Analysis device and method thereof

Abstract

An analysis device according to an embodiment of the present document may comprise: a memory for storing at least one instruction; and at least one processor for executing the at least one instruction, wherein the at least one processor: acquires text included in content searched on a specific site on the basis of a designated search word; on the basis of inputting input data according to the acquired text into a learning model, acquires, from the learning model, a first parameter indicating the state of an expected change in a market for the search word and a second parameter indicating the degree of the expected change in the market; and on the basis of the first parameter and the second parameter, identifies a market index indicating the expected change in the market according to the content.

Description

Analysis device and method thereof

[0001] Cross-citation with related applications

[0002] This application claims the benefit of priority from Republic of Korea Patent Application No. 10-2024-0103734, filed August 5, 2024, the entire contents of which are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to an analysis device and a method thereof.

[0005] As electric vehicles powered by electricity become more widespread, competition among vehicle manufacturers for research and development is intensifying. For example, electric vehicles can be powered by secondary batteries, which are rechargeable batteries and include both conventional Ni / Cd and Ni / MH batteries, as well as more recent lithium-ion batteries. Among secondary batteries, lithium-ion batteries have the advantage of having a much higher energy density than conventional Ni / Cd and Ni / MH batteries. Furthermore, lithium-ion batteries can be manufactured in a compact and lightweight form, making them a power source for mobile devices. Recently, their use has expanded to include power sources for electric vehicles, attracting attention as a next-generation energy storage medium.

[0006] Meanwhile, the proliferation of video sharing platforms has led to an increase in the sharing and dissemination of information related to electric vehicles through video. As the volume of information shared through video grows and its accuracy improves, the importance of technology for analyzing video to obtain information is growing.

[0007] According to the embodiments disclosed in this document, an analysis device and an analysis method for obtaining information by analyzing content are provided.

[0008] According to the embodiments disclosed in this document, an analysis device and analysis method for predicting changes in the market are provided.

[0009] According to the embodiments described in this document, an analysis device and analysis method for analyzing expected sales volume changes of companies are provided.

[0010] According to the embodiments described in this document, an analysis device and analysis method are provided for analyzing expected changes in the market through parameters obtained from a learning model.

[0011] The technical challenges of this document are not limited to the technical challenges mentioned above, and other technical challenges not mentioned will be clearly understood by those skilled in the art from the descriptions below.

[0012] An analysis device according to one embodiment of the present document may include a memory storing at least one instruction, and at least one processor executing the at least one instruction.

[0013] According to one embodiment, the at least one processor obtains text included in content searched on a specific site based on a specified search term, and inputs input data according to the obtained text into a learning model, and obtains a first parameter indicating a state of expected change in a market for the search term and a second parameter indicating a degree of expected change in the market from the learning model, and identifies a market indicator indicating an expected change in the market according to the content based on the first parameter and the second parameter.

[0014] According to one embodiment, the at least one processor may identify the market indicator at the first point in time as a first partial market indicator by obtaining content within a specified rank among contents searched on the specific site at a first point in time based on the search term, and text included in the content within the specified rank, and identify the market indicator at the second point in time as a second partial market indicator by obtaining content within the specified rank among contents searched on the specific site at a second point in time based on the search term, and text included in the content within the specified rank, and identify the market indicator for a period including the first point in time and the second point in time based on the first partial market indicator and the second partial market indicator.

[0015] According to one embodiment, the first parameter may represent a state of expected sales volume change of the product for the search term during a specified period, the second parameter may represent a degree of expected sales volume change of the product during the specified period, and the market indicator may represent an expected sales volume change of the product during the specified period.

[0016] According to one embodiment, the first parameter may correspond to a value greater than 0 if the sales volume of the product is expected to increase during the specified period, and may correspond to a value less than 0 if the sales volume of the product is expected to decrease during the specified period.

[0017] According to one embodiment, the at least one processor may obtain, from the learning model, the reason why the first parameter and the second parameter were identified, together with the first parameter and the second parameter, based on inputting input data according to the acquired text into the learning model.

[0018] According to one embodiment, the at least one processor performs a processing step of deleting text representing a sound included in the content from among the acquired texts, and based on inputting data according to the text on which the processing step was performed into the learning model, identifies whether the text on which the processing step was performed is related to the search word, and based on the association of the text on which the processing step was performed with the search word, generates the input data according to the text on which the processing step was performed.

