JP2019164605A - Information processing device, learning device, information processing method, production method of learning information, and program - Google Patents

Abstract

To solve the problem that it is difficult to evaluate a moving image related to a commodity in a conventional manner.SOLUTION: A moving image related to a commodity can be evaluated by an information processing device comprising: a learning information storage unit for storing learning information where learning target information, having an attribute value group containing one or more attribute values acquired from the moving image related to the commodity and sales information related to selling of the commodity, is learned; a reception unit for receiving evaluation target information containing the moving image or the attribute value group acquired from the moving image; an attribute value group acquisition unit for acquiring the attribute value group from the evaluation target information; a sales information acquisition unit for acquiring the sales information by applying the attribute value group acquired by the attribute value group acquisition unit to the learning information; and an output unit for outputting the sales information.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an information processing apparatus that performs information processing related to a moving image related to a product.

  Conventionally, there has been a product sales prediction method for predicting the number of products sold. Such a method includes the following steps (see Patent Document 1).

  The method includes a step of retrieving a first related product corresponding to the first product from a related product database storing a plurality of products and a plurality of related products corresponding to the products based on the first product. And searching a plurality of sales record data and a plurality of evaluation data corresponding to the first related product based on the price range corresponding to the first related product and the first related product via the electronic commerce platform. And generating a predicted number of customers corresponding to the first product based on the sales record data and the evaluation data, and generating a predicted number of sales corresponding to the first product based on the predicted number of customers. A product sales forecasting method comprising:

Patent No. 5918410

  However, in the prior art, it has been difficult to evaluate a moving image related to a product from the viewpoint of sales or the like. The evaluation from the viewpoint of sales or the like is, for example, prediction of sales information.

  Further, in the prior art, for example, it has not been possible to propose a change in a moving image that is estimated to be able to improve the sales situation.

  The information processing apparatus according to the first aspect stores learning information obtained by learning learning target information having an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information related to the sale of the product. Learning information storage unit, a reception unit that receives evaluation target information including an attribute value group acquired from a video or a video, an attribute value group acquisition unit that acquires an attribute value group from the evaluation target information, and an attribute value group acquisition The information processing apparatus includes a sales information acquisition unit that acquires sales information by applying the attribute value group acquired by the unit to learning information, and an output unit that outputs the sales information.

  With such a configuration, it is possible to predict sales information of products related to the moving image.

  Further, in the information processing apparatus of the second invention, in contrast to the first invention, the attribute value group is a movie attribute value that is an attribute value of a movie, or a product itself that is a movie attribute value and an attribute value of the product itself. An information processing apparatus including an attribute value.

  With such a configuration, it is possible to predict sales information of products related to the moving image.

  In addition, the information processing apparatus according to the third aspect of the present invention is a candidate for attribute values of one or more attributes of two or more attributes corresponding to the attribute value group with respect to the first or second invention. A candidate value acquisition unit for acquiring candidate values and one or more attribute values in the attribute value group acquired by the attribute value group acquisition unit are replaced with one or more candidate values acquired by the candidate value acquisition unit. A change candidate information acquisition unit that acquires the above change candidate information, and the sales information acquisition unit applies each of the one or more change candidate information acquired by the change candidate information acquisition unit to learning information, Whether or not the sales situation is so good that a predetermined condition is satisfied for the sales information corresponding to each of the one or more change candidate information. And a judgment unit that judges whether the sales status is good. An information processing apparatus for outputting one or more candidate values with the change candidate information when it is determined that the.

  With such a configuration, it is possible to propose a change in a moving image that is estimated to have a good sales situation.

  Further, in the information processing apparatus according to the fourth aspect of the present invention, the learning information is information acquired from learning target information by a machine learning algorithm, and sales information acquisition is performed. The unit is an information processing device that applies the attribute value group acquired by the attribute value group acquisition unit to learning information by a machine learning algorithm to acquire sales information.

  With this configuration, it is possible to appropriately predict sales information of products related to a moving image using a machine learning algorithm.

  In the information processing apparatus according to the fifth aspect of the present invention, the learning information has two or more pieces of correspondence information including sales information and attribute value groups for any one of the first to third aspects of the invention. The information acquisition unit is an information processing apparatus that determines, from learning information, an attribute value group that is closest to the attribute value group acquired by the attribute value group acquisition unit, and acquires sales information that is paired with the attribute value group.

  With such a configuration, it is possible to easily predict sales information of products related to a moving image.

  Further, the learning device of the sixth aspect of the invention includes a learning target information storage unit that stores one or more learning target information having a moving image related to a product and sales information related to the sale of the product, and one or more learning target information Is a learning device that includes a learning unit that acquires learning information and an output unit that outputs learning information.

  With this configuration, learning information can be acquired.

  According to the information processing apparatus of the present invention, it is possible to evaluate a moving image related to a product.

Conceptual diagram of information system A in the first embodiment Block diagram of the information system A A flowchart for explaining the operation of the information system A Flowchart explaining the candidate value acquisition process Flowchart explaining acquisition of the change candidate information Figure showing the attribute value condition management table Figure showing the product information management table Figure showing the same output example The figure which shows the vector of the same attribute value group Figure showing the same output example Block diagram of learning device 3 in the second embodiment A flowchart for explaining a first operation example of the learning device 3 A flowchart for explaining a second operation example of the learning device 3 Overview of the computer system Block diagram of the computer system

  Hereinafter, embodiments of an information processing apparatus and the like will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again.

(Embodiment 1)
In the present embodiment, learning information obtained by learning two or more product attribute information including an attribute value group including one or more attribute values acquired from a video and sales information related to the sale of the product is stored. An information system including an information processing apparatus that receives evaluation target information including the information, applies the evaluation target information to learning information, and outputs sales information will be described. In addition, a product is a transaction object and may include services and is widely understood.

  In the present embodiment, an information system including an information processing device that proposes an attribute value for improving the sales situation indicated by the sales information will be described.

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

  FIG. 2 is a block diagram of the information system A in the present embodiment.

  The information processing apparatus 1 configuring the information system A 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 an attribute value group acquisition unit 131, a candidate value acquisition unit 132, a change candidate information acquisition unit 133, a sales information acquisition unit 134, and a determination unit 135.

