JP7535716B2 - Information processing device, learning device, information processing method, learning information production method, and program - Google Patents

Description

The present invention relates to an information processing device that processes information about product group content such as electronic catalogs and web pages.

In the prior art, there was an electronic catalog editing device that could create a presentation sheet that could be freely laid out based on an electronic catalog linked to a product sales system, and that maintained the link with the product sales system (see, for example, Patent Document 1).

JP 2013-242634 A

However, with conventional technology, it has been difficult to propose product group content that is selling well or is expected to sell well. Product group content is, for example, an electronic catalog or web page that lists information about multiple products.

The information processing device of the first invention is an information processing device including a learning information storage unit that stores learning information obtained by learning learning target information having one or more product attribute information having one or more attribute values of product information related to a product and sales information related to the sale of one or more products, a reception 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 to acquire sales information, and an output unit that outputs the sales information.

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

In addition, the information processing device of the second invention is an information processing device in which the one or more attribute values possessed by the target product information include one or more types of attribute values selected from the following: a product attribute value, which is an attribute value of the product itself; an image attribute value, which is an attribute value of the product image possessed by the product information; a string attribute value, which is an attribute value of a product string, which is a string related to the product possessed by the product information; an arrangement attribute value, which is an attribute value of the arrangement of the product information; and an attribute value of product information arranged in the vicinity of the product information.

This configuration makes it possible to predict product sales information, which is the effect of product group content.

In addition, the information processing device of the third invention is different from the information processing device of the second invention in that the reception unit receives one or more target product information having one or more attribute values of the product itself attribute value and the image attribute value, and further includes an arrangement pattern information acquisition unit that acquires two or more arrangement pattern information that is arrangement pattern information having one or more arrangement attribute values of each of the one or more target product information, and the sales information acquisition unit applies the one or more attribute values received by the reception unit and the arrangement pattern information acquired by the arrangement pattern information acquisition unit to learning information to acquire sales information for each of the two or more arrangement pattern information, and further includes a determination unit that determines whether the sales situation is good enough to satisfy a predetermined condition for the sales information for each of the two or more arrangement pattern information acquired by the sales information acquisition unit, and a configuration unit that configures product group content by arranging the two or more target product information according to the arrangement pattern information when the determination unit determines that the sales situation is good, and the output unit is an information processing device that outputs the product group content configured by the configuration unit, or the product group content configured by the configuration unit and the sales information.

This configuration makes it possible to suggest placement of product information that is estimated to have good sales.

The information processing device of the fourth invention is different from the information processing device of the second invention in that the reception unit receives one or more target product information pieces having one or more attribute values, and further includes an attribute value modification unit that modifies some of the one or more attribute values received by the reception unit, the sales information acquisition unit applies the attribute values modified by the attribute value modification unit and the attribute values not modified by the attribute value modification unit among the one or more attribute values received by the reception unit to the learning information to acquire sales information, and further includes a determination unit that determines whether the sales situation is good enough that the sales information acquired by the sales information acquisition unit satisfies a predetermined condition, and a configuration unit that uses the attribute values when the determination unit determines that the sales situation is good to arrange one or more target product information pieces and configure product group content, and the output unit is an information processing device that outputs the product group content configured by the configuration unit, or the product group content configured by the configuration unit and the sales information.

This configuration makes it possible to suggest changes to the attribute values of product information that is estimated to be selling well.

The information processing device of the fifth invention is an information processing device in which, compared to the fourth invention, the attribute value change unit changes any one of the product attribute value, the image attribute value, or the character string attribute value among one or more attribute values received by the reception unit.

This configuration makes it possible to suggest changes to the attribute values of product information that is estimated to be selling well.

The information processing device of the sixth invention is an information processing device according to the fourth invention, in which the attribute value change unit changes a placement attribute value among one or more attribute values received by the reception unit.

This configuration makes it possible to suggest changes to the layout of product information that is estimated to be selling well.

The information processing device of the seventh invention is a learning device that configures learning information used by the information processing device of the first to sixth inventions, and includes a learning information storage unit that stores learning information that has learned learning target information having one or more product attribute information having one or more attribute values of product information related to a product and sales information related to the sale of one or more products, a receiving unit that receives the learning target information, and a learning unit that learns the learning target information using a machine learning algorithm, acquires learning information, and accumulates the learning information in the learning information storage unit.

This configuration makes it easy to obtain learning information.

The information processing device according to the present invention can propose product group content that lists product information for one or more products.

FIG. 1 is a conceptual diagram of an information system A according to a first embodiment. Block diagram of the information system A A flowchart illustrating an example of the operation of the information processing device 1. Flowchart for explaining an example of the same product group content acquisition process A flowchart illustrating an example of the pattern information acquisition process A flowchart for explaining an example of the operation of the terminal device 2 A diagram showing the attribute value condition management table. FIG. 13 shows the layout information management table. A diagram showing the product information management table A diagram showing the product information management table A diagram showing an example of a web page for the same car catalogue. A diagram showing an example of the sales performance of the same vehicle A diagram showing the attribute value management table A diagram showing an example of a web page for the same car catalogue. A diagram showing an example of the output A diagram showing an example of the output FIG. 2 shows an example of a block diagram of the learning device 3. Overview of the computer system Block diagram of the computer system

Embodiments of an information processing device and the like will be described below with reference to the drawings. Note that components with the same reference numerals in the embodiments perform similar operations, and therefore may not be described again.

(Embodiment 1)

In this embodiment, an information system including an information processing device that can predict the sales status of products listed in product group content, which is one or more pieces of product information such as electronic catalogs and web pages, is described. More specifically, in this embodiment, an information system including an information processing device that stores learning information that has learned learning target information having one or more pieces of product attribute information and sales information, accepts one or more pieces of target product information having one or more attribute values, and outputs sales information is described. Note that product here means an item for sale, and is interpreted broadly to include services.

In addition, in this embodiment, an information system including an information processing device that can suggest changes to the layout of product information that is selling well or is estimated to be selling well, or changes to the attribute values of the product information, etc. will be described.

In addition, in this embodiment, an information system including an information processing device that can suggest product group content that is selling well or is estimated to be selling well will be described.

FIG. 1 is a conceptual diagram of an information system A in this embodiment. Information system A includes an information processing device 1 and one or more terminal devices 2. Here, the information processing device 1 is a so-called server device. The information processing device 1 is, for example, a cloud server or an ASP server, but the type and location of the device are not important. The terminal device 2 is a mobile terminal such as a smartphone, tablet terminal, or mobile phone, a so-called personal computer, etc., and the type is not important.

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

The information processing device 1 includes a storage unit 11, a reception unit 12, a processing unit 13, and an output unit 14. The storage unit 11 includes a learning information storage unit 111, and an attribute value condition storage unit 112. The processing unit 13 includes a learning unit 131, a placement pattern information acquisition unit 132, an attribute value change unit 133, a sales information acquisition unit 134, a judgment unit 135, and a configuration unit 136. The sales information acquisition unit 134 includes an attribute value set acquisition means 1341, and a sales information acquisition means 1342.

