Apparatus and method for providing trend analysis and sales strategies based on global demand prediction

Abstract

The invention provides a device and a method for providing trend analysis and sales strategies based on global demand prediction. The electronic equipment comprises a memory and a processor connected to the memory, in the processor, search history information is received through a search word collection API, the API can collect search history records from a preset homepage operated by a target country / region, and the search history records are stored in the memory. And the recommended product and the recommended attribute value of the recommended product can be exported according to the search history information.

Description

Technical Field

[0001] This invention relates to an apparatus and method for analyzing trends and providing sales strategies based on global demand forecasts. Background Technology

[0002] Unless otherwise stated herein, the materials described in this section are not prior art to the claims of this application and are not acknowledged as prior art by virtue of their inclusion in this section.

[0003] Foreign markets are diverse by region and industry. To enter foreign markets, it is essential to conduct research in advance to determine the characteristics of the product and to develop distribution and sales channels to sell the product.

[0004] However, as mentioned above, it is actually very difficult for SMEs and startups to study the characteristics of foreign markets and develop distribution and sales channels.

[0005] Therefore, the present invention aims to provide a technology that can derive sales strategies that are advantageous for the sale of a product in a specific country by forecasting demand and analyzing trends for each product.

[0006] Existing technical documents

[0007] Patent documents

[0008] Patent Document 1: Korean Patent No. 10-2535118 (May 17, 2023) Summary of the Invention

[0009] The problem that the invention aims to solve

[0010] One embodiment of the present invention provides an apparatus and method for analyzing trends and providing sales strategies based on global demand forecasts.

[0011] The technical problems to be solved by the present invention are not limited to those described above. Those skilled in the art will be able to clearly understand other technical problems not mentioned through the following description.

[0012] means for solving problems

[0013] To achieve the aforementioned objectives, the electronic device according to an embodiment of the present invention includes a memory and a processor connected to the memory. The processor receives search history information via a search item collection API, which can collect search history from a preset homepage operating in the target country and can derive recommended products and recommended attribute values ​​of the recommended products based on the search history information.

[0014] At this point, search history information can include the search terms the user searched on the homepage and the time when those terms were searched.

[0015] At this point, the processor uses the artificial intelligence module to extract product-related search terms from the search history information, and then recommends products and derives recommended attribute values ​​based on these product-related search terms.

[0016] At this point, the processor, through the artificial intelligence module, divides product-related search terms into keyword units, and selects product name keywords and attribute values ​​representing the product name from the keywords contained in the product. It then exports the attribute value keywords representing the relevant search terms, and standardizes the product name keywords and attribute value keywords according to preset standards to obtain standard product name keywords, standard attribute value keywords, and standard product names for a first preset time period. Based on the search volume of these keywords, it derives a first recommendation score for the products indicated by the standard product name keywords, and exports products with a first recommendation score exceeding a preset first critical recommendation score as recommended products.

[0017] At this point, the processor uses the artificial intelligence module to categorize the standard attribute value keywords into attribute categories representing product attribute types, and then derives recommended attribute values ​​for recommended products from these attribute categories. For each recommended attribute category, a second recommendation score is derived for the corresponding standard attribute value keywords. If this second recommendation score exceeds a preset second threshold recommendation score, the standard attribute value keyword is then exported as a recommended attribute.

[0018] At this point, the processor exports the recommended attribute categories for recommended products from the attribute categories, sets the attribute category corresponding to the recommended product as the temporary recommended attribute category, and sets the temporary recommended attribute category as the third. It can export the recommendation score for this category and set the temporary recommended attribute category whose third recommendation score exceeds a preset third threshold recommendation score as the recommended attribute category.

[0019] At this point, the processor, based on the current time, searches for the search volume of the standard product name keywords corresponding to the product used to derive the first recommendation score within the first time period, tracing back to the preset judgment time period. The name keywords indicating the product from the first time period to the judgment time period that yielded the first recommendation score are set as the second search volume, and this is set as the average of the search volumes of all standard products within the first time period. The name keywords are used as the first average search volume, and the average search volume of all standard product name keywords in the second time period is set as the first average search volume, based on the first search volume. The recommendation score is calculated using the second search volume, the first average search volume, the second average search volume, and the first search volume of the product indicated by the standard product name keywords.

[0020] At this point, the first recommendation score is derived from the following equation:

[0021]

[0022] rs1 refers to the first recommendation score, sm_1 refers to the first search volume, sm_2 refers to the second search volume, asm_1 refers to the first average search volume, and asm_2 refers to the second search volume, which can represent the average search volume.

