enough to satisfy the predetermined conditions, or sales information where the sales situation will improve as much as the predetermined conditions are satisfied.

[0111] (Step S408) Component 136 assigns 1 to counter j.

[0112] (Step S409) Component 136 determines whether or not the j-th attribute value combination exists among the attribute value combinations obtained in step S407. If the j-th attribute value combination exists, the process proceeds to step S410; otherwise, the process returns to the higher level.

[0113] (Step S410) The component 136 arranges two or more target product information according to the combination of the j-th attribute value to constitute the product group content. The two or more target product information are usually information received by the reception unit 12, but may also be information stored in the storage unit 11.

[0114] (Step S411) The output unit 14 transmits the product group content configured in step S410 to the terminal device 2.

[0115] (Step S412) Component 136 increments counter j by 1. Return to step S409.

[0116] Next, an example of the pattern information acquisition process in step S401 will be explained using the flowchart in Figure 5.

[0117] (Step S501) The attribute value modification unit 133 assigns 1 to counter i.

[0118] (Step S502) The attribute value modification unit 133 determines whether or not an i-th type attribute value exists. If an i-th type attribute value exists, the process proceeds to step S503; otherwise, the process proceeds to step S505. The attribute value modification unit 133 determines whether or not an i-th type attribute value exists by, for example, whether or not an i-th type attribute value condition or an i-th attribute identifier exists in the attribute value condition storage unit 112.

[0119] (Step S503) The attribute value modification unit 133 obtains all possible values ​​for the i-th type of attribute value. If the attribute value modification condition corresponding to the i-th type of attribute value is a set of candidate information for the attribute value, the attribute value modification unit 133 obtains all candidate information for the attribute value from the attribute value condition storage unit 112. Also, if the attribute value modification condition corresponding to the i-th type of attribute value is information for a range of values ​​for which the attribute value can take, the attribute value modification unit 133 obtains information for that range from the attribute value condition storage unit 112, for example, and obtains a set of information for two or more candidates that satisfy that range. The attribute value modification unit 133 may obtain the set of information for two or more candidates that satisfy that range in any way. For example, the attribute value modification unit 133 may obtain the set of information for two or more candidates by shifting by a fixed value from the minimum value to the maximum value within that range, or it may obtain N values ​​(where N is, for example, a fixed number) randomly from within that range.

[0120] (Step S504) The attribute value modification unit 133 increments counter i by 1. The process returns to step S502.

[0121] (Step S505) The attribute value modification unit 133 assigns 1 to counter j.

[0122] (Step S506) The attribute value modification unit 133 determines whether the j-th attribute value pattern exists. If the j-th attribute value pattern exists, the process proceeds to step S507; otherwise, the process returns to the higher level.

[0123] The attribute value modification unit 133 obtains all attribute value sets (attribute value patterns) from the set of candidate information for each of the two or more types of attribute values ​​obtained in step S503. The attribute value modification unit 133 then determines whether or not the j-th attribute value pattern exists from the two or more attribute value patterns. For example, suppose there are two target product information (product information A, product information B), and each target product information has three attribute values ​​(attribute 1, attribute 2, attribute 3), where attribute 1 can take either attribute value 11 or attribute value 12, attribute 2 can take either attribute value 21, attribute value 22, or attribute 23, and attribute 3 can take either attribute value 31 or attribute value 32. In this case, the attribute value modification unit 133 obtains 24 possible attribute value patterns. Furthermore, suppose there is one target product information (product information A), and the target product information has attribute values ​​for two attributes (attribute 1, attribute 2), where attribute 1 can take either attribute value 11 or attribute value 12, and attribute 2 can take any of attribute value 21, attribute value 22, or attribute 23. In this case, the attribute value modification unit 133 obtains six possible attribute value patterns.

[0124] (Step S507) The arrangement pattern information acquisition unit 132 assigns 1 to counter k.

[0125] (Step S508) The arrangement pattern information acquisition unit 132 determines whether a combination of the kth arrangement order exists based on the jth attribute value pattern. If a combination of the kth arrangement order exists, the unit proceeds to step S509; otherwise, the unit proceeds to step S512.