The terminal device 2 includes a terminal storage unit 21, a terminal reception unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal reception unit 25, and a terminal output unit 26.

The storage unit 11 constituting the information processing device 1 stores various types of information. The various types of information include, for example, learning information described below, attribute value conditions described below, one or more pieces of layout information, one or more pieces of target product information, or product group content having one or more pieces of target product information. The target product information is product information to be processed by the information processing device 1.

Layout information is information for determining the placement of one or more pieces of product information. Layout information is, for example, a set of placement attribute values (e.g., the coordinate value of the top left corner of an area) indicating the placement position of the product information, and one or more attribute values of the product information that can be placed in an area determined by the placement attribute values. Product information is information about a product, and is content that is placed in product group content such as an electronic catalog or a web page. The product group content may be information that includes one piece of product information. The product group content may be content that has a concept of a page, or content that does not have a concept of a page.
The product information includes, for example, a product image, a product character string, a product video, and a product audio. A product image is an image of a product. A product character string is a character string that describes a product. A product video is a video that describes a product. A product audio is an audio that describes a product. One or more attribute values of the product information may be stored in association with the product information.

Attribute values of product information include, for example, the attribute value of the product itself, image attribute value, string attribute value, video attribute value, audio attribute value, and layout attribute value. The attribute value of the product itself is the attribute value of the product itself, such as the color of the product, the shape of the product, the weight of the product, the type of the product, and the like. The image attribute value is the attribute value of the product image possessed by the product information, such as the size of the product image, the color of the product image, the resolution of the product image, the brightness of the product image, and the shape of the product image. The color of the product image is, for example, the average value of the color components of the pixel values constituting the product image. The brightness of the product image is, for example, the average value of the brightness of the pixels constituting the product image. The string attribute value is the attribute value of the string describing the product, such as the font, character size, and length. The video attribute value is the attribute value of the product video possessed by the product information, and includes, for example, one or more feature values of the product video. The feature amount is, for example, the length of the product video, the resolution of the product video, information indicating whether the product video has subtitles, information indicating whether the product video has commercials, information indicating the number of times the product video has been viewed, information indicating whether the product video has comments, information indicating whether the product video is divided, various other feature amounts of the product video, and feature amounts of still images constituting the product video. Note that there may be various feature amounts of the video and the still images, and the technology for acquiring the feature amounts is a publicly known technology. The audio attribute value is an attribute value of the audio information possessed by the product information, and includes, for example, one or more feature amounts of the product audio. The feature amount is, 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 the product audio has background music, the insertion position of the background music, information indicating whether the product audio has sound effects, the insertion position of the sound effects, and other feature amounts of the audio. Note that there may be various feature amounts of the audio, and the technology for acquiring the feature amounts is a publicly known technology. The placement attribute value is an attribute value of the placement of the product information, and can be an absolute placement attribute value or an attribute value of product information surrounding the product information. The absolute placement attribute value is an attribute value related to the placement of the product information itself, and can be, for example, a position on a page (e.g., top, middle, bottom, left, center, right), a coordinate value, a page number, etc. Furthermore, the product information surrounding the product information can be, for example, product information adjacent to the product information or product information arranged on the same page as the product information. Furthermore, the sales information is information related to the sales of the product. Furthermore, the sales information can be, for example, the number of sales, the total sales amount, etc. The sales information is preferably the total sales amount or the total sales amount of two or more products, but can also be the sales amount or the sales amount of each of two or more products.

The learning information storage unit 111 stores learning information.

The learning information is, for example, information acquired by the learning unit 131 through learning. Details of the learning unit 131 will be described later. The learning information is, for example, information acquired by learning the learning target information. The learning target information has one or more pieces of product attribute information and sales information. The product attribute information has one or more attribute values corresponding to the product information. The one or more attribute values corresponding to the product information may be one or more attribute values possessed by the product information, one or more attribute values linked to the product information, or one or more attribute values that can be acquired from the product information. The learning target information may be information having product group content and sales information. The learning target information may be information having two or more pieces of product attribute information and sales information acquired from the product group content.

The learning information may be information that has multiple pairs of one or more attribute values and sales information for one or more pieces of product information.

The attribute value condition storage unit 112 stores one or more attribute value conditions related to the conditions that an attribute value can take. The attribute value condition has an attribute identifier that identifies the attribute value and an attribute value change condition.

The attribute identifier is, for example, an attribute name or an ID. The attribute name is, for example, "color" indicating the color of the product, "shape" indicating the shape of the product, "weight" indicating the weight of the product, "type" indicating the type of the product, "image size" indicating the size of the product image, "image color" indicating the color of the product image, "resolution" indicating the resolution of the product image, "brightness" indicating the brightness of the product image, "image shape" indicating the shape of the product image, "font" indicating the font of the character string describing the product, "character size", "character length" indicating the length of the character string describing the product, "video time" indicating the playback time of the video describing the product, "audio type" indicating the type of audio describing the product, "page position" indicating the position within the page, "coordinate value" indicating the coordinate value within the page, "page number" indicating the page number on which the product information is placed, "surrounding image size" indicating the size of the product image of the surrounding product information, "surrounding image resolution" indicating the resolution of the product image of the surrounding product information, "surrounding product character size" indicating the character size of the surrounding product information, "surrounding product character length" indicating the length of the character string of the surrounding product information, etc. The "surrounding image size" is, for example, the "upper product image size" which is the size of the adjacent upper product image, the "horizontal product image size" which is the size of the adjacent horizontal product image, and the "lower product image size" which is the size of the adjacent lower product image. The "surrounding image resolution" is, for example, the "upper product image resolution" which is the resolution of the adjacent upper product image, the "horizontal product image resolution" which is the resolution of the adjacent horizontal product image, and the "lower product image resolution" which is the resolution of the adjacent lower product image. The "surrounding product character size" is, for example, the "upper product character size" which is the character size of the adjacent upper product string, the "horizontal product character size" which is the character size of the adjacent horizontal product string, and the "lower product character size" which is the character size of the adjacent lower product string. The "surrounding product string length" is, for example, the "upper product string length" which is the length of the adjacent upper product string, the "horizontal product string length" which is the length of the adjacent horizontal product string, and the "lower product string length" which is the length of the adjacent lower product string.

The attribute value change condition is, for example, a set of candidate information that the attribute value can take, and information on the range of values that the attribute value can take. The set of candidate information that the attribute value can take is, for example, "font = Gothic, Mincho, ...", "character size = 10pt, 12pt, 14pt, ...", "position on page = (1st, left), (1st, right), (2nd, left), (3rd, right), (3rd, left), (3rd, right), ...". Information on the range of values that 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 <= peripheral product character size <= 16pt".