[0023] At this point, the processor derives a second recommendation score for the standard attribute value keywords contained in the recommended attribute category. Specifically, during the first time period, the search volume of the standard product name keyword indicating the recommended product is set as the third search volume, and the search volume of the standard attribute value keyword is set as the fourth search volume. The second recommendation score for the standard attribute value keyword is then set based on the third and fourth search volumes. This process can be deduced.

[0024] At this point, the second recommendation score is obtained by the following formula:

[0025]

[0026] rs2 can represent the second recommendation score, sm_3 can represent the third search volume, and sm_4 can represent the fourth search volume.

[0027] At this point, the processor calculates the third recommendation score for the temporary recommendation attribute category, which includes the total number of standard attribute value keywords contained in the temporary recommendation attribute category during the first time period and the corresponding third recommendation score for the temporary recommendation attribute category. This can be derived from the fifth search volume, which refers to the total search volume of all standard attribute value keywords included within it.

[0028] At this point, the third recommendation score is derived from the following formula:

[0029]

[0030] rs3 refers to the third recommendation score, at refers to the total number of standard attribute value keywords contained in the corresponding temporary recommendation attribute category, and sm_5 can refer to the fifth search volume.

[0031] Invention Effects

[0032] According to one embodiment of the invention, it can provide an apparatus and method for analyzing trends and providing sales strategies based on global demand forecasts.

[0033] The effects that can be obtained by the present invention are not limited to those described above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description. Attached Figure Description

[0034] The above and other aspects, features and advantages of certain preferred embodiments of the present invention will become more apparent.

[0035] Figure 1 A conceptual diagram of an apparatus for analyzing trends and providing sales strategies based on global demand forecasts, according to an embodiment of the present invention, is shown.

[0036] Figure 2 This is a diagram illustrating the derivation of recommended products and recommended attribute values ​​according to an embodiment of the present invention.

[0037] Throughout the accompanying drawings, the same reference numerals are used to indicate the same or similar elements, features, and structures. Detailed Implementation

[0038] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0039] In the embodiments, descriptions of technical content known in the art to which this invention pertains and not directly related to this invention will be omitted. This is to more clearly convey the spirit of the invention, rather than obscuring the spirit of the invention by omitting unnecessary explanations.

[0040] For the same reason, some parts are exaggerated, omitted, or shown schematically in the accompanying drawings. Furthermore, the dimensions of each component do not perfectly reflect its actual size. In each drawing, the same or corresponding parts are assigned the same reference numerals.

[0041] The advantages and features of the invention, as well as methods of implementing them, will become clear from the embodiments described in detail below with reference to the accompanying drawings. However, the invention is not limited to the embodiments disclosed below and can be implemented in various different forms. These embodiments are provided only to ensure that the disclosure of the invention is complete and to provide general knowledge in the art. The invention is provided to fully inform those who understand its scope, and the invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same elements.

[0042] At this point, it should be understood that each block of the flowchart and combinations thereof can be executed by computer program instructions. These computer program instructions can be mounted on the processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, are described in it to create a method for performing a function. These computer program instructions can also be stored in a computer-usable or computer-readable storage medium, which can instruct the computer or other programmable data processing apparatus to perform the function in a particular manner, such that the instructions stored in the computer-usable or computer-readable storage medium can also produce an article of manufacture containing instruction means for performing the function described in the flowchart blocks. The computer program instructions can also be mounted on a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable data processing apparatus to create a process executed by the computer or other programmable data processing apparatus. The instructions for performing the function described in the flowchart blocks can also provide steps for performing the function.

[0043] Additionally, each block can represent a module, segment, or code section containing one or more executable instructions for performing a specified logical function. It should also be noted that in some alternative execution examples, the functions mentioned in the boxes may occur out of order. For example, two boxes shown consecutively may be executed substantially simultaneously, or the boxes may be executed in reverse order depending on their corresponding functions.

[0044] In this embodiment, the term "~unit" refers to a software or hardware component such as an FPGA (Field-Programmable Gate Array) or ASIC (Application-Specific Integrated Circuit), and "~unit" refers to the role that executes them. However, "~part" is not limited to software or hardware. A "~part" can be configured to reside in addressable storage media and can be configured to reproduce one or more processors. Therefore, by way of example, "~part" refers to components such as software components, object-oriented software components, class components and task components, processes, functions, attributes and procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and "parts" can be combined into a smaller number of components and "parts," or can be further divided into additional components and "parts." Additionally, components and "parts" can be implemented to reproduce one or more CPUs within a device or secure multimedia card.

