KR102363581B1 - Method of providing a fulfillment service and service system therefor - Google Patents

Abstract

According to an embodiment of the present invention, a method for providing a fulfillment service in a service server between an online seller and an offline warehouse includes: registering a service keyword through artificial intelligence learning; receiving order information for product shipment from the online seller terminal; extracting search data in the received order information and classifying the extracted search data; comparing the classified search data with registered service keywords; generating first fulfillment service data related to the corresponding service keyword according to the comparison result; and transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped out.

Description

METHOD OF PROVIDING A FULFILLMENT SERVICE AND SERVICE SYSTEM THEREFOR

The present invention relates to a fulfillment service, and more particularly, to a method for providing a fulfillment service through automatic mapping of keywords to artificial intelligence-based order information, and a service system therefor.

As media and consumption are gradually personalized in the conventional offline commerce, online commerce has been activated. Such online commerce is also moving from the one-person media era to the one-person customized consumption era and now to the one-person seller era according to the development of mobile environment and ICT technology.

In this process, a new generation emerging as a core consumer group gradually trusts each other as influencers and searches for, purchases, and shares products that satisfy their tastes. Due to this change in the environment, in a new generation, individual sellers who directly manufacture or source products that satisfy their tastes more easily and sell them through online malls are increasing.

However, in the case of such single sellers or individual sellers, there is a practical problem in logistics processing along with the establishment of an online sales channel.

In addition, small and medium-sized warehouse owners are also facing difficulties because there is a demand for a constitutional change that requires frequent warehousing and retrieval of a small amount of a variety of products.

Therefore, it is required to develop a system for online commerce that fits the new trend between sellers and warehouse owners.

One object of the present invention is to provide a fulfillment service through automatic keyword mapping for 　 artificial intelligence-based order information.

Another object of the present invention is to provide a service platform for a fulfillment service between an online seller and an offline warehouse.

Another object of the present invention is to provide a computing device for the above method and a fulfillment service system including the same.

The technical problems to be achieved in the present invention are not limited to the above technical problems, and other technical problems not mentioned will be clearly understood by those of ordinary skill in the art to which the present invention belongs from the following description.

A method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention for solving the above-described problem, the method comprising: registering a service keyword through artificial intelligence learning; receiving order information for product shipment from the online seller terminal; extracting search data in the received order information and classifying the extracted search data; comparing the classified search data with registered service keywords; generating first fulfillment service data related to the corresponding service keyword according to the comparison result; and transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped out.

In the method for providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the received order information includes at least one of text data, image data, and audio data. do it with

In the method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the generated first fulfillment service data is transmitted to the offline warehouse terminal to control the delivery of the corresponding product The step of transmitting the confirmation data including the generated first fulfillment service data to the online seller terminal is characterized in that it is performed after feedback data for the confirmation data is received from the online seller terminal.

In the method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, at least one of the first fulfillment service data and the confirmation data includes the new service keyword, the service At least among the information on the goods stocked in the offline warehouse corresponding to the keyword, the quantity of goods extracted from the order information, the inventory information for the corresponding goods, and the total inventory information on the goods stocked by the online seller in the offline warehouse It is characterized in that it contains one or more.

According to another embodiment of the present invention, there is provided a method for providing a fulfillment service in a service server between an online seller and an offline warehouse, the method comprising: registering a service keyword through artificial intelligence learning; receiving order information for product shipment from the online seller terminal; extracting search data in the received order information, classifying the extracted search data, and comparing the classified search data with a registered service keyword; if there is no service keyword matching the comparison result, generating a new service keyword, and generating first fulfillment service data related to the new service keyword; and transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped out.

In the method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the generated first fulfillment service data is transmitted to the offline warehouse terminal to control the delivery of the corresponding product The step of transmitting the confirmation data including the generated first fulfillment service data to the online seller terminal, characterized in that it is performed after feedback data for the confirmation data is received from the online seller terminal.

In a method for providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the method further includes: registering the new service keyword as a service keyword and updating the service keyword database; It is characterized in that it is done.

In the method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the step of registering the new service keyword includes checking data including the generated first fulfillment service data. When the feedback data for the confirmation data is transmitted to the online seller terminal and received from the online seller terminal, it is characterized in that it is performed based on the received feedback data.

In a method for providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, the method comprising: parsing feedback data received from the online seller terminal; and identifying the contents of the parsed feedback data.

