KR102638234B1 - Electronic devices to predict sales volume of products and method of predicting sales volume of products using thereof - Google Patents

Abstract

A method of predicting sales volume of jewelry products and managing inventory using an electronic device for predicting sales volume of jewelry products and managing inventory includes obtaining metadata of a plurality of jewelry products, the plurality of pieces based on the metadata. It may include obtaining a first predicted sales volume of a first jewelry product among jewelry products, and displaying information about additional production or discontinuation of the first jewelry product based on the first predicted sales volume. .

Description

Electronic devices to predict sales volume of products and method of predicting sales volume of products using the same}

The disclosed embodiments relate to an electronic device for predicting sales volume of jewelry products and managing inventory, and a method for predicting sales volume of jewelry products and managing inventory using the same.

In general, managing product inventory is one of the most important tasks for manufacturers. In particular, it is necessary to always maintain an appropriate level of inventory for products.

Accordingly, manufacturers are using various methods to determine appropriate inventory. For example, a statistical inventory management method is being used to manage inventory based on demand determined according to random variable values, under the assumption that demand follows a normal distribution.
As a prior art document, Patent Publication No. 10-2020-0108521 (Electronic device and control method thereof) can be introduced.
However, this conventional inventory management method has a problem in that it does not sufficiently reflect trends. In particular, conventional inventory management methods have the problem of not being able to properly manage product types.
In other words, the conventional inventory management method does not properly reflect the product's fashion suitability, which affects the sales volume and sales period of the product, and thus there is a problem of the accumulation of malicious inventory due to the inability to discontinue products with poor fashion suitability.

delete

delete

Public Patent Publication No. 10-2020-0108521 (2020.09.21.)

In order to solve the above problems, an electronic device that obtains the fashion suitability of each product and predicts the sales volume of the products based on the obtained fashion suitability, manages inventory of products, and determines the discontinuation period, and sales volume using the same. We intend to disclose embodiments of forecasting and inventory management methods.

As a technical means for achieving the above-described technical problem, an electronic device for predicting sales volume of jewelry products using the disclosed artificial intelligence neural network includes a memory including at least one command, and executing the at least one command, thereby generating a plurality of pieces of jewelry. Obtain metadata of products, obtain a first predicted sales volume of a first jewelry product among the plurality of jewelry products based on the metadata, and add the first jewelry product based on the first predicted sales volume. It may include a processor that generates information on a production plan or information on discontinuation of a product, and a display unit that displays information on an additional production plan or information on discontinuation of the first jewelry product.

As a technical means for achieving the above-described technical problem, the disclosed method of predicting the sales volume of jewelry products using an artificial intelligence neural network includes obtaining metadata of a plurality of jewelry products, based on the metadata. Obtaining a first predicted sales volume of a first jewelry product among a plurality of jewelry products, displaying information about an additional production plan or information about discontinuation of the first jewelry product based on the first predicted sales volume. may include.

In addition, the step of acquiring the metadata includes weighting the number of views of the first jewelry product, the number of reviews of the first jewelry product, and the sales volume of the first jewelry product during a predetermined period of time. and obtaining a fashion suitability of the product, wherein the step of obtaining the first predicted sales volume comprises: obtaining the first predicted sales volume based on a correlation between the fashion suitability of the first jewelry product and the sales volume of the first jewelry product; It may include the step of obtaining sales volume.

In addition, the step of obtaining the first predicted sales volume includes obtaining a first trend graph representing the fashion suitability of the first jewelry product over time, and obtaining a first sales volume graph representing the sales volume of the first jewelry product over time. Obtaining, based on the characteristics of the first trend graph and the characteristics of the first sales graph, obtaining first correlation data indicating a correlation between the first trend graph and the first sales graph, and It may include obtaining the first predicted sales volume based on the first correlation data.

In addition, the displaying step includes identifying the first jewelry product as a discontinued product based on a result of comparing the first predicted sales volume and the inventory amount of the first jewelry product, and displaying the identified result. may include.

In addition, the displaying step includes identifying the first jewelry product as a discontinued product based on at least one of the slope of the first trend graph and the slope of the first sales graph, and displaying the identified result. May include steps.

In addition, the displaying step may include obtaining information about a sales trend of the first jewelry product from the slope of the first sales volume graph, and information about a fashion suitability trend of the first jewelry product from the slope of the first trend graph. Obtaining information and identifying the first jewelry product as a discontinued product based on the information about the sales trend of the first jewelry product and the information about the fashion fit trend, and displaying the identified result. can do.

In addition, the step of acquiring the meta data includes acquiring each external feature of the plurality of jewelry products and connecting the acquired external feature and text information about each attribute of the plurality of jewelry products, thereby metadata A step of generating data, wherein the metadata includes text information about the attributes of each of the plurality of jewelry products and an association between the plurality of jewelry products determined based on each external feature of the plurality of jewelry products. It may contain information about similarity.

In addition, the step of obtaining the first predicted sales volume includes identifying a second jewelry product similar to the first jewelry product based on information about the similarity between the plurality of jewelry products included in the metadata, It may include obtaining information about the sales volume of the second jewelry product, and obtaining the first predicted sales volume based on the information about the sales volume of the second jewelry product.

In addition, the step of obtaining information about the sales volume of the second jewelry product includes obtaining a second sales graph representing sales volume of the second jewelry product over time and obtaining characteristics of the second sales graph. Including, the step of obtaining the first predicted sales volume includes obtaining a first sales graph representing sales volume of the first jewelry product over time, obtaining characteristics of the first sales graph, and the first sales volume graph. It may include obtaining the first predicted sales volume based on the characteristics of the first sales volume graph and the characteristics of the second sales volume graph.

In addition, the step of generating the metadata includes acquiring the properties of each component of the plurality of jewelry products, the properties of each component of the plurality of jewelry products and each property of the plurality of jewelry products. Generating metadata by connecting, wherein the metadata may include a degree of similarity between the plurality of jewelry products obtained based on similarity of attributes of each component of the plurality of jewelry products. .

Additionally, as a technical means for achieving the above-described technical problem, a computer-readable recording medium may record a program for executing at least one of the embodiments of the disclosed method on a computer.

Additionally, as a technical means for achieving the above-described technical problem, an application stored in a recording medium may be used to execute at least one function of the embodiments of the disclosed method.