The reception unit 12 receives one or more pieces of target product information having one or more attribute values. The target product information is usually product information that constitutes the product group content to be output. The target product information may be, for example, one or more attribute values of the product information that constitutes the product group content to be output.

Here, it is preferable that the one or more attribute values are one or more of the attribute values of the product itself and image attribute values.

The reception unit 12 may, for example, receive learning instructions, proposal instructions, and sales forecast instructions.

The learning instruction includes information to be learned. The information to be learned is information that is used by the sales information acquisition unit 134 to acquire sales information. The information to be learned includes product attribute information and sales information for one or more products. The product attribute information includes one or more attribute values of the product information.

The proposal instruction is an instruction to propose product group content. The proposal instruction may be an instruction to output product group content that is estimated to result in good sales, or an instruction to output product group content that is estimated to improve sales. The proposal instruction has, for example, one or more pieces of target product information. The proposal instruction has, for example, product group content. When the proposal instruction has product group content, for example, the reception unit 12 acquires one or more attribute values of one or more pieces of product information contained in the product group content. Such one or more attribute values are target product information.

The sales forecast instruction is an instruction to output a sales forecast. The sales forecast instruction has, for example, one or more pieces of target product information. The sales forecast instruction has, for example, product group content. When the sales forecast instruction has product group content, for example, the reception unit 12 acquires one or more attribute values of one or more pieces of product information contained in the product group content. Such one or more attribute values are target product information.

Here, "acceptance" usually means receipt from the terminal device 2, but it is a concept that also includes the acceptance of information input from an input device such as a keyboard, mouse, or touch panel, and the acceptance of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory. Acceptance may be any process that can obtain the target information or instruction.

When the reception is reception of information input from an input device, the input means may be anything, such as a touch panel, keyboard, mouse, or menu screen. In such a case, the reception unit 12 may be realized by a device driver for the input means such as a touch panel or keyboard, or control software for the menu screen, etc.

The processing unit 13 performs various types of processing. The various types of processing are, for example, processing performed by the learning unit 131, the arrangement pattern information acquisition unit 132, the attribute value change unit 133, the sales information acquisition unit 134, the judgment unit 135, and the configuration unit 136.

The learning unit 131 learns the learning target information using a machine learning algorithm and acquires learning information. Here, machine learning refers to, for example, SVR, deep learning, decision tree, random forest, SVM, etc. However, any machine learning algorithm can be used.

The learning target information has one or more product attribute information and sales information. The product attribute information has one or more attribute values of the product information. The sales information is usually information about the sales of one or more products corresponding to the one or more product attribute information. It is preferable that the sales information held by the learning target information is information sold using 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.

The information to be learned may be product group content and sales information. In such a case, the learning unit 131 acquires one or more pieces of product attribute information from the product group content. The learning unit 131 then learns the acquired one or more pieces of product attribute information and the sales information contained in the information to be learned using a machine learning algorithm, and acquires learning information.

The learning information may be any information that allows sales information to be obtained when one or more attribute values of a product are applied.

The processing by the learning unit 131 is a known technique, and therefore a detailed description will be omitted. The learning information may be, for example, information having multiple pairs of one or more pieces of product attribute information and sales information. The learning information may be, for example, multiple pieces of correspondence information that associate one or more pieces of product attribute information with sales information.

The arrangement pattern information acquisition unit 132 acquires two or more pieces of arrangement pattern information. The arrangement pattern information is information that has one or more arrangement attribute values for one or more pieces of target product information, and is arrangement pattern information.

The arrangement pattern information acquisition unit 132, for example, adds the arrangement order of each of the two or more pieces of target product information accepted by the acceptance unit 12 to each piece of target product information. In this case, the arrangement pattern information acquisition unit 132 may add the arrangement order to the arbitrarily selected piece of target product information, for example, randomly, starting from 1. The arrangement pattern information acquisition unit 132 also determines the arrangement order of each piece of target product information (sorts the product information) based on, for example, a predetermined condition (a condition using one or more attribute values), and adds the arrangement order to each piece of target product information. The arrangement pattern information acquisition unit 132 also arranges one or more pieces of target product information according to, for example, two or more pieces of predetermined layout information, and acquires the arrangement attribute value of each piece of one or more pieces of target product information. The arrangement pattern information is information for arranging one or more pieces of product information in the product group content. Once the arrangement pattern information is determined, the arrangement of one or more pieces of product information is usually determined.

The attribute value modification unit 133 modifies some of the one or more attribute values held by each of the one or more pieces of target product information received by the reception unit 12. There is no restriction on 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 so that they match the attribute value condition. For example, if the attribute value condition is a collection of information on possible candidates for the attribute value, the attribute value modification unit 133 selects one candidate from the possible candidates for the attribute value, and determines the one candidate as the changed attribute value. Also, if the attribute value condition is information on a range of values that the attribute value can take, the attribute value modification unit 133 randomly obtains one value from the range, and determines the value as the changed attribute value.

The attribute value change unit 133 may change any of the product attribute value, image attribute value, or character string attribute value among one or more attribute values possessed by each of the one or more pieces of target product information accepted by the acceptance unit 12.

The attribute value change unit 133 may change the placement attribute value among one or more attribute values possessed by each of the one or more pieces of target product information accepted by the acceptance unit 12.

The sales information acquisition unit 134 applies one or more attribute values of each of the one or more pieces of target product information received by the reception unit 12 to the learning information to acquire sales information. Note that the sales information here can be said to be sales forecast information.

The process of applying one or more attribute values to the learning information is, for example, a process that uses a machine learning algorithm. In addition, the process of applying one or more attribute values to the learning information is, for example, a process of selecting one or more attribute values from the learning information that are closest to the one or more attribute values, and acquiring sales information contained in the selected learning information.

The process of applying one or more attribute values to the learning information is, for example, a process of selecting from the learning information one or more attribute values that are closest to one or more attribute values possessed by each of the one or more pieces of target product information accepted by the accepting unit 12, and acquiring sales information that pairs with the selected one or more attribute values from the learning information.

The sales information acquisition unit 134 acquires sales information by applying the target product information to the learning information using, for example, a machine learning algorithm. Note that the machine learning is, for example, SVR, deep learning, decision tree, random forest, SVM, etc. Also, it is preferable that the two or more pieces of target product information accepted by the acceptance unit 12 do not include sales information.

The sales information acquisition unit 134 preferably applies one or more types of attribute values accepted by the acceptance unit 12 and the arrangement pattern information acquired by the arrangement pattern information acquisition unit 132 to the learning information to acquire sales information for each of the two or more pieces of arrangement pattern information. The two or more pieces of arrangement pattern information are the arrangement pattern information acquired by the arrangement pattern information acquisition unit 132.

