KR102438337B1 - Method for selling products through multi-party permission call and selling system thereof - Google Patents

Abstract

Disclosed are a method of operating a sales server that sells products through a multi-party permission call and the server. In this method, the sales server tracks the Internet call channel as a call is connected between the first seller terminal and the buyer terminal, and registers the Internet call channel as the Internet call channel is maintained for a predetermined time or longer, and from the first seller terminal to the buyer terminal and a process of receiving user information of , and determining at least one second seller terminal matching the user information using a pre-trained neural network. Then, the sales server synchronizes the at least one second seller terminal to the Internet call channel and connects to the buyer terminal, and transmits a message including information about the product to the buyer terminal according to the request of the at least one second seller terminal, , then release the first seller terminal from the Internet call channel.

Description

Method of selling products through multi-party permission currency and its sales system {METHOD FOR SELLING PRODUCTS THROUGH MULTI-PARTY PERMISSION CALL AND SELLING SYSTEM THEREOF}

The present invention relates to a method of selling a product through a multi-party permission currency and a system for selling the same.

Sales (販賣) refers to the transfer of ownership of goods by selling goods, etc. In the past, consumers mainly visited and purchased goods sold in department stores or general stores. However, due to the recent development of communication technology, products are being sold over the phone or online. In particular, insurance requires a salesperson to explain the complex terms and conditions of the contract. Although online sales such as direct sales are being activated, this applies only to some insurances, and most of them still require sales through a designer, etc. to confirm details and set conditions. However, since not all phone sales can be handled by a planner, most insurance companies use a counselor to identify customer needs and then connect the call with the agent again. However, this method takes a considerable amount of time to attract customers, which may cause problems such as a change of mind or the customer's needs are not properly communicated to the designer. Therefore, it is necessary to introduce a method and system that can more efficiently identify customer needs and connect them to the sales process as they are by establishing a sales system.

SUMMARY OF THE INVENTION The present invention is to solve the above problems, and an object of the present invention is to provide a method for selling currency and a system for selling the same, which can more efficiently sell products.

However, the technical problems to be achieved by the present embodiment are not limited to the technical problems described above, and other technical problems may further exist.

According to an embodiment of the present invention for achieving the above object, a method of operating a sales server that sells a product through a multi-party call using a neural network according to an embodiment of the present invention is provided as a call is connected between the first seller terminal and the buyer terminal. tracking an internet call channel; registering the Internet call channel as the Internet call channel is maintained for a predetermined time or longer; receiving user information of the purchaser terminal from the first seller terminal; determining at least one second seller terminal matching the user information using a pre-trained neural network; synchronizing the at least one second seller terminal to the Internet call channel and connecting to the buyer terminal; transmitting a message including information about the product to the purchaser terminal according to the request of the at least one second seller terminal; and releasing the first seller terminal from the Internet call channel.

According to various embodiments as described above, the sales system of the present invention can provide an environment in which the operator of the sales system can more effectively sell products by matching the most suitable seller to the buyer using a pre-trained neural network.

In addition, by providing information on the product and the purchase method to the purchaser terminal using a graphic user interface (GUI) during a call, the user can purchase the product more conveniently.

1 illustrates a sales system according to an embodiment of the present invention.
2 is a flowchart illustrating a method of operating a sales server according to an embodiment of the present invention.
3 is an example of a sales server providing a message including information about a product to a purchaser terminal according to an embodiment of the present invention.
4 is an example illustrating a neural network for obtaining a second seller terminal matching user information according to an embodiment of the present invention.
5 is a block diagram of a sales server according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. In describing the present invention, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, numbers (eg, first, second, etc.) used in the description process of the present specification are merely identification symbols for distinguishing one component from other components.

1 shows a sales system 1 according to an embodiment of the invention.

The sales system 1 according to an embodiment of the present invention includes a sales server 10, a first seller terminal 11, and a second seller terminal 12 that sell products through a multi-party call using a neural network. ) is included. And the first seller terminal 11 and/or the second seller terminal 12 of the sales system (1) and a buyer terminal 20 connected to the Internet call.

