KR20200048004A - Product recommendation system and method based on user purchase criterion and product review - Google Patents

Abstract

According to one embodiment of the present invention, a system for recommending a product based on a user purchase criterion and a product review comprises: a data collection unit collecting a product list related to a product searched by a user and product review data related to the product; a product evaluation unit digitizing positive evaluation and negative evaluation contained in the product review data to calculate an evaluation score for the product; and a product recommendation unit extracting a product to be recommended to the user from the product list based on the calculated evaluation score to provide the product to be recommended to the user.

Description

Product recommendation system and method based on user purchase criteria and product review {PRODUCT RECOMMENDATION SYSTEM AND METHOD BASED USER PURCHASE CRITERION AND PRODUCT REVIEW}

Embodiments of the present invention relate to a product recommendation system and method, and more specifically, when purchasing a product, the product review is evaluated based on a purchase criterion selected by the user, and the user's preference is properly provided by arranging the products to be recommended to the user. It is possible to recommend customized product information that reflects the user's purchase criteria and product review-based product recommendation system and method to help users make efficient decisions by saving time spent purchasing products. will be.

Recently, user reviews that allow users to share their opinions on products are being reviewed by various buyers, and are shared and activated through various channels such as SNS and blogs. These product reviews contain more detailed and reliable information about the user's preferences for the product, which can be usefully utilized in the recommendation system, and in fact, many studies have been conducted.

In addition, due to the nature of the open web, the amount of product review data created by consumers online has increased rapidly, and several methods for analyzing a large amount of opinion information naturally included in product reviews have been proposed.

However, the existing product recommendation system has low satisfaction because it is based on unobjective information or does not take into account the user's preferences. Satisfaction with the recommended product can be improved if the user considers the criteria that are considered important when purchasing the product.

A related prior art is Republic of Korea Patent Registration No. 10-1621938 (Invention name: online shopping information recommendation system using user registration posting information, registration date: 2016.05.11).

According to an embodiment of the present invention, when a product is purchased, a product review is evaluated based on a purchase criterion selected by the user, and the product to be recommended to the user is sorted and provided, so that user-customized product information reflecting the user's preference can be recommended. It provides user recommendation system and product recommendation system and method based on user purchase criteria and product review to help users make efficient decisions by saving time spent purchasing products.

The problem to be solved by the present invention is not limited to the problem (s) mentioned above, and another problem (s) not mentioned will be clearly understood by those skilled in the art from the following description.

A user recommendation system and a product review-based product recommendation system according to an embodiment of the present invention include a data collection unit for collecting a product list for a product searched by a user and product review data for the product; A product evaluation unit for numerically evaluating positive and negative evaluations contained in the product review data to calculate an evaluation score for the product; And a product recommendation unit extracting a product to be recommended to the user from the product list based on the calculated evaluation score and providing the product to the user.

The data collection unit crawls and collects product information including the ID, product name, and URL (Uniform Resource Locator) of each product included in the product list, and product review data for each product from an online shopping mall system can do.

When crawling the product review data, the data collection unit may read and store sentence by sentence based on a period to be useful for later morphological analysis.

When the purchase criteria for the product are selected by the user when searching for the product, the data collection unit may collect the product list and the product review data based on the selected purchase criterion.

The data collection unit stores the collected data in a database (DB), but stores product information including the ID, product name, and URL of each product included in the product list in a first table of the database, and each The product-specific ID and the product review data are stored in a second table of the database, and product review data including the purchase criterion and related words related to the purchase criterion may be stored in a third table of the database.

The data collection unit may perform noise filtering on the product review data to remove noise including special characters and meaningless stopwords from the product review data.

The product evaluation unit may perform a morpheme analysis on the product review data from which noise has been removed through the noise filtering to quantify positive and negative evaluations contained in the product review data.

The product evaluation unit divides each product included in the product list and counts the number of positive evaluations and the number of negative evaluations among all product reviews for each product based on the result of morphological analysis of the product review data. And calculating a negative evaluation rate, calculating a positive score corresponding to the positive evaluation and a negative score corresponding to the negative evaluation based on the calculated positive evaluation rate and the negative evaluation rate, and calculating the positive and negative scores. The sum of the values can be divided by the total number of product reviews to calculate the average value of the evaluation scores.