[0126] (Step S509) The placement pattern information acquisition unit 132 acquires the k-th placement order combination based on the j-th attribute value pattern. The placement pattern information acquisition unit 132 then uses the k-th placement order combination to acquire the placement attribute values ​​for one or more product information. The placement attribute values ​​for one or more target product information are placement pattern information. The placement order combination is information indicating the placement order of one or more target product information (for example, information that shows which target product information will be placed first from the top left in the product group content, the second target product information, ..., the Nth target product information), or the coordinate value of the top left. The attribute value modification unit 133 then arranges two or more target product information in order according to the k-th placement order information based on the j-th attribute value pattern, and acquires the placement attribute values ​​for two or more target product information. The attribute value modification unit 133 also arranges one target product information according to the k-th placement pattern information based on the j-th attribute value pattern.

[0127] (Step S510) The attribute value modification unit 133 obtains a combination of attribute values ​​from the j-th attribute value pattern and the arrangement pattern information obtained in step S509, and temporarily stores it in a buffer (not shown).

[0128] (Step S511) The arrangement pattern information acquisition unit 132 increments the counter k by 1. Return to step S508.

[0129] (Step S512) The attribute value modification unit 133 increments counter j by 1. Return to step S506.

[0130] Next, an example of the operation of terminal device 2 will be explained using the flowchart in Figure 6.

[0131] (Step S601) The terminal reception unit 22 determines whether or not it has received a learning instruction. If it has received a learning instruction, it proceeds to step S602; otherwise, it proceeds to step S604.

[0132] (Step S602) The terminal processing unit 23 configures the learning instruction to be transmitted. The learning instruction to be transmitted usually includes two or more learning target information items.

[0133] (Step S603) The terminal transmission unit 24 transmits the learning instruction configured in step S602 to the information processing device 1. Return to step S601.

[0134] (Step S604) The terminal reception unit 22 determines whether or not it has received the proposal instruction. If it has received the proposal instruction, it proceeds to step S605; otherwise, it proceeds to step S610.

[0135] (Step S605) The terminal processing unit 23 configures the suggestion instruction to be transmitted. The suggestion instruction to be transmitted includes two or more target product information or product group content.

[0136] (Step S606) The terminal transmission unit 24 transmits the proposed instruction configured in step S605 to the information processing device 1.

[0137] (Step S607) The terminal receiving unit 25 determines whether or not it has received one or more product group content from the information processing device 1. If product group content has been received, the process proceeds to step S608; otherwise, the process proceeds to step S607.

[0138] (Step S608) The terminal processing unit 23 configures the product group content to be output.

[0139] (Step S609) The terminal output unit 26 outputs the product group content configured in step S608. Return to step S601.

[0140] (Step S610) The terminal reception unit 22 determines whether or not it has received a sales forecast instruction. If it has received a sales forecast instruction, it proceeds to step S611; otherwise, it returns to step S601.

[0141] (Step S611) The terminal processing unit 23 configures the sales forecast instruction to be transmitted. The sales forecast instruction to be transmitted includes information on two or more target products or product group contents.

[0142] (Step S612) The terminal transmission unit 24 transmits the sales forecast instruction configured in step S611 to the information processing device 1.

[0143] (Step S613) The terminal receiving unit 25 determines whether or not it has received sales information from the information processing device 1. If sales information has been received, the process proceeds to step S614; otherwise, the process proceeds to step S613.

[0144] (Step S614) The terminal processing unit 23 configures the sales information to be output.

[0145] (Step S615) The terminal output unit 26 outputs the sales information configured in step S614. Return to step S601.

[0146] In the flowchart shown in Figure 6, processing is terminated by power-off or processing termination interrupts.

[0147] The specific operation of information system A in this embodiment will be described below. A conceptual diagram of information system A is shown in Figure 1.

[0148] Currently, the attribute value condition storage unit 112 stores the attribute value condition management table shown in Figure 7. The attribute value condition management table is a table that manages the attribute value change conditions for each attribute. The attribute value change conditions are information that indicates the possible attribute values. The attribute value condition management table has as many records as there are changeable attributes, each having an "ID," "attribute identifier," "attribute type," and "attribute value change condition." "ID" is information that identifies the record. "Attribute identifier" is the attribute name in this case. "Attribute type" indicates the type of attribute.