[0019] In one embodiment, the search term may represent a specific company.

[0020] According to one embodiment, the text may include subtitles included in the content.

[0021] A battery diagnosis method according to another embodiment of the present document may include an operation of obtaining text included in content searched on a specific site based on a specified search word, an operation of obtaining a first parameter indicating a state of expected change in a market for the search word and a second parameter indicating a degree of expected change in the market from the learning model based on input data according to the obtained text into a learning model, and an operation of identifying a market indicator indicating an expected change in the market according to the content based on the first parameter and the second parameter.

[0022] According to one embodiment, the operation of identifying a market indicator indicating an expected change in the market according to the content based on the first parameter and the second parameter may include: an operation of identifying the market indicator at the first point in time as a first partial market indicator by obtaining content within a specified rank among contents searched on the specific site at a first point in time based on the search term, and text included in the content within the specified rank; an operation of identifying the market indicator at the second point in time as a second partial market indicator by obtaining content within the specified rank among contents searched on the specific site at a second point in time based on the search term, and text included in the content within the specified rank; and a method of identifying the market indicator for a period including the first point in time and the second point in time based on the first partial market indicator and the second partial market indicator.

[0023] According to one embodiment, the first parameter may represent a state of expected sales volume change of the product for the search term during a specified period, the second parameter may represent a degree of expected sales volume change of the product during the specified period, and the market indicator may represent an expected sales volume change of the product during the specified period.

[0024] According to one embodiment, the first parameter may correspond to a value greater than 0 if the sales volume of the product is expected to increase during the specified period, and may correspond to a value less than 0 if the sales volume of the product is expected to decrease during the specified period.

[0025] According to one embodiment, the analysis method may further include an operation of obtaining, from the learning model, the first parameter and the second parameter, along with the reason why the first parameter and the second parameter were identified, based on inputting input data according to the acquired text into the learning model.

[0026] According to one embodiment, the analysis method may further include an operation of performing a processing step of deleting text representing a sound included in the content from among the acquired text, an operation of inputting data according to the text on which the processing step was performed into the learning model, and identifying whether the text on which the processing step was performed is related to the search word, and an operation of generating the input data according to the text on which the processing step was performed based on the association of the text on which the processing step was performed with the search word.

[0027] In one embodiment, the search term may represent a specific company.

[0028] According to one embodiment, the text may include subtitles included in the content.

[0029] This technology can obtain information by analyzing content.

[0030] Additionally, this technology can predict changes in the market.

[0031] Additionally, this technology can analyze the expected sales volume changes of companies participating in the market.

[0032] Additionally, this technology can analyze expected changes in the market through parameters obtained from a learning model.

[0033] In addition, various effects may be provided, either directly or indirectly, through this document.

[0034] Figure 1 is a block diagram showing the configuration of an analysis device and an analysis method according to one embodiment of the present document.

[0035] FIG. 2 illustrates an example of a flow of operations for identifying a market indicator of an analysis device and an analysis method according to an embodiment of the present document.

[0036] FIG. 3 illustrates an example of a graph showing the output frequency of influence scores constituting a market indicator for a specific period of time in an analysis device and an analysis method according to one embodiment of the present document.

[0037] FIG. 4 illustrates an example of a graph showing the output frequency of influence scores constituting market indicators by period in an analysis device and analysis method according to one embodiment of the present document.

[0038] FIG. 5 illustrates an example of a flow of operations for identifying a market indicator of an analysis device and an analysis method according to one embodiment of the present document.

[0039] FIG. 6 is a block diagram showing the hardware configuration of a computing system that performs an analysis method in an analysis device and an analysis method according to one embodiment of the present document.

[0040] Hereinafter, some embodiments disclosed in this document are described with reference to the accompanying drawings, which illustrate various embodiments of this document. However, this is not intended to limit the present technology to specific embodiments, and it should be understood that various modifications, equivalents, and / or alternatives of the embodiments of this technology are included.

[0041] When assigning reference numerals to components in each drawing, it should be noted that identical components are assigned the same numerals whenever possible, even if they are shown in different drawings. Furthermore, when describing various embodiments disclosed in this document, if a detailed description of a related known configuration or function is deemed to hinder understanding of the embodiments of the present invention, the detailed description will be omitted. The singular form of a noun corresponding to an item may include one or more items, unless the context clearly indicates otherwise.