FIG. 1 is a diagram illustrating an example of a method in which an electronic device manages inventory of each product, according to an embodiment.
Figure 2 is a flowchart of a method by which an electronic device manages inventory of a product, according to an embodiment.
FIG. 3 is a diagram illustrating an example of a method in which an electronic device obtains metadata from the correlation between product attribute data, a sales volume graph, and a trend graph, according to an embodiment.
FIG. 4 is a diagram illustrating an example of a method by which an electronic device obtains characteristics of a sales graph and a trend graph of jewelry products, according to an embodiment.
FIG. 5 is a diagram illustrating an example of a method by which an electronic device obtains characteristics of a sales graph and a trend graph of jewelry products, according to an embodiment.
FIG. 6 is a diagram illustrating an example of a method for an electronic device to predict sales volume of jewelry products, according to an embodiment.
FIG. 7 is a diagram illustrating an example of a method by which an electronic device identifies a jewelry product as being discontinued, according to an embodiment.
FIG. 8 is a diagram illustrating an example of a method by which an electronic device identifies a jewelry product as being discontinued, according to an embodiment.
FIG. 9 is a diagram illustrating an example of a method for an electronic device to predict sales volume of jewelry products, according to an embodiment.
Figure 10 is a block diagram of an electronic device for designing jewelry products, according to one embodiment.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Some embodiments of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented in various numbers of hardware and/or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors, or may be implemented by circuit configurations for certain functions. Additionally, for example, functional blocks of the present disclosure may be implemented in various programming or scripting languages. Functional blocks may be implemented as algorithms running on one or more processors. Additionally, the present disclosure may employ conventional technologies for electronic environment setup, signal processing, and/or data processing. Terms such as “mechanism,” “element,” “means,” and “configuration” may be used broadly and are not limited to mechanical and physical components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

Additionally, connection lines or connection members between components shown in the drawings merely exemplify functional connections and/or physical or circuit connections. In an actual device, connections between components may be represented by various replaceable or additional functional connections, physical connections, or circuit connections.

Additionally, terms including ordinal numbers such as “first” or “second” used in this specification may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

FIG. 1 is a diagram illustrating an example of a method in which an electronic device manages inventory of each product, according to an embodiment.

Referring to FIG. 1 , the electronic device 10 may display results of predicting the sales volume of each jewelry product and information regarding additional production or discontinuation of each jewelry product.

Jewelry products refer to a series of accessories (e.g. rings, earrings, necklaces, bracelets, anklets) used to adorn the body. For example, jewelry products include not only jewelry containing precious stones and jewelry containing metal, but also a series of accessories made of various materials used to decorate the body.

The electronic device 10 may include a computing device such as a mobile device (eg, a smartphone, a tablet PC, etc.), a general-purpose computer (PC), or a server, including an artificial intelligence neural network. In addition, the electronic device 10 is a mobile device (e.g., smartphone, tablet PC, etc.) that can transmit and receive data through a server and network including an artificial intelligence neural network, a general-purpose computer (PC, personal computer), etc. May include a computing device.

An artificial intelligence neural network may be created by learning a plurality of text data and image data input as learning data according to a predetermined standard. An artificial intelligence neural network may include a plurality of models trained to perform at least one function. For example, the artificial intelligence neural network may include a metadata generation model, a graph feature acquisition model, a graph generation model, a sales volume prediction model, and a discontinued product judgment model. The artificial intelligence neural network can generate result data by performing learned functions in response to data received from the electronic device 10, and output the result data to the electronic device 10.

According to one embodiment, an artificial intelligence neural network may exist in the form of a processor. The processor may include at least one processor that is generally used (eg, CPU, application processor) and at least one processor manufactured to perform the function of an artificial intelligence neural network.

According to one embodiment, an artificial intelligence neural network may exist in the form of a software module. A processor manufactured to perform the functions of a general-purpose processor or artificial intelligence neural network can use an artificial intelligence neural network in the form of a software module by executing instructions.

According to one embodiment, the artificial intelligence neural network may be included in the server. The electronic device 10 transmits the input data received from the user to the server, and receives data related to the results of predicting the sales volume of each jewelry product output from the server and information about additional production or discontinuation of each jewelry product. can do. The server may apply data received from the electronic device 10 to the artificial intelligence neural network and transmit data output from the artificial intelligence neural network to the electronic device 10.

According to one embodiment, an artificial intelligence neural network may be included in the electronic device 10. The electronic device 10 can store and use data constituting an artificial intelligence neural network in its internal memory. For example, the electronic device 10 can receive data constituting an artificial intelligence neural network from a server, thereby storing and using the artificial intelligence neural network in its internal memory. Additionally, the electronic device 10 may receive data for updating the artificial intelligence neural network from the server.

Artificial intelligence neural networks can generate metadata. Metadata refers to data in which text information and image features are linked to each other. Metadata may include data in which text information and image features are linked in a many-to-many manner, data linked to each other in text information, and data linked to each other in image features. Additionally, metadata may include data about weights assigned to text information and image features linked to each other. Additionally, artificial intelligence neural networks can update metadata by changing the weights assigned to text information and image features. Metadata may include data linking attribute data and image features of the jewelry product.

The artificial intelligence neural network can predict the sales volume of each jewelry product and output information about the predicted sales volume to the electronic device 10. For example, the artificial intelligence neural network can output information on the predicted sales volume of each jewelry product obtained from each sales volume graph of jewelry products and a trend graph regarding fashion suitability to the electronic device 10.

According to one embodiment, the artificial intelligence neural network provides information about the first predicted sales volume at which the first jewelry product among the plurality of jewelry products will be sold during a predetermined period in the future based on metadata obtained from each of the plurality of jewelry products. can be obtained and output to the electronic device 10.

For example, the artificial intelligence neural network determines the fashion suitability of the first jewelry product by weighting the number of views of the first jewelry product, the number of reviews of the first jewelry product, and the sales volume of the first jewelry product during a predetermined period of time in the past. Obtaining, based on the correlation between the fashion suitability of the first jewelry product and the sales volume of the first jewelry product, information regarding the first predicted sales volume at which the first jewelry product will be sold during a predetermined period in the future, the electronic device It can be output as (10).