[0149] Furthermore, the storage unit 11 stores the layout information management table shown in Figure 8. The layout information management table has multiple records, each containing an "ID," a "layout identifier," and "layout information." The "ID" is information that identifies the record. The "layout identifier" is information that identifies the layout information, and in this case, it is the layout information name. The "layout information" here represents a diagram of the layout for arranging the elements that make up the product information, and it contains relative coordinate information for arranging the elements that make up the product information. Note that the "ID" can also be considered as the layout identifier.

[0150] Furthermore, the storage unit 11 stores the product information management table shown in Figure 9. The storage unit 11 also stores the product information management table shown in Figure 10. The product information management table manages information for two or more products. The product information management table has "ID", "product image", "product attribute value", "product name", and "product description". "ID" is the ID of the product information. "Product attribute value" here includes "price", "color", etc. "Product name" is the name of the product. "Product description" is a string of characters that describes the product.

[0151] In this context, the following four specific examples will be explained. Specific example 1 is the learning process performed by the learning unit 131. Specific example 2 is the sales forecasting process using the learned information. Specific example 3 is the process of changing the product group content to improve sales performance. Specific example 4 is the process of creating product group content to obtain favorable sales results. (Specific example 1)

[0152] In Specific Example 1, the learning process performed by the learning unit 131 will be explained.

[0153] First, assume that the user of terminal device 2 inputs learning instructions into terminal device 2, including the electronic data of the automobile catalog webpage shown in Figure 11, and the automobile sales performance resulting from the use of said webpage (see Figure 12). Note that the automobile sales performance is an example of sales information and includes the number of units sold for each automobile, the total sales amount for each automobile, the total number of automobiles sold in total, and the total sales amount for all automobiles. Also, "ID" in Figure 12 is a product identifier.

[0154] Next, the terminal receiving unit 22 receives a learning instruction. The terminal processing unit 23 configures a learning instruction to be transmitted in response to the received learning instruction. Then, the terminal transmitting unit 24 transmits the learning instruction to the information processing device 1.

[0155] Next, the receiving unit 12 of the information processing device 1 receives a learning instruction from the terminal device 2. This learning instruction includes the electronic data of the web page shown in Figure 11 (or the URL of the web page) and the sales information shown in Figure 12. The electronic data of the web page also includes information on two or more target products. Here, the target product information is the product information for each automobile.

[0156] Next, the reception unit 12 obtains attribute values ​​of each target product information from the electronic data of the web page in Figure 11. Specifically, for example, the reception unit 12 obtains the product attribute values ​​of the automobile with "ID=C1," such as "Price=2.5 million yen" and "Color=Black." The reception unit 12 also analyzes the product image with "ID=C1" contained in the electronic data of the web page in Figure 11 and obtains image attribute values ​​such as "Image size=(W1,H1)" and "Image shape=Rectangle." The reception unit 12 also obtains information such as "Font=Mincho" and "Character size=11pt" from the string with "ID=C1" contained in the electronic data of the web page in Figure 11. Furthermore, the reception unit 12 analyzes the web page in Figure 11 and obtains information regarding the arrangement of each object on the web page, and obtains information such as "Layout information=2" and "Arrangement order=1" from the product information of "ID=C1." From these attribute values, the reception unit 12 obtains the attribute value management table shown in Figure 13. Furthermore, obtaining such attribute values ​​can be described as accepting attribute values.

[0157] Next, the learning unit 131 obtains one or more attribute values ​​(attribute value management table in Figure 13) acquired by the reception unit 12. The learning unit 131 also obtains the total number of vehicles sold and the total sales amount for all vehicles from the vehicle sales records in Figure 12 received by the reception unit 12. Here, the learning unit 131 obtains two types of sales information: the total number of vehicles sold and the total sales amount. The learning unit 131 then associates one or more attribute values ​​(attribute value management table in Figure 13) with the two types of sales information and stores them in the storage unit 11 or a buffer (not shown). The pair of one or more attribute values ​​(attribute value management table in Figure 13) and sales information is the learning target information. The learning target information is a vector formed by concatenating vectors corresponding to two or more individual product information items and the sales information. In other words, the information to be learned is, for example, ((2.5 million yen, 1, 0, 0, ..., 1, 0, 1, 0, ..., 0, 1, ..., 2, 1, ...)(3 million yen, 0, 0, 1, ..., 1, 0, 1, 0, ..., 0, 1, ..., 2, 2, ...)(2.1 million yen, 0, 1, 0, ..., 1, 0, 1, 0, ..., 0, 1, ..., 2, 3, ...) ... 5,483 units, 1,425, 580 million yen). Note that the parentheses between the product information in the information to be learned are not necessary. It goes without saying that the learning unit 131 may also learn the number of units sold and the sales amount for each car in the sales record of cars in Figure 12.