The product recommendation unit may extract the top N (where N is a natural number) products having a high average value of the evaluation scores as products to be recommended to the user, and arrange the extracted products in ascending order and provide the products to the user.

A method for recommending a product based on a user purchase criterion and a product review according to an embodiment of the present invention includes: a data collection unit of the product recommendation system collecting a product list and a product review data on the product retrieved by the user; Calculating an evaluation score for the product by quantifying positive and negative evaluations contained in the product review data by the product evaluation unit of the product recommendation system; And extracting a product to be recommended to the user from the product list based on the calculated evaluation score and providing it to the user.

The user purchasing criteria and the product review-based product recommendation method according to an embodiment of the present invention, when the purchase criteria for the product are selected by the user when searching for the product, the data collection unit is based on the selected purchase criteria. The method may further include collecting the product list and the product review data.

The step of calculating an evaluation score for the product is based on a result of morphological analysis of the product review data by dividing each product included in the product list, and the number of positive evaluations and negative evaluations among all product reviews for each product Calculating a positive evaluation rate and a negative evaluation rate by counting the number of; Calculating a positive score corresponding to the positive evaluation and a negative score corresponding to the negative evaluation based on the calculated positive evaluation rate and the negative evaluation rate; And calculating a mean value of the evaluation score by dividing the sum of the calculated positive and negative scores by the total number of product reviews.

The providing step to the user may include extracting, as a product to be recommended to the user, the top N (where N is a natural number) products having a high average value of the evaluation scores; And arranging the extracted products in ascending order and providing them to the user.

Details of other embodiments are included in the detailed description and accompanying drawings.

According to an embodiment of the present invention, when a product is purchased, product reviews are evaluated based on a purchase criterion selected by a user, and products to be recommended are sorted and provided to the user, so that user-customized product information reflecting the user's preferences can be recommended. , This can help users make efficient decisions by saving time spent purchasing products.

1 is a diagram illustrating a network configuration of a product recommendation system based on user purchase criteria and product reviews according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a detailed configuration of the product recommendation system of FIG. 1.
FIG. 3 is a block diagram illustrating a detailed configuration of the database DB of FIG. 2.
4 and 5 are flowcharts illustrating a user purchasing criterion and a product review based product recommendation method according to an embodiment of the present invention.
FIG. 6 is a diagram showing a list of 12 products in which the purchasing criteria of 'cost ratio' and the keyword 'price' associated with the keyword are extracted from the list of 12 products extracted from the review sentence.
7 is an example of a review in which morphological analysis is performed by extracting only reviews including the keyword 'price' associated with the cost-effectiveness as an example of a purchase criterion of 'cost-effectiveness'.
FIG. 8 is a view showing a table summarizing the average and calculating the positive and negative scores of each of the 12 product reviews previously extracted.

Advantages and / or features of the present invention and methods for achieving them will become apparent by referring to embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains. It is provided to completely inform the person having the scope of the invention, and the present invention is only defined by the scope of the claims. The same reference numerals refer to the same components throughout the specification.

In addition, a preferred embodiment of the present invention to be carried out below is provided in each system functional configuration in order to efficiently describe the technical components constituting the present invention, or a system function commonly provided in the technical field to which the present invention pertains. The configuration is omitted as much as possible, and the functional configuration that should be additionally provided for the present invention will be mainly described. If a person having ordinary knowledge in the technical field to which the present invention pertains, it will be possible to easily understand the functions of components that have been used in the prior art among the omitted functional configurations not shown below, and also the omitted components as described above. The relationship between the elements and the components added for the invention will also be clearly understood.

In addition, in the following description, the terms "transmission", "communication", "transmission", "reception" of a signal or information, or other similar meanings means that a signal or information is directly transmitted from one component to another. Not only that, it also includes passing through other components. In particular, "transmitting" or "transmitting" a signal or information to a component indicates the final destination of the signal or information, not a direct destination. The same is true for the "reception" of a signal or information.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram showing a network configuration of a product recommendation system based on user purchase criteria and product reviews according to an embodiment of the present invention, and FIG. 2 is a block diagram illustrating a detailed configuration of the product recommendation system of FIG. 1. 3 is a block diagram illustrating a detailed configuration of the database DB of FIG. 2.