In the method of providing a fulfillment service in a service server between an online seller and an offline warehouse according to an embodiment of the present invention, if the identified feedback data content is a negative message, extracting/classifying search data in the received order information and re-comparing the classified search data with the registered service keyword; if there is no service keyword matching the re-comparison result, a new service keyword is generated, and second fulfillment service data related to the generated new service keyword generating, or if there is a service keyword matching the re-comparison result, generating second fulfillment service data according to the matching service keyword;

A service server for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention includes: a communication interface unit for receiving order information for product shipment from the online seller terminal; a data extraction/classification unit for extracting search data in the received order information and classifying the extracted search data; and registering a service keyword through artificial intelligence learning, comparing the classified search data with a registered service keyword, and generating first fulfillment service data related to the corresponding service keyword according to the comparison result, and the generated first 1 The control unit that transmits the fulfillment service data to the offline warehouse terminal to control the goods to be shipped out; characterized in that it comprises a.

In the service server providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the received order information includes at least one of text data, image data, and audio data. .

In the service server providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit transmits confirmation data including the generated first fulfillment service data to the online seller terminal Thus, after the feedback data for the confirmation data is received from the online seller terminal, the generated first fulfillment service data is transmitted to the offline warehouse terminal to control the shipment of the product.

In the service server for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, at least one of the first fulfillment service data and the confirmation data is the new service keyword and the service keyword. At least one or more of information on goods stocked in a corresponding offline warehouse, product order quantity information extracted from the order information, inventory information on the corresponding product, and total inventory information on items stocked by the online seller in the offline warehouse It is characterized in that it includes.

A service server for providing a fulfillment service between an online seller and an offline warehouse according to another embodiment of the present invention includes: a communication interface unit for receiving order information for product shipment from the online seller terminal; a data extraction/classification unit for extracting search data in the received order information and classifying the extracted search data; and registering a service keyword through artificial intelligence learning, comparing the classified search data with a registered service keyword, and if there is no service keyword matching the comparison result, generates a new service keyword, and the generated new service keyword and a control unit for generating the first fulfillment service data related to and transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped out.

In the service server providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit transmits confirmation data including the generated first fulfillment service data to the online seller terminal Thus, after the feedback data for the confirmation data is received from the online seller terminal, the generated first fulfillment service data is transmitted to the offline warehouse terminal to control the shipment of the corresponding product.

In the service server for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit registers the new service keyword as a service keyword and controls the service keyword database to be updated. characterized.

In the service server providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit transmits confirmation data including the generated first fulfillment service data to the online seller terminal Thus, when feedback data for the confirmation data is received from the online seller terminal, the new service keyword is registered based on the received feedback data.

In the service server for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit parses the feedback data received from the online seller terminal, and identifies the parsed feedback data content characterized in that

In the service server for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention, the control unit, if the identified feedback data content is a negative message, extracting/searching data from the received order information Re-compare the classified and classified search data with the registered service keyword, but if there is no service keyword matching the re-comparison result, a new service keyword is generated, and second fulfillment service data related to the generated new service keyword If there is a service keyword matching the result of the control to be generated, or the re-comparison result, it is characterized in that the control is performed to generate the second fulfillment service data according to the matching service keyword.

According to the present invention as described above, the effects described below can be obtained. However, the effect that can be obtained through the present invention is not limited thereto.

First, it has the effect of providing a fulfillment service through the automatic mapping of keywords to artificial intelligence-based order information.

Second, there is an effect of providing a service platform for fulfillment service between an online seller and an offline warehouse.

Third, there is an effect that can provide a computing device for the above method and a fulfillment service system including the same.

1 is a diagram illustrating a service system for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention.
2 is a diagram illustrating the function of the fulfillment service server 120 according to an embodiment of the present invention.
3 is a block diagram for explaining the configuration of the fulfillment service server 120 according to an embodiment of the present invention.
4 is a block diagram for explaining the configuration of the fulfillment service server 120 according to another embodiment of the present invention.
5 to 7 are diagrams for explaining the execution of a fulfillment service based on an image included in order information in the fulfillment service server 120 according to the present invention.
8 is a flowchart illustrating the concept of a fulfillment service.
9 is a diagram illustrating a fulfillment service process in the fulfillment service system 100 according to an embodiment of the present invention.
10 is a diagram illustrating a method for providing a fulfillment service according to an embodiment of the present invention.
11 is a diagram illustrating a method for providing a fulfillment service according to another embodiment of the present invention.
12 is a diagram illustrating a management system UI for a fulfillment service according to another embodiment of the present invention.
13 is a diagram illustrating a method for providing a fulfillment service according to another embodiment of the present invention.
14 is a diagram illustrating a method of providing a fulfillment service according to another embodiment of the present invention.
15 is a diagram illustrating a method for providing a fulfillment service according to another embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of the present invention, and is not intended to represent the only embodiments in which the present invention may be practiced.

