KR20180052093A - System and method for artificial intelligence electronic commerce - Google Patents

Abstract

According to the present invention, disclosed is an electronic commerce system. More particularly, the present invention relates to an artificial intelligence electronic commerce system and a method for implementing automation by applying artificial intelligence techniques to purchasing tasks such as market research, search field, negotiation, bidding and the like. According to the embodiment of the present invention, the efficiency of business is increased and fairness is secured by automating supplier market research and search field, which require the largest time, among the purchasing tasks performed in enterprises, and negotiation and supplier bidding steps, which require the most fairness and objectivity. So, it is possible to increase opportunities to secure superior suppliers and supply targets. And also, it is expected to secure cost competitiveness and high reliability through a transparency increase. The electronic commerce system includes a purchase receiving part, an environment setting part, an information collecting part, a request form generation part, a search part, an inquiry part, and a learning engine.

Description

TECHNICAL FIELD [0001] The present invention relates to an artificial intelligence electronic commerce system,

The present invention relates to an electronic commerce system, and more particularly, to an artificial intelligence electronic commerce system and method in which automation is implemented by applying an artificial intelligence technique to a purchase task such as a market research, a search field, a negotiation and a winning bid for a company.

Artificial intelligence technology has a very long history and aims to enable computers to communicate with intellectual actions such as recognition and judgment similar to human beings. Since the 1950s, when artificial intelligence was first discussed, artificial intelligence has remained largely untouched by research, but in the 1990s there have been significant attempts to apply artificial intelligence to industry.

At that time, the Rule-based Expert System was the mainstream. Such an expert system is a system that constructs and operates a knowledge base that stores expert knowledge, called domain expert, in a system as rules and methods, need.

Therefore, in order to construct such a knowledge base, an expert system development engineer was required to collect expert knowledge through interviews with the relevant experts, or to learn knowledge of the relevant field and input it in the form of rules and methods.

Accordingly, according to the conventional method, it is not possible to apply expert knowledge to the system at all, and it is impossible to expect continuous development. For this reason, the artificial intelligence field based on the expert system has reached the dark age and reached to the present.

However, recent theoretical developments have been made in the field of neural networks, and the interest in artificial intelligence increases again. The neural network theory has been mainly used for Back Propagation Multi Layer Perceptron (MLP) as a field of artificial intelligence.

Conventionally, the multi-layer perceptron method is a neural network having one or more hidden layers between one input layer and one output layer, and has been utilized in a relatively simple field such as image recognition and classification by characteristics. Here, the neural network is called a multi-layered perceptron, but in practice, when a plurality of hidden layers are applied, an over fitting problem occurs, resulting in a problem of lowering the learning rate. Thus, generally, one or two hidden layers And it is impossible to learn complex input patterns.

However, a deep learning neural network has been developed which overcomes these limitations and combines the non-beacon learning and the guidance learning in a multi-layered hidden layer to learn complex input patterns. As a result, a more complex, A technique capable of processing an input pattern is developed. It is possible to construct a desired system by properly combining these in-depth neural networks and existing rule base systems.

The rule base system is a form that compares conditions and executes defined items of the execution unit if they are satisfied. Here, the execution unit can call another rule or execute an instruction for an action. In addition, we applied the forward reasoning to search the target in all directions and the backward reasoning to search the cause of the result in reverse while executing the rules satisfying the condition, and to derive a good result such as priority processing or conflict resolution strategy May be provided.

On the other hand, the online electronic purchasing system using the Internet is one of the fields of electronic commerce, and many institutions and companies have introduced and operated the system since the early 2000s at home and abroad.

1 is a view schematically showing a purchase process of a conventional online electronic purchase system.

Referring to FIG. 1, the conventional electronic purchase system purchasing process includes a purchase request step S10, an investigation step S11, a planning step S12, a purchase approval step S13, a purchase notification step S14, S15), a winning step (S16), a contracting step (S17), a stocking and accepting step (S18), and a payment step (S19).

According to the above-described process, a large number of personnel need to intervene in each process, which leads to an increase in work efficiency due to heavy work of a person in charge. In addition, there is a possibility of infringement of fairness and transparency which is an important purpose of electronic purchasing, and improvement is required.