[0042] In describing the components of the embodiments of this document, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components, and the nature, order, or sequence of the components may not be limited by the terms. In addition, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this application.

[0043] In addition, in the present disclosure, expressions such as "more than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled. However, this is merely a description for expressing an example and does not exclude descriptions such as "more than" or "less than." Conditions described as "more than" may be replaced with "more than," conditions described as "less than," and conditions described as "more than and less than" may be replaced with "more than and less than." In addition, hereinafter, "A" to "B" mean at least one of the elements from A (including A) to B (including B).

[0044] In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" may include any one of the items listed together in that phrase, or all possible combinations thereof.

[0045] In this document, when a component (e.g., a first component) is referred to as being “connected,” “coupled,” or “connected,” with or without the terms “functionally” or “communicatively,” or is referred to as being “coupled” or “connected,” it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0046] According to one embodiment, the method according to the various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store or directly between two user devices. In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0047] According to various embodiments, each component (e.g., a module or a program) of the described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0048] Hereinafter, embodiments of the present document will be described in detail with reference to FIGS. 1 to 6.

[0049] Figure 1 is a block diagram showing the configuration of an analysis device and an analysis method according to one embodiment of the present document.

[0050] FIG. 2 illustrates an example of a flow of operations for identifying a market indicator of an analysis device and an analysis method according to an embodiment of the present document.

[0051] Referring to FIGS. 1 and 2, the analysis device (101) may include a memory (103) and at least one processor (105).

[0052] At least one processor (105) may include a data collection unit (107), a parameter extraction unit (109), and a market indicator identification unit (111). The memory (103) may include at least one instruction. At least one processor (105) may execute at least one instruction.

[0053] According to one embodiment, at least one processor (105) of the analysis device (101) can obtain information (e.g., expected changes in the market) by analyzing content (e.g., video) obtained based on a search term.

[0054] According to one embodiment, at least one processor (105) of the analysis device (101) can identify a market indicator indicating an expected change in a market related to a product for a specified search term (e.g., an expected change in sales of a specific company) based on search results from a specific site (e.g., a video sharing platform) based on a specified search term (e.g., a name of a specific company).

[0055] In the first operation (201), at least one processor (105) of the analysis device (101) according to an embodiment may, at a specific point in time, perform text acquisition and preprocessing related to a search term. In other words, at least one processor (105) of the analysis device (101) according to an embodiment may, in order to determine the recognition of search terms by users on a specific site, acquire text included in each of the contents searched on a specific site based on a specified search term through the data collection unit (107) and perform preprocessing on the text.

[0056] For example, at a specific point in time, at least one processor (105) of the analysis device (101) may acquire contents within a specified rank (e.g., approximately 10th) among contents searched on a specific site based on a search term. The rank among the contents may be determined based on the search results. Since the rank among the contents may change depending on the sorting criteria, the sorting criteria for acquiring the contents while identifying the market indicator may be determined based on one of several specified criteria (e.g., by number of views, by most recent, by upload date, by rating).

[0057] For example, text included in content may include subtitles included in the content. For example, subtitles included in the content may include subtitles provided by the content publisher or subtitles generated using a learning model.

[0058] For example, at least one processor (105) of the analysis device (101) may perform a processing step of deleting text representing sounds included in the content (e.g., music, music, BGM) from among the acquired text. That is, according to various embodiments, at least one processor (105) may not use text representing sounds when identifying market indicators.

[0059] For example, at least one processor (105) of the analysis device (101) can identify whether the text on which the processing was performed is related to a search word based on inputting data (e.g., input data) according to the text on which the processing was performed into a learning model.

[0060] For example, at least one processor (105) of the analysis device (101) may input data according to text on which a processing process has been performed into a learning model, and may input a command requesting the learning model to identify whether the data according to text on which a processing process has been performed is related to a search term (e.g., read the data, and if the data is related to the search term, indicate only “yes,” if the data is not related to the search term, indicate only “no”). The learning model may output whether the data according to text on which a processing process has been performed is related to the search term (e.g., related, not related).

[0061] For example, at least one processor (105) of the analysis device (101) may generate input data to be input to the learning model for identifying a market indicator at a specific point in time based on the text on which the processing was performed, if the text on which the processing was performed is associated with a search word.