  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.

  Various types of information are stored in the storage unit 11 constituting the information processing apparatus 1. The various information includes, for example, learning information described later, attribute value conditions described later, one or more target product information, one or more moving images, and the like. The target product information is product information of a product to be processed by the information processing apparatus 1. The product information includes, for example, a product identifier for identifying a product and one or more product itself attribute values. The product identifier may be anything as long as it can identify the product, for example, an ID. Further, the product itself attribute value is an attribute value of the product itself, for example, the color, shape, weight, type, price, type, etc. of the product. The moving image is a moving image related to the product, and here, it is assumed that it corresponds to the product identifier. In addition, the video related to the product is, for example, a PR video advertising the product, a video showing the product, an image video reminiscent of the product, a company or brand image video, and the like.

  The learning information storage unit 111 stores learning information. The learning information is used for outputting sales information.

  The learning information is information obtained as a result of learning learning target information including an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information. The learning information is, for example, information obtained by a machine learning algorithm using learning target information by the learning device 3 described later. The machine learning is, for example, SVR, deep learning, decision tree, random forest, SVM, and the like.

  However, the learning information that is information obtained as a result of learning the learning target information may be information having a plurality of sets of attribute value groups and sales information.

  Sales information is information relating to the sale of products. The sales information includes, for example, the number of sales and the total sales. The sales information may be the total sales amount or the total number of sales of one or two or more products, or the sales amount or the number of sales of one product.

  The attribute values included in the attribute value group are, for example, a product itself attribute value and a moving image attribute value. The movie attribute value is, for example, a content attribute value or an external attribute value. The content attribute value is, for example, an object attribute value or an image attribute value.

  The moving image attribute value is a moving image attribute value. The content attribute value is an attribute value extracted from the moving image. The content attribute value is information acquired by performing image processing or image recognition on a moving image. The object attribute value is information about a person or thing in the image. The object attribute value is information obtained by performing image recognition on a moving image. The object attribute value is, for example, information on the presence or absence of a performer indicating whether or not a person is reflected in the video, performer information, time or percentage of the product image being reflected, the type of object being reflected, For example, the time or ratio of each object being reflected. The performer information is information about the performers in the video. For example, the estimated gender, the estimated age, the name of the person being shown, and the type of object worn by the performer (for example, necklace, Muffler, etc.) and attribute values of objects in the video (for example, the color of the performer's clothes, the color of the background building, the color or shape of the performer's pants). The image attribute value is information obtained by analyzing an image, and is, for example, a feature amount of one or more images. The image feature amount is, for example, information related to a value (for example, an average value or an intermediate value) obtained by calculating pixel values of one or more still images included in the moving image, and information about the color of one or more still images included in the moving image. . The external attribute value is an external attribute value that is not the content of the video, for example, the time of the video (the time when the video is played back, which may be referred to as “video time”), spatial resolution, temporal resolution, etc. It is.

  Note that processing for performing image processing such as image recognition on one or more still images constituting a moving image and obtaining one or more moving image attribute values is a known technique.

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

  The attribute identifier is, for example, an attribute name or ID. The attribute name is, for example, the attribute name of the object attribute value (eg, the gender of the performer, the color of the performer's clothes, the color of the background building, the color of the performer's pants), the name of the attribute of the image attribute value ( For example, a calculated value of a pixel value of a moving image (for example, an average value, an intermediate value), an attribute name of an external attribute value (for example, moving image time, spatial resolution, temporal resolution), “color” indicating the color of the product, “Shape” indicating the shape, “Weight” indicating the weight of the product, “Type” indicating the type of the product, “Image size” indicating the size of the product image in the video, and the color of the product image in the video "Image color" to indicate, "Image shape" to indicate the shape of the product image in the video, "Font" to indicate the font of the character string that describes the product in the video, "Character size", the product in the video "Character string length" indicating the length of the character string to be described The show is the "voice type", and the like.

  The attribute value changing condition is, for example, information on a set of candidate information that can be taken by the attribute value and a range of values that can be taken by the attribute value. A set of candidate information that can be attribute values is, for example, “gender of performer = male (1), female (2)”, “video time = 10 seconds, 15 seconds, 20 seconds, 30 seconds, 1 minute, "3 minutes", "Spatial resolution = 1K, 2K, 4K, 8K", "Time resolution = 15 fields / second, 30 fields / second, 45 fields / second, 60 fields / second", "Font = Gothic, Mincho Body,... ”And“ character size = 10 pt, 12 pt, 14 pt,. Information on the range of values that the attribute value can take is, for example, “(x1, y1) <= image size <= (x2, y2) (x1, x2 are widths, y1, y2 are heights)” “10 pt <= Peripheral product character size <= 16 pt ".

  The receiving unit 12 receives evaluation target information. The evaluation target information is information to be evaluated. The evaluation target information includes a moving image or attribute value group related to the product. The attribute value group is a set of attribute values acquired from the moving image.

  The accepting unit 12 may accept, for example, a suggestion instruction, a sales prediction instruction, an operation start instruction, and the like.

  The proposal instruction is an instruction for making a proposal of a moving image or the like. The suggestion instruction may be an instruction to output an attribute value of a moving image that is estimated to be in a favorable sales situation, or an instruction to output an identifier of a product that is estimated to be improved in sales situation. The proposal instruction has, for example, evaluation target information.

  The sales forecast instruction is an instruction for outputting a sales forecast. The sales prediction instruction has evaluation target information, for example.

  The operation start instruction is an instruction to start the operation of the information processing apparatus 1 or the learning apparatus 3 described later.

  Here, “reception” refers to reception of information transmitted from the terminal device 2 via, for example, a wired or wireless communication line, but reception of information input from an input device such as a keyboard, a mouse, or a touch panel, an optical disc It may be considered that the concept includes reception of information read from a recording medium such as a magnetic disk or a semiconductor memory. The reception may be any process that can acquire target information and instructions.

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

  The processing unit 13 performs various processes. The various processes are processes performed by the attribute value group acquisition unit 131, the candidate value acquisition unit 132, the change candidate information acquisition unit 133, the sales information acquisition unit 134, and the determination unit 135, for example.