1 to 3, the user purchasing criteria and product review based product recommendation system 100 according to an embodiment of the present invention includes a data collection unit 210, a product evaluation unit 220, and a product recommendation unit 230 ), A database (DB) 240, and a control unit 250.

The data collection unit 210 may collect a product list related to a product searched by a user and product review data related to the product. Specifically, the user may access the online shopping mall system 102 through the user terminal 101 and search for a product to be purchased. In this case, the data collection unit 210 may collect a product list related to the searched product and product review data related to the product in conjunction with the online shopping mall system 102.

To this end, the data collection unit 210 stores product information including the ID of each product included in the product list, a product name, and a URL (Uniform Resource Locator) of each product, and product review data for each product in the online shopping mall. It can be collected by crawling from the system 102.

In addition, when crawling the product review data, the data collection unit 210 reads and stores the sentences included in the product review data one by one based on a period to be useful for later morpheme analysis. Can be.

Meanwhile, when the purchase criteria for the product are selected by the user when searching for the product, the data collection unit 210 may collect the product list and the product review data based on the selected purchase criterion. . Here, the purchase criterion is a criterion that is given priority when the user selects a product, and may include durability, design, and cost ratio of the product.

For example, when the user selects a price ratio as a purchase criterion when searching for the product, the data collection unit 210 selects a review including a sentence related to a price from among reviews related to the product, and the selected Reviews can be collected as the product review data.

In addition, the purchase criteria may further include an influencer. Here, influencer is a term that refers to a “power blogger” who runs a high-impact blog on a portal site, a social network service (SNS) user with hundreds of thousands of followers, and one broadcaster. Influencers can be divided into creator-type influencers that produce content and model-type influencers in the fashion beauty field. On the other hand, the marketing method using a person who exerts influence is influencer marketing, and the user purchase criteria and product review based product recommendation system 100 according to an embodiment of the present invention can also be applied to influencer marketing.

 For example, when the user selects an influencer as a purchase criterion when searching for the product, the data collection unit 210 is a product related to the influencer among products searched by the user, that is, a celebrity or celebrity or YouTube. A product used or recommended by an influencer such as a star may be selected, and reviews related to the selected product may be collected as the product review data. At this time, the data collection unit 210 may select a product related to the influencer among products searched by the user through data mining.

As described above, when the product is searched, the user may directly select a purchase criterion for the product, but in another embodiment, when searching for the product, the recommended purchase criterion may be automatically applied without selecting a purchase criterion for the product. have. For example, the data collection unit 210 analyzes purchase criteria for a certain period (eg, 1 year) to calculate the number of user selections for each purchase criterion, and is based on the calculated number of user selections for each purchase criterion By giving priority to each purchase criterion, the purchase criterion of the highest priority may be recommended to the user to assist the user's selection or the purchase criterion of the highest priority may be directly applied as the purchase criterion selected by the user.

For another example, the data collection unit 210 analyzes the purchase criteria for a certain period (eg, 1 year) to calculate the number of user selections for each purchase criterion, and the calculated number of user selections for each purchase criterion. On the basis of this, the purchase criterion with the highest weight is recommended to the user by assigning a weight for each purchase criterion. By recommending both (A) and purchasing criteria (B) to the user, it is also possible to provide the purchasing criteria preference list (A, B) to the user to directly select the purchasing criteria preferred by other users.

For another example, the data collection unit 210 analyzes purchase criteria for a certain period (eg, 1 year) according to gender and age conditions to calculate the number of user selections for each purchase criteria according to gender and age conditions. In addition, a weight may be assigned to each purchase criterion based on the calculated number of user selections for each purchase criterion.

The data collection unit 210 may store the collected data (product list, product review data) in a database (DB) 240. To this end, the database 240 may include a first table 310, second data 320 and third data 330 as shown in FIG. 3.

In other words, the data collection unit 210 stores product information including the ID, product name, and URL of each product included in the product list in the first table 310 of the database 240, and The product-specific ID and the product review data may be stored in the second table 320 of the database 240. In addition, the data collection unit 210 may store product review data including the purchase criterion and related words related to the purchase criterion in the third table 330 of the database 240.

The data collection unit 210 may perform noise filtering on the product review data to remove noise such as special characters and meaningless stopwords from the product review data. As a result, the data collection unit 210 may reconstruct the product review data with only meaningful data so that it can be useful for later morphological analysis.