Only these embodiments are provided so that the disclosure of the present invention is complete, 　 to fully inform those of ordinary skill in the art to which the present invention belongs, the scope of the invention, 　 The present invention is to be defined by the scope of the claims only

In some cases, well-known structures and devices may be omitted in order to avoid obscuring the concept of the present invention, or may be shown in block diagram form focusing on core functions of each structure and device. In addition, 　 will be described using the same reference numerals for the same components throughout this specification.

Throughout the specification, when a part refers to a component as “comprising” or “including”, this does not exclude other components unless otherwise stated, but means that other components may be further included. do.

In addition, the term “unit” described in the specification refers to a unit that processes at least one function or operation, and may be implemented as hardware or software or a combination of hardware and software. Furthermore, "a" or "an", "one", 　 and similar related words in the context of describing the present invention are used in both the singular and the plural unless otherwise indicated herein or otherwise clearly contradicted by the context. It can be used in the meaning of including.

In addition, specific terms used in the embodiments of the present invention are provided to aid the understanding of the present invention, and unless otherwise defined, all terms used herein, including technical or scientific terms, are It has the same meaning as commonly understood by those of ordinary skill in the art to which it belongs. The use of these specific terms may be changed to other forms without departing from the technical spirit of the present invention.

Hereinafter, even if named as an on-line seller, an off-line warehouse, etc. in this specification, it does not mean a user such as a person itself, but rather the online seller, the offline warehouse and the computing to be described later. As a computing device, it may mean a means capable of communicating with a fulfillment service server, for example, a terminal of an online seller, a terminal of an offline warehouse, and the like.

Meanwhile, in the above, all of the terminals or devices may include software for driving them based on hardware. For example, as a computing device, the fulfillment service server may perform various operations based on a fulfillment service platform, which will be described later. In addition, these devices are not limited to stationary devices such as TVs and PCs, and include mobile devices such as cell phones, smart phones, tablet PCs, and notebook computers.

In addition, in the following, various configurations described in the present specification or illustrated by the drawings are mainly described in the singular form to help the understanding of the present invention and for convenience of description, but the present invention is not necessarily limited thereto. Accordingly, although described in the singular or illustrated in the singular in the drawings, through context, etc., the meaning may be plural.

Hereinafter, various embodiments according to the present invention will be described with reference to the accompanying drawings, as follows.

1 is a diagram illustrating a service system for providing a fulfillment service between an online seller and an offline warehouse according to an embodiment of the present invention.

Referring to FIG. 1 , a system for providing a fulfillment service (hereinafter referred to as a 'fulfillment service server') 100 includes an online seller 110 and an offline warehouse 130 , A computing device 120 for providing a fulfillment service is included between the online seller 110 and the offline warehouse 130 .

Accordingly, both devices, that is, the online seller 110 and the offline warehouse 130 may be connected to each other through the fulfillment service server 120 .

The online seller 110 may perform data communication with the fulfillment service server 120 through a wired/wireless communication network.

Here, the wired/wireless communication network supports a communication protocol so that various data can be exchanged between the components of the fulfillment service system 100 according to the present invention, and the type is not particularly limited. If necessary, 　 may be supported even when data is collected through the web through the fulfillment service server 120 or the like. According to an embodiment, 　the wired/wireless communication network is an IP (Internet Protocol) network that supports large-capacity data communication through Internet Protocol (IP) or an All IP network that integrates different 　IP networks can According to another embodiment, the wired/wireless communication network is a wired network, a mobile communication network including WCDMA, High Speed Downlink Packet Access (HSDPA), and a mobile communication network including LTE (Long Term Evolution), LTE advanced (LTE-A) ), including a mobile communication network, a satellite communication network and a Wi-Fi network, or may be formed by a combination of at least two or more of them. Bluetooth communication may also be supported here.

The fulfillment service server 120 is a component that supports and performs the provision of a fulfillment service through the offline warehouse 130 according to the request of the online seller 110, and may be located remotely, but is not necessarily limited thereto. not.

As described above, such a fulfillment service server 120, 　 implement the fulfillment service platform according to the present invention to generate, 　 processing, 　 storage, etc. processing or supporting it refers to hardware / software (Hardware / Software) That is, depending on the embodiment, it may be named and described as a processor, a controller, etc., but it should not be construed as being limited by the names.

On the other hand, according to the embodiment, the fulfillment service server 120, the cloud (Cloud) server, IMS (IP Multimedia Subsystem) server, telephony application (Telephony Application) server, IM (Instant Messaging) server, MGCF (Media Gateway Control) Function) 　 server, MSG (Messaging Gateway) 　 server, CSCF (Call Session Control Function) 　 server, etc. may be implemented in any one form.