SUMMARY OF THE INVENTION The present invention has been conceived to solve the above-described problems, and it is an object of the present invention to provide a system and a method for automatically processing part of a purchasing process directly handled by a plurality of personnel, There is a problem in providing an artificial intelligent electronic commerce system and method that improves performance.

In order to solve the above-mentioned problems, an artificial intelligence electronic commerce system according to an embodiment of the present invention includes: a purchase reception unit for receiving a purchase request for an article from a user terminal; An information collecting unit for storing the sales information collected by the web crawler on the basis of the web URL; and an information collecting unit for receiving the sales information inputted from the user terminal, And a server for receiving and collecting a plurality of pieces of reception information for the request from a plurality of other terminals, comparing the received pieces of reception information with the set purchase rules, A selection unit for selecting one of the extracted reception information by the user terminal, Surface, and a query unit and the result information stored in the knowledge database to provide the result information corresponding to the selected information received may include a learning engine using a machine learning data.

The environment setting unit may include a template module for providing a plurality of purchase templates including a UI for inputting at least one of a keyword, a price, a unit, a country of origin, a supplier, a due date and a category for an article, And a crawler module for providing a web crawler for searching and extracting data in the web URL based on the crawler module.

The information collecting unit may convert the collected irregular sales information into formatted data.

The search unit compares the sales information with the purchase template, and if there is a difference, the search unit can transmit a negotiation request message to the corresponding company according to the purchase rule.

The purchase rule may define one or more purchase conditions for the purchase of the article and the content of the message corresponding to the purchase condition.

According to another aspect of the present invention, there is provided an electronic commerce method using an artificial intelligence electronic commerce system, comprising: receiving a purchase request for an article from a user terminal; The method of claim 1, further comprising the steps of: providing at least one purchase template, setting at least one web URL and setting a range of the web crawler, storing the sales information collected by the web crawler on the web URL, A step of generating and publishing a request including an evaluation of sales information to be input on the web, receiving and collecting a plurality of acceptance information for the request from a plurality of other terminals, A step of generating reception information, and a step of, among the extracted reception information, Generating result information corresponding to the selected acceptance information, and storing the result information in a knowledge database.

The step of providing one or more purchase templates to the user terminal and receiving the one or more web URLs from the user terminal and setting the range of the web crawler may include the steps of selecting keywords, prices, units, origin, suppliers, The method comprising: providing a plurality of purchase templates including a UI for receiving at least one item; and searching and extracting data in the web URL based on data input in the purchase template through the web crawler.

The step of collecting sales information by the web crawler may further include converting the collected atypical sales information into formatted data.

The step of extracting one or more pieces of reception information suitable for comparison with the set purchase rule includes a step of comparing the sales information and a purchase template, and a step of transmitting a negotiation request message to the vendor according to the purchase rule Step < / RTI >

The purchase rule may define one or more purchase conditions for the purchase of the goods and message contents corresponding to the purchase conditions.

According to the artificial intelligent electronic commerce system and method according to the embodiment of the present invention, the supplier market research and search field which takes the most time among the purchasing tasks performed in the enterprise and the negotiation and supplier bidding that requires the most fairness and objectivity By automating the steps through artificial intelligence, it is possible not only to increase the opportunity to secure superior supplier and supply target through improvement of work efficiency and fairness, but also to be able to expect high price competitiveness and reliability by improving transparency It is effective.

1 is a view schematically showing a purchase process of a conventional online electronic purchase system.
2 is a flowchart illustrating an overall process of purchasing an artificial intelligence electronic commerce system according to an embodiment of the present invention.
3 is a diagram illustrating the structure of an artificial intelligence electronic commerce system according to an embodiment of the present invention.
4 is a diagram illustrating a structure of a learning engine of an artificial intelligence electronic commerce system according to an embodiment of the present invention.
5 is a diagram illustrating an artificial intelligence electronic commerce method according to an embodiment of the present invention.
FIG. 6 is a detailed view of an artificial intelligent electronic commerce method according to an embodiment of the present invention by purchase process.
FIGS. 7A and 7B are views showing an example of purchase template setting screen and purchase rule setting screen used in negotiation in the artificial intelligence electronic commerce system according to the embodiment of the present invention.

