KR102619471B1 - Method and apparatus for evaluating product information - Google Patents

Abstract

A product information evaluation method performed by a computing device including at least one processor according to an embodiment of the present disclosure, comprising: generating standardized product data corresponding to unstructured product text; Calculating price information based on a product data set including a plurality of product data; And it may include generating evaluation information corresponding to at least one product data included in the product data set based on the price information.

Description

{METHOD AND APPARATUS FOR EVALUATING PRODUCT INFORMATION}

The present invention relates to a method of evaluating product information, and more specifically, to a method of generating evaluation information about product information from text, which is unstructured data, using a computing device.

In the industry, there are various evaluation techniques for processing unstructured data into structured data and deriving meaningful results from the processed structured data.

Among evaluation techniques for evaluating structured data based on big data, trading brokerage services are characterized by the fact that evaluations must be performed taking into account differences in the positions of sellers and buyers.

However, in the case of the prior art, there was an evaluation technique in which the main evaluation was made only from the perspective of the seller who created the data for sale. Accordingly, there has been a continuous demand for a more effective evaluation method that narrows the gap between the perspectives of the seller and the buyer. .

Korean registered patent KR10-2194528 discloses a collateral asset valuation method, device, and program.

The present disclosure has been devised in response to the above-mentioned background technology, and its purpose is to provide a method for evaluating product information.

A product information evaluation method performed by a computing device including at least one processor according to an embodiment of the present disclosure for realizing the above-described problem, comprising the step of generating standardized product data corresponding to unstructured product text. ; Calculating price information based on a product data set including a plurality of product data; And it may include generating evaluation information corresponding to at least one product data included in the product data set based on the price information.

In an alternative embodiment, generating the product data comprises: based on a rating list comprising at least one rating index, each of the at least one rating index being assigned at least one token to be compared; It may include generating standardized product data from product text.

In an alternative embodiment, the product data includes at least one comparison result token, wherein the comparison result token is obtained based on a result of comparing a comparison target token assigned to the evaluation index with the unstructured product text. You can.

In an alternative embodiment, the method includes calculating authenticity information for each of a plurality of product data included in the product data set; And it may further include removing at least one product data from the product data set based on the authenticity information.

In an alternative embodiment, calculating the authenticity information may include inspecting the unstructured product text based on a fake index included in an evaluation list for evaluating product information.

In an alternative embodiment, calculating the authenticity information may be performed based on the price information.

In an alternative embodiment, calculating the price information includes calculating a product quantity distribution according to product price; And it may include calculating price information based on the product quantity distribution and at least one price reference value.

In an alternative embodiment, the at least one price reference value may be determined based on a statistical value calculated from the product quantity distribution.

In an alternative embodiment, the at least one price reference value may be determined based on a distribution of actual sales quantity according to product price.

In an alternative embodiment, the at least one price reference value may be determined based on a statistical value calculated from the product quantity distribution, but additionally based on the actual sales quantity distribution according to the product price.

In an alternative embodiment, the method further includes calculating status information based on the product data set, and generating the evaluation information further based on the status information included in the product data set. It may include generating evaluation information corresponding to at least one product data.

In an alternative embodiment, calculating the status information may include calculating a status score for each product data included in the product data set based on at least one status index; and correcting the calculated health score based on at least one health assistance index.

In an alternative embodiment, the comparison result token included in the state auxiliary index may be a string that modifies the comparison result token included in the state index.

In an alternative embodiment, correcting the state score may be performed based on a token distance between a comparison result token corresponding to the state index and a comparison result token corresponding to the state auxiliary index.

In an alternative embodiment, correcting the status score based on the token distance may be performed in such a way that as the token distance becomes closer, the amount of change in the status score due to correction increases.

In an alternative embodiment, the method further includes calculating seller information based on the product data set, and generating the evaluation information is further based on the seller information included in the product data set. It may include generating evaluation information corresponding to at least one product data.

According to an embodiment of the present disclosure for realizing the above-described object, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, it performs the following operations for evaluating product information, which operations include: generating standardized product data corresponding to unstructured product text; An operation of calculating price information based on a product data set including a plurality of product data; and generating evaluation information corresponding to at least one product data included in the product data set based on the price information.

A product information evaluation device is disclosed according to an embodiment of the present disclosure for realizing the above-described problem. The device may include one or more processors; Memory; and a network, wherein the one or more processors generate standardized product data corresponding to unstructured product text, calculate price information based on a product data set including a plurality of product data, and the price information. Based on this, evaluation information corresponding to at least one product data included in the product data set can be generated.

The present disclosure can provide a method for evaluating product information in a more intuitive and efficient manner.

1 is a block diagram of a computing device for evaluating product information according to an embodiment of the present disclosure.
Figure 2 is an example diagram visually illustrating 'product quantity distribution according to price' data according to an embodiment of the present disclosure.
Figure 3 is an example diagram visually illustrating 'actual sales quantity according to price' data according to an embodiment of the present disclosure.
Figure 4 is an example diagram visually illustrating 'product quantity distribution according to price' and 'actual sales quantity according to price' data according to an embodiment of the present disclosure.
Figure 5 is a flowchart showing a process for evaluating product information according to an embodiment of the present disclosure.
Figure 6 is a flowchart showing a process for evaluating product information according to another embodiment of the present disclosure.
7 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “if it contains only A,” “if it contains only B,” or “if it is a combination of A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present invention is not limited to the embodiments presented herein. The present invention is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

1 is a block diagram of a computing device for evaluating product information according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100.