In addition, the artificial intelligence neural network creates a first trend graph and A correlation between the first sales volume graph can be obtained. The artificial intelligence neural network obtains information about the predicted sales volume that the first jewelry product will be sold during a predetermined period in the future based on the correlation between the first trend graph and the first sales volume graph, and outputs it to the electronic device 10. You can.

In addition, the artificial intelligence neural network can identify the first jewelry product as a discontinued product based on the result of comparing the predicted sales volume and the inventory amount of the first jewelry product and output the information to the electronic device 10.

Additionally, the artificial intelligence neural network may identify the first jewelry product as a discontinued product based on at least one of the slope of the first trend graph and the slope of the first sales volume graph, and output the information to the electronic device 10.

In addition, the artificial intelligence neural network is based on information about the sales trend of the first jewelry product obtained from the slope of the first sales volume graph and information about the fashion suitability trend of the first jewelry product obtained from the slope of the first trend graph, The first jewelry product may be identified as a discontinued product and output to the electronic device 10.

In addition, the artificial intelligence neural network generates metadata containing information about the similarity between multiple jewelry products by connecting the external characteristics of each jewelry product and text information about each attribute of the multiple jewelry products. can do. The artificial intelligence neural network can identify a second jewelry product similar to the first jewelry product based on information about the similarity between a plurality of jewelry products included in the metadata. The artificial intelligence neural network can obtain information about the predicted sales volume of the first jewelry product to be sold during a predetermined period in the future, based on information about the sales volume of the second jewelry product, and output the information to the electronic device 10.

In addition, the artificial intelligence neural network determines whether the first jewelry product is Information on predicted sales volume to be sold during a predetermined period in the future can be obtained and output to the electronic device 10.

In addition, the artificial intelligence neural network connects the properties of each component of a plurality of jewelry products with the properties of each component of the multiple jewelry products, thereby connecting multiple jewelry products based on the similarity of the properties of each component of the multiple jewelry products. Metadata containing the similarity can be generated. The artificial intelligence neural network can identify a second jewelry product similar to the first jewelry product based on information about the similarity between a plurality of jewelry products included in the metadata. The artificial intelligence neural network can obtain information about the predicted sales volume of the first jewelry product to be sold during a predetermined period in the future, based on information about the sales volume of the second jewelry product, and output the information to the electronic device 10.

According to the disclosed embodiment, the electronic device 10 outputs information on the predicted sales volume of each of the plurality of jewelry products to be sold during a predetermined period in the future, thereby allowing the user to determine the quantity to be additionally produced for each of the jewelry products. Or it can help you decide to discontinue a product.

Figure 2 is a flowchart of a method by which an electronic device manages inventory of a product, according to an embodiment.

Referring to step S210 of FIG. 2, the electronic device 10 may obtain metadata of a plurality of jewelry products.

According to one embodiment, the electronic device 10 may use an artificial intelligence neural network to obtain metadata linked to image characteristics of a plurality of jewelry products and text information about the attributes of the jewelry products.

For example, the electronic device 10 applies the image of each of the plurality of jewelry products to an artificial intelligence neural network to generate metadata linking the classified attributes as shown in Table 1 and the external characteristics of each of the plurality of jewelry products. It can be obtained.

According to one embodiment, the electronic device 10 may acquire metadata including the fashion suitability of the first jewelry product based on the consumer's response to the first jewelry product over a predetermined period of time.

For example, the electronic device 10 may obtain the first jewelry product by weighting the number of times consumers have viewed the first jewelry product, the number of reviews written for the first jewelry product, and the sales volume of the first jewelry product during a predetermined period of time. 1 Metadata including the fashion suitability of jewelry products can be obtained.

According to one embodiment, the electronic device 10 may obtain metadata linking the fashion suitability of the first jewelry product and attribute data of the first jewelry product. Additionally, the electronic device 10 may obtain metadata linking the attribute data of each component constituting the first jewelry product and the fashion suitability of the first jewelry product.

According to one embodiment, the electronic device 10 acquires metadata containing information about the similarity of each of the plurality of jewelry products based on text information about the external characteristics and attributes of each of the plurality of jewelry products. You can. Additionally, the electronic device 10 may obtain metadata including information about the similarity of each of the plurality of jewelry products based on information about the properties of each component of the plurality of jewelry products.

According to one embodiment, the electronic device 10 may update metadata every predetermined period. The electronic device 10 may acquire each fashion suitability of a plurality of jewelry products and obtain metadata in which the obtained fashion suitability is updated.

Referring to step S230 of FIG. 2, the electronic device 10 may obtain information about the first predicted sales volume of the first jewelry product among the plurality of jewelry products.

According to one embodiment, the electronic device 10 uses an artificial intelligence neural network to display characteristics of a first trend graph representing the fashion suitability of the first jewelry product over time and a graph representing the sales volume of the first jewelry product over time. 1 Based on the characteristics of the sales volume graph, information regarding the first predicted sales volume of the first jewelry product during a predetermined period may be obtained.

For example, the electronic device 10 may acquire the characteristics of the first trend graph and the characteristics of the first sales volume graph using an artificial intelligence neural network. The electronic device 10 may acquire first correlation data indicating the correlation between the first trend graph and the first sales volume graph using an artificial intelligence neural network. The electronic device 10 may infer and obtain the first sales volume graph for a predetermined period from the first correlation data using an artificial intelligence neural network. The electronic device 10 may obtain information about the first predicted sales volume from a graph of the first sales volume for a predetermined period.

According to one embodiment, the electronic device 10 may identify a second jewelry product similar to the first jewelry product based on the similarity of each of the plurality of jewelry products included in the metadata. The electronic device 10 may obtain information about the first predicted sales volume of the first jewelry product based on the sales volume, fashion suitability, and second predicted sales volume of the second jewelry product during a predetermined period.

Referring to step S250 of FIG. 2, the electronic device 10 may display information about additional production or discontinuation of the first jewelry product.

According to one embodiment, the electronic device 10 obtains information about additional production or discontinuation of the first jewelry product based on a result of comparing the first predicted sales volume of the first jewelry product and the inventory amount of the first jewelry product. , information regarding additional production or discontinuation of the first jewelry product may be displayed.

For example, when the electronic device 10 compares the first predicted sales volume obtained using an artificial intelligence neural network with the inventory amount of the first jewelry product and determines that the inventory of the first jewelry product will not be sold for a predetermined period of time, 1 Jewelry products can be identified and displayed as products subject to discontinuation.