[0062] For example, at least one processor (105) of the analysis device (101) according to one embodiment may perform an additional preprocessing process (e.g., removing blank spaces based on strings in the text on which the processing was performed) to increase the text identification rate of the learning model when the text on which the processing was performed is associated with a search term. However, the embodiments of the present document may not be limited thereto.

[0063] For example, at least one processor (105) of the analysis device (101) may generate input data based on content other than the searched content if the text on which the processing was performed is not related to the search word.

[0064] At least one processor (105) of the analysis device (101) can identify cases where content and search terms are not related by identifying whether the text on which the processing is performed is related to the search term. If the content and search term are not related, the at least one processor (105) of the analysis device (101) can exclude texts based on content that are not related to the search term from the process of identifying market indicators.

[0065] According to one embodiment, the learning model may be stored on a different server than the analysis device (101).

[0066] In one embodiment, the learning model may include a large language model (LLM). LLM may represent a natural language processing model trained based on a large text data set.

[0067] According to one embodiment, examples of learning algorithms performed by the learning model may include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0068] However, LLM mainly uses unsupervised learning to identify patterns and structures in text, and based on these identified patterns and structures, it can perform language-related tasks such as text generation, context understanding, translation, and summarization.

[0069] In one embodiment, the learning model may include a deep neural network (DNN). Examples of deep neural networks include a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks. However, the embodiments of this document may not be limited to the above-described examples.

[0070] In a second operation (203), at least one processor (105) of the analysis device (101) according to an embodiment may obtain parameters (e.g., a first parameter, a second parameter) through a learning model through a parameter extraction unit (109). The first parameter may include an indicator indicating the state of expected market changes for the search term. The second parameter may include an indicator indicating the degree of expected market changes.

[0071] According to one embodiment, at least one processor (105) of the analysis device (101) may input input data and a command requesting parameters to the learning model to obtain parameters (e.g., a first parameter, a second parameter) for each content.

[0072] For example, a command requesting a first parameter may include at least one of a command indicating the status of the learning model (e.g., you are a world-class electric vehicle market expert), a command requesting output of the expected state of change in the market (e.g., based on the input data, tell me whether the expected change in sales of a product for a search term over a given period will be increasing, decreasing, or neutral), or a combination thereof.

[0073] For example, a command requesting a second parameter may include at least one of a command indicating the status of the learning model (e.g., you are a world-class electric vehicle market expert), a command requesting output of an expected degree of change in the market (e.g., based on input data, output an integer greater than or equal to 1 and less than or equal to 5, indicating an expected degree of change in sales of a product for a search term over a specified period. The larger the integer, the greater the expected degree of change.), a command requesting a reason why the second parameter was identified (e.g., based on input data, output the reason why the expected change in the market for the search term is the first parameter and the second parameter), or any combination thereof.

[0074] According to one embodiment, at least one processor (105) of the analysis device (101) may include instructions requesting that the first parameter or the second parameter be output as a reason for which it is identified (e.g., output the reason why the expected change in the market for the search term based on the input data is indicated by the first parameter and the second parameter).

[0075] In the third operation (205), at least one processor (105) of the analysis device (101) according to one embodiment can identify a partial market indicator through a market indicator identification unit (111).

[0076] For example, at least one processor (105) of the analysis device (101) may identify an influence score for each content included in a designated rank (e.g., about 10th place) among contents searched for on a specific site based on a search term at a specific point in time, based on a product of a value corresponding to a first parameter and a second parameter. The influence score may include a number indicating an expected market change based on the content. The influence score (e.g., -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5) may be identified based on a product of a value corresponding to a first parameter (e.g., -1, 0, 1) and a second parameter (e.g., 1, 2, 3, 4, 5).

[0077] For example, at least one processor (105) of the analysis device (101) may identify a partial market indicator at a specific point in time based on the sum of the influence scores of each content included in a specified ranking at a specific point in time. The partial market indicator may include an indicator indicating expected market changes based on content searched on a specific site at a specific point in time.

[0078] For example, at least one processor (105) of the analysis device (101) may correspond the first parameter to a value greater than 0 (e.g., +1) if the sales volume of the product is expected to increase during a specified period of time. At least one processor (105) of the analysis device (101) may correspond the first parameter to a value less than 0 (e.g., -1) if the sales volume of the product is expected to decrease during a specified period of time. At least one processor (105) of the analysis device (101) may correspond the first parameter to 0 if the sales volume of the product is expected to remain unchanged during a specified period of time.