The computing device 100 may include a processor 110, a memory 130, and a network unit 150.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may process the unstructured product text to generate standardized product data corresponding to the unstructured product text. The processor 110 may calculate price information based on a product data set including a plurality of product data. A product data set may include at least one product data. The processor 110 may generate evaluation information corresponding to each piece of product data based on the calculated price information. The processor 110 may additionally calculate at least one of status information or seller information based on a product data set including a plurality of product data. When the processor 110 additionally calculates at least one of the status information or the seller information, the processor 110 calculates the product data corresponding to the product data based on the price information and additionally based on at least one additional information of the status information or the seller information. Evaluation information can also be generated.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150. According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure may include any wired or wireless communication network capable of transmitting and receiving arbitrary types of data and signals, etc., as expressed in the present disclosure. In the present disclosure, the network unit 150 may be configured regardless of the communication mode, such as wired or wireless, and may be composed of various communication networks such as a personal area network (PAN) and a wide area network (WAN). You can. Additionally, the network may be the well-known World Wide Web (WWW), or may use wireless transmission technology used for short-distance communication, such as Infrared Data Association (IrDA) or Bluetooth. The techniques described herein can be used in the networks mentioned above, as well as other networks.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different configurations for performing the computing environment of the computing device 100, and only some of the disclosed configurations may configure the computing device 100. Although not shown in FIG. 1, the computing device 100 according to the present disclosure may additionally include an input unit for receiving a user's input.

The computing device 100 according to the present disclosure can generate standardized product data corresponding to unstructured product text. The processor 110 according to the present disclosure may receive unstructured product text as input and generate standardized product data corresponding to the unstructured product text.

In the present disclosure, the unstructured product text may include content related to the product. Content related to the product may include, for example, product code, product brand, product purchase price, product sales price, product-related explanatory text, etc. Content included in unstructured product text may be divided into a title area, body area, and other areas. The title area may include, for example, the title of the post, a summary sentence, etc. The body area may include, for example, sentences and paragraphs to describe the product. Other areas may include, for example, creation time, modification time, log information, meta information, etc. of unstructured product text.

The processor 110 according to an embodiment of the present disclosure may generate standardized product data from unstructured product text based on the evaluation list. In the present disclosure, the term “standardized product data” may be used interchangeably with the term “product data” for brevity. The evaluation list of the present disclosure may include at least one evaluation index. When the evaluation list includes two or more evaluation indexes, one evaluation index may be an evaluation index dependent on another evaluation index. At this time, the dependent evaluation index may be called a 'lower evaluation index', and the remaining evaluation index may be called a 'higher evaluation index'. The evaluation list according to the present disclosure may include a plurality of evaluation indexes, and the plurality of evaluation indexes are in the form of a tree in which at least one upper evaluation index and each upper evaluation index includes at least one lower evaluation index. It can be made up of data structures. At least one comparison target token may be assigned to at least one evaluation index included in the evaluation list according to the present disclosure. For example, the evaluation list may include the A index, B index, and C index. At this time, the A index may include a-1 comparison target token and a-2 comparison target token. The B index may include b-1 comparison target token and b-2 comparison target token. In a specific example, the evaluation list may include a color index, a material index, a purchase location index, etc. At this time, the color index may include tokens to be compared such as "red", "gold", and "black", the material index may include tokens to be compared such as "velvet", "nylon", and "cashmere", and the purchase place index. may include comparison tokens such as "Express Terminal Underground Shopping Mall", "Department Store", and "Outlet". The above-described examples of types of evaluation indexes and tokens to be compared are merely examples for implementing the present disclosure, and the present disclosure includes various types of evaluation indexes and tokens to be compared.

Product data generated by the processor 110 according to an embodiment of the present disclosure may include at least one comparison result token. The comparison result token may be obtained based on a result of comparing a comparison target token assigned to at least one evaluation index included in the evaluation list with the unstructured product text. In the present disclosure, the “token to be compared” may be a candidate string included in an evaluation list for evaluation of unstructured product text. In the present disclosure, the “comparison result token” may be a string obtained from the unstructured product text as a result of comparing the unstructured product text and the comparison target token. The product data of the present disclosure may equally include at least part of the evaluation index included in the evaluation list. The evaluation index included in the product data may be a subset of the evaluation index included in the evaluation list. The evaluation index included in the product data may be composed of indexes that exist in the unstructured product text among the evaluation indexes included in the evaluation list. Each evaluation index included in product data may include a plurality of comparison result tokens. The set of comparison result tokens included in the product data may be a subset of the set of comparison target tokens included in the evaluation list. Comparison result tokens included in product data may each have a single evaluation index. In other words, the data connection relationship between the evaluation index and the comparison result token may be a One-to-Many relationship.

In an example according to the present disclosure, it is assumed that the evaluation list includes 'brand index' and 'status index' as evaluation indices. Additionally, the 'Brand Index' includes comparative tokens consisting of {"Chanel", "Gucci", "Burberry", "Goyard"} and the 'Condition Index' includes {"New", "Nearly New", " It is assumed that comparison target tokens consisting of "slight feeling of use" and "life wear" are included. At this time, when the atypical product text “Selling a new Goyard men’s half wallet” is input to the processor 110, the processor 110 compares the atypical product text with one or more comparison target tokens included in the ‘brand index’. By comparing, a comparison result token called “Goyard” can be obtained from the unstructured product text. Additionally, the processor 110 may obtain a comparison result token called “new product” from the unstructured product text by comparing the unstructured product text with one or more comparison target tokens included in the ‘state index’. As a result, the processor 110 may generate product data corresponding to the unstructured product text, including a comparison result token of “Goyard” and a comparison result token of “New Product.”

In another example according to the present disclosure, the processor 110 detects a comparison result token that matches the comparison target token included in the price index within the unstructured product text, and then sets the number following the detected comparison result token to the price. It can be obtained by value. For example, the evaluation list includes a 'price index', and the 'price index' may include comparison target tokens consisting of {"sale price", "sale price", and "desired price"}. At this time, when the unstructured product text “Chanel bag desired price 2,000,000 won” is input to the processor 110, the processor 110 may generate product data including data “2,000,000” in the price value.