Meanwhile, the fulfillment service server 120 may provide a file for installing a program or software in the form of a related application or for a fulfillment service to the online seller 110 connected through a wired/wireless communication network. In this case, the online seller 110 may use the file provided from the fulfillment service server 120 to download and/or install the application. Also, the online seller 110 may be connected to the fulfillment service server 120 through its operating system or program to receive or use the fulfillment service.

In particular, the fulfillment service server 120 receives order information from the online seller 110 and compares the received order information with keyword data learned through artificial intelligence from the received order information according to the present invention. may provide a fulfillment service to the online seller 110 by searching for .

Meanwhile, although not shown, in FIG. 1 , the fulfillment service server 120 may be implemented as an internal component of the online seller 110 in the form of one module, or any of the internal components of the online seller 110 . One may perform some or all of the functions of the fulfillment service server 120 . For example, when the fulfillment service according to the present invention is performed through an application installed in the online seller 110 , an internal control configuration such as a central processing unit (CPU) of the online seller 110 controls the fulfillment service It may replace or partially perform the function of the server 120 .

2 is a diagram illustrating the function of the fulfillment service server 120 according to an embodiment of the present invention, and FIG. 3 is a diagram illustrating the configuration of the fulfillment service server 120 according to an embodiment of the present invention. 4 is a block diagram for explaining the configuration of the fulfillment service server 120 according to another embodiment of the present invention, and Figures 5 to 7 are the fulfillment service server 120 according to the present invention. FIG. 8 is a flowchart illustrating the concept of a fulfillment service, and FIG. 9 is a view illustrating the fulfillment service performance based on an image included in order information. FIG. 9 is a fulfillment service according to an embodiment of the present invention. A diagram illustrating a fulfillment service process in the system 100, and FIGS. 10 to 11 are diagrams illustrating a method for providing a fulfillment service according to the present invention, and FIGS. 12 to 15 are views of the present invention It is a diagram illustrating a method of providing various fulfillment services according to an embodiment.

Hereinafter, various methods of providing fulfillment services will be described for better understanding of the present invention and for convenience of explanation. At this time, although steps are sequentially described for description in the drawings and descriptions related thereto, it is not necessarily limited to the illustrated order. For example, some steps may be performed simultaneously or in steps other than those shown.

Referring to FIG. 2 , the fulfillment service server 120 according to an embodiment of the present invention may participate in or support the following functions.

That is, the fulfillment service server 120 may be involved in or process product warehousing, storage, ordering, packaging, delivery, return/inventory management, settlement, distribution support, and the like.

In relation, the concept of the fulfillment service will be briefly described with reference to FIG. 8 as follows.

For example, when a consumer in the first country (US) places an order for a seller (AU) in a second country through online (S110), the second seller finds the product in the offline warehouse after receiving the order, packs it, and sends it request (S120).

Accordingly, the goods are shipped to the first country after being declared to the customs (S130), and finally delivered to the consumer in the first country (S140).

This whole process can be called a fulfillment service.

Referring to FIG. 3 , there is shown a block diagram of a fulfillment service server 120 according to an embodiment of the present invention. Hereinafter, while explaining FIGS. 13 and 14, the configuration of FIG. 3 will be described together.

Basically, the fulfillment service server 120 is configured to include a communication interface unit 310 , a data extraction/classification unit 320 , a data processing unit 330 , a control unit 340 , and a database 350 .

According to an embodiment, referring to FIGS. 13 and 3 , the fulfillment service according to the present invention may be performed as follows.

The communication interface unit 310 may receive order information for product shipment from the online seller terminal 110 (S402).

The data extraction/classification unit 320 may extract search data in the received order information and classify the extracted search data (S403).

The controller 340 may directly or control the data processing unit 330 to register a service keyword through artificial intelligence learning (S401), and compare the classified search data with the registered service keyword (S404). In addition, the control unit 340 generates fulfillment service data related to the corresponding service keyword according to the comparison result (S405), and transmits the generated fulfillment service data to the offline warehouse terminal 130 to transmit the corresponding product It can be controlled to be released (S406).

According to another embodiment, referring to FIGS. 14 and 3 , the fulfillment service according to the present invention may be performed as follows.

The communication interface unit 310 may receive order information for product shipment from the online seller terminal 110 ( S502 ).

The data extraction/classification unit 320 may extract search data in the received order information and classify the extracted search data (S503).

The controller 340 may directly or control the data processing unit 330 to register a service keyword through artificial intelligence learning (S501), and compare the classified search data with the registered service keyword (S504/S505) . In addition, if there is no service keyword matching the comparison result, the control unit 340 generates a new service keyword (S506), and generates first fulfillment service data related to the generated new service keyword (S507) , by transmitting the generated first fulfillment service data to the offline warehouse terminal, it is possible to control the product to be shipped out (S508).