Prior to the description, when an element is referred to as being "comprising" or "including" an element throughout the specification, it is to be understood that the element may be further comprised of other elements . The term " Unit ... " and "Module" in the specification mean a unit for processing at least one function or operation, And a combination of software.

Furthermore, the term "embodiment" is used herein to mean serving as an example, instance, or illustration, but the subject matter of the invention is not limited by such example. It is also to be understood that other similar terms are used, such as " comprising, "" including, "and" having, " Is used generically in a manner similar to the term "Comprising. &Quot;

The various techniques described herein may be implemented with hardware or software, or may be implemented with a combination of both, where appropriate. As used herein, terms such as "Unit," "Module," and "System" are likewise equally applicable to computer-related entities such as a combination of hardware, It can be handled as equivalent to the software at the time of execution. For example, a program module may be composed of one component or a combination of two or more components. Further, in the present invention, both the application program and the hardware executed in the server or the terminal can be configured on a module basis, and can be recorded in one physical memory or distributed among two or more memories and recording media.

In the artificial intelligence electronic commerce system and method according to the embodiment of the present invention, the steps such as investigation, planning, announcement, and negotiation, which are carried out directly by a person in charge according to a plurality of purchase processes (FIG. 1) The intelligent electronic commerce system is configured to be automatically processed so that it can be operated and reduced to the stage of purchase request, review and approval of the winning bidder, contract, receipt and verification, and settlement.

To this end, in the embodiment of the present invention, when the artificial intelligence electronic commerce system receives a purchase template such as a predetermined purchase requisition purchase condition (Rule) and an evaluation item (factor) from a user, Is registered in the system, the system collects and analyzes the information of the online supply site on the basis of the purchase template, and searches for the supply target.

Here, if the supply target is found as the search result, the automatic negotiation module compares and analyzes the supply conditions, and the analysis result is displayed in order of priority according to the result. The result of the selection is used as learning or evaluation data, By reflecting on the base, it is possible to improve the accuracy of autonomous performance in the future based on the knowledge database.

2 is a flowchart illustrating an overall process of purchasing an artificial intelligence electronic commerce system according to an embodiment of the present invention.

Referring to FIG. 2, in the artificial intelligence electronic commerce system according to the embodiment of the present invention, when a representative accesses the system through his / her terminal and inputs information about an article to be purchased using a purchase template having a certain format (S20), the artificial intelligence electronic commerce system proceeds to the autonomous electronic purchasing step for the article using the purchase template (S21). At this time, the system can be regarded as a step S21-1 of referring to the built-in knowledge database (DB5) for proxy processing.

In particular, in steps S21 and S21-1, the web crawler collects the sales information required for the product purchase decision on the web site according to the set purchasing environment, and converts the sales information into regular formatted data .

Here, as the collected data is formulated, direct comparison with the purchase template can be made by the searching means, and it is possible to judge whether or not it is suitable, and the system presents the reception information by shortening the appropriate sales information.

Then, the person in charge examines the reception information provided by the system, approves the contract for the specific company and the goods (S22), and the system transmits the approval to the terminal of the corresponding company so that the goods receipt and verification step S24 ).

Thereafter, performance evaluation for the present purchase process is performed (S25). At this time, in step S23 to step S25, the person in charge can refer to the previously constructed knowledge database and receive a guidance (S25-1), thereby increasing the work efficiency of each purchasing process.

Next, the system applies the performance evaluation result to the artificial intelligence technique to perform machine learning (S26), and accumulates the learning result in the knowledge database (DB5) (S26-1).

 According to steps S26 and S26-1, the artificial intelligence electronic commerce system of the present invention implements the autonomous purchasing function by reflecting the learning results accumulated in the proxy processing step S21-1.

The above-described knowledge database may have a hybrid type structure in which a production rule of the form "If ~ then ~ else ~" is combined with a model of a multi-layer neural network.