For another example, if the first predicted sales volume is more than a predetermined multiple of the inventory amount of the first jewelry product, the electronic device 10 may identify the first jewelry product as an additional production product and identify and display the quantity to be additionally produced. there is.

According to one embodiment, the electronic device 10 produces additional or discontinues the first jewelry product based on at least one of the slope of the first trend graph of the first jewelry product and the slope of the first sales volume graph of the first jewelry product. By obtaining information about, information about additional production or discontinuation of the first jewelry product can be displayed.

For example, if the slope of the first sales volume graph is a negative number that is less than or equal to a predetermined value, the electronic device 10 may identify the first jewelry product as a product subject to discontinuation and display it.

For another example, when the slope of the first trend graph is a negative number less than or equal to a predetermined value, the electronic device 10 may identify the first jewelry product as a product subject to discontinuation and display it.

For another example, when the slope of the first sales volume graph is a positive number and the slope of the first trend graph is a negative number less than or equal to a predetermined value, the electronic device 10 determines that the first jewelry product will be sold during a predetermined period. Estimating the predicted sales volume, and based on the results of comparing the first predicted sales volume with the inventory amount of the first jewelry product, identify additional quantities of the first jewelry product to be produced, or identify and display the first jewelry product as a discontinued product. You can.

According to one embodiment, the electronic device 10 uses an artificial intelligence neural network to obtain information about the sales trend of the first jewelry product from the slope of the first sales volume graph and the trend of the first jewelry product from the slope of the first trend graph. Information on compliance trends can be obtained. The electronic device 10 obtains information about additional production or discontinuation of the first jewelry product based on information about the sales trend of the first jewelry product and information about the fashionable trend, thereby adding the first jewelry product. Information about production or discontinuation can be displayed.

For example, the electronic device 10 may determine a sales trend value representing the sales trend of the first jewelry product by comparing the slope value and change in slope of the first sales volume graph over a predetermined period with a predetermined threshold value. .

For another example, the electronic device 10 may use an artificial intelligence neural network to obtain a sales trend line that passes between inflection points of the first sales volume graph. The electronic device 10 may determine a sales trend value representing the sales trend of the first jewelry product by comparing the slope of the sales trend trend line with a predetermined threshold.

For another example, the electronic device 10 compares the slope value and the change in slope of the first trend graph over a predetermined period with a predetermined threshold value to determine a fashion suitability trend value indicating the fashion suitability trend of the first jewelry product. You can decide.

For another example, the electronic device 10 may use an artificial intelligence neural network to obtain a fashionable trend line that passes between the inflection points of the first trend graph. The electronic device 10 may determine a fashion trend value indicating the fashion trend of the first jewelry product by comparing the slope of the fashion trend trend line with a predetermined threshold.

For another example, the electronic device 10 may compare the slopes of each trend graph of a plurality of jewelry products, thereby identifying and displaying a predetermined number of products with low trend graph slopes as discontinued products.

FIG. 3 is a diagram illustrating an example of a method in which an electronic device obtains metadata from the correlation between product attribute data, a sales volume graph, and a trend graph, according to an embodiment.

Referring to FIG. 3 , the electronic device 10 may display an image of the first jewelry product 310, attribute data 320, and graphs 330 related to the first jewelry product 310. The electronic device 10 may display a trend graph 331 indicating the fashion suitability of the first jewelry product 310 and a sales volume graph 333 of the first jewelry product.

The electronic device 10 may obtain information about the sales volume of the first jewelry product 310 during a predetermined period and generate a first sales volume graph 333. For example, the electronic device 10 obtains information about the sales volume of the first jewelry product 310 stored in the DB of the memory/storage unit/server and creates a first sales volume graph 333 showing the sales volume over time. Can be created and displayed.

The electronic device 10 may generate a first trend graph 331 by obtaining information about the fashion suitability of the first jewelry product 310 over a predetermined period of time. For example, the electronic device 10 records the number of times consumers have viewed the first jewelry product 310 during a predetermined period, the number of reviews written for the first jewelry product 310, and the first jewelry product 310. By weighting the sales volume of , a first sales volume graph 333 representing sales volume over time can be generated and displayed.

The electronic device 10 may acquire metadata linking the attribute data 320 of the first jewelry product 310, the characteristics of the first sales volume graph 333, and the characteristics of the first trend graph 331.

According to one embodiment, the electronic device 10 may obtain attribute data 320 of the first jewelry product 310 from the image of the first jewelry product 310 using an artificial intelligence neural network. For example, the electronic device 10 applies the image of the first jewelry product 310 to an artificial intelligence neural network learned to classify the attributes of the jewelry product as shown in Table 1 from the images for each of the plurality of jewelry products, Attribute data 320 of the first jewelry product 310 may be obtained. Additionally, the electronic device 10 may link the image characteristics of the first jewelry product 310 and the attribute data 320 of the first jewelry product 310 using an artificial intelligence neural network.

According to one embodiment, the electronic device 10 may acquire the characteristics of the first sales volume graph 333 and the characteristics of the first trend graph 331 using an artificial intelligence neural network. For example, the electronic device 10 may acquire the curve characteristics of the first sales volume graph 333 and the first trend graph 331 as characteristics of the graphs 330. For another example, the electronic device 10 may obtain the main components of the first sales volume graph 333 and the first trend graph 331 as features of the graphs 330. Additionally, the electronic device 10 may link the characteristics of the first sales volume graph 333 and the characteristics of the first trend graph 331 using an artificial intelligence neural network.

In addition, the electronic device 10 uses an artificial intelligence neural network to link the attribute data 320 of the first jewelry product 310, the characteristics of the first sales graph 333, and the characteristics of the first trend graph 331. , correlation data between the attribute data 320 of the first jewelry product 310 and the first sales volume graph 333 and the first trend graph 331 can be obtained.

FIG. 4 is a diagram illustrating an example of a method by which an electronic device obtains characteristics of a sales graph and a trend graph of jewelry products, according to an embodiment.

Referring to FIG. 4 , the electronic device 10 may acquire the characteristics of the graphs 410 of the first jewelry product using an artificial intelligence neural network and obtain correlation data by linking them.