[0079] In the fourth operation (207), at least one processor (105) of the analysis device (101) according to one embodiment can identify a market index through a market index identification unit (111).

[0080] According to one embodiment, at least one processor (105) of the analysis device (101) can identify a partial market indicator at a specific point in time and a partial market indicator at a different point in time from the specific point in time, and, based on the partial market indicator at the specific point in time and the partial market indicator at the different point in time, can identify a market indicator for a period including the specific point in time and the different point in time.

[0081] For example, at least one processor (105) of the analysis device (101) may identify a first partial market indicator based on contents posted on a specific site during a period (e.g., the first week of August) that includes a specific point in time (e.g., the first Sunday of August), identify a second partial market indicator based on contents posted on the specific site during a period (e.g., the second week of August) that includes another point in time (e.g., the second Sunday of August), identify a third partial market indicator based on contents posted on the specific site during a period (e.g., the third week of August) that includes another point in time (e.g., the third Sunday of August), and identify a fourth partial market indicator based on contents posted on the specific site during a period (e.g., the fourth week of August) that includes another point in time (e.g., the fourth Sunday of August) that is different from the above points in time.

[0082] For example, at least one processor (105) of the analysis device (101) can identify a market indicator for a specific point in time, another point in time, another point in time, or a period including the points in time and another point in time (e.g., the month of August) based on a sum of the first partial market indicator, the second partial market indicator, the third partial market indicator, and the fourth partial market indicator.

[0083] According to one embodiment, at least one processor (105) of the analysis device (101) can provide the user with the identified market indicator and the reason why the first parameter and the second parameter were identified for each content.

[0084] FIG. 3 illustrates an example of a graph showing the output frequency of influence scores constituting a market indicator for a specific period of time in an analysis device and an analysis method according to one embodiment of the present document.

[0085] Referring to FIG. 3, a graph (301) may represent the output frequency according to the influence score for contents searched at a point in time included in a specific period (e.g., the month of August). A bar (305) may represent the frequency at which the influence score is output at a point in time included in a specific period. Each output frequency may be normalized so that the sum of the frequencies at which the influence score is output becomes 1. A line (303) may represent a distribution of the estimated output frequency based on the distribution of the bar (305) as a curve. For example, the line (303) may represent a probability density function of the estimated output frequency by a KDE (kernel density estimation) plot method.

[0086] According to one embodiment, at least one processor (105) of the analysis device (101) may identify a market indicator based on the average value of the influence scores of each content searched at points in time included in a specific period (e.g., the first week of August, the second week of August, the third week of August, and the fourth week of August). However, since the market indicator is an average value of the influence scores, it may be difficult to examine the distribution of the influence scores. Therefore, at least one processor (105) of the analysis device (101) may provide a user with a graph (301) indicating the output frequency according to the influence score.

[0087] FIG. 4 illustrates an example of a graph showing the output frequency of influence scores constituting market indicators by period in an analysis device and analysis method according to one embodiment of the present document.

[0088] Referring to FIG. 4, a first line (403) may represent an output frequency according to an influence score at a time included in a first period (e.g., the first week of March). A second line (405) may represent an output frequency according to an influence score at a time included in a second period (e.g., the second week of March). A third line (407) may represent an output frequency according to an influence score at a time included in a third period (e.g., the third week of March). A fourth line (409) may represent an output frequency according to an influence score at a time included in a fourth period (e.g., the fourth week of March). A fifth line (411) may represent an output frequency according to an influence score at a time included in a fifth period (e.g., the fifth week of March).

[0089] According to one embodiment, at least one processor (105) of the analysis device (101) may provide a user with a graph (401) representing the output frequency of influence scores over a period of time.

[0090] FIG. 5 illustrates an example of a flow of operations for identifying a market indicator of an analysis device and an analysis method according to one embodiment of the present document.

[0091] Referring to FIG. 5, in the first operation (501), at least one processor (105) of the analysis device (101) according to one embodiment can obtain text included in content searched on a specific site based on a specified search word.

[0092] In a second operation (503), at least one processor (105) of the analysis device (101) according to an embodiment may obtain a first parameter indicating a state of expected change in the market for the search word and a second parameter indicating a degree of expected change from the learning model based on inputting input data according to the acquired text into the learning model.