In this structure, the role of a rule is used to describe a logical process, such as asking for certain actions on certain conditions. For example, you can set up such items as "If the type of the product is a hiking, and the price is between 100,000won and 150,000won, put it in the purchase target list".

In addition, the neural network learns a pattern for a value of a factor referred to by a specific rule, and learns the value of the factor to be accurate according to the learned information can do. For example, if you want to treat "what kind of mountain climbing products are preferred by thirties, put them in the list of purchasing objects", you learn the preference pattern of " The preference can be derived by prediction.

The value for this factor is tuned by the learning of the neural network and used as a conditional value to make a correct conclusion in the rule part. Also, the value of the corresponding evaluation factor can be changed as a result of a logical rule. For example, "If a product has 30% of the purchase ratio of less than 10%, it is possible to process a factor of 5 by decreasing the factor value of the preference of 30s by 5".

Due to the nature of the neural network, as the learning for many learning data is improved, the accuracy is improved and the accuracy is improved as the operation period of the system becomes longer and the amount of feedback information becomes larger.

In such a hybrid artificial intelligence structure, the life cycle of a rule may be changed according to verification of the execution result of the rule. That is, the importance of a rule can be changed according to a conflict resolution strategy, and the addition, modification and deletion of a rule can be determined according to the importance. Such processing can be implemented in a manual manner by a human and an automatic manner by a system.

Accordingly, the artificial intelligence electronic commerce system according to the embodiment of the present invention automates the investigation process, the information search and the negotiation process of purchase through the artificial intelligence in the existing product purchase process. Here, the survey processing, the search and negotiation processing processes are the parts that require the greatest amount of manpower resources, and a large part of the manpower resources are automatized by the system, thereby saving manpower and time resources.

In the purchase request step S20, a purchase template and a negotiation rule (Rule) are used in setting the purchase environment. This can be reused after registration and can be used by modifying only the changed part when reusing. The purchase template and the negotiation rule (Rule) will be described later in detail.

Hereinafter, a structure of an artificial intelligence electronic commerce system according to an embodiment of the present invention will be described with reference to the drawings.

3 is a diagram illustrating the structure of an artificial intelligence electronic commerce system according to an embodiment of the present invention.

3, an artificial intelligence electronic commerce system 200 according to an embodiment of the present invention includes a purchase reception unit 210 receiving a purchase request for an article from a user terminal 100, An environment setting unit 220 for receiving at least one web URL and setting a range of the web crawler, an information collecting unit 230 for storing the sales information collected by the web crawler on the web URL, A request form generation unit 240 for generating a request including an evaluation of sales information input from the user terminal 100 and posting the request form on the web, receiving and collecting a plurality of pieces of reception information for the request form from a plurality of other terminals A search unit (S250) for generating one or more pieces of reception information suitable for comparison with a set purchase rule, and, if any of the extracted pieces of reception information is selected by the user terminal, An inquiry unit 260 that provides result information corresponding to the selected acceptance information, and a learning engine 270 that uses the result information stored in the knowledge database as machine learning data.

The purchase reception unit 210 receives a purchase request for a predetermined article from the terminal 100 of a user who is a business person in charge and starts a purchase process accordingly.

The environment setting unit 220 provides purchase templates and rules for proceeding the purchase process to the user terminal 100 and receives and registers the set values of the web crawler for information search.

For this, the environment setting unit 220 includes a template module 221 for providing a plurality of purchase templates including a UI for receiving at least one of a keyword, a price, a unit, a country of origin, a supplier, And a crawler module 222 for providing a web crawler for searching and extracting data in the web URL based on the input data in the purchase template.

The information collecting unit 230 collects the website information of the web URL specified by the web crawler and plays a role of shaping the collected atypical data. In order to perform such a function, the information collecting unit 230 can refer to the machine learning result accumulated in the knowledge database 280. [

Also, the information collecting unit 230 determines whether or not the atypical data matches the purchase template, and as a result, supplies the appropriate sales information to the user terminal 100, and stores the result as sales information. This procedure can be repeatedly performed on the target sales website.