The electronic device 10 applies the first trend graph 411 of the first jewelry product and the first sales volume graph 413 of the first jewelry product to the artificial intelligence neural network, thereby creating a first trend graph output from the artificial intelligence neural network ( The characteristics of the curve of (421) and the curve of the first sales volume graph (431) can be obtained.

For example, the electronic device 10 applies the first trend graph 421 and the first sales graph 431 to an artificial intelligence neural network using CNN (Convolution Neural Network) technology, thereby creating the first trend graph 421. The characteristics of the curve and the curve of the first sales volume graph 431 can be obtained.

According to one embodiment, the electronic device 10 applies the first trend graph 411 to an artificial intelligence neural network, thereby converting the inflection point 423 and slope 425 of the first trend graph 421 into the first trend graph ( 421) can be obtained using the curve characteristics.

According to one embodiment, the electronic device 10 may obtain the inflection point 433 and slope 435 of the first sales volume graph 431 by applying the first sales volume graph 413 to an artificial intelligence neural network.

The electronic device 10 may obtain correlation data between the first sales graph 431 and the first trend graph 421 from the characteristics of the first sales graph 431 and the characteristics of the first trend graph 421. there is. For example, the electronic device 10 uses an artificial intelligence neural network using CNN (Convolution Neural Network) technology to determine the correlation between the curve characteristics of the first trend graph 421 and the curve characteristics of the first sales volume graph 431. Relationship data can be obtained.

According to one embodiment, the electronic device 10 uses an artificial intelligence neural network to determine the correlation between the inflection points 433 of the first sales graph 431 and the inflection points 423 of the first trend graph 421. , By comparing the correlation between the slope 435 between the inflection points 433 of the first sales volume graph 431 and the slope 425 between the inflection points 423 of the first trend graph 421, the first sales volume Correlation data between the graph 431 and the first trend graph 421 may be obtained.

For example, the electronic device 10 uses an artificial intelligence neural network to generate correlation data about the change in the slope 435 of the first sales graph 431 according to the slope 425 of the first trend graph 421. It can be obtained.

For another example, the electronic device 10 uses an artificial intelligence neural network to determine the correlation between the location of the inflection point 433 of the first sales volume graph 431 according to the location of the inflection point 423 of the first trend graph 421. Relationship data can be obtained.

According to one embodiment, the electronic device 10 may acquire correlation data between the inflection point 433 of the first sales volume graph 431 and the inflection point 423 of the first trend graph 421 every predetermined period. there is. Additionally, the electronic device 10 may obtain correlation data between the slope 435 of the first sales volume graph 431 and the slope 425 of the first trend graph 421 every predetermined period. In this case, the predetermined period may be determined based on the inflection point 433 of the first sales volume graph 431 and the inflection point 423 of the first trend graph 421. Alternatively, the predetermined period may be determined based on the slope 435 of the first sales volume graph 431 and the slope 425 of the first trend graph 421.

FIG. 5 is a diagram illustrating an example of a method by which an electronic device obtains characteristics of a sales graph and a trend graph of jewelry products, according to an embodiment.

Referring to FIG. 5 , the electronic device 10 may obtain a principal component and a principal component coefficient as characteristics of graphs of the first jewelry product.

According to one embodiment, the electronic device 10 applies the first trend graph 511 of the first jewelry product and the first sales volume graph 513 of the first jewelry product to an artificial intelligence neural network, thereby creating a first trend graph ( 521) and the main components of the first sales volume graph 531 can be obtained.

For example, the electronic device 10 performs principal component analysis on the first trend graph 521 and the first sales graph 531, thereby determining the principal components of the first trend graph 521 and the first sales graph 531. can be identified.

Specifically, the electronic device 10 may convert the first trend graph 521 and the first sales graph 531 into grid images 523 and 533, respectively. The electronic device 10 can convert the grid images 523 and 533 into a matrix. The electronic device 10 can calculate the covariance of the matrix. The electronic device 10 may calculate the eigenvectors and eigenvalues of the matrix based on the calculated covariance. The electronic device 10 can identify the main component of the matrix using the eigenvector and eigenvalue.

According to one embodiment, the electronic device 10 has the first trend graph 521 and the first sales volume graph each composed of N grids horizontally (N is a natural number) and M grids vertically (M is a natural number). It can be converted to a grid image (523, 533).

According to one embodiment, the electronic device 10 includes grids corresponding to the curve of the first trend graph 521 and the curve of the first sales graph 531 among the grids constituting the grid images 523 and 533. By entering a value of 1 and entering a value of 0 for the remaining grids, the grid images 523 and 533 can be converted into a matrix.

According to one embodiment, the electronic device 10 may determine each main component and coefficient of the main component of the first trend graph 521 and the first sales graph 531 from the converted matrix.

According to one embodiment, the electronic device 10 displays the first trend graph 521 and the first sales volume based on the main components and coefficients of each of the first trend graph 521 and the first sales volume graph 531. Correlation data of the graph 531 can be obtained.

FIG. 6 is a diagram illustrating an example of a method for an electronic device to predict sales volume of jewelry products, according to an embodiment.

Referring to FIG. 6, the electronic device 10 uses an artificial intelligence neural network to create a first sales volume graph 613 after a certain point in time from correlation data between the first trend graph 611 and the first sales volume graph 613. Can be created and displayed. For example, the electronic device 10 uses GAN (Generative Adversarial Nets) based on correlation data between the first trend graph 611 and the first sales graph 613 obtained using CNN (Convolution Neural Network) technology. ) technology can be used to infer and generate the first sales volume graph 617 after a certain point in time (615).

According to one embodiment, the electronic device 10 uses an artificial intelligence neural network to determine a predetermined level based on correlation data about the change in the slope of the first sales graph 613 according to the slope of the first trend graph 611. The first sales volume graph 617 after the point in time 615 can be inferred and generated.

According to one embodiment, the electronic device 10 uses an artificial intelligence neural network based on correlation data about the location of the inflection point of the first sales graph 613 according to the location of the inflection point of the first trend graph 611. , the first sales volume graph 617 after a predetermined point in time (615) can be inferred and generated.