[0093] In a third operation (505), at least one processor (105) of the analysis device (101) according to one embodiment can identify a market indicator indicating an expected change in the market according to the content based on the first parameter and the second parameter.

[0094] According to one embodiment, at least one processor (105) of the analysis device (101) can provide market indicators to a user through an application of the analysis device (101) that analyzes the market.

[0095] For example, at least one processor (105) of the analysis device (101) can provide market indicators to a user by outputting them to a display included in the analysis device (101).

[0096] For example, at least one processor (105) of the analysis device (101) may generate a graph (e.g., a graph of output frequency according to influence score) regarding market prediction based on market indicators.

[0097] For example, at least one processor (105) of the analysis device (101) may provide the user with at least one of the market indicator, the reason why the market indicator was output (e.g., the reason why the first parameter and the second parameter were output), a graph regarding market prediction (e.g., a graph of output frequency according to influence score), or any combination thereof, based on the market indicator.

[0098] FIG. 6 is a block diagram showing the hardware configuration of a computing system that performs an analysis method in an analysis device and an analysis method according to one embodiment of the present document.

[0099] Referring to FIG. 6, a computing system (600) according to an embodiment disclosed in this document may include an MCU (610), a memory (620), an input / output I / F (630), and a communication I / F (640).

[0100] The MCU (610) may be at least one processor that executes various programs (e.g., a battery cell data collection program, a graph generation program, a data analysis program, a data decomposition algorithm, a normalization program, a battery cell diagnosis program, etc.) stored in the memory (620), processes various information including battery cell characteristic data and latent variables through these programs, and performs the functions of the analysis device (101) shown in the aforementioned FIGS. 1 to 5.

[0101] The memory (620) can store various programs such as a battery cell data collection program, a graph generation program, a data analysis program, a data decomposition algorithm, a normalization program, and a battery cell diagnosis program.

[0102] Such memories (620) may be provided in multiples as needed. The memories (620) may be volatile memories or non-volatile memories. As volatile memories (620), RAM, DRAM, SRAM, etc. may be used. As non-volatile memories (620), ROM, PROM, EAROM, EPROM, EEPROM, flash memories, etc. may be used. The examples of the memories (620) listed above are merely examples and are not limited to these examples.

[0103] The input / output I / F (630) can provide an interface that enables data transmission and reception between an input device (not shown) such as a keyboard, mouse, or touch panel, and an output device (not shown) such as a display and the MCU (610).

[0104] The communication I / F (640) is a component capable of transmitting and receiving various data with the server, and may be any device capable of supporting wired or wireless communication. For example, the analysis device (101) can transmit and receive various information, including battery cell shape models, from a separately provided external server via the communication I / F (640).

[0105] In this way, a computer program according to an embodiment disclosed in this document may be implemented as a module that performs each function illustrated in FIG. 2, for example, by being recorded in a memory (620) and processed by an MCU (610).

[0106] In the above, although all components constituting the embodiments disclosed in this document have been described as being combined or operating in combination as one, the embodiments disclosed in this document are not necessarily limited to such embodiments. That is, within the scope of the purpose of the embodiments disclosed in this document, all of the components may be selectively combined and operated one or more times.

[0107] In addition, terms such as "include," "comprise," or "have" described above, unless specifically stated to the contrary, should be interpreted to imply the inclusion of the corresponding component, and thus should not be interpreted to exclude other components, but rather to include other components. All terms, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong, unless otherwise defined. Commonly used terms, such as terms defined in a dictionary, should be interpreted to be consistent with the contextual meaning of the relevant technology, and shall not be interpreted in an idealized or overly formal sense, unless explicitly defined in this document.

[0108] The foregoing disclosure outlines features of several embodiments to enable those skilled in the art to better understand the aspects of the present disclosure. Those skilled in the art will readily appreciate that the present disclosure can be readily used as a basis for designing or modifying other structures to achieve the same purposes or advantages of the embodiments introduced herein. Furthermore, those skilled in the art will recognize that such equivalent structures do not depart from the scope of the present disclosure, and that various changes, substitutions, and modifications can be made herein without departing from the scope of the present disclosure.