The product evaluation unit 220 may calculate the evaluation score for the product by quantifying the positive and negative evaluations contained in the product review data. To this end, the product evaluation unit 220 performs morphological analysis on product review data from which noise has been removed through the noise filtering, thereby quantifying the positive and negative evaluations contained in the product review data. The evaluation score for can be calculated.

Specifically, the product evaluation unit 220 morphologically analyzes the product review data by dividing each product included in the product list, and based on the result of the morpheme analysis, a positive evaluation among all product reviews for the product The number and the number of negative evaluations can be counted. The product evaluation unit 220 calculates a positive evaluation ratio based on the number of positive evaluations compared to the total number of product reviews for each product, and is negative based on the number of negative evaluations compared to the total number of product reviews for each product. The evaluation rate can be calculated.

The product evaluation unit 220 may calculate a positive score corresponding to the positive evaluation based on the calculated positive evaluation rate, and calculate a negative score corresponding to the negative evaluation based on the calculated negative evaluation rate. have. The product evaluation unit 220 may calculate a mean value of the evaluation scores for the product by performing a division operation that divides the sum of the calculated positive and negative scores by the total number of product reviews.

The product recommendation unit 230 extracts a product to be recommended to the user from the product list based on the evaluation score (average value) calculated by the product evaluation unit 220, and extracts the extracted product from the user terminal ( 101), it is possible to provide a recommendation product based on a purchase criterion and a product review to the user.

At this time, the product recommendation unit 230 extracts the top N (where N is a natural number) having a high average value of the evaluation score, for example, 10 products as products to be recommended to the user, and sorts the extracted products in ascending order. Can be provided to the user.

The database 240 may store data collected by the data collection unit 210. In particular, as described above, the database 240 may distribute and store the collected data in the first to third tables 310, 320, and 330.

Specifically, the first table 310 stores product information including each product ID, product name, and URL of each product included in the product list, and the second table 320 includes each product ID and the product. Review data may be stored. In addition, the third table 330 may store product review data including purchase criteria selected by the user when searching for products and related words related to the purchase criteria.

The control unit 250 is a product recommendation system 100 based on user purchase criteria and product reviews according to an embodiment of the present invention, that is, the data collection unit 210, the product evaluation unit 220, and the product recommendation unit ( 230), the operation of the database 240 and the like can be overall controlled.

The apparatus described above may be implemented with hardware components, software components, and / or combinations of hardware components and software components. For example, the devices and components described in the embodiments include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor (micro signal processor), a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose computers or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may run an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and / or data may be interpreted by a processing device, or to provide instructions or data to a processing device, of any type of machine, component, physical device, virtual equipment, computer storage medium or device. , Or may be permanently or temporarily embodied in the transmitted signal wave. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

4 and 5 are flowcharts illustrating a user purchasing criterion and a product review based product recommendation method according to an embodiment of the present invention.

The product recommendation method described here is only one embodiment of the present invention. In addition, various steps may be added as necessary, and the following steps may also be performed by changing the order. It is not limited to each step described and the order.

Referring first to FIGS. 1, 2 and 4, in step 410, a user may access the online shopping mall system 102 through the user terminal 101 and search for a product to be purchased.

Next, in step 420, the user may select a purchase criterion for the product when searching for the product. Here, the purchase criterion is a criterion that is given priority when the user selects a product, and may include durability, design, and cost ratio of the product.

Next, in step 430, the data collection unit 210 of the product recommendation system 100 may collect a product list related to the product searched by the user and product review data related to the product.

Next, in step 440, the data collection unit 210 of the product recommendation system 100 may store the collected data (product list, product review data, etc.) in the database 240.

Next, in step 450, the product evaluation unit 220 of the product recommendation system 100 may quantify the positive and negative evaluations contained in the product review data to calculate evaluation scores for the product. . This will be described in detail with reference to FIG. 5 as follows.

That is, in step 510, the product evaluation unit 220 may morphologically analyze the product review data by dividing each product included in the product list. Thereafter, in step 520, the product evaluation unit 220 counts the number of positive evaluations and the number of negative evaluations among all product reviews for each product based on the result of the morpheme analysis, and the positive evaluation ratio and the negative evaluation The ratio can be calculated. Thereafter, in step 530, the product evaluation unit 220 may calculate a positive score corresponding to the positive evaluation and a negative score corresponding to the negative evaluation based on the calculated positive evaluation rate and negative evaluation rate. . Thereafter, in step 540, the product evaluation unit 220 may calculate the average value of the evaluation scores for the product by dividing the sum of the calculated positive and negative scores by the total number of product reviews.