According to one embodiment, the electronic device 10 is based on correlation data between the inflection point of the first sales volume graph 613 and the inflection point of the first trend graph 611 obtained every predetermined period, after a predetermined point in time. The first sales volume graph 613 can be inferred and generated. In addition, the electronic device 10 displays the first sales volume graph after a predetermined point in time based on correlation data between the slope of the first sales volume graph 613 and the slope of the first trend graph 611 obtained at regular intervals. (613) can be inferred and generated. In this case, the predetermined period may be determined based on the inflection point of the sales volume graph () and the inflection point of the first trend graph 611. Alternatively, the predetermined period may be determined based on the slope of the first sales volume graph 613 and the slope of the first trend graph 611.

According to one embodiment, the electronic device 10 displays the first trend graph 611 and the first sales volume graph 611 obtained based on the main components and coefficients of the main components, respectively, of the first trend graph 611 and the first sales volume graph 613. Based on the correlation data of the sales volume graph 613, the first sales volume graph 617 after a certain point in time (615) can be inferred and generated.

The electronic device 10 may infer the first predicted sales volume from the first sales volume graph 617 after a predetermined point in time (615). Specifically, the first predicted sales volume can be inferred by calculating the area of the first sales volume graph 617.

FIG. 7 is a diagram illustrating an example of a method by which an electronic device identifies a jewelry product as being discontinued, according to an embodiment.

Referring to FIG. 7 , the electronic device 10 may identify the first jewelry product as a product subject to discontinuation based on a result of comparing the first predicted sales volume of the first jewelry product and the inventory amount of the first jewelry product.

According to one embodiment, the electronic device 10 compares the first sales volume graph 717 after a certain point in time (715) obtained using an artificial intelligence neural network with a predetermined threshold value 719, thereby 1 It is possible to predict whether the inventory of jewelry products can be sold. If the electronic device 10 determines that the inventory of the first jewelry product cannot be completed for sale during a predetermined period, it may identify the first jewelry product as a product subject to discontinuation.

According to one embodiment, the electronic device 10 compares the first sales volume graph 717 and a predetermined threshold 719 after a predetermined time point 715, at which point the inventory of the first jewelry product is sold ( 716) can be predicted. The electronic device 10 may identify the first jewelry product as a product to be discontinued based on the time 716 when the inventory of the first jewelry product is completed for sale. Specifically, the electronic device 10 may identify the first jewelry product as a discontinued product if it is not predicted that the inventory of the first jewelry product will be sold within a predetermined period from the date of obtaining the first predicted sales volume. there is.

According to one embodiment, the electronic device 10 may display information about products subject to discontinuation. For example, the electronic device 10 may display the external image of the product to be discontinued, attribute data, inventory amount, predicted sales volume, and information about products similar to the product to be discontinued.

According to one embodiment, the electronic device 10 can identify and display information about appropriate prices for products subject to discontinuation. For example, the electronic device 10 may display a fixed rate discount price for the regular price of a discontinued product based on the difference between the predicted sales volume and inventory amount of the discontinued product. Specifically, when the inventory of the discontinued product is 100 units and the predicted sales volume is 90, the electronic device 10 can identify and display the appropriate price of the discontinued product as 90% of the list price.

FIG. 8 is a diagram illustrating an example of a method by which an electronic device identifies a jewelry product as being discontinued, according to an embodiment.

Referring to FIG. 8, the electronic device 10 identifies the first jewelry product as a product to be discontinued based on the result of comparing the first trend graph 820 of the first jewelry product and the first sales volume graph 830. can do.

According to one embodiment, the electronic device 10 discontinues the first jewelry product based on at least one of the slope 823 of the first trend graph 820 and the slope 833 of the first sales graph 830. It can be identified as a target product and information about the product subject to discontinuation can be displayed.

For example, when the slope 833 of the first sales volume graph 830 is a negative number less than or equal to a predetermined value, the electronic device 10 may identify the first jewelry product as a product subject to discontinuation.

For another example, when the slope 823 of the first trend graph 820 is a negative number less than or equal to a predetermined value, the electronic device 10 may identify the first jewelry product as a product subject to discontinuation.

For another example, when the slope 833 of the first sales volume graph 830 is a positive number and the slope 823 of the first trend graph 820 is a negative number less than or equal to a predetermined value, the electronic device 10 Based on the first sales volume graph 825 after a certain point in time, the first predicted sales volume of the first jewelry product during a certain period of time can be estimated. The electronic device 10 may identify the additional quantity to be produced of the first jewelry product or identify the first jewelry product as a product subject to discontinuation based on the result of comparing the first predicted sales volume and the inventory amount of the first jewelry product. .

According to one embodiment, the electronic device 10 may display information about products subject to discontinuation. Additionally, the electronic device 10 can identify and display information about appropriate prices for products subject to discontinuation. Since the specific contents were described above with reference to FIG. 7, overlapping contents will be omitted.

According to one embodiment, the electronic device 10 stores the first jewelry based on information about the sales trend of the first jewelry product and information about the fashionable trend of the first jewelry product, which are obtained using an artificial intelligence neural network. The product can be identified as a product subject to discontinuation.

For example, the electronic device 10 may display a sales trend value obtained by comparing the slope 833 and the change in slope 833 of the first sales volume graph 830 over a predetermined period with a predetermined threshold. If it is below the threshold, the first jewelry product can be identified as a product subject to discontinuation.

For another example, the electronic device 10 may have a sales trend value obtained by comparing the slope of a sales trend trend line passing between the inflection points 831 of the first sales volume graph 830 with a predetermined threshold value. If it is below the threshold, the first jewelry product can be identified as a product subject to discontinuation.

For another example, the electronic device 10 obtains a fashionable trend value by comparing the slope 823 and the change in slope 823 of the first trend graph 820 over a predetermined period with a predetermined threshold. If the value is below this predetermined threshold, the first jewelry product can be identified as a product subject to discontinuation.

For another example, the electronic device 10 may display a fashionable trend value obtained by comparing the slope of the sales trend trend line passing between the inflection points 821 of the first trend graph 820 with a predetermined threshold value. If the value is below a predetermined threshold, the first jewelry product may be identified as a product subject to discontinuation.

For another example, the electronic device 10 compares the respective sales trend values or fashion fit trend values of a plurality of jewelry products, thereby selecting a predetermined number of jewelry products with small sales trend values or fashion fit trend values as discontinued products. It can be identified as:

For another example, the electronic device 10 may compare the slopes of each trend graph of a plurality of jewelry products, thereby identifying a predetermined number of products with low trend graph slopes as products to be discontinued.