[0158] Assume that the above processing is applied to the electronic data and sales information of numerous other web pages, and that a large amount of learning data is accumulated.

[0159] Next, the learning unit 131 learns from the accumulated large amount of learning target information using a machine learning algorithm, acquires the learning information, and stores it in the learning information storage unit 111.

[0160] Based on the above, we obtained learning information that shows how sales information can be obtained when two or more target product information items are applied. (Specific example 2)

[0161] In Specific Example 2, we will explain the process of performing sales forecasting using the learning information accumulated in Specific Example 1.

[0162] First, let's assume that the user of terminal device 2 wants to make a sales forecast using the automobile catalog shown in Figure 14, and has entered a sales forecast instruction containing the URL of the automobile catalog's webpage shown in Figure 14 into terminal device 2.

[0163] Next, the terminal receiving unit 22 receives a sales forecast instruction. The terminal processing unit 23 configures a sales forecast instruction to be transmitted in response to the received instruction. Then, the terminal transmitting unit 24 transmits the sales forecast instruction to the information processing device 1. The sales forecast instruction includes the URL of the automobile catalog webpage shown in Figure 14.

[0164] Next, the receiving unit 12 of the information processing device 1 receives a sales forecast instruction from the terminal device 2.

[0165] Next, the receiving unit 12 obtains the URL contained in the received sales forecast instruction. Next, the receiving unit 12 obtains the webpage of the automobile catalog corresponding to the URL, and then the receiving unit 12 obtains information on two or more target products from the webpage.

[0166] Next, the sales information acquisition unit 134 acquires a set of attribute values ​​from the information of each of the two or more target products. The acquired set of attribute values ​​has a structure, for example, as shown in Figure 13. The acquired set of attribute values ​​is, for example, a vector ((2.3 million yen, 0, 1, 0, ..., 1, 0, ..., 1, 0, ..., 1, 1, ...)(2.8 million yen, 0, 0, 1, ..., 1, 0, 1, 0, ..., 1, 0, ..., 1, 2, ...)(2.1 million yen, 0, 1, 0, ..., 1, 0, 1, 0, ..., 1, 0, ..., 1, 3, ...)).

[0167] Next, the sales information acquisition unit 134 applies the above vector to the learning information in the storage unit 11 and acquires sales information using a machine learning algorithm. This vector is a vector formed by concatenating vectors corresponding to two or more target product information. Here, let's assume that the sales information acquisition unit 134 obtained a total number of units sold of "8210" and a total sales amount of "2,102,492".

[0168] Next, the output unit 14 transmits the acquired sales information (total number of units sold: "8210", total sales amount: "2,102,492") to the terminal device 2.

[0169] Next, the terminal receiving unit 25 receives the sales information from the information processing device 1. Then, the terminal processing unit 23 configures the sales information to be output. The terminal output unit 26 outputs the configured sales information. An example of such output is shown in Figure 15. (Specific example 3)

[0170] In Specific Example 3, we will explain the process of modifying product group content to improve sales performance using the learning information accumulated in Specific Example 1.

[0171] Currently, the sales figures for automobiles based on the electronic data of the webpage shown in Figure 14 are not good, so the user has entered a suggestion instruction into terminal device 2, which includes the URL of the webpage shown in Figure 14.

[0172] Next, the terminal receiving unit 22 receives the proposal instruction. The terminal processing unit 23 configures the proposal instruction to be transmitted in response to the received proposal instruction. Then, the terminal transmitting unit 24 transmits the proposal instruction to the information processing device 1. The proposal instruction includes the URL of the automobile catalog webpage shown in Figure 14.