The sales information acquisition unit 134 preferably applies the attribute values changed by the attribute value change unit 133 and the attribute values that have not been changed by the attribute value change unit 133 among the one or more attribute values accepted by the acceptance unit 12 to the learning information to acquire the sales information.

It is preferable that the sales information acquisition unit 134 applies, 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 attribute values that have not been changed by the attribute value change unit 133 among the one or more attribute values accepted by the acceptance unit 12, to the learning information to acquire sales information.

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 one or more pieces of target product information accepted by the reception unit 12. The attribute value set may also be a set of attribute values acquired from one or more arrangement attribute values acquired by the arrangement pattern information acquisition unit 132 in addition to one or more attribute values possessed by one or more pieces of target product information accepted by the reception unit 12. The attribute value set may also be a set of attribute values acquired from attribute values that have not been changed by the attribute value change unit 133 and attribute values that have been changed by the attribute value change unit 133, among one or more attribute values possessed by one or more pieces of target product information accepted by the reception unit 12. The attribute value set may also be a set of attribute values acquired from the attribute values not changed by the attribute value change unit 133, the attribute values changed by the attribute value change unit 133, and the one or more layout attribute values acquired by the layout pattern information acquisition unit 132, among the one or more attribute values possessed by each of the one or more pieces of target product information accepted by the acceptance unit 12. The attribute value set acquired by the attribute value set acquisition means 1341 and the one or more attribute values possessed by each of the one or more pieces of target product information accepted by the acceptance unit 12 may have the same structure or may have different structures.

The attribute value set acquisition means 1341 preferably acquires possible values for one or more attributes so as to satisfy the attribute value change condition corresponding to each attribute, and acquires possible combinations of attribute values from the set of possible values for the attribute values. The combinations of attribute values may be referred to as attribute value sets.

The sales information acquisition means 1342 applies the attribute value set acquired by the attribute value set acquisition means 1341 to the learning information to acquire 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 to acquire sales information by a machine learning algorithm. In addition, the sales information acquisition means 1342 searches the learning information for one or more attribute values whose similarity to the attribute value set acquired by the attribute value set acquisition means 1341 is large enough to satisfy a predetermined condition, and acquires one or more pieces of sales information paired with the one or more attribute values from the learning information. In addition, the sales information acquisition means 1342 searches the learning information for one or more attribute values whose similarity to the attribute value set acquired by the attribute value set acquisition means 1341 is largest, and acquires sales information paired with the one or more attribute values from the learning information.

The judgment unit 135 judges whether the sales situation is good enough to satisfy a predetermined condition for the sales information for each of the two or more pieces of arrangement pattern information acquired by the sales information acquisition unit 134. The predetermined condition is, for example, that the sales information, which is the total sales amount, is equal to or greater than a threshold value. Also, the predetermined condition is, for example, that the sales information, which is the total sales volume, is equal to or greater than a threshold value. Also, the predetermined condition is, for example, that the sales situation has improved compared to the accepted sales information. This means, for example, that the acquired total sales amount is greater than the accepted total sales amount, and that the acquired total sales volume is greater than the accepted total sales volume. Note that the accepted total sales amount and the accepted total sales volume are usually information on the sales performance of the product group content to be improved.

The determination unit 135 determines whether the sales situation is good enough that the sales information acquired by the sales information acquisition unit 134 satisfies a predetermined condition.

The configuration unit 136 configures product group content by arranging one or more pieces of target product information according to the arrangement pattern information when the determination unit 135 determines that the sales situation is good, for example.

The configuration unit 136, for example, uses the attribute values when the determination unit 135 determines that the sales situation is good to arrange one or more pieces of target product information and configure the product group content.

When two or more pieces of sales information are acquired, the configuration unit 136 may select the sales information that satisfies a predetermined condition. Then, the configuration unit 136 arranges one or more pieces of target product information using the attribute value corresponding to the selected sales information to configure the product group content.

The output unit 14 outputs, for example, the sales information acquired by the sales information acquisition unit 134. The output unit 14 outputs, for example, the product group content configured by the configuration unit 136. The output unit 14 also 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 about a single product.

In this case, output usually means transmission to an external device (usually terminal device 2), but it may also be considered as a concept that includes display on a display, projection using a projector, printing on a printer, sound output, storage on a recording medium, and delivery of processing results to other processing devices or other programs, etc.

When the output is the transfer of sales information, for example, the sales information is transferred to the judgment unit 135.

The terminal storage unit 21 constituting the terminal device 2 stores various types of information. The various types of information are, for example, a user identifier that identifies a user. The various types of information are, for example, information received by the terminal receiving unit 25. The user identifier may also be information that identifies the terminal device 2.

The terminal reception unit 22 receives various instructions and information. Examples of various instructions and information include learning instructions, proposal instructions, sales forecast instructions, learning target information, and one or more target product information. Here, reception is a concept that includes the reception of information input from an input device such as a keyboard, mouse, or touch panel, the reception of information transmitted via a wired or wireless communication line, and the reception of information read from a recording medium such as an optical disk, magnetic disk, or semiconductor memory.

The input means for various instructions and information may be anything, such as a touch panel, keyboard, mouse, or menu screen. The terminal reception unit 22 may be realized by a device driver for an input means such as a touch panel or keyboard, or control software for a menu screen.

The various processes performed by the device processing unit 23 include, for example, processing to configure the information received by the device receiving unit 25 into data to be displayed. The various processes include, for example, processing to configure the instructions received by the device accepting unit 22 into instructions to be transmitted.

The terminal transmission unit 24 transmits various instructions, information, etc. to the information processing device 1. Examples of the various instructions, information, etc. include instructions configured by the terminal processing unit 23, instructions and information accepted by the terminal acceptance unit 22, etc.

The terminal receiving unit 25 receives various information from the information processing device 1. The various information includes, for example, sales information and product group content.

The terminal output unit 26 acquires various types of information. Examples of the various types of information include information accepted by the terminal acceptance unit 22, information received by the terminal reception unit 25, and information constructed by the device processing unit 23. Examples of the various types of information include sales information and product group content.

Here, output is a concept that includes displaying on a display, projecting using a projector, printing on a printer, outputting sound, sending to an external device, storing on a recording medium, and passing on the processing results to other processing devices or other programs, etc.

The storage unit 11, learning information storage unit 111, attribute value condition storage unit 112, and terminal storage unit 21 are preferably non-volatile recording media, but can also be realized using volatile recording media.

The process by which information is stored in the storage unit 11, etc. is not important. 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 inputted via an input device may be stored in the storage unit 11, etc.

The processing unit 13, learning unit 131, arrangement pattern information acquisition unit 132, attribute value change unit 133, sales information acquisition unit 134, judgment unit 135, configuration unit 136, and device processing unit 23 can usually be realized by an MPU, memory, etc. The processing procedures of the processing unit 13, etc. are usually realized by software, and the software is recorded on a recording medium such as a ROM. However, they may also be realized by hardware (dedicated circuitry).