FIG. 9 is a diagram illustrating an example of a method for an electronic device to predict sales volume of jewelry products, according to an embodiment.

Referring to FIG. 9, the electronic device 10 identifies a second jewelry product 930 similar to the first jewelry product 910, and displays the first trend graph 911 of the first jewelry product 910 and the first jewelry product 910. A sales volume graph 913 and a second trend graph 931 and a second sales volume graph 933 of the second jewelry product 930 can be displayed.

According to one embodiment, the electronic device 10 may identify a second jewelry product 930 similar to the first jewelry product 910 using metadata obtained using an artificial intelligence neural network.

For example, the electronic device 10 may provide text information about each attribute of a plurality of jewelry products and information about the degree of similarity between the plurality of jewelry products determined based on the external characteristics of each of the plurality of jewelry products. Based on metadata including, a second jewelry product 930 similar to the first jewelry product 910 may be identified.

For another example, the electronic device 10 may acquire properties of each component of a plurality of jewelry products. The electronic device 10 provides text information about the properties of each component of the plurality of jewelry products and information about the similarity of the properties of each component of the plurality of jewelry products created by linking each property of the plurality of jewelry products. Based on metadata containing information, a second jewelry product 930 similar to the first jewelry product 910 may be identified.

According to one embodiment, the electronic device 10 may obtain the second predicted sales volume of the second jewelry product 930 based on information about the sales volume of the first jewelry product 910.

For example, the electronic device 10 uses an artificial intelligence neural network to compare the characteristics of the first sales volume graph 913 of the first jewelry product 910 and the second sales volume graph 933 of the second jewelry product 930. Correlation data between features can be obtained. In this case, the characteristics of the first sales volume graph 913 and the characteristics of the second sales volume graph 933 may include an inflection point, slope, principal component, and principal component coefficient. The electronic device 10 displays the second jewelry product 930 based on correlation data between the features of the first sales volume graph 913 and the features of the second sales volume graph 933 of the second jewelry product 930. ), the second sales volume graph 933 can be generated, and the second predicted sales volume can be inferred.

For another example, the electronic device 10 may provide information between the features of the first trend graph 911 of the first jewelry product 910 obtained using an artificial intelligence neural network and the features of the first sales graph 913. Correlation data can be obtained. In this case, the characteristics of the first sales graph 913 and the characteristics of the first trend graph 911 may include an inflection point, slope, principal component, and principal component coefficient. The electronic device 10 displays the second trend graph 931 of the second jewelry product 930 based on correlation data between the features of the first sales volume graph 913 and the features of the first trend graph 911. ), the second sales volume graph 933 can be generated, and the second predicted sales volume can be inferred.

According to one embodiment, the electronic device 10 may display the generated second sales volume graph 933.

For example, the electronic device 10 displays images of the first jewelry product 910 and the second jewelry product 930 along with the first trend graph 911 and the first sales volume graph of the first jewelry product 910 ( 913) and a second trend graph 931 and a second sales volume graph 933 of the second jewelry product 930 can be displayed.

Additionally, the electronic device 10 may display a first sales volume graph 913 and a second sales volume graph 933 together with the attribute data of the first jewelry product 910 and the attribute data of the second jewelry product 930. there is.

Figure 10 is a block diagram of an electronic device for designing jewelry products, according to one embodiment.

Referring to FIG. 10 , the electronic device 10 according to some embodiments may include a user input unit 11, an output unit 12, a processor 13, a communication unit 15, and a memory 17. However, not all of the components shown in FIG. 10 are essential components of the electronic device 10. The electronic device 10 may be implemented with more components than those shown in FIG. 10 , or the electronic device 10 may be implemented with fewer components than the components shown in FIG. 10 .

The user input unit 11 refers to a means through which a user inputs data to control the electronic device 10. For example, the user input unit 11 includes a key pad, a dome switch, and a touch pad (contact capacitive type, pressure resistive type, infrared detection type, surface ultrasonic conduction type, and integral type). Tension measurement method, piezo effect method, etc.), touch screen, jog wheel, jog switch, etc., but are not limited to these. The user input unit 11 may receive user input necessary for the electronic device 10 to perform the embodiments described with reference to FIGS. 1 to 9 .

The output unit 12 displays and outputs information processed by the electronic device 10. The output unit 12 may output information related to the embodiments described with reference to FIGS. 1 to 9 . The output unit 12 may include a display unit 12-1 that displays information about an external image of a jewelry product, text data about its attributes, a trend graph, and a sales graph. Additionally, the display unit 12-1 can display information about additional production or discontinuation of jewelry products. The display unit 12-1 may display a user interface (eg, graphic user interface (GUI)) for interaction with the user.

The processor 13 typically controls the overall operation of the electronic device 10. For example, the processor 13 can generally control the user input unit 11, output unit 12, communication unit 15, memory 17, etc. by executing programs stored in the memory 17. .

The processor 13 may control the overall operation of the electronic device 10 to perform the embodiments described above with reference to FIGS. 1 to 9 . For example, the processor 13 may perform the function of the artificial intelligence neural network described above with reference to FIGS. 1 to 9.

The processor may include at least one processor manufactured to perform the function of an artificial intelligence neural network. Alternatively, the processor may be at least one processor that is used for general purposes. The processor 13 can perform the function of an artificial intelligence neural network that exists in the form of a software module by executing a series of instructions stored in the memory 17.

The processor 13 can control the communication unit 15 to perform the function of the artificial intelligence neural network stored in the server 20. The processor 13 can control the communication unit 15 to transmit data to the server 20 in order to perform the function of the artificial intelligence neural network. The processor 13 may control the communication unit 15 to receive data output from the artificial intelligence neural network stored in the server 20. The processor 13 may control the communication unit 15 to receive data for updating the artificial intelligence neural network from the server 20. The processor 13 may execute a series of instructions to enable the artificial intelligence neural network to learn new training data.

The communication unit 15 may include one or more components that allow the electronic device 10 to communicate with other devices (not shown) and the server 20. The other device (not shown) may be a computing device such as, but is not limited to, electronic device 10.

The memory 17 can store programs for processing and control of the processor 13, and can also store data input to or output from the electronic device 10.