[0173] Next, the receiving unit 12 of the information processing device 1 receives the proposal instruction from the terminal device 2.

[0174] Next, the reception unit 12 obtains the URL of the proposed instruction. Next, the reception unit 12 obtains the webpage of the automobile catalog corresponding to the URL. Next, the reception unit 12 obtains information on two or more target products from the webpage.

[0175] Next, the attribute value modification unit 133 obtains one or more attribute values ​​from each of the two or more target product information. This method of obtaining attribute values ​​is possible through the process described above.

[0176] Next, the attribute value modification unit 133 obtains possible values ​​for each attribute value so as to satisfy the attribute value modification information in the attribute value condition management table in Figure 7. Then, the attribute value modification unit 133 obtains two or more attribute value patterns.

[0177] Next, the arrangement pattern information acquisition unit 132 acquires two or more arrangement pattern information for each attribute value pattern acquired by the attribute value modification unit 133.

[0178] As a result, multiple attribute value sets (combinations of attribute values) were obtained. The process of obtaining these attribute value sets was explained using the flowchart in Figure 5, so a detailed explanation is omitted here.

[0179] Next, the sales information acquisition unit 134 applies each of the multiple attribute value sets to the learning information in the learning information storage unit 111 and acquires sales information by associating it with the attribute value sets.

[0180] Next, the determination unit 135 selects sales information that satisfies predetermined conditions from among the sales information associated with the attribute value set. For example, suppose the determination unit 135 selects the sales information with the largest total sales amount. The determination unit 135 then obtains the attribute value set corresponding to the selected sales information with the largest total sales amount.

[0181] Next, the component 136 determines the attribute values ​​of the product information in Figure 9 according to the acquired set of attribute values, and also determines the arrangement of each element constituting the product information, thereby constructing the product group content. Note that the technique of constructing product group content using the elements constituting the product information, given that the attribute values ​​of the product information and the arrangement of each element constituting the product information have been determined, is publicly known, so a detailed explanation is omitted.

[0182] Next, the output unit 14 transmits the configured product group content and the total sales amount (an example of sales information) to the terminal device 2.

[0183] Next, the terminal receiving unit 25 of the terminal device 2 receives the product group content and sales information from the information processing device 1. Then, the terminal processing unit 23 configures the product group content and sales information to be output. The terminal output unit 26 outputs the configured product group content and sales information. An example of such output is shown in Figure 16. (Specific example 4)

[0184] In Specific Example 4, we will explain the process of generating product group content in a way that yields good sales results, using the learning information accumulated in Specific Example 1.

[0185] Now, let's assume the user has entered a suggestion instruction specifying the product information database shown in Figure 10, in order to create a new electronic catalog for car sales using the product information database shown in Figure 10.

[0186] Next, the terminal receiving unit 22 receives the proposal instruction. The terminal processing unit 23 configures the proposal instruction to be transmitted in response to the received proposal instruction. Then, the terminal transmitting unit 24 transmits the proposal instruction to the information processing device 1. The proposal instruction contains information from the product information database shown in Figure 0.

[0187] Next, the receiving unit 12 of the information processing device 1 receives the proposal instruction from the terminal device 2. The receiving unit 12 then acquires information on two or more target products associated with the proposal instruction.

[0188] Next, the attribute value modification unit 133 obtains possible values ​​for each attribute value so as to satisfy the attribute value modification information in the attribute value condition management table in Figure 7. Then, the attribute value modification unit 133 obtains two or more attribute value patterns.

[0189] Next, the arrangement pattern information acquisition unit 132 acquires two or more arrangement pattern information for each attribute value pattern acquired by the attribute value modification unit 133.

[0190] Based on the above, multiple attribute value sets (combinations of attribute values) were obtained.

[0191] Next, the sales information acquisition unit 134 applies each of the multiple attribute value sets to the learning information in the learning information storage unit 111 and acquires sales information by associating it with the attribute value sets.

[0192] Next, the decision unit 135 determines the sales information that satisfies predetermined conditions from among the sales information associated with the attribute value set. For example, suppose the decision unit 135 selects the top three sales information by total sales volume. The decision unit 135 then obtains the attribute value set corresponding to each of the three selected sales information.