  The attribute value group acquisition unit 131 acquires an attribute value group from the evaluation target information. When the evaluation target information received by the reception unit 12 does not have a moving image, the attribute value group acquisition unit 131 acquires an attribute value group included in the evaluation target information. When the evaluation target information received by the receiving unit 12 includes a moving image, the attribute value group acquisition unit 131 analyzes the moving image included in the evaluation target information and acquires one or more moving image attribute values from the moving image. The one or more moving image attribute values constitute an attribute value group. When the evaluation target information received by the reception unit 12 has a moving image and one or more attribute values, the attribute value group acquisition unit 131 analyzes the moving image included in the evaluation target information and determines one or more moving image attribute values from the moving image. And one or more attribute values of the evaluation target information are acquired. Such one or more moving image attribute values and one or more attribute values constitute an attribute value group.

  The candidate value acquisition unit 132 acquires candidate values that are candidates for attribute values of one or more attributes among two or more attributes corresponding to the attribute value group. It does not matter how the candidate value acquisition unit 132 acquires the candidate value. For example, the candidate value acquisition unit 132 acquires attribute identifiers of two or more attribute values included in the attribute value group acquired by the attribute value group acquisition unit 131, and sets the attribute value condition paired with the attribute identifier as the attribute value condition. Obtained from the storage unit 112. Then, the candidate value acquisition unit 132 acquires two or more candidate values corresponding to the attribute identifier using the acquired attribute value condition. For example, the candidate value acquisition unit 132 acquires one or more candidate values included in the attribute value condition. Further, the candidate value acquisition unit 132, for example, from information indicating a range included in the attribute value condition (for example, “1 to 5”), two or more candidate values (for example, “1, 2, 3, 4, 5”). )). In addition, it does not ask | require with which width | variety a candidate value is acquired using the information which shows a range.

  Further, the candidate value acquisition unit 132 may acquire, for example, attribute identifiers associated with two or more attribute values included in the attribute value group acquired by the attribute value group acquisition unit 131, or acquire the attribute value group The attribute identifier included in the attribute value group acquired by the unit 131 and paired with the attribute value may be acquired, or an attribute identifier corresponding to the order of the attribute values in the attribute value group is acquired. You may do it. Then, the candidate value acquisition unit 132 holds the acquired candidate value and the attribute identifier in association with each other, for example.

  The change candidate information acquisition unit 133 replaces one or more attribute values in the attribute value group acquired by the attribute value group acquisition unit 131 with one or more candidate values acquired by the candidate value acquisition unit 132. Get change candidate information. The change candidate information is usually a set of two or more attribute values. The change candidate information preferably includes the attribute value group acquired by the attribute value group acquisition unit 131. The attribute value group includes a ratio equal to or higher than the threshold, a ratio higher than the threshold, a number equal to or higher than the threshold, or a number higher than the threshold. That is, it is preferable that the change candidate information acquisition unit 133 adopts candidate values for the ratio or the number of attributes that are equal to or less than the threshold value or less than the threshold value to configure the change candidate information.

  The sales information acquisition unit 134 applies the attribute value group acquired by the attribute value group acquisition unit 131 to the learning information, and acquires the sales information.

In addition, the sales information acquisition part 134 applies an attribute value group to learning information, and the method of acquiring sales information is any one of the following (1)-(3), for example.
(1) Method using machine learning

For example, the sales information acquisition unit 134 applies the attribute value group to the learning information using a machine learning algorithm, and acquires the sales information. The machine learning is, for example, SVR, deep learning, decision tree, random forest, SVM, or the like. In addition, it is preferable that the attribute value group received by the receiving unit 12 does not include sales information.
(2) Method for obtaining sales information paired with the most approximate vector

For example, the sales information acquisition unit 134 detects an attribute value group that is a vector closest to the vector that is the attribute value group acquired by the attribute value group acquisition unit 131 from the learning information, and sells a pair with the attribute value group. Information may be acquired from learning information.
(3) Method of obtaining sales information by calculating two or more sales information pairs with two or more approximate vectors

  For example, the sales information acquisition unit 134 detects, from the learning information, attribute value groups that are two or more vectors that are approximated to satisfy a predetermined condition with a vector that is the attribute value group acquired by the attribute value group acquisition unit 131. Sales information paired with the attribute value group acquired by the attribute value group acquisition unit 131 may be calculated using sales information paired with the two or more attribute value groups. For example, the sales information acquisition unit 134 detects, from the learning information, an attribute value group that is a vector having a threshold number (for example, 2 or 3) that approximates the vector that is the attribute value group acquired by the attribute value group acquisition unit 131. The sales information may be calculated by performing a predetermined operation (for example, an average value, a weighted average considering distance) on the sales information paired with each attribute value group of the threshold number. .

  The sales information acquisition unit 134 applies the one or more pieces of change candidate information acquired by the change candidate information acquisition unit 133 to the learning information, and acquires the sales information for each of the one or more pieces of change candidate information. Note that the change candidate information is also a set of attribute values, and may be referred to as an attribute value group.

  The sales information acquisition unit 134 applies the change candidate information to the learning information and acquires the sales information. The sales information acquisition unit 134 applies the attribute value group acquired by the attribute value group acquisition unit 131 to the learning information. For example, it is one of (1) to (3) described above.

  The determination unit 135 determines whether the sales status is better as the predetermined condition is satisfied for the sales information corresponding to each of the one or more change candidate information. Such sales information is the sales information acquired by the sales information acquisition unit 134.

The predetermined condition is, for example, the following (a) or (b).
(A) The sales information acquisition unit 134 is information on a sales situation better than the sales information acquired using the attribute value group acquired by the attribute value group acquisition unit 131 (for example, “sales corresponding to change candidate information” Information> Sales information acquired using the attribute value group acquired by the attribute value group acquiring unit 131 ”)
(B) Sales information acquired by the sales information acquisition unit 134 using the attribute value group acquired by the attribute value group acquisition unit 131 is information that has a good sales situation that is more than or equal to a threshold value times or more than the threshold value ( For example, “sales information corresponding to change candidate information> (sales information acquired using the attribute value group acquired by the attribute value group acquiring unit 131) × N (N is a real number of 1 or more)”)

  The output unit 14 outputs sales information. The output unit 14 may output one or more candidate values included in the change candidate information when the determination unit 135 determines that the sales situation is good.