Referring back to FIG. 5, in step 460, the product recommendation unit 230 of the product recommendation system 100 receives the product from the product list based on the evaluation score calculated by the product evaluation unit 220 to the user. You can extract products to recommend. In this case, the product recommendation unit 230 may extract the top N (where N is a natural number) products having a high average value of the evaluation scores as products to be recommended to the user.

Next, in step 470, the product recommendation unit 230 of the product recommendation system 100 may arrange the extracted products in ascending order and provide them to the user through the user terminal 101.

Hereinafter, an example of implementing a user recommendation system and a product review based product recommendation system according to an embodiment of the present invention will be described in detail.

System implementation

The system's building environment used CPU-Intel i5-4690, RAM-8G based on Windows operating system. The language used is Python, and the database is built using MySQL. In addition, a case in which the user selects 'cost ratio' as a purchase basis is implemented as an example.

The data collection site recorded the highest transaction amount in Korea and was selected as 'G Company', which was ranked first in consumer brand reputation. Among the categories of G company in the largest shopping mall in Korea, the 'stroller' of child care products is limited to collecting product information and user-written reviews. As the quality of product reviews influences this experiment, a category was selected as a child care product with many relatively honest reviews. In more detail, we collect the product name, product URL, and product review of the 'stroller' product item, which has the most reviews in the category 'Child care products', using Beautifulsoup, a Python library that can crawl web data.

However, product reviews provided by the online shopping mall system that you want to crawl can only be viewed by clicking the 'More' button or when a certain number of reviews are created, and then an action on the web browser to page through is required. Therefore, we use Selenium, a web page test tool that can automatically perform these actions when crawling these actions. The Selenium package functions to launch a web browser through the product URL in a Python environment. Crawls the product name, product classification, reviews, etc. using HTML tag names.

Of the product reviews that were previously crawled and saved, among the reviews that included 'cost ratio' and 'price', only the reviews with more than 20 reviews were extracted and stored. As a result of extraction as in FIG. 6, it was considered as 12 products. FIG. 6 shows a list of 12 products in which the purchase criteria of 'cost ratio' and the keyword 'price' associated with the keyword are extracted from the list of 12 products extracted only from the names of the included products in the review sentence.

For the product reviews obtained by crawling, install 'KoNLP', a package that processes Hangul of the Python program. In addition, the morpheme analysis is performed based on the morpheme analysis based on the kid dictionary to extract only nouns and adjectives from each product review sentence. A part-of-speech that can judge the characteristics of a product is a noun, and a part-of-speech that can express the user's sensitivity to that characteristic is judged to be an adjective. In this process, sentences that do not contain adjectives that can judge positive or negative among sentences in the review are judged as noise and excluded from analysis.

FIG. 7 is an example of a review in which morphological analysis is performed by extracting only reviews including the keyword 'price' associated with the price ratio by taking the purchase criterion 'cost ratio' as an example.

In order to recommend a product, it is necessary to determine whether there are many positively evaluated product reviews or negatively evaluated product reviews among the previously extracted product reviews. Therefore, by counting the number of positive or negative ratings among all product reviews, the average is calculated to recommend the product with the best rating among the entire product list to the user.

By calculating the number of product reviews with positive evaluation, you can see the percentage of all product reviews with positive evaluation. Therefore, the average value is obtained by dividing the sum of positive and negative scores by the total number of product reviews (C).

Neutral opinions were judged as noise due to difficulties in discrimination, and overall product reviews were positive, but they were included in the rating exclusion list with no good evaluation of the keyword 'price' or 'price ratio'.