[0193] Next, component 136 constructs three product group contents according to the three acquired attribute value sets.

[0194] Next, the output unit 14 transmits three sets of configured product group content and total sales figures (an example of sales information) to the terminal device 2.

[0195] Next, the terminal receiving unit 25 of the terminal device 2 receives three sets of product group content and sales information from the information processing device 1. Then, the terminal processing unit 23 configures three sets of product group content and sales information to be output. The terminal output unit 26 outputs the three sets of product group content and sales information.

[0196] Next, the user checks three sets of product group content and sales information, and selects, for example, one set of product group content. This selected set of product group content is the one that is adopted.

[0197] As described above, according to this embodiment, it is possible to predict product sales information, which is the effect of product group content.

[0198] Furthermore, according to this embodiment, it is possible to propose product group content that is estimated to have good sales performance. Note that, as mentioned above, the product group content may consist of information on a single product.

[0199] Furthermore, according to this embodiment, it is possible to propose changes to the attribute values ​​of product information for products that are presumed to be selling well. Note that changing the attribute values ​​of product information may be done for just one product.

[0200] Furthermore, according to this embodiment, it is possible to propose changes to the attribute values ​​of product information that are estimated to improve sales performance. Note that the changes to the attribute values ​​of product information may be as simple as changing the attribute values ​​of a single product.

[0201] The learning process described above may be performed by a device independent of the information processing device. In this case, the learning device 3 comprises a storage unit 11, a reception unit 12, and a learning unit 131. An example of a block diagram of such a learning device 3 is shown in Figure 17. The learning device 3 comprises a learning information storage unit 111 that stores learning information learned from learning target information having two or more pieces of product attribute information each having one or more attribute values ​​of product information and one or more pieces of sales information relating to the sale of a product; a reception unit 12 that receives the learning target information; and a learning unit 131 that learns the learning target information using a machine learning algorithm, acquires the learning information, and stores the learning information in the learning information storage unit 111.

[0202] Furthermore, the processing in this embodiment may be implemented in software. This software may be distributed by software download or the like. Alternatively, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software that implements the information processing device 1 in this embodiment is a program as follows. In other words, this program is a program that causes a computer that can access a recording medium having a learning information storage unit that stores learning target information having learned learning target information having one or more attribute values ​​of product information having one or more attribute values ​​of product information relating to a product, and sales information relating to the sale of one or more products, to function as a receiving unit that receives one or more target product information having one or more attribute values, a sales information acquisition unit that applies one or more attribute values ​​of each of the one or more target product information to the learning information and acquires sales information, and an output unit that outputs the sales information.

[0203] Furthermore, the software that realizes the learning device 3 is a program as follows. In other words, this program is a program that produces learning information used by the information processing device 1, and is a program that causes the computer to function as a receiving unit that receives learning target information having one or more product attribute information having one or more attribute values ​​of product information about a product, and sales information relating to the sale of one or more products, and a learning unit that learns the learning target information using a machine learning algorithm, acquires learning information, and stores the learning information on a recording medium.

[0204] Figure 18 also shows the external appearance of a computer that executes the program described herein to realize the various embodiments of the information processing device 1 described above. The embodiments described above can be realized with computer hardware and computer programs executed thereon. Figure 18 is an overview of this computer system 300, and Figure 19 is a block diagram of the system 300.

[0205] In Figure 18, the computer system 300 includes a computer 301 with a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0206] In Figure 19, the computer 301 includes, in addition to the CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as boot-up programs, a RAM 3016 connected to the MPU 3013 for temporarily storing application program instructions and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card for providing connectivity to a LAN.

[0207] The program that causes the computer system 300 to execute the functions of the information processing device 1, etc., as described above, may be stored on the CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 during execution. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0208] The program does not necessarily have to include an operating system (OS) or third-party program that causes the computer 301 to execute the functions of the information processing device 1, etc., as described above. The program only needs to include the instruction portion that calls the appropriate function (module) in a controlled manner and obtains the desired result. How the computer system 300 operates is well known, so a detailed explanation is omitted.

[0209] In the above program, steps such as sending information and receiving information do not include hardware-based processing, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0210] Furthermore, the computer running the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

[0211] Furthermore, it goes without saying that in each of the above embodiments, two or more communication means present in a single device may be physically implemented in a single medium.