In one embodiment of the present disclosure, the processor 110 may calculate price information based on a product data set including a plurality of product data. The processor 110 may calculate price information from a product data set including product data about the same product. In the present disclosure, price information may include, for example, a price score and a purchase opinion regarding the price. Price scores can be awarded for different price ranges. The price score can be a real number within a certain range with a minimum and maximum value. Buying opinions on price may include words such as “expensive,” “reasonable,” “cheap,” “caution,” and similar words.

The processor 110 may calculate price information based on product quantity distribution according to price and at least one price reference value. The processor 110 may calculate product quantity distribution according to price based on a plurality of price values for a specific product included in the product data set. Hereinafter, it will be described in detail with reference to FIG. 2.

Figure 2 is an example diagram visually illustrating 'product quantity according to price' data according to an embodiment of the present disclosure. Figure 2 is a visual representation of the data to specifically explain the operation of the processor 110 using the 'product quantity according to price' data and does not limit the format or structure of the 'product quantity according to price' data. The graph in Figure 2 is a diagram showing the quantity distribution according to price in two-dimensional coordinates. The X-axis in Figure 2 represents the price, and the Y-axis represents the product quantity. If the parameters of the product data are sufficient, the distribution of 'product quantity according to price' may have an approximate normal distribution form, as shown in the graph of FIG. 2. If the parameters of product data are not sufficient, the distribution of product quantity according to price may have a random distribution form rather than a normal distribution.

The processor 110 may calculate price information using at least one price reference value. Below, a method of determining a price reference value according to the present disclosure will first be described, and then a method of calculating price information using the price reference value will be described. In some embodiments according to the present disclosure, the processor 110 may determine at least one price reference value based on a statistical value calculated from the product quantity distribution.

In a first embodiment of determining a price reference value according to the present disclosure, the processor 110 determines a price value that distinguishes N (N is a positive real number) percent and (100-N) percent of the total quantity from the product quantity distribution. It can be decided based on the price standard. There may be multiple price reference values. Referring again to Figure 2, in Figure 2 represents a plurality of price reference values. When the processor 110 determines the price reference value based on a statistical value calculated from the product quantity distribution, the price reference value may be the price value that distinguishes the bottom 20% (i.e., top 80%) from the rest. price threshold may be the price value that distinguishes the bottom 40% (i.e., top 60%) from the rest. Also, the price reference value may be the price value that distinguishes the bottom 60% (i.e., top 40%) from the rest. Price threshold in the same example continued: may be the price value that distinguishes the bottom 80% (i.e., top 20%) from the rest.

In the second embodiment of determining the price reference value according to the present disclosure, the processor 110 may determine the median of all price values from the product quantity distribution and then determine at least one price reference value according to the relative ratio with the median. . In this case, the first price reference value may be determined as 16% of the determined median value, the second price reference value may be determined as 32% of the determined median value, the third price reference value may be determined as 63% of the determined median value, etc.

In some embodiments according to the present disclosure, the processor 110 may determine at least one price reference value based on actual sales quantity distribution according to product price. “Actual sales quantity” according to the present disclosure refers to the quantity of actually traded products and can be calculated based on sales completion information included in product data. The processor 110 may identify one or more strings indicating completion of sale among the strings included in the unstructured product text and generate sale completion information of the product data based on this. One or more strings indicating the completion of the sale may include, for example, “sale completed”, “sale completed”, “transaction closed”, “transaction completed”, etc. The processor 110 may generate sale completion information of product data based on the sale completion time included in the unstructured product text. The sales completion time included in the unstructured product text may be time information entered by the author of the unstructured product text. If a plurality of product data overlaps with each other and sales completion information exists only for part of the overlapping product data, the processor 110 may not calculate the actual sales quantity for some product data for which the sales completion information exists. there is. In this case, the product data may not be data that has actually been sold, but data created as a result of the author duplicating unstructured product text. The processor 110 may calculate an overlap ratio of comparison result tokens included in the first product data and the second product data to determine whether the plurality of product data overlap each other. The processor 110 may compare the overlap ratio of comparison result tokens included in the first product data and the second product data with a predetermined overlap threshold ratio to determine whether there is duplicate data.

Figure 3 is an example diagram visually illustrating 'actual sales quantity according to price' data according to an embodiment of the present disclosure. Figure 3 is only a visual representation of the data to specifically explain the operation of the processor 110 using the data, and does not limit the format or structure of the 'actual sales quantity according to price' data. The X-axis in Figure 3 represents the price, and the Y-axis represents the actual sales quantity.

In a third embodiment of determining a price reference value according to the present disclosure, the processor 110 may determine at least one price reference value based on a point where the actual sales quantity according to price has a maximum value. The processor 110 uses two price values (eg Max_price - d, Max_price + d) that are separated by a predetermined price difference (d, d is a positive real number) from the price (Max_price) at which the actual sales quantity has the maximum value as the price reference value. You can decide. in Figure 3 represents a plurality of price reference values according to the third embodiment of the present disclosure. According to the present disclosure, the method of setting a price reference value in consideration of 'actual sales quantity according to price' and determining price information accordingly has the advantage of reasonably determining price information by reflecting actual transaction information that occurred between actual sellers and buyers. has

In some embodiments according to the present disclosure, the processor 110 determines at least one price reference value based on a statistical value calculated from the product quantity distribution, but additionally determines at least one price based on the actual sales quantity according to the product price. A standard value can be determined.

In the fourth embodiment of determining the price reference value according to the present disclosure, the processor 110 may add the product quantity according to the price and the actual sales quantity according to the price and determine at least one price reference value based on the summed quantity distribution. there is. The processor 110 may determine the price reference value based on the summed quantity distribution by applying at least one embodiment of the first to third embodiments for determining the price reference value described above.