When the user who has confirmed the sales information inputs the result of the review of the sales information and the evaluation through the terminal, the request form generation unit 240 generates and announces the corresponding request form on the web.

In addition, the request form generation unit 240 can announce a request for proposal (RFP) or a request for quotation (RFQ) on the web according to the setting. As a result of the announcement of the request, the proposal or quotation may be received from the terminal through the terminal, and the search unit 250 may search the information included in the purchase template of the work to determine whether the proposal or the estimate matches with the above- And one or more pieces of reception information are generated as the evaluation result.

If the request is not publicized on the web, the request generator 240 compares the collected sales information with the purchase template to determine whether the condition is met. If there is a difference, The terminal can be connected to each other through a messenger such as a chat, a character, or an e-mail, so that a message for requesting a negotiation between the user and the company can be transmitted.

When a response to the message is transmitted from the vendor, the user can directly contact the vendor to proceed with the purchase negotiation. The above-described process can be repeatedly performed on the target sales information.

The search unit 250 also provides the generated one or more pieces of reception information to the user terminal so that the user can determine the final successful bidder based thereon.

In the negotiation procedure according to the present invention, the search unit searches the proposal or the quotation and the purchase rule provided by the vendor, compares the contents of the proposal or the purchase rule, extracts a predetermined number of companies matching the condition, generates the acceptance information, The final successful bidder is selected by referring to the reception information.

In detail, the negotiation procedure is based on the data of the goods such as the price, unit, origin, supplier, and delivery date of the goods included in the proposal and the quotation received from the vendor, the sales amount of the company, And the search unit 250 compares the contents with the conditions defined in the purchase rule and extracts a few companies and provides them to the user terminal as reception information.

The inquiry unit 260 can provide the negotiation and determination result, that is, the inquiry about the final successful bidder, to the user terminal 100 for the negotiated purchase order.

The learning engine 270 performs machine learning on the selection result and stores the learning result in the knowledge database 280 when the final successful bidder is selected based on the sales negotiation result information. The knowledge database 280 can be utilized to help select a more suitable object to be used in the forecasting function of artificial intelligence at the time of search and negotiation of sales information.

In addition, the artificial intelligence electronic commerce system 200 of the present invention includes data learned by the learning engine 270, registration information such as a Web URL registered in a web crawler, purchase registration information generated by a purchase template, And a knowledge database 280 for storing various information for driving the system such as sales information and request form.

According to this structure, the artificial intelligence electronic commerce system 200 according to the embodiment of the present invention does not perform the complicated purchasing process of 10 steps directly when a person performs work such as purchasing goods in a company, It is possible to process the task through a simpler and more accurate purchasing process by referring to the data learned and extracted through artificial intelligence in the request generation.

That is, the present invention collects sales information about various companies through a web crawler, and when a user posts a request with reference to sales information, a company confirms the request and provides a proposal or a quotation, Or the contents of the quotation is suitable for the purchase rule, and provides the reception information to the user by trimming it to a certain number of companies. Then, the user selects one of the companies with reference to the reception information, thereby completing the purchase procedure.

In particular, the artificial intelligence electronic commerce system 200 according to the embodiment of the present invention performs learning, evaluation, and prediction through a learning engine based on a neural network learning technique, thereby performing research processing, search and negotiation processing The procedure can be automated by the system. Hereinafter, a learning engine according to an embodiment of the present invention will be described in detail with reference to the drawings. Such a learning engine may be implemented in a plurality of program modules and recorded in a recording medium readable and writable by the computing device and executed in the form of a program process by a processor of the artificial intelligence electronic commerce system.

4 is a diagram illustrating a structure of a learning engine of an artificial intelligence electronic commerce system according to an embodiment of the present invention.

Referring to FIG. 4, the learning engine 270 of the artificial intelligence electronic commerce system of the present invention may include a plurality of processes, and each process may include one or more sub-processes.

This process includes a pre-processing process 271 for pre-processing learning data or evaluation data, a work process 273 for performing learning, evaluation and prediction on the preprocessed data, a process controller A neural network standard interface 277 connected to a user terminal through an information communication network to perform input and output of data, a post-processing process 279 for converting a result derived by the work process 273 into data, A knowledge database 280 may be included.