The output unit 14 and the terminal transmission unit 24 are typically implemented using wireless or wired communication means, but may also be implemented using broadcasting means.

The output unit 14 may be realized by driver software for an output device, or by a combination of driver software for an output device and an output device, etc.

The terminal output unit 26 may or may not include an output device such as a display or speaker. The terminal output unit 26 may be realized by driver software for an output device, or by a combination of driver software for an output device and an output device, etc.

Next, the operation of information system A will be described. First, an example of the operation of information processing device 1 will be described using the flowchart in FIG. 3.

(Step S301) The reception unit 12 determines whether or not a learning instruction has been received. If a learning instruction has been received, the process proceeds to step S302. If a learning instruction has not been received, the process proceeds to step S304.

(Step S302) The learning unit 131 acquires the learning target information contained in the learning instruction received in step S301. Then, the learning unit 131 acquires one or more attribute values contained in 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. Then, the learning unit 131 performs machine learning processing on the acquired two or more attribute values and the sales information as pairs, and acquires learning information. Note that when the two or more attribute values are applied to the learning information, the sales information is acquired.

The learning unit 131 may 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 of one or more pieces of product information contained in the product group content. The learning unit 131 then performs machine learning processing by pairing one or more attribute values of one or more pieces of product information with the sales information to acquire learning information. Note that when one or more attribute values are applied to the learning information, the sales information is acquired.

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

(Step S304) The reception unit 12 determines whether or not a proposal instruction has been received from the terminal device 2. If a proposal instruction has been received, the process proceeds to step S305; if a proposal instruction has not been received, the process proceeds to step S307.

(Step S305) The processing unit 13 acquires product group content using one or more pieces of target product information contained in the suggestion instruction. This product group content acquisition process will be described with reference to the flowchart in FIG. 4.

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

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

(Step S308) The sales information acquisition unit 134 acquires one or more pieces of target product information contained in the sales forecast instruction received in step S307. If the sales forecast instruction includes product group content, the sales information acquisition unit 134 acquires target product information corresponding to each of the one or more pieces of product information from the product group content.

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

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

In the flowchart in Figure 3, processing ends when the power is turned off or an interrupt occurs to end processing.

Next, an example of the product group content acquisition process in step S305 will be described using the flowchart in FIG.

(Step S401) The arrangement pattern information acquisition unit 132 etc. acquires pattern information. Such pattern information acquisition processing will be described with reference to the flowchart in FIG. 5. Pattern information is usually a combination of two or more attribute values. It may also be said that pattern information is a set of two or more attribute values. The pattern information acquisition processing acquires a set of two or more attribute values. It is to be noted that each set of two or more attribute values has at least some different attribute values. It may also be thought that there are cases in which pattern information can be a single attribute value.

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

(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 values. It may also be considered that a single attribute value may be sufficient for the combination of attribute values.

(Step S404) If the sales information acquisition unit 134 is able to acquire the i-th attribute value combination, it proceeds to step S405; if not, it proceeds to step S407.

(Step S405) The sales information acquisition unit 134 applies the i-th attribute value combination to the learning information in the learning information storage unit 111 to acquire sales information. Then, the sales information acquisition unit 134 associates the acquired sales information with the i-th attribute value combination and temporarily stores it in a buffer (not shown).

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

(Step S407) The judgment unit 135 determines sales information that satisfies a predetermined condition from the one or more pieces of sales information acquired in step S405. Then, the judgment unit 135 acquires a combination of attribute values corresponding to each of the one or more pieces of sales information determined from a buffer (not shown). Note that sales information that satisfies a predetermined condition is usually sales information whose sales situation is good enough to satisfy the predetermined condition, or sales information whose sales situation is improving enough to satisfy the predetermined condition.

(Step S408) The configuration unit 136 assigns 1 to counter j.

(Step S409) The configuration unit 136 determines whether or not the jth attribute value combination exists among the attribute value combinations acquired in step S407. If the jth attribute value combination exists, the process proceeds to step S410, and if the jth attribute value combination does not exist, the process returns to the upper level process.

(Step S410) The configuration unit 136 arranges two or more pieces of target product information according to the combination of j-th attribute values to configure product group content. Note that the two or more pieces of target product information are usually information accepted by the acceptance unit 12, but may also be information stored in the storage unit 11.

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

(Step S412) The configuration unit 136 increments the counter j by 1. Return to step S409.

Next, an example of the pattern information acquisition process in step S401 will be described using the flowchart in FIG.

(Step S501) The attribute value change unit 133 assigns 1 to counter i.

(Step S502) The attribute value modification unit 133 judges whether or not the i-th type of attribute value exists. If the i-th type of attribute value exists, the process proceeds to step S503, and if the i-th type of attribute value does not exist, the process proceeds to step S505. Note that the attribute value modification unit 133 judges whether or not the i-th type of attribute value exists based on, for example, whether or not the i-th attribute value condition or the i-th attribute identifier exists in the attribute value condition storage unit 112.

(Step S503) The attribute value change unit 133 acquires all possible values of the i-th type of attribute value. When the attribute value change condition corresponding to the i-th type of attribute value is a set of candidate information that the attribute value can take, the attribute value change unit 133 acquires all candidate information that the attribute value can take from the attribute value condition storage unit 112. When the attribute value change condition corresponding to the i-th type of attribute value is information on a range of values that the attribute value can take, for example, the attribute value change unit 133 acquires information on the range from the attribute value condition storage unit 112 and acquires a set of information on two or more candidates that satisfy the range. Note that the attribute value change unit 133 may acquire a set of information on two or more candidates that satisfy the range in any way. For example, the attribute value change unit 133 may acquire a set of information on two or more candidates by shifting the value by a fixed value from the minimum value to the maximum value in the range, or may randomly acquire N values (N is, for example, a fixed number) from the range.

(Step S504) The attribute value change unit 133 increments the counter i by 1. Return to step S502.

(Step S505) The attribute value change unit 133 assigns 1 to counter j.

(Step S506) The attribute value modification unit 133 determines whether the jth attribute value pattern exists. If the jth attribute value pattern exists, the process proceeds to step S507; if the jth attribute value pattern does not exist, the process returns to the upper level process.

The attribute value change unit 133 acquires all attribute value sets (attribute value patterns) from the set of candidate information for each of the two or more types of attribute values acquired in step S503, for example. The attribute value change unit 133 then determines whether or not the j-th attribute value pattern exists from the two or more attribute value patterns. For example, there are two pieces of target product information (product information A, product information B), each piece of target product information has attribute values for three attributes (attribute 1, attribute 2, attribute 3), 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 change unit 133 acquires 24 different attribute value patterns. Also, assume that there is one piece of target product information (product information A), the target product information has attribute values for two attributes (attribute 1, attribute 2), attribute 1 can take either attribute value 11 or attribute value 12, and attribute 2 can take either attribute value 21, attribute value 22, or attribute value 23. In this case, the attribute value change unit 133 obtains six different attribute value patterns.