In general, Internet calls are classified into a PC-to-PC method, a PC-to-Phone method, and a Phone-to-Phone method. According to the PC-to-PC method, after executing call-related software in the called device and inputting the IP (Internet Protocol) address of the receiving device, a call is connected to the receiving device through the Internet network and a call is possible. The PC-to-Phone method, which is a development model, connects a telephony gateway between the Internet and PSTN (Public Switched Telephone Network) to enable calls between PCs and mobile phones. By connecting another gateway between them, it was possible to make calls between mobile phones. Hereinafter, in the present invention, it is preferably described as a PC-to-Phone method, but it is obvious that the embodiments of the present invention can also be applied to an Internet call connection method of a PC-to-PC method or a Phone-to-Phone method. .

The sales server 10 uses the sales server 10 and the first seller terminal 11 and/or the second seller terminal 12 to communicate through an intranet to provide a product to the user of the purchaser terminal 20 . carry out the sales process. In this case, the first seller terminal 11 functions as a primary salesperson to understand the user's needs, and the second seller terminal 12 functions as a final salesperson who exchanges detailed information and payment information necessary for actual product purchase with the user. can

When it is estimated that the user intends to purchase the product through the Internet communication channel between the first seller terminal 11 and the buyer terminal 20, the sales server 10 sends the second seller terminal 12 to the Internet without delay. Encourage users to purchase products by adding them to a currency channel.

In particular, the sales server 10 provides an environment in which the operator of the sales system 1 can sell products more effectively by matching the second seller terminal 12 most suitable to the buyer using a pre-trained neural network. In addition, by providing information on the product and a purchase method to the purchaser terminal 20 using a graphic user interface (GUI), the user can purchase the product more conveniently.

The first seller terminal 11 and the second seller terminal 12 may be, as non-limiting examples, a PC, a tablet, a desktop, a notebook computer, a smart phone, and the like. In addition, the purchaser terminal 20 may include a mobile phone, a smart phone, etc., but is not limited thereto and may include various devices having an Internet call function.

Hereinafter, an operation in which the sales server 10 performs a product sales process will be described in detail with reference to FIGS. 2 to 4 .

2 is a flowchart illustrating an operation method of the sales server 10 according to an embodiment of the present invention.

First, the sales server 10 creates an Internet communication channel with the purchaser terminal 20 through the first seller terminal 11 (s21), and tracks the created Internet communication channel (s22).

The first seller terminal 11 requests a call connection based on the phone number and IP address of the purchaser terminal 20 previously registered in the sales server 10 through the intranet, and creates an Internet call channel in response thereto. can do. The purchaser terminal 20 may agree to a product guide through an arbitrary path, and a phone number, an IP address, and the like may be previously registered in the sales server 10 . Alternatively, the purchaser terminal 20 requests a call connection from the purchaser terminal 20 to the sales server 10, and the sales server 10 allocates the first seller terminal 11 to respond to the call server (not shown). (20) and may create an Internet call channel.

When an Internet communication channel with the first seller terminal 11 is created, the sales server 10 tracks the corresponding Internet communication channel. For example, the sales server 10 may track the current state of the corresponding Internet call channel and track whether the Internet call channel is terminated or in progress.

If the corresponding Internet communication channel is maintained for a predetermined time, the sales server 10 registers the corresponding Internet communication channel (s23). The sales server 10 may estimate that the user of the purchaser terminal 20 intends to purchase the product when the corresponding Internet call channel is maintained for a predetermined time. And register an Internet call channel. Here, the registration of the Internet call channel may mean storing the access information of the first seller terminal 11 to the call server and/or the access information of the buyer terminal 20 to the call server, but is not limited thereto. it is not

And the sales server 10 receives the user information of the purchaser terminal 20 from the first seller terminal 11 (s24). In this case, the user information may include, but is not limited to, the gender, age, occupation, past purchase history, similar product purchase history, and the like of the user of the purchaser terminal 20 . The sales server 10 provides a screen (eg, a pop-up window, etc.) for inputting user information to the first seller terminal 11 , and registers information input to the corresponding screen.