[0045] While the embodiments of this invention primarily focus on examples of specific systems, the key point claimed in this specification is that the scope of this specification applies to other communication systems and services with similar technical backgrounds, and can be applied within a range that is not significantly deviated from, and can be determined by a person skilled in the relevant technical field.

[0046] Figure 1 A conceptual diagram of an apparatus for analyzing trends and providing sales strategies based on global demand forecasts, according to an embodiment of the present invention, is shown.

[0047] See Figure 1 According to embodiments of the present invention, an apparatus for providing trend analysis and sales strategies based on global demand forecasting determines what products and attributes people are searching for in target countries where they want to enter global markets. Through analysis, trends can be inferred, and suggestions can be made regarding which product attributes are suitable for sale.

[0048] Meanwhile, the device used to provide trend analysis and sales strategies based on global demand forecasts may also be referred to as "electronic device 100" in this invention.

[0049] An electronic device 100 of one embodiment includes a processor 110 and a memory 120. The processor 110 can execute at least one of the methods described above. The memory 120 can store information related to the methods described above or store programs implementing the methods described above. The memory 120 can be volatile memory or non-volatile memory. The memory 120 can be referred to as a "database", "storage unit", etc.

[0050] Processor 110 can execute programs and control electronic device 100. The code of the program executed by processor 110 can be stored in memory 120. Device 100 can be connected to external devices (e.g., personal computers or networks) via input / output devices (not shown) and can exchange data.

[0051] At this time, the processor 110 can receive search history information through the search term collection API, which can collect search history from a preset homepage operated by the target country.

[0052] In this case, the homepage could be a portal or shopping mall primarily used by citizens of the target country, and the search term collection API could be an API that provides access to information about the history of search terms on the homepage.

[0053] Information about the search terms users use on the homepage and the times when those terms were searched.

[0054] Additionally, the processor can derive recommended products and their attribute values ​​based on search history information. This will be described in more detail later.

[0055] Figure 2 This is a diagram illustrating the derivation of recommended products and recommended attribute values ​​according to an embodiment of the present invention.

[0056] See Figure 2The processor uses an artificial intelligence module to extract product-related search terms from the search history information. Based on these product-related search terms, it can deduce recommended products and Recommended attribute values.

[0057] At this point, the AI ​​module utilizes deep learning from machine learning to identify which search terms are relevant to the product from search history, and then extracts only the product-related search terms from the search history. A machine learning model capable of performing this task is created.

[0058] Furthermore, the artificial intelligence module can compute the weights of multiple inputs in a function through deep learning. In addition, various models such as RNNs (Recurrent Neural Networks), DNNs (Deep Neural Networks), and DRNNs (Dynamic Recurrent Neural Networks) can be used as AI network models for this type of learning.

[0059] Here, RNN is a deep learning technique that considers both current and past data. A Recurrent Neural Network (RNN) represents a type of neural network where the connections between the units that make up the artificial neural network form a directed loop. Furthermore, various methods can be used to construct RNNs, such as fully recurrent networks, Hopfield networks, Elman networks, ESN (Echo State Network), LSTM (Long Short-Term Memory Network), bidirectional RNNs, CTRNNs (Continuous-Time RNNs), hierarchical RNNs, and quadratic RNNs, all of which are representative examples. Additionally, methods such as gradient descent, Hessian free optimization, and global optimization methods can be used to learn RNNs.

[0060] In addition, the processor can also categorize product-related search terms into keyword units through an artificial intelligence module.

[0061] At this point, word segmentation tools can be used to categorize keywords. Additionally, an artificial intelligence module can be trained to classify product-related search terms composed in the target country's language as keywords based on the language's grammar.

[0062] In addition, the processor can use the artificial intelligence module to derive product name keywords and attribute value keywords that indicate the attribute values ​​of the product name from the keywords included in the product-related search terms.

[0063] For example, the keyword "rug" can be a product name keyword, while the keywords "red" and "big" can be attribute value keywords.

[0064] In addition, the processor can standardize product name keywords and attribute value keywords according to preset standards to obtain standard product name keywords and standard attribute value keywords.