When the learning and evaluation processing is requested, the learning engine 270 refers to the learning data and the evaluation data of the knowledge database to perform the machine learning, and stores the result in the knowledge database again.

In detail, the preprocessing process 271 of the learning engine 270 serves to normalize the sales information collected by the web crawler according to various formats such as HTTP and PHP. The preprocessing process 271 can generate and update learning data of the knowledge database 280. [

The work process 273 is a process for performing a learning function a, an evaluation function b and a prediction function c, which are main functions provided by the learning engine 270. The learning function a includes an evaluation variable And input variables, defines the attributes of each variable, defines the network parameters, and then derives the optimal answer that can be obtained through data analysis by the learning method.

In addition, the evaluation function (b) is a function of evaluating and analyzing whether an answer derived by data analysis is appropriate, and the prediction function (c) is a function of finding a target variable through input variables by data learning.

In order to implement this function, the work process can refer to learning data, evaluation data, parameters, and neural network data stored in the knowledge database 280. [

The process controller 275 performs signal control between each process executed by the learning engine 270 and can provide the learning result to the neural network standard interface in response to the request from the neural network standard interface 277. [

The neural network standard interface 277 connects the learning engine 270, the external terminal, and the database (not shown) in a wired or wireless manner through the information communication network.

The system administrator can access the learning engine 270 via the terminal to change settings related to driving, reset parameters, and add or update learning data and evaluation data.

The post-processing process 279 serves to output the data according to the learning result derived by the work process 273 in the form of a report as valid information by the system administrator.

Hereinafter, an artificial intelligent electronic commerce method according to an embodiment of the present invention will be described with reference to the drawings.

5 is a diagram illustrating an artificial intelligence electronic commerce method according to an embodiment of the present invention. In the following description, the subject of each step is the artificial intelligence electronic commerce system of Fig. 3 described above and each constituent unit of the system without any other instruction.

5, an artificial intelligent electronic commerce method according to an exemplary embodiment of the present invention includes receiving a purchase request for an article from a user terminal (S100), providing one or more purchase templates to the user terminal, A step of setting a range of a web crawler by receiving a URL (S110), storing sales information collected by a web crawler on a web URL (S120), evaluating sales information inputted from the user terminal (S130) of receiving a request for a request from a plurality of terminals, receiving and collecting a plurality of receipt information for the request from a plurality of other terminals, and generating one or more receipt information S140), generating one or more pieces of result information corresponding to the selected piece of received information when the user terminal selects one of the extracted pieces of received information (S150) , And storing the result information in the knowledge database (S160).

First, in step S100, when a person in charge of business related to the purchase of an article, that is, a user receives a purchase request for an article in the artificial intelligence electronic commerce system using his / her terminal, the system receives it and starts the purchase process.

Next, in step S110, a purchase template and a rule for proceeding the purchase process are provided to the user terminal, a purchase template input from the user terminal is stored thereafter, and a web URL inputted from the user terminal is registered in the system, The range is set.

Then, the sales information is collected by the web crawler, and the result is stored (S120). At this time, the system formalizes the collected unstructured data.

Next, in step S130, it is determined whether or not the atypical data is compatible with the purchase template. As a result, evaluation is performed on the sales information, if appropriate, and the result is stored as sales information. The step S130 may be repeatedly performed on the target sales website.

Then, when the user who confirmed the sales information inputs the result of the sales information review and evaluation through his / her terminal, the system can generate a proposal request or a request for quotation according to the input information and announce it on the web.

The above-mentioned proposal request or quotation request form can be generated by inputting the result of reviewing the sales information by the user on the form provided by the system and the evaluation content in text form.

At this time, the request requests may be announced or not announced according to the setting. If the request is notified, the proposal or quotation is received as a reply to the request form according to step S140, the target is searched based on the purchase template, And generates one or more pieces of reception information.

If the request is not announced in step S130, the collected sales information is compared with the purchase template to determine whether the condition is met. If there is a difference, negotiation is performed through the messenger such as chatting, text, And sends a message for the request. Accordingly, when a response to the message is transmitted from the corresponding company, the negotiation is continued according to whether the purchase template is satisfied or not.