Thereafter, the sales server 10 determines at least one second seller terminal 12 matching the user information using the pre-trained neural network (s25). The pre-learned neural network may be provided in the sales server 10 or may be provided in an external server.

The neural network is pre-trained using training data composed of pairs of input values and corresponding output values (target values), and as non-limiting examples, Deep Neural Network (DNN), Recurrent Neural Network (RNN), LSTM ( Long Short-Term Memory models), BRDNN (Bidirectional Recurrent Deep Neural Network), CNN (Convolutional Neural Networks), etc. may be configured, but is not limited thereto.

In addition, the learning data of the neural network uses at least one of the past product purchaser's age, gender, occupation, past purchase history, and similar product purchase history as an input value, and identification information of the second seller terminal that sold the product to the past product purchaser (eg, intranet address, name, MAC address, etc.) can be used as an output value. The neural network may estimate an output value corresponding to an arbitrary input value by learning the correlation between each input value and the output value.

Thereafter, the sales server 10 may acquire identification information of at least one second seller terminal matching the user information by inputting user information of the current product purchaser to the neural network learned from the learning data. The neural network used by the sales server 10 will be described later with reference to FIG. 4 .

The sales server 10 synchronizes the at least one second seller terminal 12 with the Internet call channel and connects to the buyer terminal 20 (s26). The sales server 10 may create a virtual Internet call channel based on the information on the pre-registered Internet call channel in step s23. For example, the sales server 10 may create a virtual Internet call channel by changing the connection information of the first seller terminal 11 to the virtual connection information generated by the sales server 10 based on the connection information of the first seller terminal 11 , but is limited thereto. it's not going to be

The sales server 10 may synchronize the created virtual Internet call channel with the Internet call channel. The sales server 10 may provide the synchronized virtual Internet call channel to the at least one second merchant terminal 12 . Through this, the second seller terminal 12 is connected to the buyer terminal 20 , and can listen to and/or participate in an Internet call channel between the buyer terminal 20 and the first seller terminal 11 .

At least one second seller terminal 12 connected to the Internet call channel requests information about the product to the sales server 10 so that the user of the purchaser terminal 20 can purchase the product (s27-1), The sales server 10 transmits a message including information about the product requested by the second seller terminal 12 to the purchaser terminal 20 (s27-2).

3 is an example in which the sales server 10 provides a message including information about a product to the purchaser terminal 20 according to an embodiment of the present invention.

Referring to FIG. 3 , the sales server 10 may transmit a message including a Uniform Resource Locator (URL) link of a web-page 300 providing information about the product to the purchaser terminal 20 . There is (s31). The user of the purchaser terminal 20 may select the corresponding link to access the web page (s32). At this time, the web page 300 moves the sales server 10 to a page where the sales server 10 pays for the corresponding Internet call channel tracking information (ie, current channel status information) 310 , the product terms and conditions information 320 , and the product payment. It may include a first link 330 for terminating the web page 300 and a second link 340 for returning to a previous page (s33).

Through this, the user of the buyer terminal 20 conducts a multi-party call with the first seller terminal 11 and/or at least one second seller terminal 12 to receive desired information through the screen of the buyer terminal 20 You can purchase the product right away.

On the other hand, the second seller terminal 12 can change the product purchase conditions in real time through the Internet call channel with the buyer terminal 20 , and requests the terms and conditions changed accordingly to the sales server 10 , and the user It can be checked directly through the web page 300 .

Referring back to FIG. 2 , the sales server 10 switches the Internet call channel to a channel between the buyer terminal 20 and the second seller terminal 12 ( s28-1 ), and connects the first seller terminal 11 . Release from the Internet call channel (s28-2). The sales server 10 requests the establishment of an additional Internet communication channel between the second seller terminal 12 and the purchaser terminal 20 to the call server (not shown) of the Internet communication channel, and the additional Internet communication channel is opened. Accordingly, the Internet call channel can be terminated. In this case, the sales server 10 may provide the access information of the buyer terminal 20 and the access information of the second seller terminal 12 to the call server.