[0065] At this time, the standard can be arbitrarily set by the administrator of this invention. If there are multiple names representing a product, a representative name can be selected. If it is a keyword representing a specific attribute, a representative keyword can be selected as the standard.

[0066] In addition, the processor calculates a first recommendation score for the product indicated by the standard product name keyword based on the search volume of the standard product name keyword within a preset first time period. The first recommendation score is based on the search volume of the product indicated by the standard product name keyword. Products that exceed a set first threshold recommendation score for the standard product name keyword can be exported as recommended products.

[0067] At this point, the first critical recommendation score can be set as the average of the first recommendation scores of all products.

[0068] In addition, the processor uses an artificial intelligence module to classify standard attribute value keywords into attribute categories representing product attribute categories, and derives recommended attribute values ​​for recommended products from these attribute categories, thus deducing the attribute categories. For each recommended attribute category, a second recommendation score is calculated for each standard attribute value keyword corresponding to that category, and it is determined whether the second recommendation score exceeds a preset second critical recommendation score. This determines whether the standard attribute value keyword is used as the recommended attribute value.

[0069] At this point, the second critical recommendation score can be set as the average of the second recommendation scores of all standard attribute value keywords.

[0070] At this point, the attribute category represents the product's attributes, which can be arbitrarily set by the administrator of this invention, such as smell, taste, size, color, use, durability, etc.

[0071] In addition, the processor can also derive the recommended attribute categories of recommended products from the attribute categories, and set the attribute categories corresponding to the recommended products in the attribute categories as temporary recommended attribute categories.

[0072] For example, in the case of a mat, there is no space to apply categories such as "smell" or "odor," so only the applicable categories are exported first. At this point, temporary recommended attribute categories can also be derived from the attribute categories corresponding to at least one attribute value keyword searched with the product, based on search history information.

[0073] In addition, the processor can also derive a third recommendation score for temporary recommendation attribute categories and set temporary recommendation attribute categories whose third recommendation scores exceed a preset third threshold recommendation score as existing recommendation attribute categories.

[0074] This requires not only analyzing which products are popular in the target country, but also analyzing which product attributes are popular.

[0075] For example, if red cushions are only popular in the target country, then producing and selling cushions in other colors would not be advisable. Therefore, in this example, the attribute category "color" is derived as the recommended attribute category, and the attribute value keyword "red" is derived as the recommended attribute value to help develop a product sales strategy for the target country.

[0076] At this point, the third critical recommendation score can be set as the average of the third recommendation scores for all temporary recommendation attribute categories.

[0077] Additionally, the processor can calculate the search volume of the corresponding standard product name keywords indicating the product used to derive the first recommendation score based on the current time, as the first search volume during the first time period traced back to the preset judgment period.

[0078] At this time, the judgment period can be arbitrarily set by the administrator of this invention, such as 1 month, 3 months, 6 months or 1 year.

[0079] Additionally, the processor determines the second search volume for the standard product name keywords used to derive the first recommendation score during a second time period, tracing back from the first time period to a defined time period. During the first time period, the average search volume of all standard product name keywords is set as the first average search volume, and the average search volume of all standard product name keywords during the second time period is also set as the first average search volume. Based on the first search volume, the second search volume, the first average search volume, and the second average search volume, a recommendation score for the first search volume of the product indicated by the standard product name keywords can be derived.

[0080] More specifically, the first recommended score can be derived using Equation 1 below.

[0081] [Equation 1]

[0082]

[0083] At this point, rs1 refers to the first recommendation score, sm_1 refers to the first search volume, sm_2 refers to the second search volume, asm_1 refers to the first average search volume, and asm_2 refers to the second average search volume.

[0084] It can reflect how much the search volume has increased compared to the past period and how much the weight has increased compared to other products, thus deriving the first recommendation score.

[0085] Additionally, the processor derives a second recommendation score for standard attribute value keywords contained within the recommended attribute categories, and calculates the search volume of standard product name keywords indicating the recommended product within the first time period, setting this as the third search volume. Within the first time period, the search volume of the corresponding standard attribute value keywords is set as the fourth search volume, and the second recommendation score for the standard attribute value keywords is set based on the third and fourth search volumes. This is derived from...

[0086] More specifically, the second recommended score can be derived using Equation 2 below.

[0087] [Equation 2]

[0088]

[0089] At this point, rs2 can represent the second recommendation score, sm_3 can represent the third search volume, and sm_4 can represent the fourth search volume.