In step S150, the user selects one of the winning bidders by referring to the reception information generated by the system through the terminal, and the system generates the result information.

In step S160, the system stores the result information in the knowledge database when the final successful bidder is selected. This can be used as learning data for future learning engines.

Hereinafter, each step of the artificial intelligent electronic commerce method of the present invention shown in FIG. 4 will be described in detail with reference to the accompanying drawings.

FIG. 6 is a detailed view of an artificial intelligent electronic commerce method according to an embodiment of the present invention by purchase process.

Referring to FIG. 6, after receiving the purchase request, the purchasing environment setting is received from the user (S200), and the site address to be searched by the web crawler is stored and managed as the Web crawler registration information DB1. In addition, a purchase template as a reference to be purchased is inputted and stored as purchase registration information DB2. The stored purchase template is then used as reference information when the automated electronic purchasing system processes the survey processing and sales negotiation by the web crawler.

Next, the system conducts information investigation according to the purchase of the goods according to whether or not the investigation is carried out (S201). When an investigation is made, the information is collected by accessing the corresponding site with the URL registered by the web crawler (S202), and the unstructured data collected by the crawling of the sales site is formatted (S203). The system refers to the purchase registration information (DB2) and judges whether it is compatible with the purchase template (S204, S205). If it is judged to be suitable, the system evaluates the sales information, Information DB4 (S206). The stored sales information DB3 can then be used as basic information for preparing a request for proposal (RFP) or a request for quotation (RFQ). (S205). If there is more information of another web site, the above process is repeatedly performed on the target selling site (S202).

(S207), the RFP (Request for Proposal) is generated (Step S209) with the result value (Evaluation Request) or the RFP (Evaluation Request) previously evaluated at the time of the investigation. At this time, if the announcement is made (S208), the request information is announced to the website, and after the proposal or quotation is received, it is evaluated and analyzed according to the criteria of the purchase rule, and the acceptance information, (S210).

If not, the system compares the collected sales information with the purchase template to determine whether the conditions are met. If there is a difference, a message is sent to the vendor according to the purchase rule through a messenger such as chat, text, or e-mail . If a response is received in the negotiation message, it is determined whether or not the purchase template satisfies the same (S211). The above steps are repeated for the target sales information.

The plurality of pieces of reception information selected by the system in step S210 are reviewed by the user as a negotiation procedure to select the final successful bidder (S212).

Thereafter, the auction result according to the step S212 can be reflected in the machine learning (S213) and stored as the electronic purchase knowledge database DB5, and can be provided as a report. This knowledge database DB5 can be utilized for predicting the learning engine at the time of searching for sales information and negotiating (S211) for the purchase of other goods later, and contributing to performance improvement in selecting a more suitable company.

Hereinafter, the technical idea of the present invention will be described with reference to an example of a screen provided to an artificial intelligence electronic commerce system according to an embodiment of the present invention with reference to the drawings.

FIGS. 7A and 7B are views showing an example of purchase template setting screen and purchase rule setting screen used in negotiation in the artificial intelligence electronic commerce system according to the embodiment of the present invention.

7A, the artificial intelligence electronic commerce system provides a screen for setting a purchase environment after receiving a purchase request from a user terminal. The environment setting window w100 includes a setting field w110 for receiving a set value as a purchase template, And a condition input field w120 for inputting an item condition.

The set value input to the setting input field w110 includes, for example, a keyword, a price, a unit, a country of origin, a supplier, a delivery date, a category, and a supplier size. In the condition input field w120, delivery information on an actual article can be input. The crawler of the artificial intelligence electronic commerce system of the present invention searches the information of the specified website to collect sales information meeting the conditions of the purchase template, and the collected information is analyzed through the analysis function and processed .