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

(Step S508) The arrangement pattern information acquisition unit 132 determines whether or not a combination of the jth attribute value pattern element and the kth arrangement order exists. If the kth arrangement order combination exists, the process proceeds to step S509, and if the kth arrangement order combination does not exist, the process proceeds to step S512.

(Step S509) The arrangement pattern information acquisition unit 132 acquires the kth arrangement order combination of the jth attribute value pattern element. Then, the arrangement pattern information acquisition unit 132 acquires the arrangement attribute value of one or more pieces of product information using the kth arrangement order combination. The arrangement attribute value of one or more pieces of target product information is arrangement pattern information. The arrangement order combination is information indicating the arrangement order of one or more pieces of target product information (for example, information indicating the target product information to be arranged first, the target product information to be arranged second, ..., the target product information to be arranged Nth from the top left of the product group content), or the top left coordinate value. The attribute value change unit 133 arranges two or more pieces of target product information in order according to, for example, the jth attribute value pattern element and the information indicating the kth arrangement order, and acquires the arrangement attribute value of each of two or more pieces of target product information. The attribute value change unit 133 arranges one piece of target product information according to, for example, the jth attribute value pattern element and the kth arrangement pattern information.

(Step S510) The attribute value change 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 the combination in a buffer (not shown).

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

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

Next, an example of the operation of the terminal device 2 will be described using the flowchart in FIG. 6.

(Step S601) The terminal reception unit 22 determines whether or not a learning instruction has been received. If a learning instruction has been received, the process proceeds to step S602. If a learning instruction has not been received, the process proceeds to step S604.

(Step S602) The device processing unit 23 composes a learning instruction to be sent. Note that the learning instruction to be sent typically includes two or more pieces of learning target information.

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

(Step S604) The terminal reception unit 22 determines whether or not a proposal instruction has been received. If a proposal instruction has been received, the process proceeds to step S605. If a proposal instruction has not been received, the process proceeds to step S610.

(Step S605) The device processing unit 23 composes a proposal instruction to be sent. The proposal instruction to be sent includes two or more pieces of target product information or product group content.

(Step S606) The terminal transmission unit 24 transmits the proposal instruction constructed in step S605 to the information processing device 1.

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

(Step S608) The device processing unit 23 composes the product group content to be output.

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

(Step S610) The terminal reception unit 22 determines whether or not a sales forecast instruction has been received. If a sales forecast instruction has been received, the process proceeds to step S611. If a sales forecast instruction has not been received, the process returns to step S601.

(Step S611) The device processing unit 23 composes a sales forecast instruction to be sent. The sales forecast instruction to be sent includes two or more pieces of target product information or product group content.

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

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

(Step S614) The device processing unit 23 composes the sales information to be output.

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

In the flowchart in Figure 6, processing ends when the power is turned off or an interrupt occurs to end processing.

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.

Currently, the attribute value condition storage unit 112 stores the attribute value condition management table shown in FIG. 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 indicate possible attribute values. The attribute value condition management table has records, each having an "ID," "attribute identifier," "attribute type," and "attribute value change condition," for the number of changeable attributes. The "ID" is information that identifies the record. The "attribute identifier" here is the attribute name. "Attribute type" indicates the type of attribute.

The storage unit 11 also stores a layout information management table as shown in FIG. 8. The layout information management table has multiple records each having an "ID", "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 is the name of the layout information. The "layout information" here represents a layout diagram for arranging the elements that make up the product information, and has relative coordinate information for arranging the elements that make up the product information. The "ID" may also be considered as a layout identifier.

The storage unit 11 also stores a product information management table shown in FIG. 9. The storage unit 11 also stores a product information management table shown in FIG. 10. The product information management table manages two or more pieces of product information. The product information management table has an "ID," "product image," "product attribute value," "product name," and "product description." "ID" is the ID of the product information. The "product attribute value" here has "price," "color," etc. "Product name" is the name of the product. "Product description" is a string of characters that describes the product.

In this situation, the following four specific examples will be described. Specific Example 1 is a learning process by the learning unit 131. Specific Example 2 is a sales prediction process using the learning information. Specific Example 3 is a process for changing the product group content so as to improve the sales situation. Specific Example 4 is a process for creating the product group content so as to obtain good sales results.
(Specific Example 1)

In specific example 1, the learning process performed by the learning unit 131 is explained.

First, assume that a user of terminal device 2 inputs a learning instruction to terminal device 2, including electronic data of the web page of the automobile catalog shown in FIG. 11 and automobile sales results using the web page (see FIG. 12). Note that the automobile sales results are an example of sales information, and include the number of automobiles sold, the total sales amount of each automobile, the total number of automobiles sold, and the total sales amount of all automobiles. Also, "ID" in FIG. 12 is a product identifier.

Next, the terminal reception unit 22 receives a learning instruction. The terminal processing unit 23 constructs a learning instruction to be transmitted in response to the received learning instruction. Then, the terminal transmission unit 24 transmits the learning instruction to the information processing device 1.

Next, the reception unit 12 of the information processing device 1 receives a learning instruction from the terminal device 2. The learning instruction includes electronic data of the webpage in FIG. 11 (which may be the URL of the webpage) and the sales information shown in FIG. 12. The electronic data of the webpage also includes information on two or more target products. Here, the target product information is product information for each automobile.

Next, the reception unit 12 acquires attribute values of each target product information from the electronic data of the web page of FIG. 11. Specifically, the reception unit 12 acquires, for example, 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, for example, the product image with "ID=C1" contained in the electronic data of the web page of FIG. 11, and acquires image attribute values such as "image size=(W ₁ , H ₁ )" and "image shape=rectangle". The reception unit 12 also acquires, for example, "font=Mincho" and "character size=11pt" from the character string with "ID=C1" contained in the electronic data of the web page of FIG. 11. The reception unit 12 also analyzes, for example, the web page of FIG. 11, and acquires information regarding the arrangement of each object on the web page, and acquires, for example, "layout information=2" and "arrangement order=1" from the product information with "ID=C1". The reception unit 12 acquires an attribute value management table shown in FIG. 13 from such attribute values. Incidentally, the acquisition of such attribute values may be said to be acceptance of the attribute values.

Next, the learning unit 131 acquires one or more attribute values acquired by the reception unit 12 (attribute value management table in FIG. 13). The learning unit 131 also acquires the total number of cars sold and the total sales amount of all cars from the car sales record in FIG. 12 received by the reception unit 12. Here, the learning unit 131 acquires two types of sales information, the total number of cars sold and the total sales amount. The learning unit 131 then associates one or more attribute values (attribute value management table in FIG. 13) with the two types of sales information, and accumulates them in the storage unit 11 or a buffer not shown. Note that a pair of one or more attribute values (attribute value management table in FIG. 13) and sales information is the information to be learned. The learning information is also a vector that concatenates vectors corresponding to two or more pieces of product information and sales information. That is, the learning target information 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, 5.8 million yen). It is not necessary to put () between the product information of such learning target information. It goes without saying that the learning unit 131 may learn the sales volume and sales amount of each automobile in the automobile sales record of FIG. 12.