In the above, the service keyword registration process is continuously performed and updated, and may have been performed before receiving the order information, or may be continuously updated thereafter.

In the above, the order information may include at least one of text data, image data, and audio data. A detailed description of the data processing process for each case will be described later.

Meanwhile, referring to FIG. 15 , in the above, the controller 340 transmits the confirmation data including the generated first fulfillment service data to the online seller terminal 110 ( S601 ), and the online seller terminal When feedback data for the confirmation data is received from 110 ( S602 ), thereafter, the generated first fulfillment service data is transmitted to the offline warehouse terminal 130 to control the product to be shipped out.

In the above, at least one of the first fulfillment service data and the confirmation data includes the new service keyword, information on the goods stocked in the offline warehouse 130 corresponding to the service keyword, and an order quantity of goods extracted from the order information. It may include at least one of information, inventory information on the corresponding product, and total inventory information on the products stocked by the online seller 110 in the offline warehouse 130 .

The controller 340 may control to register the generated new service keyword as a service keyword and update the service keyword database 350 .

The control unit 340 may parse the feedback data received from the online seller terminal 110 and identify the contents of the parsed feedback data (S603).

If the identified feedback data content is a negative message (S604), the control unit 340 re-compares the search data re-extraction/re-classification and re-classification in the received order information with the registered service keyword ( S605), if there is no service keyword matching the re-comparison result (S606), a new service keyword is generated (S607), and control to generate second fulfillment service data related to the generated new service keyword (S608); Alternatively, if there is a service keyword matching the re-comparison result, it is possible to control to generate the second fulfillment service data according to the matching service keyword (S507).

As described above, the fulfillment service server 120 accurately catches the item requested by the online seller 110 or its customer from the order information received from the online seller 110, and through the offline warehouse 120 To ensure that the product is shipped or delivered to the customer.

In this case, the order information may be implemented in various forms, as described above, may be in the form of text data, may be in the form of image data, may be in another data form, or may be any combination of the above data types. .

However, in the present specification, for convenience, when the order information consists of text data and the case of image data, the content of obtaining accurate logistics search data according to artificial intelligence learning from the two cases will be described.

First, when the order information is text data (including voice data), the processing or operation process of the fulfillment service server 120 will be described as follows.

FIG. 4 may itself be a fulfillment service server 120 of an embodiment different from that of FIG. 3 , or may be a detailed configuration of a configuration within the fulfillment service server 120 shown in FIG. 3 .

4 is a detailed configuration of the control unit 240 of the fulfillment service server 120 of FIG. 3 , but the scope of the present invention is not limited thereto. The control unit 240 automatically maps the goods in the offline warehouse 130 from the order information of the online seller 110 by using an artificial intelligence-based search engine including contents to be described later.

Meanwhile, in FIG. 4, only key components are illustrated and described for convenience, but the present invention is not limited thereto.

Referring to FIG. 4 , the fulfillment service server 120 includes a communication module 310 , a speech-to-text (STT) module 410, and a speech synthesis (Text-To-Speech; TTS) module. a module 420 , a natural language processing module 430 , an operation/comparison/control module 440 , and the like.

The communication interface unit 310 may communicate with the database 350 or communicate with the above-described online seller 110 and the offline warehouse 130 . The communication interface unit 310 receives order information including text data from the online seller 110 .

The communication interface unit 302 may receive information of the separate online seller 110 and/or the offline warehouse 130 in or together with the above-described order information. Here, the information of the online seller 110 includes, for example, identification information (ID) for identifying the corresponding online seller 110, various state information (eg, the physical state of the online seller terminal 110, online software and/or hardware state of the seller terminal 110). Meanwhile, the offline warehouse information may include information on the type or type of goods in the warehouse, information on goods of a specific seller, quantity information of each article, and other state information of the warehouse.

The STT module 410 may receive a voice input among the order information received through the communication interface unit 310 and convert the received voice input into text data based on various well-known methods. The STT module 410 may generate a feature vector sequence by extracting features such as keywords, such as specific words, from the voice input.