Claims

1. Memory that stores at least one instruction; and comprising at least one processor executing at least one instruction; At least one processor, Obtain text included in content searched on a specific site based on a specified search term; Based on inputting input data according to the acquired text into a learning model, a first parameter indicating the state of expected change in the market for the search term and a second parameter indicating the degree of expected change in the market are obtained from the learning model, Based on the first parameter and the second parameter, a market indicator is configured to be identified that indicates an expected change in the market according to the content. Analysis device.

2. In claim 1, At least one processor, By obtaining content within a specified rank among the contents searched on the specific site at a first point in time based on the search term, and text included in the content within the specified rank, the market indicator at the first point in time is identified as a first partial market indicator, By obtaining content within the specified rank among the contents searched on the specific site at a second point in time based on the search term, and text included in the content within the specified rank, the market indicator at the second point in time is identified as a second partial market indicator, Based on the first partial market indicator and the second partial market indicator, configured to identify the market indicator for a period including the first point in time and the second point in time, Analysis device.

3. In claim 1, The above first parameter is, Indicates the status of expected sales volume changes for the product for the above search term over a specified period of time, The second parameter above is, Indicates the extent of expected sales change of the above product during the above specified period, The above market indicators are, Configured to represent the expected sales volume change of the above product during the above specified period, Analysis device.

4. In claim 3, The above first parameter is, If the sales volume of the above product is expected to increase during the above specified period, a value greater than 0 is corresponding. If the sales volume of the above product is expected to decrease during the above specified period, corresponding to a value less than 0, Analysis device.

5. In claim 1, At least one processor, Based on inputting input data according to the acquired text into the learning model, the learning model is configured to obtain the reason why the first parameter and the second parameter are identified, together with the first parameter and the second parameter. Analysis device.

6. In claim 1, At least one processor, Performing a processing step of deleting text representing sounds included in the content from the obtained text, Based on inputting data according to the text on which the above processing has been performed into the above learning model, it is identified whether the text on which the above processing has been performed is related to the above search word, Based on the association between the text on which the above processing has been performed and the search word, the input data is configured to be generated according to the text on which the above processing has been performed. Analysis device.

7. In claim 1, The above search term is, Representing a specific company, Analysis device.

8. In claim 1, The above text, Including subtitles included in the above content, Analysis device.

9. An action to obtain text included in content searched on a specific site based on a specified search term; An operation of obtaining a first parameter representing the state of expected change in the market for the search term and a second parameter representing the degree of expected change in the market from the learning model based on input data according to the acquired text into the learning model; and An operation for identifying a market indicator representing an expected change in the market according to the content, based on the first parameter and the second parameter, Analysis method.

10. In claim 9, An operation of identifying a market indicator representing an expected change in the market according to the content based on the first parameter and the second parameter is as follows: An operation of identifying a market indicator at the first point in time as a first partial market indicator by obtaining content within a specified rank among contents searched on the specific site at the first point in time based on the search term, and text included in the content within the specified rank; An operation of identifying a market indicator at the second point in time as a second partial market indicator by obtaining content within the specified rank among the contents searched on the specific site at the second point in time based on the search term, and text included in the content within the specified rank; and A method for identifying the market indicator for a period including the first point in time and the second point in time, based on the first partial market indicator and the second partial market indicator, Analysis method.

11. In claim 9, The above first parameter is, Indicates the status of expected sales volume changes for the product for the above search term over a specified period of time, The second parameter above is, Indicates the extent of expected sales change of the above product during the above specified period, The above market indicators are, Indicates the expected sales volume change of the above product during the above specified period, Analysis method.

12. In claim 11, The above first parameter is, If the sales volume of the above product is expected to increase during the above specified period, a value greater than 0 is corresponding. If the sales volume of the above product is expected to decrease during the above specified period, corresponding to a value less than 0, Analysis method.

13. In claim 9, Based on inputting input data according to the acquired text into the learning model, further comprising an operation of obtaining the reason why the first parameter and the second parameter are identified, together with the first parameter and the second parameter, from the learning model. Analysis method.

14. In claim 9, An action for performing a processing step of deleting text representing a sound included in the content from among the obtained text; An operation of identifying whether the text on which the processing has been performed is related to the search word based on inputting data according to the text on which the processing has been performed into the learning model; Further comprising an action of generating the input data according to the text on which the processing was performed, based on the association of the text on which the processing was performed and the search word. Analysis method.

15. In claim 9, The above search term is, Representing a specific company, Analysis method.

16. In claim 9, The above text, Including subtitles included in the above content, Analysis method.

Images