  Here, the output is, for example, transmission to an external device such as the terminal device 2, but display on a display, projection using a projector, output using AR technology, printing on a printer, sound, and the like. The concept may include output, storage in a recording medium, delivery of processing results to another processing device or another program, and the like.

  Further, when the output is delivery of sales information, for example, it is delivery of sales information to the determination unit 135.

  Various information is stored in the terminal storage unit 21 constituting the terminal device 2. The various types of information are, for example, user identifiers that identify users. The various information is information received by the terminal receiving unit 25, for example. The user identifier may be information for identifying the terminal device 2.

  The terminal reception unit 22 receives various instructions and information. The various instructions and information are, for example, a proposal instruction, a sales prediction instruction, and evaluation target information. Here, reception means reception of information input from an input device such as a keyboard, mouse, touch panel, reception of information transmitted via a wired or wireless communication line, recording on an optical disk, magnetic disk, semiconductor memory, or the like. It is a concept including reception of information read from a medium.

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

  The terminal processing unit 23 is, for example, a process that configures information received by the terminal receiving unit 25 into data to be displayed. The various types of processing are, for example, processing configured as an instruction to transmit an instruction received by the terminal reception unit 22 or the like.

  The terminal transmission unit 24 transmits various instructions and information to the information processing apparatus 1. The various instructions and information are, for example, instructions configured by the terminal processing unit 23, instructions and information received by the terminal receiving unit 22, and the like.

  The terminal receiving unit 25 receives various types of information from the information processing apparatus 1. The various types of information are, for example, sales information and one or more attribute values.

  The terminal output unit 26 outputs various information. The various types of information are, for example, information received by the terminal receiving unit 22, information received by the terminal receiving unit 25, and information configured by the terminal processing unit 23. The various types of information are, for example, sales information and one or more attribute values.

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

  The process in which information is stored in the storage unit 11 or the like is not limited. For example, information may be stored in the storage unit 11 or the like via a recording medium, information transmitted via a communication line or the like may be stored in the storage unit 11 or the like, Alternatively, information input via the input device may be stored in the storage unit 11 or the like.

  The receiving unit 12 and the terminal receiving unit 25 are usually realized by wireless or wired communication means, but may be realized by means for receiving broadcasts.

  The processing unit 13, the attribute value group acquisition unit 131, the candidate value acquisition unit 132, the change candidate information acquisition unit 133, the determination unit 135, the sales information acquisition unit 134, and the terminal processing unit 23 are usually realized by an MPU, a memory, or the like. obtain. The processing procedure of the processing unit 13 or the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  The output unit 14 and the terminal transmission unit 24 are usually realized by wireless or wired communication means, but may be realized by broadcasting means.

  The terminal output unit 26 may be considered as including or not including an output device such as a display or a speaker. The terminal output unit 26 may be implemented by output device driver software, or output device driver software and an output device.

  Next, the operation of the information system A will be described using the flowchart of FIG.

  (Step S <b> 301) The receiving unit 12 determines whether a proposal instruction has been received from the terminal device 2. When the proposal instruction is received, the process goes to step S302, and when the proposal instruction is not received, the process goes to step S304. It is assumed that the proposal instruction has evaluation target information regarding the product to be proposed.

  (Step S302) The processing unit 13 acquires one or more candidate values using the evaluation target information included in the proposal instruction. Such candidate value acquisition processing will be described with reference to the flowchart of FIG.

  (Step S303) The output unit 14 transmits one or more candidate values acquired in Step S302 to the terminal device 2. The process returns to step S301.

  (Step S <b> 304) The receiving unit 12 determines whether a sales prediction instruction is received from the terminal device 2. When the sales forecast instruction is received, the process goes to step S305, and when the sales forecast instruction is not received, the process returns to step S301. It is assumed that the sales prediction instruction has evaluation target information regarding the product for which sales prediction is intended.

  (Step S305) The attribute value group acquisition unit 131 determines whether or not a moving image is included in the evaluation target information included in the sales prediction instruction received in step S304. If a moving image is included, the process proceeds to step S306, and if no moving image is included, the process proceeds to step S308. In addition, when a moving image is included, the case where the information (for example, URL, a file name, etc.) of access to a moving image is included also corresponds.

  (Step S306) The attribute value group acquisition unit 131 acquires a moving image in the evaluation target information included in the sales prediction instruction received in step S304, analyzes the moving image, and acquires one or more moving image attribute values. .

  (Step S307) The attribute value group acquisition unit 131 configures an attribute value group using the one or more moving image attribute values acquired in step S306. Go to step S309. Note that the attribute value group acquisition unit 131 configures an attribute value group, for example, from one or more attribute values in the evaluation target information received in step S304 and one or more moving image attribute values acquired in step S306. .

  (Step S308) The attribute value group acquisition unit 131 configures an attribute value group from one or more attribute values included in the evaluation target information received in step S304.

  (Step S309) The sales information acquisition unit 134 applies the attribute value group configured in step S307 or step S308 to the learning information, and acquires the sales information.

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

  In the flowchart of FIG. 3, the process ends when the power is turned off or the process is terminated.

  Next, an example of the candidate value acquisition process in step S302 will be described with reference to the flowchart of FIG.

  (Step S401) The change candidate information acquisition unit 133 or the like acquires one or more change candidate information. Such change candidate information acquisition will be described with reference to the flowchart of FIG.

  (Step S402) Sales information acquisition part 134 substitutes 1 to counter i.

  (Step S403) The sales information acquisition unit 134 determines whether or not the i-th change candidate information exists among the change candidate information acquired in step S401. If the i-th change candidate information exists, the process goes to step S404. If the i-th change candidate information does not exist, the process goes to step S406.

  (Step S404) The sales information acquisition unit 134 applies the i-th change candidate information to the learning information, and acquires the sales information. Then, the sales information acquisition unit 134 temporarily stores the acquired sales information in a buffer (not shown) in association with the i-th change candidate information.