In the fifth embodiment of determining the price reference value according to the present disclosure, the processor 110 primarily determines at least one price reference value based on the product quantity distribution according to price and then determines the price reference value according to the actual sales quantity distribution according to price. Based on this, the price standard can be determined secondarily. The fifth embodiment will be described with reference to FIG. 4. Figure 4 is an example diagram visually showing 'product quantity according to price' data and 'actual sales quantity according to price' data according to an embodiment of the present disclosure. Like Figures 2 and 3, Figure 4 is only a visual representation of data to specifically explain the operation of the processor 110 using a plurality of data, and does not limit the format or structure of the data according to the present disclosure. The first graph 510 in FIG. 4 shows the product quantity distribution function according to price. The second graph 530 in FIG. 4 shows the actual sales quantity distribution function according to price. In Figure 4, the processor 110 primarily based on the first graph 510 Two price reference values expressed as can be determined. The processor 110 may determine two price reference values from the first graph 510 based on the first or second embodiment described above. The processor 110 is a section defined by the two price reference values determined above (ie ), the price reference value can be determined secondarily based on the second graph 530. The processor 110 may secondarily add a new price reference value or change an existing price reference value based on the second graph 530. k in FIG. 5 may be a threshold value of the actual sales quantity calculated by the processor 110 in relation to the second graph 530 showing the actual sales quantity according to price. The processor 110 selects a section defined by the two determined price reference values in the second graph 530 (ie ) The threshold value (eg k) of the actual sales quantity can be determined based on the maximum and minimum values within ). For example, in the second graph 530 of FIG. 5 The maximum actual sales quantity within a section may be 100, and the minimum actual sales quantity may be 70. At this time, the processor 110 may determine the threshold value of the actual sales quantity by multiplying the difference between the maximum and minimum values by a predetermined ratio and adding it to the minimum value of the actual sales quantity. The above-mentioned example is only an example for implementation, and the present disclosure includes various methods for determining the threshold value of the actual sales quantity based on the second graph 530 without limitation.

When the processor 110 determines the actual sales quantity threshold (eg k) in the second graph 530, the processor 110 secondarily determines the price reference value primarily determined from the first graph 510. A price standard can be determined. The processor 110 uses the two primarily determined price reference values (eg ), as shown in Figure 5, the new price reference value ( ) can be added. According to the present disclosure, the price reference value can be determined by additionally considering the actual sales quantity according to the price, rather than only considering the quantity of the product according to the price. This has the effect of determining the price standard by considering both the “product quantity” that is currently being sold, which is considered in terms of the seller's desired sales price, and the “actual sales quantity,” which is the transaction that has been concluded, which is taken into account in terms of the buyer's desired purchase price. have Hereinafter, a method for the processor 110 to calculate price information using the price reference value calculated through some of the above-described embodiments will be described.

The processor 110 according to the present disclosure may calculate price information based on product quantity distribution according to price and at least one price reference value. Product quantity distribution according to price according to the present disclosure may include a maximum price value and a minimum price value. The processor 110 may assign a price score to each of the different 'partial price sections' divided based on at least one price reference value in the 'total price section' consisting of the maximum price value and the minimum price value. At least one price reference value that serves as a standard for setting a partial price range may be calculated based on some of the above-described embodiments. The processor 110 may grant a price score allocated to the corresponding partial price range to product data included in the partial price range. In one embodiment, when the minimum price value is 10,000 won, the maximum price value is 1,000,000 won, and the price reference value is 100,000 won, the processor 110 processes the product data included in the (10,000, 100,000) section and the (100,000, 1,000,000) section. Different price scores can be assigned to each product data included in . For product data whose price is a boundary value (e.g. 100,000), the processor 110 may assign a price score according to a predetermined method. For example, the price score for product data whose price is the boundary value of the price range may be the price score of the lower price range or the price score of the upper price range. In another embodiment, when the minimum price for a specific product is 10,000 won and the maximum price is 1,000,000 won, and the price reference value calculated by the processor 110 is 50,000 and 200,000, the processor 110 determines the price based on the price reference value. A price score of 2 points, 3 points, and 1 point can be assigned to each of the created sections (i.e., (10,000, 50,000) section, (50,000, 200,000) section, and (200,000, 1,000,000) section). The price information calculation method according to the present disclosure can calculate more effective price information by calculating a price reference value based on both the quantity of products sold and the actual quantity of products sold, and calculating price information based on this.

The processor 110 according to an embodiment of the present disclosure may assign the highest price score to the section containing the maximum value among a plurality of price sections included in a price range that is smaller than the average price value of all prices. . For example, the average price of all prices is 10,000 won, and multiple price ranges calculated according to at least one price standard are [2,000, 4,000], (4,000, 6,000), (6,000, 8,000], (8,000, 12,000], (12,000, 16,000], the processor 110 is in a price range smaller than 10,000 won, which is the average price, and provides A higher price score can be given compared to other products.

The processor 110 according to the present disclosure may generate evaluation information corresponding to at least one product data included in the product data set based on the calculated price information. The processor 110 may normalize the price score for each product data and generate evaluation information corresponding to each product data. The processor 110 may generate evaluation information based on the normalized evaluation information ranking. For example, the processor 110 may generate evaluation information from price information based on the normalization formula shown in Equation 1.

[Equation 1]

z represents the evaluation score generated as a result of normalization. represents the set of entire product data. represents the price score of each product data. represents the average value of the price scores. represents the standard deviation of price scores.

The processor 110 can stably provide price information by generating evaluation information corresponding to product data based on the price information. If normalization is not performed on the price information, the price information can be easily affected by outliers, such as the end values of the entire price range. In other words, price information may be information that is sensitive to outlier data. At this time, if evaluation information is generated by normalizing price scores as in the present disclosure, sensitivity to outlier data can be reduced. This has the effect of stably providing users with reliable evaluation information by reducing the amount of change in each score due to outliers.