[0090] Therefore, a second recommendation score can be derived based on the closeness of the search for recommended products together with the standard attribute value keywords and the standard product name keywords.

[0091] Additionally, the processor derives the third recommendation score for each temporary recommended attribute category and calculates the total number of standard attribute value keywords contained within each temporary recommended attribute category during the first time period. This can be derived from the fifth search volume, which refers to the sum of search volumes for all included standard attribute value keywords.

[0092] More specifically, the third recommendation score can be derived using Equation 3 below.

[0093] [Equation 3]

[0094]

[0095] At this point, rs3 can represent the third recommendation score, at can represent the total number of standard attribute value keywords contained in the corresponding temporary recommendation attribute category, and sm_5 can represent the fifth search volume.

[0096] This means that when the corresponding temporary recommendation attribute category contains a wide variety of standard attribute value keywords, it is economical for product manufacturers to recommend specific attribute values, while it is the public's responsibility to search for multiple attribute value keywords for temporary recommendations. Because it is a category that users are interested in, the third recommendation score also increases as the number of standard attribute value keywords and the fifth search volume increase.

[0097] According to an embodiment of the present invention, the method for analyzing global demand forecasting trends and providing sales strategies can receive search history information through a search term collection API, which can collect search history from a preset homepage operating in the target country S101.

[0098] Furthermore, the method for providing trend analysis and sales strategies based on global demand forecasting according to embodiments of the present invention can derive recommended products and recommended attribute values ​​of recommended products based on search history information S103.

[0099] Furthermore, the method for providing trend analysis and sales strategies based on global demand forecasting according to embodiments of the present invention can be used in conjunction with... Figure 1 and Figure 2 It is configured in the same way as the publicly disclosed device that provides trend analysis and sales strategies based on global demand forecasting.

[0100] The above embodiments can be implemented using hardware components, software components, and / or combinations of hardware and software components. For example, the apparatus, methods, and components described in the embodiments may include, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, and field-programmable gate arrays (FPGAs). It can be implemented using one or more general-purpose or special-purpose computers, such as arrays, programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Additionally, the processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, it may be described as using a single processing device; however, those skilled in the art will understand that a processing device may include multiple processing elements and / or various types of processing elements. For example, a processing apparatus may include multiple processors or a processor and a controller. Furthermore, other processing configurations, such as parallel processors, are also possible.

[0101] The methods of the embodiments can be implemented in the form of program instructions executable by various computer devices and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., individually or in combination. The program instructions recorded on the medium may be specifically designed and configured for the embodiments, or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; and magnetic media such as floppy disks—including optical media (magneto-optical media). Hardware devices specifically designed for storing and executing program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as code generated by a compiler, and high-level language code that can be executed by a computer using an interpreter. The aforementioned hardware devices may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

[0102] Software may include computer programs, code, instructions, or a combination of one or more of these, which may configure processing units to operate as needed, or may independently or jointly command devices. Software and / or data may be used on any type of machine, component, physical device, virtual device, computer storage medium, or may be permanently or temporarily embodied in a device or transmitted signal wave. Software may be distributed across networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0103] As described above with limited accompanying drawings, embodiments have been presented, but those skilled in the art can make various modifications and variations based on the above application of techniques. For example, the described techniques may be performed in a different order than the described methods, and / or components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different form than the described methods, or other components may be substituted or replaced with equivalents, and appropriate results may be obtained.

[0104] Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims

1. An electronic device, characterized in that, The electronic device includes: Memory; and The processor connected to the memory, In the processor, Search history information is received through a search term collection API, which can collect search history from preset homepages operated in the target country. Export recommended products and their attribute values ​​based on search history information.

2. The electronic device according to claim 1, characterized in that, Search history information includes the search terms users used on the homepage and the times when those terms were searched. In the processor, The artificial intelligence module extracts product-related search terms from search history information. Based on the product-related search terms, recommend products and attribute values ​​are derived.

3. The electronic device according to claim 2, characterized in that, In the processor, The AI ​​module categorizes product-related search terms into keywords. From the keywords contained in product-related search terms, derive the product name keywords and attribute value keywords that represent the attribute values ​​of the product name. Based on preset standards, product name keywords and attribute value keywords are standardized to obtain standard product name keywords and standard attribute value keywords. Based on the search volume of standard product name keywords within a preset first time period, the first recommendation score for the product indicated by the standard product name keywords is obtained. Products whose first recommendation score exceeds a preset first threshold recommendation score are recommended products.

Images