The memory 17 is a memory that temporarily stores data such as RAM (Random Access Memory), SRAM (Static Random Access Memory), flash memory type, hard disk type, and multimedia card. Micro type (multimedia card micro type), card type memory (e.g. SD or XD memory, etc.), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) It may include at least one type of data storage that stores data non-temporarily, such as (Only Memory), magnetic memory, magnetic disk, and optical disk.

According to the embodiments of FIGS. 1 to 10, the electronic device 10 acquires the fashion suitability of each jewelry product and predicts the sales volume of the products based on the obtained fashion suitability, thereby influencing the sales volume and sales period of the product. Users can be provided with information related to products subject to discontinuation that reflects the trend suitability of the product.

Some embodiments may also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

Claims (12)

In a method for an electronic device to predict sales volume of jewelry products using an artificial intelligence neural network,
Obtaining metadata of a plurality of jewelry products;
Obtaining a first predicted sales volume of a first jewelry product among the plurality of jewelry products based on the metadata;
Based on the first predicted sales volume, displaying information about additional production or discontinuation of the first jewelry product,
The step of obtaining the first predicted sales volume is,
Obtaining a first trend graph showing the fashion suitability of the first jewelry product over time,
Obtaining a first sales volume graph showing sales volume of the first jewelry product over time,
Converting the first trend graph and the first sales volume graph into grid images, respectively,
Convert the grid image into a matrix,
Obtaining each main component and coefficient of the main component of the first trend graph and the first sales graph from the converted matrix,
Based on the main component and the coefficient of the main component, obtaining first correlation data indicating a correlation between the first trend graph and the first sales graph; and
Comprising: obtaining the first predicted sales volume based on the first correlation data,
method.
According to paragraph 1,
The step of acquiring the metadata is,
Comprising the step of obtaining the fashion suitability of the first jewelry product by weighting the number of views of the first jewelry product, the number of reviews of the first jewelry product, and the sales volume of the first jewelry product during a predetermined period of time. doing,
method.
delete According to paragraph 1,
The display step is,
Identifying the first jewelry product as a discontinued product based on a result of comparing the first predicted sales volume and the inventory amount of the first jewelry product; and
comprising displaying the identified results,
method.
According to paragraph 1,
The display step is,
Identifying the first jewelry product as a discontinued product based on at least one of the slope of the first trend graph and the slope of the first sales volume graph; and
comprising displaying the identified results,
method.
According to clause 5,
The display step is,
Obtain information about the sales trend of the first jewelry product from the slope of the first sales volume graph,
Obtaining information about a fashionable trend of the first jewelry product from the slope of the first trend graph,
Identifying the first jewelry product as a discontinued product based on information about a sales trend and a fashionable trend of the first jewelry product; and
comprising displaying the identified results,
method.
According to paragraph 1,
The step of acquiring the metadata is,
acquiring external characteristics of each of the plurality of jewelry products; and
Generating metadata by linking the obtained external features with text information about each attribute of the plurality of jewelry products,
The metadata includes text information about each attribute of the plurality of jewelry products and information about the degree of similarity between the plurality of jewelry products determined based on the external characteristics of each of the plurality of jewelry products.
method.
In clause 7,
The step of obtaining the first predicted sales volume is,
identifying a second jewelry product similar to a first jewelry product based on information about the degree of similarity between the plurality of jewelry products included in the metadata;
Obtaining information on sales volume of the second jewelry product;
Comprising the step of obtaining the first predicted sales volume based on information about the sales volume of the second jewelry product,
method.
According to clause 8,
The step of obtaining information about the sales volume of the second jewelry product is,
Obtaining a second sales volume graph showing sales volume of the second jewelry product over time; and
Comprising the step of acquiring characteristics of the second sales volume graph,
The step of obtaining the first predicted sales volume is,
Obtaining a first sales volume graph representing sales volume of the first jewelry product over time;
Obtaining characteristics of the first sales volume graph;
Comprising the step of obtaining the first predicted sales volume based on the characteristics of the first sales volume graph and the characteristics of the second sales volume graph,
method.
In clause 7,
The step of generating the metadata is,
acquiring properties of each component of the plurality of jewelry products;
Generating metadata by connecting the properties of each component of the plurality of jewelry products with each property of the plurality of jewelry products,
The metadata includes similarity between the plurality of jewelry products obtained based on similarity of attributes of each component of the plurality of jewelry products,
method.
An application stored in a recording medium that allows an electronic device to perform the following functions for predicting sales of jewelry products using an artificial intelligence neural network, the functions being:
Ability to obtain metadata of multiple jewelry products;
A function of obtaining a first trend graph indicating a fashion suitability over time of a first jewelry product among the plurality of jewelry products;
A function of obtaining a first sales volume graph representing sales volume of the first jewelry product over time;
Converting the first trend graph and the first sales volume graph into grid images, respectively,
Convert the grid image into a matrix,
Obtaining each main component and principal component coefficient of the first trend graph and the first sales graph from the converted matrix,
A function of obtaining first correlation data indicating a correlation between the first trend graph and the first sales volume graph, based on the main component and the coefficient of the main component;
a function of obtaining a first predicted sales volume of the first jewelry product based on the meta data and the first correlation data;
Based on the first predicted sales volume, including a function to display information about additional production plans or information about discontinuation of the first jewelry product,
application.
In an electronic device that predicts sales volume of jewelry products using an artificial intelligence neural network,
a memory containing at least one instruction;
By executing the at least one command, metadata of a plurality of jewelry products is obtained, a first trend graph indicating a fashion suitability of a first jewelry product over time among the plurality of jewelry products is obtained, and the first trend graph is obtained by executing the at least one command. Obtain a first sales graph representing the sales volume of jewelry products over time, convert the first trend graph and the first sales graph into grid images, respectively, convert the grid image into a matrix, and from the converted matrix Obtaining each main component and coefficient of the main component of the first trend graph and the first sales graph, and indicating a correlation between the first trend graph and the first sales graph based on the main component and the coefficient of the main component. Obtain first correlation data, obtain a first predicted sales volume of the first jewelry product based on the meta data and the first correlation data, and obtain a first predicted sales volume of the first jewelry product based on the first predicted sales volume. processors to generate information about further production plans or information about discontinuation of products; and
Comprising a display unit that displays information about additional production plans or information about discontinuation of the first jewelry product,
Electronic devices.

Images