The processor 110 according to the present disclosure can calculate authenticity information for each of a plurality of product data included in the product data set. In the present disclosure, authenticity information may be information for providing reliability of product data to buyers. Authenticity information may include a trust score that scores the reliability of product data. Authenticity information may include a description tag to explain reliability to buyers. Description tags may include, for example, content such as 'counterfeit product', 'caution of counterfeit product', 'genuine product', or tags with similar content. The description tag included in the authenticity information may be calculated based on the trust score included in the authenticity information.

The processor 110 may calculate authenticity information about product data corresponding to the unstructured product text from the unstructured product text. The evaluation list for evaluating product information may include fake indices. The processor 110 may inspect the unstructured product text based on a fake index included in the evaluation list. The false index may include multiple sub-indexes. A plurality of sub-indexes included in the false index according to the present disclosure may include a fake product pattern index, a purchase index, etc. The counterfeit product pattern index according to the present disclosure may include one or more comparison target tokens related to language expressions that may appear when the product is counterfeit. For example, the counterfeit pattern index may include comparative tokens such as “imitation,” “almost identical to the genuine product,” “distinguished from the genuine product,” “feel,” and “style.” The above-mentioned example is only an example for explanation, and the present disclosure includes various language expressions included in the text when the product is a counterfeit product. A purchase index according to the present disclosure may include one or more comparison tokens that relate to a linguistic expression for purchasing, but not for selling, an item. For example, the purchase index may include comparative tokens such as “buy,” “buy,” and “want to buy.” The purchase index is an index for detecting unstructured product text written for purchase rather than for sale, and may not be information used to evaluate a product.

The processor 110 may inspect the unstructured product text based on one or more comparison target tokens assigned to the false index and then calculate authenticity information according to the inspection result. The processor 110 may calculate authenticity information based on the number of detections in which one or more comparison target tokens assigned to a false index are present in the unstructured product text. For example, if the number of detections is 0, the trust score of the product data may be 3 and the description tag may be “genuine.” In the continued embodiment, if the number of detections is 1 to 3, the trust score of the corresponding product data may be 2 and the description tag may be “Beware of counterfeit product.” Additionally, if the number of detections is 4 or more, the trust score is 1 and the description tag may be “fake.” The above-mentioned example is only an example for explanation, and the present disclosure includes, without limitation, various methods of calculating authenticity information using a false index based on unstructured product text.

The processor 110 may calculate authenticity information about product data based on price information calculated from the product data set. The price information calculation method has been described above, and detailed description thereof will be omitted below. Price information according to the present disclosure may include quantity according to price of product data, scores for each price section of product data, etc. The processor 110 may calculate authenticity information based on at least some of the plurality of price ranges included in the price information. For example, the processor 110 may determine product data included in the lowest price range among a plurality of price ranges as “counterfeit products” or “caution of counterfeit products.” Referring again to FIG. 2, the processor 110 determines the price reference value of FIG. 2 Product data with a smaller price can be determined as “counterfeit” or “counterfeit.” The processor 110 according to the present disclosure can generate authenticity information by considering the difference between the price of the product and the average price of the product.

The processor 110 according to the present disclosure may calculate authentic information based on both false index and price information. As described above, the processor 110 may calculate a trust score for each product data after examining the unstructured product text based on at least one comparison target token assigned to the false index. Additionally, the processor 110 may determine a section in which a counterfeit product is suspected based on price information. The processor 110 may calculate authenticity information by multiplying the calculated trust scores by a weight according to the price range. For example, the trust score and price for each of the multiple product data calculated based on the false index are {(X1: 10,000 won, 2 points), (X2: 30,000 won, 3 points), (X3: 50,000 won, 1 point)} Let’s assume it appears like this. Continuing, let us assume that the weight according to the price range is 0.5 for less than 20,000 won and 1 for more than 20,000 won. At this time, the weighted trust score may appear as {(X1: 10,000 won, 1 point), (X2: 30,000 won, 3 points), (X3: 50,000 won, 1 point)}. The processor 110 may assign a description tag of “counterfeit product” to the X1 product data, “genuine product” to the X2 product data, and “counterfeit product” to the X3 product data. The processor 110 may remove at least one product data from the product data set based on the calculated authenticity information. If the product is a counterfeit product, the data is noise, and the present disclosure has the effect of not providing noise data to the user and further removing noise when calculating statistics on the entire data.

The processor 110 according to an embodiment of the present disclosure may calculate status information based on the product data set. In the present disclosure, 'state information' for a product may be used interchangeably with 'score indicating the state' of the product. The processor 110 generates product data by recognizing a string representing the status of the product (e.g. preservation status, purchase time, place of purchase, presence or absence of components, etc.) of the product in the unstructured product text, and then calculates status information based on the generated product data. can do. State information may be calculated based on state indexes included in product data and comparison result tokens included in each state index. The set of condition indices included in the product data may be a subset of the set of condition indices included in the evaluation list.

In order to calculate state information, the processor 110 according to an embodiment of the present disclosure calculates a state score for each product data included in the product data set based on at least one state index, and then calculates the state score for each product data included in the product data set. The calculated state score can be corrected based on the state auxiliary index.