The STT module 410 may generate a text recognition result, for example, a sequence of words, based on various models such as a deep neural network model. In this case, the STT module 410 may refer to the database 350 when processing the received voice input, that is, converting it into text data. but,

The natural language processing module 430 may receive a text input from the communication interface unit 310 or the STT module 410 . The text input received from the natural language processing module 430 is, for example, from a text input received from the online seller 110 in the communication interface unit 310 or a voice input received from the communication interface unit 310 in the STT module 304 . The generated text recognition result may be, for example, a sequence of words. The natural language processing module 430 may receive, together with or after receiving the text input, status information associated with the corresponding user input, for example, status information of the online seller 110 at the time of the corresponding user input. As described above, the status information includes, for example, various status information related to the online seller 110 at the time of user voice input and/or text input in the online seller 110 (eg, the physical state of the online seller 110, software and/or hardware status, environmental status information around the online seller 110, etc.).

The natural language processing module 430 may correspond the received text input to one or more service keywords. Here, the service keyword may be associated with a series of operation(s) that can be understood and performed by the operation/comparison/control module 440 . The natural language processing module 430 may refer to the above-described state information when matching the received text input to one or more service keywords. The natural language processing module 430 may refer to data of the database 350 to be described later in matching the received text input to one or more service keywords.

The calculation/comparison/control module 440 may include, for example, a predefined ontology model. The ontology model may be expressed, for example, in a hierarchical structure between nodes, and each node may be a service keyword or one of its sub-properties. The ontology model may be dynamically changed by adding or deleting nodes in relation to a new service keyword, or by modifying a relationship between nodes.

The operation/compare/control module 440 may be respectively associated with words and/or phrases related to a service keyword or sub-attributes thereof from the text data. The operation/comparison/control module 440 may implement the ontology model in the form of, for example, a vocabulary dictionary (not shown), consisting of nodes in a hierarchical structure and a set of words and/or phrases related to each node, The natural language processing module 430 may determine the service keyword based on the ontology model implemented in the form of a vocabulary dictionary as described above.

Upon receiving the text input or sequence of words, the natural language processing module 430 may determine which nodes in the ontology model are associated with each word in the sequence, and determine a corresponding service keyword or attribute based on the determination. can Through this determination, the product corresponding to the service keyword can be identified.

When the natural language processing module 430 interprets a text input based on an ontology model in the form of a lexicon on the operation/comparison/control module 440 , it may not be able to determine an appropriate service keyword. For example, the received text input does not include a predetermined word or phrase defined as being mapped to a specific service keyword, and indirectly expresses the desired service keyword by listing entity information completely unrelated to the predetermined word or phrase. There may be cases.

In other words, when the text input through the calculation/comparison/control module 440 is not direct product or quantity data, it is not easy to determine the service keyword through the natural language processing module 430 .

To this end, the natural language processing module 430 to the operation/comparison/control module 440 are learning basic data for machine learning, such as previous history, online dictionary data, direct input data, online seller data, and offline warehouse data. Logistics-related data and the like may be referred to and used for the above determination.

Meanwhile, the determined service keyword may be different from, for example, logistics-related data of an offline warehouse. These contents may be resolved by receiving related data in advance and referring to the dictionary definition of the service keyword or may be processed in the form of a link.

For example, if the text data is "Necklace silver 1ea", "Necklace 1ea silver", "Necklace 1 silver color", "Embroidery 1 silver color", "Neckclass 1ea silver color", "Necklace 1ea silver", It may be "one silver necklace class", "one silver necklace necklace", etc. In this case, the natural language processing module 430 to the calculation/comparison/control module 440 finally correctly sets "one silver necklace" as the service keyword of the corresponding online seller 110 stocked on the online warehouse 130. It can be determined by the goods and their quantity.

On the other hand, the natural language processing module 430 determines an appropriate service keyword from the ontology model in the form of a vocabulary dictionary on the operation/comparison/control module 440, but if an error occurs, it analyzes a plurality of entities existing in the input and Based thereon, an appropriate service keyword may be determined or a new service keyword may be created and determined. For example, if the same type of entity is repeated multiple times, the natural language processing module 430 may determine that such input relates to a complaint receipt or return request.

The natural language processing module 430 may secure various databases for words indicating quality, such as size, color, performance, price, etc., among the received input, and may refer to it in determining the service keyword.

The database 350 may store and manage history data including the personalized data of the corresponding online seller 110 . This may be referred to for later processing or determination of the calculation/comparison/control module 440 or the natural language processing module 430, thereby contributing to fast calculation and accurate processing/determination. On the other hand, the personalized data included in the database 350 includes, for example, the seller's previous history, the seller's pronunciation, vocabulary preference, location, set language, contact/friend list, and other various personal personalization information of the seller for each seller. can

As described above, the STT module 410 may obtain more accurate text data by referring to the personalized data of each seller in the database 350, for example, the pronunciation characteristics of each seller, when converting the voice input into text data. there is. In determining the service keyword, the natural language processing module 430 may more accurately determine the service keyword by referring to each seller personalized data in the database 350 , for example, a personalized feature or context of each seller.