[0212] Furthermore, in each of the above embodiments, each process may be implemented by centralized processing by a single device, or by distributed processing by multiple devices. For example, it goes without saying that the information processing device 1 may operate standalone. In such a case, the reception unit 12 receives, for example, instructions from the user. The output unit 14 displays information on, for example, a display.

[0213] It goes without saying that the present invention is not limited to the embodiments described above, and various modifications are possible, all of which are also included within the scope of the present invention. [Industrial applicability]

[0214] As described above, the information processing device according to the present invention has the effect of being able to propose product group content in which information on multiple products is displayed, and is useful as an information processing device, etc. [Explanation of symbols]

[0215] 1. Information Processing Device 2 Terminal devices 3. Learning device 11 Storage Unit 12 Reception Department 13 Processing Unit 14 Output section 21 Terminal storage section 22 Terminal Reception Section 23 Terminal Processing Unit 24 Terminal transmission unit 25 Receiving part of the terminal 26 Terminal output section 111 Learning Information Storage Unit 112 Attribute Value Condition Storage Unit 131 Learning Department 132 Arrangement Pattern Information Acquisition Unit 133 Attribute Value Change Section 134 Sales Information Acquisition Department 135 Judgment Department 136 Components 1341 Means for obtaining attribute value sets 1342 Means of obtaining sales information

Claims

1. A learning information storage unit stores learning information which has been learned from two or more learning target information, each having two or more product attribute information having one or more attribute values ​​including placement attribute values ​​which are attribute values ​​for the placement of two or more product information in the entire electronic catalog or web page, and sales information relating to the sale of the two or more product information as a whole that is published in the entire electronic catalog or web page. A receiving unit that receives two or more target product information entries, each having one or more attribute values ​​including the placement attribute value of the target product information in the entire input electronic catalog or the entire input web page, A sales information acquisition unit applies one or more attribute values ​​from each of the two or more target product information received by the reception unit to the learning information and acquires sales information for the entire input electronic catalog or sales information for the entire input web page. An information processing apparatus comprising: an output unit that outputs the sales information acquired by the sales information acquisition unit.

2. The aforementioned learning information is information obtained as a result of learning the two or more learning target information using a machine learning algorithm. The aforementioned sales information acquisition unit, The information processing device according to claim 1, which uses a machine learning algorithm to apply one or more attribute values ​​possessed by each of the two or more target product information to the learning information and obtains the sales information.

3. An information processing method implemented by a learning information storage unit, a reception unit, a sales information acquisition unit, and an output unit, which store learning information that has been learned, learning information having learned learning target information having two or more product attribute pieces having one or more attribute values ​​including placement attribute values ​​which are attribute values ​​of the placement of two or more product pieces of information in the entire electronic catalog or the entire web page, and sales information relating to the sale of the entire two or more product pieces of information published in the entire electronic catalog or the entire web page, The receiving unit receives two or more target product information items, each of which has one or more attribute values ​​including the placement attribute value of the target product information in the entire input electronic catalog or the entire input web page, and the receiving step includes: The sales information acquisition step involves the sales information acquisition unit applying one or more attribute values ​​from each of the two or more target product information received by the reception unit to the learning information, and acquiring sales information for the entire input electronic catalog or the entire input web page. An information processing method comprising: an output step in which the output unit outputs the sales information acquired by the sales information acquisition unit.

4. A computer that can access a recording medium having a learning information storage unit that stores learning information obtained by learning two or more learning target information, each having two or more product attribute information having one or more attribute values ​​including placement attribute values ​​which are attribute values ​​for the placement of two or more product information in the entire electronic catalog or web page, and sales information relating to the sale of the two or more product information as a whole published in the entire electronic catalog or web page, A receiving unit that receives two or more target product information entries, each having one or more attribute values ​​including the placement attribute value of the target product information in the entire input electronic catalog or the entire input web page, A sales information acquisition unit applies one or more attribute values ​​from each of the two or more target product information received by the reception unit to the learning information and acquires sales information for the entire input electronic catalog or sales information for the entire input web page. A program to function as an output unit that outputs the sales information acquired by the sales information acquisition unit.

Images