7B, an artificial intelligence electronic commerce system according to the present invention is an example of a purchasing rule setting screen. In the artificial intelligent electronic commerce system of the present invention, when a portion that does not meet the conditions for verifying sales information analyzed is collected, (Rule), and such negotiation is conducted by negotiating with the vendor through e-mail or chat. In this purchase rule, one or more purchase conditions for purchasing the goods and the message content corresponding to the purchase conditions can be defined. When the system receives a response from the vendor, the system compares the negotiation contents with the contents of the negotiation using the natural language processing function . The purchase rule setting window w200 for this purpose may include a check box w210 for selecting an instruction for one or more rules (rule1 to rule3).

While a great many are described in the foregoing description, it should be construed as an example of preferred embodiments rather than limiting the scope of the invention. Accordingly, the invention is not to be determined by the embodiments described, but should be determined by equivalents to the claims and the appended claims.

100: User terminal 200: Artificial intelligence electronic commerce system
210: purchase reception unit 220: environment setting unit
221: template module 222: crawler module
230: information collection unit 240: request form generation unit
250: searching unit 260:
270: learning engine 280: knowledge database

Claims (10)

A purchase reception unit receiving a purchase request for an article from a user terminal;
An environment setting unit for providing one or more purchase templates to the user terminal, receiving one or more web URLs, and setting a range of the web crawler;
An information collecting unit for storing sales information collected by the web crawler on the basis of the web URL;
A request generation unit for generating a request including an evaluation of sales information input from the user terminal and posting the request on the web;
A searching unit for receiving and collecting a plurality of pieces of reception information for the request from a plurality of other terminals and generating one or more pieces of reception information suitable for matching with the set purchase rules;
An inquiry unit that provides result information corresponding to the selected acceptance information when any one of the extracted acceptance information is selected by the user terminal; And
A learning engine that uses the result information stored in the knowledge database as machine learning data
An artificial intelligence e-commerce system comprising: The method according to claim 1,
The environment setting unit,
A template module for providing a plurality of purchase templates including a UI for inputting at least one of a keyword, a price, a unit of origin, a country of origin, a supplier, a delivery date and a category for the article; And
And a web crawler for searching and extracting data in the web URL based on the data input in the purchase template
An artificial intelligence e-commerce system comprising: The method according to claim 1,
Wherein the information collecting unit converts the collected irregular sales information into stereotyped data. The method according to claim 1,
The searching unit searches,
And compares the sales information with the purchase template, and transmits a negotiation request message to the vendor terminal according to the purchase rule when there is a difference. 5. The method of claim 4,
The purchasing rule includes:
Wherein at least one purchase condition for the purchase of the article and a content of a message corresponding to the purchase condition are defined. As an electronic commerce method using an artificial intelligence electronic commerce system,
Receiving a purchase request for an article from a user terminal;
Providing one or more purchase templates to the user terminal, receiving one or more web URLs, and setting a range of the web crawler;
Storing sales information collected by the web crawler on the web URL;
Generating a request including an evaluation of sales information input from the user terminal and posting the request on the web;
Receiving and collecting a plurality of pieces of reception information for the request from a plurality of other terminals and generating one or more pieces of reception information suitable for matching with the set purchase rules;
Generating result information corresponding to the selected acceptance information when any one of the extracted acceptance information is selected by the user terminal; And
Storing the result information in a knowledge database
The method comprising the steps of: The method according to claim 6,
The step of providing one or more purchase templates to the user terminal, receiving one or more web URLs from the user terminal, and setting a range of the web crawler,
Providing a plurality of purchase templates including a UI for inputting at least one of a keyword, a price, a unit, a country of origin, a supplier, a delivery date, and a category for an article; And
Searching and extracting data in the web URL based on data input in the purchase template through the web crawler
The method comprising the steps of: The method according to claim 6,
After collecting sales information by the web crawler,
And converting the collected atypical sales information into stereotyped data. The method according to claim 6,
The step of extracting one or more pieces of reception information suitable for the set purchase rule,
Comparing the sales information and the purchase template; And
If there is a difference in the comparison result, transmitting the negotiation request message to the vendor according to the purchase rule
The method comprising the steps of: 10. The method of claim 9,
The purchasing rule includes:
Wherein at least one purchase condition for purchasing the article and message content corresponding to the purchase condition are defined.

Images