The database 350 may exist, for example, in the online seller terminal 110 , or may be distributed and disposed in the online seller terminal 110 and the offline warehouse 130 .

The operation/comparison/control module 440 may generate a series of operation flows corresponding thereto according to the service keyword determined by the natural language processing module 430 . The operation/comparison/control module 440 may determine which operation and/or task to be performed in response to the service keyword received from the natural language processing module 430 , and generate a detailed operation flow accordingly.

The TTS module 420 may receive the conversation response generated to be transmitted to the online seller terminal 110 by the conversation generating module 314 . The dialogue response received from the TTS module 420 may be a natural language having a text form or a sequence of words. The TTS module 420 may convert the received text input into a voice form according to various types of algorithms.

In addition, when determining each service keyword, the natural language processing module 430 or the operation/comparison/control module 440 may calculate a mapping or matching similarity and refer to it. Accordingly, when the calculated mapping or matching similarity is less than a predetermined threshold, the above-described process may be re-performed or returned to the online seller 110 to request confirmation, and may determine accordingly. Meanwhile, the confirmation, that is, the feedback of the online seller 110 may be reflected in the next operation and keyword determination.

On the other hand, the natural language processing module 430 to the operation/comparison/control module 440 separately mark various text data or words, phrases, and etymologies that are not previously registered in the database 350 to determine the mapping or matching similarity. can reflect

Next, an embodiment in which the fulfillment service server 120 performs a fulfillment service from the order information received from the online seller 110 when an image is included will be described.

5 to 7 , in the method for providing a fulfillment service according to an embodiment of the present invention, an image to be searched for an item is received from the online seller terminal 110 .

The fulfillment service server 120 classifies the received product search target image of the online seller terminal 110 .

The fulfillment service server 120 recognizes a product-related object from the classified product search target image of the online seller terminal 110, and sets the product-related part in the object as a region of interest (ROI), Crop the set region of interest (ROI).

The fulfillment service server 120 estimates the image similarity through the operation of the cropped image data and the article image data stored in the database 350 using sub-networks included in the pre-learned network function. For example, the fulfillment service server 120 performs a product search through an image-to-image method estimation using a similarity estimation model for an ROI part cropped from the product search target image.

The fulfillment service server 120 transmits the corresponding article data to the terminal of the offline warehouse 130 as a result of the search based on the estimated image similarity.

The fulfillment service server 120 communicates with the online seller terminal 110 shown in FIG. 1 and receives various data including the image data of the item to be searched from the online seller terminal 110 . Here, the image data to be searched received from the online seller terminal 110 may correspond to at least one of a captured or snapshot image, a captured image, a downloaded image, an image pre-stored in the online seller terminal 110, etc. there is.

The fulfillment service server 120 receives the received product search target image data of the online seller terminal 110 .

The fulfillment service server 120 classifies the search target image data of the received online seller terminal 110 . Meanwhile, as described above, the fulfillment service server 120 uses a deep learning-based multi-class classification model to classify the received product search target image of the online seller terminal 110 as described above. types can be distinguished. To this end, the fulfillment service server 120 receives various types of product image data collected through the web, the manufacturer's product image, the online seller 110 provided image, and the like, and uses the deep learning model in advance. can learn The learned result may be stored in the database 350 . Meanwhile, the deep learning-based multi-class classification model used in the fulfillment service server 120 may be stored in the database 350 in advance.

The fulfillment service server 120 performs object detection and cropping using a Faster R-CNN (Convolutional Neural Network features) model. FIG. 5A shows a feature map pyramid extracted from FPN, and FIG. 5B shows an example of an R-CNN structure using a feature map pyramid extracted from FPN. The detailed description of the Faster R-CNN model and the description of FIGS. 5 (a) and (b) to be described later refer to known content, and detailed description thereof will be omitted. However, in relation to the present invention, not only the currently published R-CNN model but also the R-CNN model developed and announced in the future is used in the process of detecting an object containing an item and automatically cropping the item-related item from the detection object. can be

First, the fulfillment service server 120 determines that it is an article image as a result of the above classification, and when the class is confirmed, an object related to an article image of the identified class in the search target image previously received from the terminal 110 recognize

In other words, in particular, a Faster R-CNN model trained in advance specifically for the item item is built, and the at least one or more objects in the image received from the online seller terminal 110 using the constructed model are related to the item item. object can be detected. In the case of the conventional object detection model, it was common to detect all objects included in the received image, but the present invention specializes in the item item and detects only the necessary object from the image as a meaningful object through a pre-learned object detection model. By doing so, it is possible to increase the efficiency of the entire system by reducing the time required for object detection and calculation.