The condition score according to the present disclosure is data included in status information and can be calculated based on a status index included in product data. The state index included in product data may include a plurality of sub-state indexes. Each substate index may include at least one comparison result token. The state index may include a preservation state index, an age index, a place of purchase index, etc. as a sub-state index. For example, the first product data is “I purchased it at Hyundai Department Store early this year. In the case of data generated for an unstructured product text such as “This is a completely new product without unpacking,” the preservation status index of the first product data generated by the processor 110 may include a comparison result token called ‘New product’. . Additionally, the year index of the first product data may include a comparison result token of 'early this year', and the purchase place index of the first product data may include a comparison result token of 'department store'. For another example, the second product data is “I bought it directly from overseas last year. In the case of data generated for the unstructured product text “There is a slight feeling of use,” the preservation status index of the second product data generated by the processor 110 may include a comparison result token called “Feeling of use.” Additionally, the year index of the second product data may include a comparison result token of 'last year', and the purchase place index of the second product data may include a comparison result token of 'overseas direct purchase'.

The processor 110 may calculate a status score for each product data based on the comparison result token assigned to each index. The processor 110 may calculate a status score for product data in proportion to the number of comparison result tokens included in the status index. The processor 110 may assign a higher score as the number of comparison result tokens included in the state index increases. For example, if the number of status index-related comparison result tokens included in the i product data is 10 and the number of status index-related comparison result tokens included in the j product data is 5, the processor 110 processes the i product data A high score can be given for .

The processor 110 may calculate a status score for product data by weighting each token as a result of comparing at least one index. In a continued embodiment relating to the first product data and the second product data, processor 110 may assign predetermined scores to the comparison result tokens assigned to the retention status index. The predetermined score of the preservation status index may be set to give a higher score to a string that is judged to have a good preservation status. For example, a predetermined score can be assigned to one or more comparison result tokens by varying the size of the score, such as “new product” > “just like new” > “feel of use.” Additionally, the processor 110 may assign a higher score as the comparison result token assigned to the age index indicates a closer past. For example, the scores given to the year index can be differentiated, such as “early this year” > “last year” > “a few years ago.” Additionally, the processor 110 may grant predetermined scores to the comparison result tokens assigned to the purchase destination index. For example, the scores given to the purchase place index can be differentiated, such as “Department Store” > “Outlet” > “Overseas Direct Purchase”. When converting scores as in the example above, the processor 110 may grant a higher status score to the first product data than to the second product data. The above-described embodiment is merely intended to specifically describe one embodiment of the present disclosure that calculates the status score for product data based on the status index, and the present disclosure includes various embodiments without limitation.

The processor 110 according to the present disclosure may correct the state score calculated as described above based on at least one state auxiliary index. The comparison result token included in the state auxiliary index of the present disclosure may be a string that modifies the comparison result token included in the state index. For example, the comparison result token included in the status auxiliary index may be a negative or an adverb. Negative words can include “no”, “without”, “not”, “but”, etc. Adverbs can include “a little,” “a little,” “a lot,” and “completely.” The status auxiliary index according to the present disclosure may be composed of tokens that increase or decrease the strength of the linguistic meaning indicated by the comparison result token included in the status index. The processor 110 may correct the state score calculated based on the state index based on the state assistance index.

An example of a condition score correction method will be described using the above-described first product data. “I bought it at Hyundai Department Store early this year. In the first product data regarding “This is a completely new product without even opening the packaging,” the token as a result of comparing the condition index included in the product data may include “New product.” In this case, as a token that modifies “new product,” the status auxiliary index may include a comparison result token called “complete.” For example, a comparison result token called “complete” may be a token that increases the strength of the linguistic meaning of the comparison result token it modifies. The processor 110 may correct the status score based on the modifying comparison result token and the modifying comparison result token. If the score given to the token as a result of the comparison of “new product” is 10 points, the processor 110 may increase the absolute value of the score by considering the modifier “complete.” Additionally, the processor 110 may consider the modifier “complete” and increase the absolute value of the previously assigned status score by multiplying the number by a number whose absolute value is 1 or more. As a result of correction by the processor 110, the score given to the comparison result token as “new product” can be adjusted to 11 points.

Another embodiment of the condition score correction method will be described using the above-described second product data. “I bought it directly from overseas last year. In the second product data regarding “There is a slight feeling of use.”, the token as a result of comparison of the condition index included in the product data may include “a feeling of use.” In this case, as a token that modifies “feel of use,” the status auxiliary index may include a comparison result token called “a little.” For example, a comparison result token of “a little” may be a token that reduces the strength of the linguistic meaning of the comparison result token it modifies. If the score given to the token by the processor 110 as a result of the comparison of “feel of use” is 5 points, the processor 110 may reduce the absolute value of the score by considering the modifier “slightly.” Additionally, the processor 110 may reduce the absolute value of the previously assigned status score by considering the modifier “slightly” and multiplying the number by a number whose absolute value is less than 1. As a result of correction by the processor 110, the score given to the token as a result of the comparison of “feel of use” may be adjusted to 4 points. The above-described embodiment is nothing more than a description to specifically disclose an embodiment of the present disclosure that corrects the previously calculated status score for product data based additionally on the status auxiliary index, and the present disclosure is intended to describe various embodiments without limitation. Includes.

According to an embodiment of the present disclosure, the step of correcting the status score may be performed based on the token distance between the comparison result token corresponding to the status index and the comparison result token corresponding to the status auxiliary index. In the present disclosure, token distance may mean word distance within a sentence. For example, in the sentence “Lorem ipsum dolor sit amet” the token distance between Lorem and dolor might be 2. Also, the token distance between sit and amet can be 1.

In one embodiment of the present disclosure, the processor 110 may correct the state score when the token distance between the comparison result token corresponding to the state index and the comparison result token corresponding to the state auxiliary index is less than or equal to a predetermined threshold token distance. there is. In one embodiment, assume that the comparison result token corresponding to the state index is “scratch” and the comparison result token corresponding to the state auxiliary index is “missing.” And the predetermined threshold token distance may be 2. At this time, there may be third product data created based on the text “There are a few scratches, but not really,” and fourth product data created based on the text “There are no scratches.” In the third product data, the token distance between “scratch” and “no” is 4. In the third product data, the processor 110 may not correct the status score calculated based on the token “scratch”. On the other hand, in the fourth product data, the token distance between “scratch” and “nothing” is 1, and the processor 110 corrects the status score calculated based on the token “scratch” based on the comparison result token of “nothing”. can do. As described above, the processor 110 according to the present disclosure can reasonably analyze the text and finally calculate the state score by considering the distance between the state auxiliary index and the state index, and considering the fact that the strength of the formula is different even if the formula is the same. there is.