Alternatively, the sales server 10 may register a virtual Internet call channel synchronized with the Internet call channel in the call server and terminate the Internet call channel. The call server registers a virtual Internet call channel to open an Internet call channel between the purchaser terminal 20 and the sales server 10 , and the sales server 10 transmits access information of the sales server 10 through the intranet to the second seller. It can be changed to access information of the terminal 12 .

In this way, the sales server 10 switches the Internet call channel, so that the user of the purchaser terminal 20 can receive a more detailed description of the product, notices, etc. from the user of the second seller terminal 12 . At the same time, it is possible to make the first seller terminal 11 attract other customers.

Meanwhile, step s28 may be performed simultaneously with step s27, or may be performed before step s27. Furthermore, steps s21 to s28 may be further divided into additional steps or combined into fewer steps according to an embodiment of the present invention. In addition, some steps may be omitted if necessary, and the order between the steps may be changed.

Also, in the above description, each step is described as being performed by the sales server 10 , but the subject of each step is not limited thereto, and at least a portion of each step may be performed in different devices according to embodiments.

4 is an example illustrating a neural network 400 for obtaining a second seller terminal 12 matching user information according to an embodiment of the present invention.

Referring to FIG. 4 , a neural network 400 of the present invention may include a plurality of input nodes I1 to I5 , intermediate nodes H1 to H3 , and an output node O1 . In addition, each node may perform a calculation process of assigning a weight to the input value.

User information may be input to the input nodes I1 to I5 , and the output value O1 is identification information of the second seller terminal 12 .

First, a value input to the input nodes I1 to I5 may be a value of -1 to 1 . For example, +1 for male and -1 for female may be input to node I1 (gender). Also, in the I2 node (age), -1 for teens, -0.5 for 20s, 0 for 30s, +0.5 for 40s, and +1 for 50s or older. Similarly, values for the user's occupation, past purchase history, and similar product purchase history may be input as -1 to 1 in I3 to I5.

The neural network 400 of the present invention performs learning by using the learning data (set of input values and output values) so as to determine the exact correlation between the log values and the output values. A weight of -1 to 1 is additionally assigned between each node and the operation is performed. In addition, at least one of sum, multiplication, subtraction, and division of weighted values may be performed in the intermediate nodes H1 to H3 which are hidden nodes. The neural network 400 may change the size and sign of a node and a weight value between the nodes through learning. Meanwhile, although FIG. 4 illustrates that the neural network includes three hidden nodes in one hidden layer, the number of hidden layers and the number of hidden nodes may vary according to implementations.

The neural network learned through the above process may be used to obtain an output value O1 suitable for user information, that is, at least one second seller terminal 12 . For example, when the output value is 0 to 0.7, at least one second seller terminal classified into the first group may be output, and when the output value is 0.8 to 1.4, at least one second seller terminal classified into the second group This can be output.

On the other hand, when the user information is not sufficiently obtained, the input value may be replaced with an average value of the learning data. For example, when information on the occupational group of a man in his 30s cannot be obtained, the occupational group may be input as a value corresponding to the office worker. may be input as a value corresponding to the student.

5 is a block diagram of a sales server 10 according to an embodiment of the present invention. Since the sales server 10 of FIG. 5 is related to the embodiments of FIGS. 1 to 4 , the embodiments described in FIGS. 1 to 4 are also applied to the sales server 10 of FIG. 5 . Accordingly, a description overlapping with the content described above with reference to FIGS. 1 to 4 will be omitted.

The processor 510 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus, etc.) for transmitting and receiving signals to and from other components. .

The processor 510 according to an embodiment of the present invention executes one or more instructions stored in the memory 520 , thereby performing the method described with reference to FIGS. 1 to 4 . For example, the processor 510 according to an embodiment tracks the Internet call channel as a call is connected between the first seller terminal 11 and the buyer terminal 20, and the Internet call channel is maintained for a predetermined time or longer. At least one second seller terminal 12 that registers an Internet call channel accordingly, receives user information of the buyer terminal 20 from the first seller terminal 11, and matches the user information using a pre-trained neural network to decide

In addition, the processor 510 synchronizes the at least one second seller terminal 12 with an internet call channel to connect with the buyer terminal 20, and according to the request of the at least one second seller terminal 12, A message including information about the product is transmitted to the buyer terminal 20 , and the first seller terminal 11 is released from the Internet call channel.