The above process is performed on the electronic data and sales information of many other web pages, and a large amount of learning information is accumulated.

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

As a result of the above, learning information is obtained from which sales information can be obtained when two or more pieces of target product information are applied.
(Specific Example 2)

In specific example 2, we will explain the process of performing sales forecasting using the learning information accumulated in specific example 1.

First, assume that the user of terminal device 2 wishes to predict sales based on the automobile catalog shown in FIG. 14 and inputs a sales prediction command having the URL of the web page of the automobile catalog shown in FIG. 14 into terminal device 2.

Next, the terminal reception unit 22 receives a sales forecast instruction. The terminal processing unit 23 composes a sales forecast instruction to be transmitted in response to the received sales forecast instruction. The terminal transmission unit 24 then transmits the sales forecast instruction to the information processing device 1. The sales forecast instruction includes the URL of the web page of the automobile catalog shown in FIG. 14.

Next, the reception unit 12 of the information processing device 1 receives a sales forecast instruction from the terminal device 2.

Next, the reception unit 12 acquires the URL contained in the received sales forecast instruction. Next, the reception unit 12 acquires the web page of the automobile catalog corresponding to the URL, and then the reception unit 12 acquires information on two or more target products from the web page.

Next, the sales information acquisition unit 134 acquires a set of attribute values from each of the two or more target product information. The acquired set of attribute values has, for example, the structure shown in FIG. 13. The acquired set of attribute values is, for example, a vector ((2.3 million yen, 0, 1, 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, 0, ..., 1, 3, ...)).

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. Note that this vector is a vector that concatenates vectors corresponding to two or more pieces of target product information. Here, it is assumed that the sales information acquisition unit 134 has acquired the total number of units sold of "8210" and the total sales amount of "2,102,492."

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.

Next, the terminal receiving unit 25 receives the sales information from the information processing device 1. Next, the terminal processing unit 23 composes the sales information to be output. The terminal output unit 26 outputs the composed sales information. An example of such output is shown in FIG. 15.
(Specific Example 3)

In specific example 3, we will explain the process of changing the product group content to improve sales using the learning information accumulated in specific example 1.

Now, assume that the sales situation of automobiles according to the electronic data of the web page shown in FIG. 14 is not good, so the user inputs a proposal instruction including the URL of the web page shown in FIG. 14 to the terminal device 2.

Next, the terminal reception unit 22 receives the proposal instruction. The terminal processing unit 23 composes a proposal instruction to be transmitted in response to the received proposal instruction. The terminal transmission unit 24 then transmits the proposal instruction to the information processing device 1. The proposal instruction includes the URL of the web page of the automobile catalog shown in FIG. 14.

Next, the reception unit 12 of the information processing device 1 receives the proposal instruction from the terminal device 2.

Next, the reception unit 12 acquires the URL contained in the suggestion instruction. Next, the reception unit 12 acquires a web page of the automobile catalog that corresponds to the URL. Next, the reception unit 12 acquires information on two or more target products from the web page.

Next, the attribute value change unit 133 acquires one or more attribute values from each of the two or more pieces of target product information. The method for acquiring such attribute values is possible by the process described above.

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 of FIG. 7. Then, the attribute value modification unit 133 obtains two or more attribute value patterns.

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

As a result of the above, multiple attribute value sets (combinations of attribute values) can be obtained. Note that the process of obtaining such attribute value sets has been explained using the flowchart in Figure 5, so a detailed explanation will be omitted here.

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 in association with the attribute value sets.

Next, the determination unit 135 determines sales information that satisfies a predetermined condition from among the sales information associated with the attribute value set. Here, for example, it is assumed that the determination unit 135 selects the sales information with the largest total sales amount. Then, the determination unit 135 acquires the attribute value set corresponding to the selected sales information with the largest total sales amount.

Next, the composition unit 136 determines the attribute values of the product information in FIG. 9 according to the acquired set of attribute values, and determines the arrangement of each element that constitutes the product information, thereby composing the product group content. Note that the technology for composing the product group content using the elements that constitute the product information when the attribute values of the product information and the arrangement of each element that constitutes the product information have been determined is a publicly known technology, so a detailed description will be omitted.

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.

Next, the terminal receiving unit 25 of the terminal device 2 receives the product group content and the sales information from the information processing device 1. Next, the terminal processing unit 23 composes the product group content and the sales information to be output. The terminal output unit 26 outputs the composed product group content and the sales information. An example of such output is shown in FIG. 16.
(Specific Example 4)

In Specific Example 4, we explain the process of generating product group content using the learning information accumulated in Specific Example 1 to achieve good sales results.

Now, suppose that the user is trying to create a new electronic catalog for automobile sales using the product information DB shown in Figure 10, and has entered a proposal instruction specifying the product information DB in Figure 10.

Next, the terminal reception unit 22 receives the proposal instruction. The terminal processing unit 23 composes a proposal instruction to be transmitted in response to the received proposal instruction. Then, the terminal transmission unit 24 transmits the proposal instruction to the information processing device 1. The proposal instruction includes information of the product information DB shown in FIG. 0.

Next, the reception unit 12 of the information processing device 1 receives the suggestion instruction from the terminal device 2. The reception unit 12 then acquires information about two or more target products contained in the suggestion instruction.

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 of FIG. 7. Then, the attribute value modification unit 133 obtains two or more attribute value patterns.

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

As a result, multiple sets of attribute values (combinations of attribute values) can be obtained.

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 in association with the attribute value sets.

Next, the determination unit 135 determines sales information that satisfies a predetermined condition from among the sales information associated with the attribute value set. Here, for example, it is assumed that the determination unit 135 selects the top three sales information items in terms of total sales volume. Then, the determination unit 135 acquires attribute value sets corresponding to each of the selected three sales information items.

Next, the composition unit 136 composes three product group contents according to the three acquired sets of attribute values.

Next, the output unit 14 transmits three sets of the configured product group content and the total number of items sold (an example of sales information) to the terminal device 2.

Next, the terminal receiving unit 25 of the terminal device 2 receives the three sets of product group content and sales information from the information processing device 1. Next, the terminal processing unit 23 configures the 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.

Next, the user checks the three sets of product group content and sales information, and selects, for example, one product group content. The selected product group content is the adopted product group content.

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

Furthermore, according to this embodiment, it is possible to propose product group content that is estimated to have good sales. Note that the product group content may be information about a single product, as described above.