In an additional embodiment of the present disclosure, the processor 110 may correct the state score in such a way that the range of change in the state score due to correction increases as the token distance becomes closer. For example, based on the same token pair (tokens included in the state index - tokens included in the state secondary index), the change in state score when the token distance is 1 may be greater than the change in state score when the token distance is 3. . Refer again to the third and fourth product data described above, but assume that the status score given for “scratch” is '-5'. At this time, in order to increase the variation due to correction of the status score as the token distance becomes closer, the processor 110 uses a correction method using the negative word “no”. You can take the multiplication method. That is, in the third product data, the status score given to “scratch” has This can be multiplied. As a result, the corrected health score is It can be. Similarly, in the fourth product data, the status score assigned to “scratch” has This can be multiplied. The resulting corrected health score may be 5. In this way, the processor 110 according to the present disclosure corrects the status score based on the token as a result of comparison with the status auxiliary index, and additionally corrects the status score in inverse proportion to the distance, so that even words with the same modifier relationship have meaning according to the distance. It can be taken into account that the intensity varies. For example, the expression “there are no scratches” conveys the presence or absence of “scratches” more clearly than the expression “there are no scratches” above, and according to the present disclosure, the difference in status scores reflecting the above linguistic meaning is expressed as a token. It can be effectively calculated based on the ratio of distance and fluctuation width. The above-described example is merely an example for specifically describing the present disclosure, and the present disclosure includes various embodiments without limitation.

The processor 110 according to an embodiment of the present disclosure may generate evaluation information corresponding to at least one product data included in the product data set based on price information and additionally based on status information. The processor 110 may generate a normalized state score by normalizing the state score included in the state information. The normalized status score can be calculated based on statistics such as the mean, variance, and standard deviation of the status score. The normalized state score can be calculated based on the operation of converting each state score into a normal distribution based on Equation 1 described above. The processor 110 may generate evaluation information by weighting the normalized status score and the above-described normalized price score. The weighting ratio for the weighted sum of the status score and the price score can be predetermined at an arbitrary ratio for personalization. The weight for the weighted sum of the status score and price score may be 1:1. According to one embodiment, let's assume that the status score and price score are 6 and 8, respectively. If the weighting ratio for the weighted sum of the status score and the price score is 3:7, the evaluation score may be 6*0.3 + 8*0.7 = 0.74. On the other hand, if the weighting ratio for the weighted sum of the status score and the price score is 6:4, the evaluation score may be 6*0.6 + 8*0.4 = 0.68. That is, the processor 110 may calculate different evaluation information according to the final weighting ratio even if the price score and status score are calculated identically.

The processor 110 according to an embodiment of the present disclosure calculates seller information based on the product data set and generates evaluation information corresponding to at least one product data included in the product data set based on the seller information additionally. You can.

The processor 110 may calculate seller information based on the seller's activity period, seller score, etc. included in the product data. The processor 110 may obtain the first upload time of product data of a specific seller from the product data set. The processor 110 may obtain the last upload time of product data of a specific seller from the product data set. The processor 110 may calculate the seller's activity period based on the difference between the first upload time and the last upload time of a specific seller. The processor 110 may assign a higher score the longer the seller's activity period is and calculate seller information based on this. The processor 110 may obtain a seller score for each seller included in the meta information of the unstructured product text and calculate seller information based on this.

The processor 110 may generate evaluation information corresponding to product data included in the product data set based additionally on the seller information. Processor 110 may normalize seller scores to generate evaluation information based on seller information. Since the normalized seller score can be calculated in a similar way to the above-described price score or status score, the description below is omitted. Processor 110 may calculate final evaluation information based on the relative ratio of condition score, price score, and seller score. The processor 110 may assign weights to each of the status score, price score, and seller score, and calculate evaluation information based on the assigned weights. For example, the weights for the condition score, price score, and seller score may each be set at a ratio of 1:1:1. The relative ratio (i.e., weight) between at least two scores for generating evaluation information of the present disclosure may be predetermined at an arbitrary ratio. The processor 110 may randomly determine the weight assigned to each score and calculate evaluation information based on the assigned weight. Here, the method of arbitrarily determining the weight may be performed, for example, based on a user's input through the input unit of the computing device 100. The processor 110 may calculate different evaluation information according to the weighting ratio in the price score, condition score, and seller score calculated equally. This disclosure has the advantage of being able to finally calculate evaluation information by considering a specific user's tendencies such as price preference, status preference, or seller preference.

Figure 5 is a flowchart showing a process for evaluating product information according to an embodiment of the present disclosure. The processor 110 according to the present disclosure may generate standardized product data corresponding to unstructured product text in step S610. The processor 110 may generate standardized product data based on an evaluation list including an evaluation index. One or more comparison target tokens are assigned to each evaluation index, and as a result of comparison by the processor 110, a token determined to be included in the unstructured product text among the comparison target tokens may be included in the product data as a 'comparison result token'. In step S630, the processor 110 may calculate price information based on a product data set including a plurality of product data. The processor 110 may calculate price information based on product quantity distribution according to price and at least one price reference value. The price reference value may be determined based on statistical values calculated from product quantity distribution. The price reference value may be determined based on the actual sales quantity according to the product price. The price reference value is based on a statistical value calculated from the product quantity distribution, but may be determined additionally based on the actual sales quantity according to the product price. In step S650, the processor 110 may generate evaluation information corresponding to at least one product data included in the product data set based on the calculated price information. The processor 110 may normalize the price scores included in the price information to generate an evaluation score that takes the overall distribution into consideration.