  (Step S405) The sales information acquisition unit 134 increments the counter i by 1. The process returns to step S403.

  (Step S406) The determination unit 135 determines sales information satisfying a predetermined condition from sales information stored in a buffer (not shown).

  (Step S407) The determination unit 135 acquires one or more candidate values in the change candidate information corresponding to the sales information determined in Step S406. Return to upper process.

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

  (Step S501) The attribute value group acquisition unit 131 acquires an attribute value group. This attribute value group is a product attribute value group corresponding to the proposal instruction.

  (Step S502) The candidate value acquisition unit 132 substitutes 1 for the count i.

  (Step S503) The candidate value acquisition unit 132 determines whether or not “i <= number of changeable attributes”. If “i <= number of changeable attributes” is satisfied, the process goes to step S504, and if not, the process returns to the upper process. Note that the number of attributes that can be changed is stored in the storage unit 11, for example. Here, the candidate value acquisition unit 132 may use all combinations of changeable attribute values.

  (Step S504) The candidate value acquisition unit 132 substitutes 1 for the count j.

  (Step S505) The candidate value acquisition unit 132 determines whether there is a j-th attribute combination of i changeable attribute combinations. If it exists, go to step S506, otherwise go to step S513.

  (Step S506) The candidate value acquisition unit 132 acquires an attribute value identifier of each attribute of i changeable attribute combinations from the attribute value condition storage unit 112.

  (Step S507) The candidate value acquisition unit 132 substitutes 1 for the count k.

  (Step S508) The candidate value acquisition unit 132 determines whether or not there is a kth combination of one or more attribute values corresponding to the one or more attribute value identifiers acquired in Step S506. Judgment is made using an attribute value change condition corresponding to the identifier. If the k-th combination exists, the process goes to step S509, and if not, the process goes to step S512.

  (Step S509) The candidate value acquisition unit 132 sets the k-th combination of one or more attribute values corresponding to the one or more attribute value identifiers acquired in step S506 to attribute values corresponding to the one or more attribute value identifiers. Acquired using the change condition.

  (Step S510) The change candidate information acquisition unit 133 sets the kth combination of one or more attribute values corresponding to the one or more attribute value identifiers acquired in step S506 in the attribute value group acquired in step S501. Replace with each attribute value included in, and obtain change candidate information.

  (Step S511) The candidate value acquisition unit 132 increments the count k by 1. The process returns to step S508.

  (Step S512) The candidate value acquisition unit 132 increments the count j by 1. The process returns to step S505.

  (Step S513) The candidate value acquisition unit 132 increments the count i by one. The process returns to step S503.

  Next, the operation of the terminal device 2 will be described. The terminal reception unit 22 of the terminal device 2 receives various instructions and information from the user. Next, the terminal processing unit 23 configures an instruction to be transmitted from the instruction received by the terminal receiving unit 22 or the like. Next, the terminal transmission unit 24 transmits the configured instruction or the like to the information processing apparatus 1. In response to the transmission, the terminal reception unit 25 receives information from the information processing apparatus 1. Next, the terminal processing unit 23 performs processing for configuring information to be displayed from information received by the terminal receiving unit 25. Next, the terminal output unit 26 outputs information configured by the terminal processing unit 23.

  Hereinafter, a specific operation of the information system A in the present embodiment will be described. A conceptual diagram of the information system A is shown in FIG.

  The attribute value condition storage unit 112 stores the attribute value condition management table shown in FIG. The attribute value condition management table is a table for managing attribute value change conditions for each attribute. The attribute value change condition is information indicating attribute values that can be taken. The attribute value condition management table has records having “ID”, “attribute identifier”, and “attribute value change condition” as many as the number of attributes that can be changed. “ID” is information for identifying a record. The “attribute identifier” is an attribute name here. The “attribute value change condition” is a set of candidate values that can be taken here, but may be any information as long as candidate values can be acquired, such as information indicating a range. In FIG. 6, there are two records, but three or more records may exist.

  The storage unit 11 stores a product information management table shown in FIG. The product information management table manages two or more product information. The product information management table includes “ID”, “product image”, “product itself attribute value”, “product name”, “product description”, and “moving image”. “ID” is an ID of product information. The “product itself attribute value” here includes “price”, “color”, and the like. “Product name” is the name of the product. “Product description” is a character string describing the product. “Movie” is a CM movie that advertises a product.

  In this situation, the following two specific examples will be described. Specific example 1 is a sales prediction process using learning information. Specific example 2 is a process for proposing a change of one or more attribute values so that the sales situation is improved.

(Specific example 1)
Now, the learning information storage unit 111 stores learning information. Such learning information stores learning information created by learning a large number of sets of one or more moving image attribute values extracted from a CM moving image of a car, and the product itself attribute values and sales information. The sales information here is the number of sales. The sales information may be the total sales amount.

  Then, it is assumed that the user wants to predict the sale of the product, and has input the evaluation target information having the product ID “1” to the terminal device 2. Then, the terminal reception unit 22 receives the evaluation target information having the ID “1”. Next, the terminal processing unit 23 constitutes a sales prediction instruction including evaluation target information transmitted from the evaluation target information received by the terminal receiving unit 22. Next, the terminal transmission unit 24 transmits the sales prediction instruction to the information processing apparatus 1.

  Next, the reception unit 12 of the information processing apparatus 1 receives a sales prediction instruction having the product ID “1” from the terminal device 2.

  Next, the reception unit 12 acquires the product ID “1” from the received sales prediction instruction. Next, the reception unit 12 acquires the product attribute value “price: 2.5 million yen, color: black,...” And a moving image from the record of FIG. 9 identified by the product ID “1”. Then, the reception unit 12 passes the attribute value “price: 2.5 million yen, color: black,...” And the moving image to the attribute value group acquisition unit 131.