Furthermore, according to this embodiment, it is possible to propose a change to the attribute values of product information that is estimated to be selling well. Note that the change to the attribute values of the product information may be a change to the attribute values of the product information of a single product.

Furthermore, according to this embodiment, it is possible to propose a change in the attribute value of the product information that is estimated to improve sales. Note that the change in the attribute value of the product information may be a change in the attribute value of the product information of a single product.

The above-mentioned learning process may be performed by a device independent of the information processing device. In such a case, the learning device 3 includes 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 FIG. 17. Such a learning device 3 includes a learning information storage unit 111 in which learning information is stored that has learned learning target information having two or more product attribute information having one or more attribute values of product information related to a product and sales information related to the sale of one or more products, 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 learning information, and accumulates the learning information in the learning information storage unit 111.

The processing in this embodiment may be realized by software. This software may be distributed by software download or the like. 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 realizes the information processing device 1 in this embodiment is a program as follows. That is, this program is a program for making a computer that can access a recording medium having a learning information storage unit in which learning information that has learned learning target information having one or more product attribute information having one or more attribute values of product information related to a product and sales information related to the sale of one or more products is stored, function as a reception 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.

The software that realizes the learning device 3 is a program as described below. That is, this program is, for example, a program that produces learning information to be used by the information processing device 1, and causes a computer to function as a reception unit that receives learning target information having one or more product attribute information having one or more attribute values of product information related to a product and sales information related 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 in a recording medium.

FIG. 18 also shows the appearance of a computer that executes the programs described in this specification to realize the information processing device 1 and the like of the various embodiments described above. The above-mentioned embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 18 is an overview of this computer system 300, and FIG. 19 is a block diagram of system 300.

In FIG. 18, computer system 300 includes computer 301, which includes a CD-ROM drive, keyboard 302, mouse 303, and monitor 304.

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

A program that causes the computer system 300 to execute the functions of the information processing device 1 of the above-mentioned embodiment may be stored on a CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be sent to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 when executed. The program may be loaded directly from the CD-ROM 3101 or the network.

The program does not necessarily have to include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the information processing device 1 of the above-mentioned embodiment. The program only needs to include an instruction portion that calls appropriate functions (modules) in a controlled manner to obtain the desired results. How the computer system 300 operates is well known, and a detailed description will be omitted.

In the above program, the steps of transmitting information and receiving information do not include processing performed by hardware, such as processing performed by a modem or interface card in the transmission step (processing that is performed only by hardware).

The program may be executed by a single computer or multiple computers. In other words, the program may be executed by centralized processing or distributed processing.

Furthermore, in each of the above embodiments, it goes without saying that two or more communication means present in one device may be realized physically by one medium.

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

The present invention is not limited to the above-described embodiment, and various modifications are possible, and it goes without saying that these are also included within the scope of the present invention.

As described above, the information processing device of the present invention has the effect of being able to propose product group content in which multiple product information is posted, and is useful as an information processing device, etc.

REFERENCE SIGNS LIST 1 Information processing device 2 Terminal device 3 Learning device 11 Storage unit 12 Reception unit 13 Processing unit 14 Output unit 21 Terminal storage unit 22 Terminal reception unit 23 Terminal processing unit 24 Terminal transmission unit 25 Terminal reception unit 26 Terminal output unit 111 Learning information storage unit 112 Attribute value condition storage unit 131 Learning unit 132 Arrangement pattern information acquisition unit 133 Attribute value change unit 134 Sales information acquisition unit 135 Determination unit 136 Configuration unit 1341 Attribute value set acquisition means 1342 Sales information acquisition means

Claims (4)

a learning information storage unit for storing learning information obtained by learning two or more learning target information items including two or more product attribute information items having one or more attribute values of each of two or more product information items in an electronic catalog or a web page, and sales information items related to the sales of the two or more products as a whole;
A reception unit that receives two or more pieces of target product information each having one or more attribute values;
an attribute value changing unit that changes a part of the one or more attribute values received by the receiving unit;
a sales information acquisition unit that applies the attribute value changed by the attribute value change unit and one or more attribute values received by the reception unit that are not changed by the attribute value change unit to the learning information, and acquires sales information;
a determination unit that determines whether the sales information acquired by the sales information acquisition unit satisfies a predetermined condition, and
a configuration unit that configures a product group content by arranging the one or more pieces of target product information using the attribute value when the determination unit determines that the sales situation is good;
An information processing device comprising : a product group content configured by said configuration unit, or an output unit that outputs the product group content configured by said configuration unit and said sales information. The learning information is information acquired as a result of learning the two or more pieces of learning target information by a machine learning algorithm,
The sales information acquisition unit
The information processing device according to claim 1 , further comprising: a machine learning algorithm that applies one or more attribute values of each of the two or more target product information to learning information to acquire sales information. An information processing method implemented by a learning information storage unit, a receiving unit, an attribute value changing unit, a sales information acquiring unit, a determining unit, a configuring unit, and an output unit , storing learning information obtained by learning learning information having two or more product attribute information items each having one or more attribute values of two or more product information items in an electronic catalog or a web page, and sales information items related to the overall sales of the two or more products, the method comprising:
A receiving step in which the receiving unit receives two or more pieces of target product information each having one or more attribute values;
an attribute value changing step in which the attribute value changing unit changes a part of the one or more attribute values accepted by the accepting unit;
a sales information acquisition step in which the sales information acquisition unit applies the attribute value changed by the attribute value change unit and one or more attribute values received by the reception unit that are not changed by the attribute value change unit to the learning information, and acquires sales information ;
a determination step in which the determination unit determines whether the sales situation is good enough that the sales information acquired by the sales information acquisition unit satisfies a predetermined condition;
a configuration step in which the configuration unit arranges the one or more pieces of target product information by using the attribute value when the determination unit determines that the sales situation is good, and configures a product group content;
an output step in which the output unit outputs the product group content composed by the composition unit, or the product group content composed by the composition unit and the sales information . A computer that can access a recording medium including a learning information storage unit that stores learning information obtained by learning two or more learning target information items that include two or more product attribute information items having one or more attribute values of each of two or more product information items in an electronic catalog or a web page, and sales information items related to the sales of the two or more products as a whole,
A reception unit that receives two or more pieces of target product information each having one or more attribute values;
an attribute value changing unit that changes a part of the one or more attribute values received by the receiving unit;
a sales information acquisition unit that applies the attribute value changed by the attribute value change unit and one or more attribute values received by the reception unit that are not changed by the attribute value change unit to the learning information, and acquires sales information;
a determination unit that determines whether the sales information acquired by the sales information acquisition unit satisfies a predetermined condition, and
a configuration unit that configures a product group content by arranging the one or more pieces of target product information using the attribute value when the determination unit determines that the sales situation is good;
A program for causing the configuration unit to function as an output unit that outputs the product group content configured by the configuration unit, or the product group content configured by the configuration unit and the sales information.

Images