Figure 6 is a flowchart showing a process for evaluating product information according to another embodiment of the present disclosure. The processor 110 may generate standardized product data corresponding to the unstructured product text in step S710. In step S730, the processor 110 may calculate price information based on a product data set including a plurality of product data. S710 and S730 may consist of steps similar to S610 and S630 of FIG. 5. In step S750, the processor 110 may calculate status information based on a product data set including a plurality of product data. Status information can be calculated based on a comparison result token corresponding to the status index in the product data. The processor 110 may correct the status score calculated based on the comparison result token corresponding to the status auxiliary index in the product data. The comparison result token included in the state auxiliary index may be a string for modifying the comparison result token included in the state index. The processor 110 may correct the state score based on the token distance between the comparison result tokens corresponding to each of the state index and the state auxiliary index. In step S770, the processor 110 may calculate seller information based on a product data set including a plurality of product data. Seller information may be calculated based on the seller's activity period, seller score, etc. In step S790, the processor 110 may generate evaluation information based on price information, status information, and seller information. The processor 110 may normalize the calculated price score, status score, and seller score, respectively, and convert them into numerical data that can be summed. The processor 110 may calculate the final evaluation score by weighting the normalized price score, condition score, and seller score at a predetermined ratio. The predetermined ratio may be determined to be a different ratio depending on the user.

7 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented. Although the present disclosure has generally been described above as being capable of being implemented by a computing device, those skilled in the art will understand that the present disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or in hardware and software. It will be well known that it can be implemented as a combination.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like (each of which may be It will be appreciated that the system may be implemented with other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media may also be used in the example operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as via the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (18)

A product information evaluation method performed by a computing device including at least one processor, comprising:
Generating standardized product data corresponding to unstructured product text;
Calculating price information based on a product data set including a plurality of product data;
calculating status information based on the product data set; and
generating evaluation information corresponding to at least one product data included in the product data set based on the price information and additionally based on the status information;
Including,
The step of calculating the status information is,
calculating a state score for each product data included in the product data set based on at least one state index; and
correcting the calculated health score based on at least one health assistance index;
Including,
How to evaluate product information.
According to claim 1,
The step of generating the product data is,
generating standardized product data from the unstructured product text based on an evaluation list including at least one evaluation index, each of the at least one evaluation index being assigned at least one token to be compared;
Including,
How to evaluate product information.
According to claim 2,
The product data is,
Contains at least one comparison result token,
The token as a result of the comparison is,
Obtained based on the results of comparing the comparison target token assigned to the evaluation index with the unstructured product text,
How to evaluate product information.
According to claim 1,
calculating authenticity information for each of a plurality of product data included in the product data set; and
removing at least one product data from the product data set based on the authenticity information;
Containing more,
How to evaluate product information.
According to claim 4,
The step of calculating the authenticity information is,
inspecting the unstructured product text based on a fake index included in an evaluation list for evaluating product information;
Including,
How to evaluate product information.
According to claim 4,
The step of calculating the authenticity information is,
Carried out based on the above price information,
How to evaluate product information.
According to claim 1,
The step of calculating the price information is,
Calculating product quantity distribution according to product price; and
calculating price information based on the product quantity distribution and at least one price reference value;
Including,
How to evaluate product information.
According to claim 7,
The at least one price reference value is,
Determined based on statistical values calculated from the product quantity distribution,
How to evaluate product information.
According to claim 7,
The at least one price reference value is,
Determined based on the actual sales quantity distribution according to product price,
How to evaluate product information.
According to claim 7,
The at least one price reference value is,
Based on statistical values calculated from the product quantity distribution,
Determined additionally based on the actual sales quantity distribution according to product price,
How to evaluate product information.
delete delete According to claim 1,
The comparison result token included in the state auxiliary index is,
A string that modifies the comparison result token included in the status index,
How to evaluate product information.
According to claim 1,
The step of correcting the status score is,
Performed based on the token distance between the comparison result token corresponding to the state index and the comparison result token corresponding to the state auxiliary index,
How to evaluate product information.
According to claim 14,
The step of correcting the status score based on the token distance is,
This is performed in such a way that the closer the token distance is, the greater the change in status score due to correction.
How to evaluate product information.
According to claim 1,
calculating seller information based on the product data set;
It further includes,
The step of generating the evaluation information is,
generating evaluation information corresponding to at least one product data included in the product data set based additionally on the seller information;
Including,
How to evaluate product information.
A computer program stored in a computer-readable storage medium, wherein the computer program, when executed on one or more processors, performs the following operations for evaluating product information, the operations being:
An operation of generating standardized product data corresponding to unstructured product text;
An operation of calculating price information based on a product data set including a plurality of product data;
An operation of calculating status information based on the product data set; and
generating evaluation information corresponding to at least one product data included in the product data set based on the price information and additionally based on the status information;
Including,
The operation of calculating the status information is,
Computing a state score for each product data included in the product data set based on at least one state index; and
Correcting the calculated health score based on at least one health assistance index;
Including,
A computer program stored on a computer-readable storage medium.
As a product information evaluation device,
One or more processors;
one or more memories; and
network department;
Includes, and
The one or more processors:
Generate standardized product data corresponding to unstructured product text,
Calculate price information based on a product data set containing multiple product data,
Calculate status information based on the product data set, and
Generating evaluation information corresponding to at least one product data included in the product data set based on the price information, but additionally based on the status information,
The process of calculating the status information includes calculating a status score for each product data included in the product data set based on at least one status index; and
correcting the calculated state score based on at least one state auxiliary index;
Including,
Product information evaluation device.

Images