  Next, the attribute value group acquisition unit 131 analyzes the passed moving image and acquires one or more moving image attribute values. Here, the attribute value group acquisition unit 131 sets the video attribute values such as the video time “30 seconds”, “spatial resolution = 4K”, “time resolution = 30 fields / second”, presence / absence of performer “no“ 0 ””, and the like. Suppose that it was acquired. Then, the attribute value group acquisition unit 131 uses the product itself attribute value “price: 2.5 million yen, color: black,...” Passed from the reception unit 12 and the acquired one or more moving image attribute values. The attribute value group is configured. This attribute value group is a vector.

  Next, it is assumed that the sales information acquisition unit 134 acquires the sales information “8210 units” by applying the configured attribute value group vector to the learning information.

  Next, the output unit 14 transmits the acquired sales information “8210 units” to the terminal device 2. The transmitted information includes product information corresponding to the product ID “1”.

  Next, the terminal receiving unit 25 of the terminal device 2 receives information including the sales information “8210 units” from the information processing device 1. Next, the terminal processing unit 23 performs processing for configuring information to be displayed from information received by the terminal receiving unit 25. Next, the terminal output unit 26 outputs information configured by the terminal processing unit 23. An example of such output is shown in FIG.

(Specific example 2)
In specific example 2, it is assumed that the storage unit 11 stores the number of changeable attributes “2”.

  Then, it is assumed that the user wants to increase the sales volume of “CarX” and inputs a proposal instruction having evaluation target information having the product ID “1” to the terminal device 2. Then, the terminal reception part 22 receives the proposal instruction | indication which has ID "1". Next, the terminal processing unit 23 configures a proposal instruction that is transmitted from the proposal instruction received by the terminal reception unit 22. Next, the terminal transmission unit 24 transmits the proposal instruction to the information processing apparatus 1. The proposal instruction has ID “1”.

  Next, the receiving unit 12 of the information processing apparatus 1 receives a proposal instruction having the product ID “1” from the terminal device 2.

  Next, the reception unit 12 acquires the product ID “1” from the received proposal instruction. Next, the reception unit 12 acquires the product itself attribute value “price: 2.5 million yen, color: black,...” And a moving image from the record identified by the product ID “1”. Then, the reception unit 12 passes the product itself attribute value “price: 2.5 million yen, color: black,...” And a moving image to the processing unit 13.

  Next, the attribute value group acquisition unit 131 analyzes the moving image included in the record identified by the product ID “1”, and acquires one or more moving image attribute values. Here, the attribute value group acquisition unit 131 sets the video attribute values such as the video time “30 seconds”, “spatial resolution = 4K”, “time resolution = 30 fields / second”, presence / absence of performer “no“ 0 ””, and the like. Suppose that it was acquired. Then, the attribute value group acquisition unit 131 uses the product itself attribute value “price: 2.5 million yen, color: black,...” Passed from the reception unit 12 and the acquired one or more moving image attribute values. The attribute value group is configured and stored in a buffer (not shown). This attribute value group is a vector. Further, vectors of attribute value groups stored in such a buffer (not shown) are included in FIG.

  Further, with reference to FIG. 6, the candidate value acquisition unit 132 refers to the attribute value change condition “15 seconds, 30 seconds” of the attribute value “video time” and the attribute value change condition of “performer presence / absence” that is the attribute value Acquire “present“ 1 ”, no [0]”. Then, the candidate value acquisition unit 132 determines from the candidate values “15 seconds, 30 seconds” of the moving image time acquired by the attribute value group acquisition unit 131 and “Yes“ 1 ”, no [0]” of presence / absence of the performer ( The attribute value group acquisition unit 131 acquires (movie time) from the combinations (30 seconds, 0), (15 seconds, 0), (30 seconds, 1), and (15 seconds, 1) of the movie time and performer presence / absence. , Presence / absence of performers), three combinations (15 seconds, 0), (30 seconds, 1), and (15 seconds, 1) are acquired.

  Then, the candidate value acquisition unit 132 acquires three pieces of change candidate information using the three combinations and the set of fixed attribute values acquired by the attribute value group acquisition unit 131, and accumulates them in a buffer (not shown). . Note that the vector of attribute value groups stored in the buffer (not shown) is included in FIG.

  FIG. 9 manages records having “ID”, “change candidate value”, and “attribute value group”. “ID” is information for identifying a record. “Change candidate value” manages only the attribute value that changes for the current product information. Here, the “change candidate value” is the moving image time and / or presence / absence of a performer. “-” In the “change candidate value” indicates that there is no change. The “attribute value group” is a vector applied to the learning information, and includes “change candidate values”.

  In FIG. 9, the attribute value group of “ID = 1” is an attribute value group corresponding to the product ID “1”. The attribute value group of “ID = 2 to 4” is the change candidate information acquired by the change candidate information acquisition unit 133.

  Next, it is assumed that the sales information acquisition unit 134 applies the attribute value group of “ID = 1” in FIG. 9 to the learning information, acquires the sales information “8210”, and stores it in a buffer (not shown).

  Further, it is assumed that the sales information acquisition unit 134 applies the attribute value group of “ID = 2” in FIG. 9 to the learning information, acquires the sales information “10025”, and stores it in a buffer (not shown).

  Further, it is assumed that the sales information acquisition unit 134 applies the attribute value group of “ID = 3” in FIG. 9 to the learning information, acquires the sales information “8260”, and stores it in a buffer (not shown).

  Furthermore, it is assumed that the sales information acquisition unit 134 applies the attribute value group of “ID = 4” in FIG. 9 to the learning information, acquires the sales information “12750 units”, and stores it in a buffer (not shown).

  Next, the determination unit 135 determines that the sales information satisfying a predetermined condition (the most sales number) among the sales information stored in a buffer (not shown) is “12750”. To do.

  Next, the determination unit 135 determines the moving image time “15 seconds” from the “change candidate value” in the change candidate information that is the record of “ID = 4” in FIG. 9 corresponding to the determined sales information “12750 units”. , Appearance presence / absence “1” is acquired.

  Next, the output unit 14 transmits the acquired candidate value (video time “15 seconds”, presence / absence of performer “1”) and sales information “12750” to the terminal device 2. The information to be transmitted also includes product information corresponding to the product ID “1” and sales information “8210” corresponding to the product ID “1”.