In addition, the processor 510 creates a virtual Internet call channel based on information on the registered Internet call channel in order to synchronize the second seller terminal 12 with the Internet call channel, and converts the virtual Internet call channel into an Internet call. In synchronization with the channel, the synchronized virtual Internet call channel may be transmitted to the at least one second seller terminal 12 . Thereafter, the processor 510 is added between the second seller terminal 12 and the buyer terminal 20 to a call server (not shown) of the Internet call channel in order to release the first seller terminal 11 from the Internet call channel. The Internet call channel may be requested, and as the additional Internet communication channel is created, the Internet call channel may be terminated.

Alternatively, the processor 510 may terminate the Internet communication channel by registering a virtual Internet communication channel synchronized with the Internet communication channel to the call server in order to release the first seller terminal 11 from the Internet communication channel.

Meanwhile, the processor 510 includes a random access memory (RAM) and a read-only memory (ROM) that temporarily and/or permanently store signals (or data) processed inside the processor 510 . , not shown) may be further included. In addition, the processor 510 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, a RAM, and a ROM.

The memory 520 may store programs (one or more instructions) for processing and controlling the processor 510 . Programs stored in the memory 520 may be divided into a plurality of modules according to functions.

The steps of the method or algorithm described in relation to the embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software components, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors.

The above description is merely illustrative of the technical spirit of the present invention, and various modifications and variations will be possible without departing from the essential characteristics of the present invention by those skilled in the art to which the present invention pertains. In addition, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to illustrate, and the scope of the technical spirit of the present invention is not limited by these embodiments. Accordingly, the scope of the present invention should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

1: Sales system
10: Sales Server
11: first seller terminal
12: second seller terminal
20: buyer terminal
I1 to I5: input node
H1 to H3: intermediate node
O1: output node (output value)
510: processor
520: memory

Claims (5)

In the operating method of a sales server that sells a product through a multi-party call based on a neural network,
tracking an Internet call channel as a call is connected between the first seller terminal and the buyer terminal;
registering the Internet call channel as the Internet call channel is maintained for a predetermined time or longer;
receiving user information of the purchaser terminal from the first seller terminal;
determining at least one second seller terminal matching the user information using a pre-trained neural network;
synchronizing the at least one second seller terminal to the Internet call channel and connecting to the buyer terminal;
transmitting a message including information about the product to the purchaser terminal according to the request of the at least one second seller terminal; and
Comprising the step of releasing the first seller terminal from the Internet call channel,
The step of synchronizing with the Internet communication channel and connecting to the purchaser terminal may include: creating a virtual Internet communication channel based on information on the registered Internet communication channel; synchronizing the virtual Internet calling channel to the Internet calling channel; and transmitting the synchronized virtual Internet call channel to the at least one second merchant terminal. The method of claim 1,
The step of releasing the first seller terminal from the Internet call channel comprises:
requesting an additional Internet communication channel between the second seller terminal and the purchaser terminal to the call server of the Internet communication channel; and terminating the internet communication channel as the additional internet communication channel is created. The method of claim 1,
The step of releasing the first seller terminal from the Internet call channel comprises:
registering the virtual internet call channel synchronized with the internet call channel in a call server; and
and terminating the internet call channel. The method of claim 1,
The input parameter of the neural network includes at least one of a buyer's age, gender, occupation, past purchase history, and similar product purchase history, and the output value of the neural network is identification information of the at least one second seller terminal,
The learning data of the neural network includes an input value including at least one of the buyer's age, gender, occupation, and product purchase history, and an output value including identification information of the second seller terminal. The method of claim 1,
Sending the message includes:
transmitting a message including a URL of a web page providing information about the product to the purchaser terminal; and
As the buyer terminal accesses the URL, providing tracking information of the Internet call channel, information on terms and conditions of the product, and a link for moving to a page for paying for the product on the web page how to be.

Images