8 is a table summarizing the average and calculating the positive and negative scores of each of the 12 product reviews previously extracted.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the embodiments or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CDROMs, DVDs, and magneto-opticals such as floptical disks. And hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and / or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

100: product recommendation system
101: user terminal
102: online shopping mall system
210: data collection unit
220: product evaluation department
230: product recommendation department
240: DB
250: control unit
310: first table
320: second table
330: third table

Claims (13)

A data collection unit for collecting a product list related to the product searched by the user and product review data related to the product;
A product evaluation unit for numerically evaluating positive and negative evaluations contained in the product review data to calculate an evaluation score for the product; And
A product recommendation unit extracting a product to be recommended to the user from the product list based on the calculated evaluation score and providing it to the user
Product recommendation system based on user purchase criteria and product reviews, characterized in that it comprises a.
According to claim 1,
The data collection unit
It is characterized by crawling and collecting product information including each product ID, product name, and URL (Uniform Resource Locator) of each product included in the product list, and product review data for each product from an online shopping mall system. Product recommendation system based on user purchase criteria and product reviews.
According to claim 2,
The data collection unit
When crawling the product review data, a user recommendation system and a product review-based product recommendation system, characterized by reading and storing each sentence based on a period to be useful for later morphological analysis.
According to claim 1,
The data collection unit
When a purchase criterion for the product is selected by the user when searching for the product, a user purchase criterion and a product review based product characterized by collecting the product list and the product review data based on the selected purchase criterion. Recommendation system.
The method of claim 4,
The data collection unit
The collected data is stored in a database (DB), but product information including each product ID, product name, and URL of each product included in the product list is stored in a first table of the database, and each product ID and the Product review data is stored in a second table of the database, and product purchase data including the purchase criterion and related terms related to the purchase criterion is stored in a third table of the database. Based product recommendation system.
According to claim 1,
The data collection unit
A product recommendation system based on user purchase criteria and product reviews, wherein noise filtering including special characters and meaningless stopwords is removed from the product review data by performing noise filtering on the product review data.
The method of claim 6,
The product evaluation unit
User purchasing criteria and product review-based products characterized by quantifying positive and negative evaluations contained in the product review data by performing morpheme analysis on the product review data from which noise has been removed through the noise filtering. Recommendation system.
According to claim 1,
The product evaluation unit
Based on the result of morphological analysis of the product review data by dividing each product included in the product list, a positive evaluation rate and a negative evaluation rate are counted by counting the number of positive and negative evaluations among all product reviews for each product And calculates a positive score corresponding to the positive evaluation and a negative score corresponding to the negative evaluation based on the calculated positive evaluation rate and a negative evaluation rate, and calculates the sum of the calculated positive score and negative score. User recommendation criteria and product review based product recommendation system, characterized by calculating the average value of the evaluation score by dividing by the total number of product reviews.
The method of claim 8,
The product recommendation section
A user purchasing criterion characterized by extracting the top N (where N is a natural number) products having a high average value of the evaluation scores as products to be recommended to the user, and providing the extracted products in ascending order to the user, and Product review based product recommendation system.
In a product recommendation method using a product recommendation system based on user purchase criteria and product reviews,
Collecting, by the data collection unit of the product recommendation system, a product list related to a product searched by a user and product review data related to the product;
Calculating an evaluation score for the product by quantifying positive and negative evaluations contained in the product review data by the product evaluation unit of the product recommendation system; And
The product recommendation unit of the product recommendation system extracts a product to be recommended to the user from the product list based on the calculated evaluation score and provides it to the user.
User recommendation criteria and product review based product recommendation method comprising a.
The method of claim 10,
When the purchase criteria for the product is selected by the user when searching for the product,
The data collection unit collecting the product list and the product review data based on the selected purchase criteria
Product recommendation method based on user purchase criteria and product reviews, characterized in that it further comprises.
The method of claim 10,
The step of calculating an evaluation score for the product is
Based on the result of morphological analysis of the product review data by dividing each product included in the product list, a positive evaluation rate and a negative evaluation rate are counted by counting the number of positive and negative evaluations among all product reviews for each product Calculating a;
Calculating a positive score corresponding to the positive evaluation and a negative score corresponding to the negative evaluation based on the calculated positive evaluation rate and the negative evaluation rate; And
Calculating an average value of the evaluation scores by dividing the sum of the calculated positive and negative scores by the total number of product reviews
User recommendation criteria and product review based product recommendation method comprising a.
The method of claim 12,
The steps provided to the user
Extracting the upper N (where N is a natural number) products having a high average value of the evaluation scores as products to be recommended to the user; And
Arranging the extracted products in ascending order and providing them to the user
User recommendation criteria and product review based product recommendation method comprising a.

Images