  Next, the terminal receiving unit 25 of the terminal device 2 receives information including the acquired candidate value (video time “15 seconds”, presence / absence of performer “1”) and sales information “12750 units” from the information processing device 1. To do. Next, the terminal processing unit 23 performs processing for configuring information to be displayed from information received by the terminal receiving unit 25. Next, the terminal output unit 26 outputs information configured by the terminal processing unit 23. An example of such output is shown in FIG.

  In the above specific example, the algorithm by which the sales information acquisition unit 134 acquires the sales information is preferably a machine learning algorithm, but may be a method using a correspondence table or the like.

  As mentioned above, according to this Embodiment, the moving image relevant to goods can be evaluated.

  Moreover, according to this Embodiment, the sales information of the goods relevant to a moving image can be estimated.

  Moreover, according to this Embodiment, the change point of the moving image estimated that the sales condition is good can be proposed.

  Moreover, according to this Embodiment, the sales information of the goods relevant to a moving image can be estimated appropriately using a machine learning algorithm.

  Furthermore, according to the present embodiment, it is possible to easily predict the sales information of the product related to the moving image using the correspondence table.

  Note that the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded and distributed on a recording medium such as a CD-ROM. This also applies to other embodiments in this specification. In addition, the software which implement | achieves the information processing apparatus 1 in this Embodiment is the following programs, for example. In other words, this program stores, for example, learning information obtained by learning learning target information including an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information related to the sale of the product. A computer that can access the learning information storage unit, a reception unit that receives evaluation target information including an attribute value group acquired from a video or a video, an attribute value group acquisition unit that acquires an attribute value group from the evaluation target information, This is a program for applying the attribute value group acquired by the attribute value group acquiring unit to the learning information to function as a sales information acquiring unit for acquiring sales information and an output unit for outputting the sales information.

(Embodiment 2)
In the present embodiment, a learning device that acquires the learning information described in the first embodiment will be described.

  FIG. 11 is a block diagram of the learning device 3 in the present embodiment. The learning device 3 includes a receiving unit 12, a storage unit 31, a learning unit 32, and an output unit 33. The storage unit 31 includes a learning information storage unit 111 and a learning target information storage unit 311.

  The learning target information storage unit 311 stores one or more pieces of learning target information. The learning target information is learning target information. The learning target information includes a moving image and sales information. The moving image is a moving image related to the product. The learning target information may include one or more moving image attribute values acquired from the moving image instead of or together with the moving image. Note that the learning target information is, for example, a vector.

  In the learning unit 32, the learning target information storage unit 311 acquires learning information from one or more pieces of learning target information.

  For example, the learning unit 32 learns one or more pieces of learning target information using a machine learning algorithm, and acquires learning information.

  The learning unit 32 configures a correspondence table having one or more pieces of learning target information, for example. The correspondence table usually has two or more correspondence information. The correspondence information is information in which the sales information included in the learning target information is associated with the information group other than the sales information included in the learning target information. The correspondence information is, for example, information having a pair of sales information included in the learning target information and a vector composed of an information group other than the sales information included in the learning target information.

  The output unit 33 outputs the learning information acquired by the learning unit 32. For example, the output unit 33 accumulates the learning information acquired by the learning unit 32 in the learning information storage unit 111.

  The storage unit 31 and the learning target information storage unit 311 are preferably non-volatile recording media, but can also be realized by volatile recording media.

  The process in which information is stored in the storage unit 31 or the like is not limited. For example, information may be stored in the storage unit 31 or the like via a recording medium, information transmitted via a communication line or the like may be stored in the storage unit 31 or the like, Alternatively, information input via the input device may be stored in the storage unit 31 or the like.

  The learning unit 32 and the output unit 33 can be usually realized by an MPU, a memory, or the like. The processing procedure of the learning unit 32 or the like is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  Next, a first operation example of the learning device 3 will be described using the flowchart of FIG.

  (Step S1201) The learning unit 32 substitutes 1 for a counter i.

  (Step S1202) The learning unit 32 determines whether or not the i-th learning target information exists in the learning target information storage unit 311. If the i-th learning target information exists, the process goes to step S1202, and if not, the process goes to step S1205.

  (Step S1203) The learning unit 32 reads out the i-th learning target information from the learning target information storage unit 311, constructs a vector using the learning target information, and temporarily stores it in a buffer (not shown). The vector is, for example, (sales information, first video attribute value, second video attribute value, ..., nth video attribute value, ..., first product itself attribute value, second product Own attribute value,..., M-th product itself attribute value). That is, the vector has, for example, n (n is 1 or 2 or more) moving image attribute values. Further, it is preferable that the vector has m (m is 1 or 2 or more) product itself attribute values.

  (Step S1204) The learning unit 32 increments the counter i by one. The process returns to step S1202.

  (Step S1205) The learning unit 32 receives one or more vectors stored in a buffer (not shown) as an input, learns by a machine learning algorithm, and acquires learning information. The machine learning algorithm may be any of deep learning, SVR, random forest, decision tree, etc. as described above. The learning information outputs sales information when a vector having information other than sales information as an input is input.

  (Step S1206) The output unit 33 accumulates the learning information acquired in step S1205 in the learning information storage unit 111. End the process.

  Next, a second operation example of the learning device 3 will be described using the flowchart of FIG. In the flowchart of FIG. 13, the description of the same steps as those in the flowchart of FIG. 12 is omitted.

  (Step S1301) The learning unit 32 acquires sales information from the i-th learning target information in the learning target information storage unit 311.

  (Step S1302) The learning unit 32 constructs a vector from information other than the sales information of the i-th learning target information in the learning target information storage unit 311.

  (Step S1303) The learning unit 32 configures correspondence information including the sales information acquired in Step S1301 and the vector configured in Step S1302.

  (Step S1304) The learning unit 32 adds the correspondence information configured in step S1303 to the correspondence table.

  (Step S1305) The learning unit 32 increments the counter i by one. The process returns to step S1202.

  As described above, according to the present embodiment, learning information can be acquired.

  Note that the learning device 3 according to the present embodiment starts the operation when the reception unit 12 receives an operation start instruction, for example.

  Moreover, the software which implement | achieves the learning apparatus 3 in this Embodiment is the following programs, for example. That is, this program, for example, uses a computer that can access a learning target information storage unit in which one or more learning target information having a moving image related to a product and sales information related to the sale of the product is stored. This is a program for learning learning target information using a machine learning algorithm and functioning as a learning unit that acquires learning information and an output unit that outputs the learning information.

  FIG. 14 shows the external appearance of a computer that executes the program described in this specification to realize the information processing apparatus 1 and the like according to the various embodiments described above. The above-described embodiments can be realized by computer hardware and a computer program executed thereon. FIG. 14 is an overview diagram of the computer system 300, and FIG. 15 is a block diagram of the system 300.

  In FIG. 14, a computer system 300 includes a computer 301 including a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

  In FIG. 15, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as a bootup program, and the MPU 3013. It includes a RAM 3016 for temporarily storing application program instructions and providing a temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card that provides connection to a LAN.

  A program that causes the computer system 300 to execute the functions of the information processing apparatus 1 and the like of the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. . Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored in the hard disk 3017. The program is loaded into the RAM 3016 at the time of execution. The program may be loaded directly from the CD-ROM 3101 or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 301 to execute the functions of the information processing apparatus 1 according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 300 operates is well known and will not be described in detail.

  Further, the computer that executes the program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

  Further, in each of the above embodiments, it goes without saying that two or more communication units existing in one apparatus may be physically realized by one medium.

  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 a plurality of devices.

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

  As described above, the information processing apparatus according to the present invention has an effect of being able to evaluate a moving image related to a product, and is useful as a moving image evaluation apparatus or the like.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 2 Terminal apparatus 3 Learning apparatus 11, 31 Storage part 12 Reception part 13 Processing part 14, 33 Output part 21 Terminal storage part 22 Terminal reception part 23 Terminal processing part 24 Terminal transmission part 25 Terminal reception part 26 Terminal output part 32 learning unit 111 learning information storage unit 112 attribute value condition storage unit 131 attribute value group acquisition unit 132 candidate value acquisition unit 133 change candidate information acquisition unit 134 sales information acquisition unit 135 determination unit 311 learning target information storage unit

Claims (10)

A learning information storage unit that stores learning information obtained by learning learning target information including an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information related to the sale of the product;
A reception unit for receiving evaluation target information including an attribute value group acquired from a video or a video;
An attribute value group acquisition unit for acquiring an attribute value group from the evaluation target information;
Applying the attribute value group acquired by the attribute value group acquisition unit to the learning information, a sales information acquisition unit for acquiring sales information;
An information processing apparatus comprising: an output unit that outputs the sales information. The attribute value group is:
The information processing apparatus according to claim 1, comprising a moving image attribute value that is an attribute value of a moving image, or a product attribute value that is an attribute value of the moving image attribute value and the product itself. A candidate value acquisition unit that acquires candidate values that are candidates for attribute values of one or more of the two or more attributes corresponding to the attribute value group;
Change that acquires one or more change candidate information by replacing one or more attribute values in the attribute value group acquired by the attribute value group acquisition unit with one or more candidate values acquired by the candidate value acquisition unit A candidate information acquisition unit,
The sales information acquisition unit
Applying each of the one or more change candidate information acquired by the change candidate information acquisition unit to the learning information and acquiring sales information for each of the one or more change candidate information,
The sales information corresponding to each of the one or more change candidate information further includes a determination unit that determines whether or not the sales status is good enough to satisfy a predetermined condition,
The output unit is
The information processing apparatus according to claim 1, wherein the determination unit outputs one or more candidate values included in the change candidate information when it is determined that the sales situation is good. The learning information is information acquired from the learning target information by a machine learning algorithm,
The sales information acquisition unit
The information processing apparatus according to claim 1, wherein the attribute value group acquired by the attribute value group acquisition unit is applied to the learning information by a machine learning algorithm to acquire sales information. The learning information has two or more correspondence information including sales information and attribute value groups,
The sales information acquisition unit
The attribute value group that is closest to the attribute value group acquired by the attribute value group acquisition unit is determined from the learning information, and sales information that is paired with the attribute value group is acquired. The information processing apparatus according to item. A learning target information storage unit in which one or more learning target information having a video related to the product and sales information related to the sale of the product is stored;
A learning unit that learns the one or more pieces of learning target information using a machine learning algorithm, and acquires learning information;
A learning apparatus comprising: an output unit that outputs the learning information. A learning information storage unit for storing learning information obtained by learning learning target information including an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information related to the sale of the product; And an information processing method realized by an attribute value group acquisition unit, a sales information acquisition unit, and an output unit,
A receiving step in which the receiving unit receives the evaluation target information including a moving image or an attribute value group acquired from the moving image;
The attribute value group acquisition unit acquires an attribute value group from the evaluation target information, and
The sales information acquisition unit applies the attribute value group acquired by the attribute value group acquisition unit to the learning information, and acquires sales information; and
An information processing method, wherein the output unit includes an output step of outputting the sales information. A learning information production method realized by a learning object information storage unit storing one or more learning object information having a video related to a product and sales information related to the sale of the product, a learning unit, and an output unit. There,
A learning step in which the learning unit learns the one or more pieces of learning target information by a machine learning algorithm, and acquires learning information;
A learning information production method, wherein the output unit includes an output step of outputting the learning information. Access to a learning information storage unit that stores learning information obtained by learning learning target information having an attribute value group including one or more attribute values acquired from a moving image related to a product and sales information related to the sale of the product Computer
A reception unit for receiving evaluation target information including an attribute value group acquired from a video or a video;
An attribute value group acquisition unit for acquiring an attribute value group from the evaluation target information;
Applying the attribute value group acquired by the attribute value group acquisition unit to the learning information, a sales information acquisition unit for acquiring sales information;
A program for functioning as an output unit for outputting the sales information. A computer accessible to a learning target information storage unit in which one or more learning target information having a video related to the product and sales information related to the sale of the product is stored;
A learning unit that learns the one or more pieces of learning target information using a machine learning algorithm, and acquires learning information;
A program for functioning as an output unit that outputs the learning information.