Meanwhile, although not shown, for example, according to the user's selection or setting, for example, items that are not handled by the online seller 110 are excluded, and only the specific item(s) being handled and learned in advance. By using an object detection model, the efficiency can be further increased.

Alternatively, item items may be arbitrarily classified and a plurality of object detection models corresponding to the classified items may be used. In this case, the object detection model is applied sequentially or in parallel according to criteria such as a high level of user interest or a high level of sales or the number of types or numbers of products owned by the user to determine the object related to the product item. can detect

In addition, in the case of object detection, since the cropping process described later remains, the cropping process is performed by detecting the object according to a predetermined criterion, without performing a complicated process such as critically classifying an object with an item item. can

On the other hand, when the fulfillment service server 120 detects a plurality of objects related to the item as a result of the object detection, the fulfillment service server 120 may process according to the setting. Here, according to the setting, for example, all objects detected to select a specific object from among a plurality of objects in the cropping process are transferred to the cropping process, or a plurality of detection objects are determined in advance for convenience in the cropping process. Among them, it is also possible to determine only the object including the item item related to the desired item item and deliver it to the cropping process. Meanwhile, among the detected objects, it is preferable to group objects including article items belonging to the same category and transmit them to the cropping process.

The fulfillment service server 120 determines the actual part of the image of the item of the identified class from the recognized object as a region of interest, that is, an ROI (Region of Interest), and crops the corresponding part, that is, the ROI part from the object. . As an object detection and crop model used in the present invention, if the R-CNN model is used, the ROI is automatically cropped and can be directly used for a corresponding article search, which will be described later.

In this way, a learning model specialized for a product item is used through the fulfillment service server 120 according to the present invention, and the recognition accuracy is increased through this, and a plurality of cropped images for each object in the image search step in the online seller terminal 110 are displayed. Rather than manually inputting each item individually, it is possible to search for a corresponding item by inserting a single coordinated image, thereby improving user convenience.

As described above, it was a process of performing object detection and cropping a portion of an actual item to be searched from the detected object from the ROI. However, the present invention is not necessarily limited thereto. For example, in the case of object detection, a product item to be searched is cropped from an image and used for a search. Although not shown, an object including the item item is detected according to learning or through a pre-entered item item. The process may be omitted. That is, since the product item to be used for search is extracted from the image in the end, the process of detecting an object including the same may be removed and replaced with a process of detecting the article item instead. In this way, it is possible to increase the system efficiency by directly cropping the detected item item to reduce the processing speed or the amount of association.

The fulfillment service server 120 calculates a similarity by comparing the image of the cropped item with the image of the item stored in the database 350 image-to-image. The fulfillment service server 120 may set the rank of the product candidates returned as a search result based on the calculated similarity.

According to the present invention, the fulfillment service server 120 calculates the cropped image data and the product image data stored in the database using subnetworks included in the pre-learned network function to estimate and search the image similarity to obtain the image similarity. Estimate and search for the item through it. Here, the sub-networks may include a convolutional neural network (CNN) structure among deep neural network structures. 7 , the sub-networks may constitute at least a portion of a Siamese network. However, the present invention is not necessarily limited thereto. Meanwhile, as described above, detailed descriptions of a convolutional neural network (CNN), a Siamese network, and the like among the deep neural network structures will be omitted herein with reference to known technologies.

According to the present invention, if the image-to-image search method using the Siamese network shown in FIG. 7 is used, an index of similarity can be numerically calculated. Accordingly, by arbitrarily adjusting or setting the calculated similarity index, the product search result value may vary, and through this adjustment, it is possible to better meet the intention or needs of the online seller 110 .

In relation to this, in the present invention, a logistics ontology can be constructed through the above-described similarity estimation model and used for product search.

6 shows a learning model. Through this learning model, an attribute value of a detected object can be extracted. In one embodiment, Google's Inception-V3 learning model is shown in FIG. 6, and reference is made to related known content, and a detailed description of the learning model is omitted herein.

For example, images having the same attribute as the detected attribute may be read from the database 350 and used as a search candidate group. Thereafter, in connection with the Siamese network-based similarity estimation model, the candidate group can be ranked and determined/returned as a search result.

Also, it is possible to use the items returned as a search result according to the detected attribute as a filter function that allows the online seller 110 to exclude/include a detailed search.

That is, in the prior art, there was a hassle of having to directly input accurate product attribute information through the online seller 110 or offline warehouse 130 terminal. By tagging, it is possible to shorten the service procedure as well as increase the convenience of the online seller 110 .

On the other hand, the above-described process between the online seller - the fulfillment service server - the offline warehouse, that is, the item search request - the item search result determination/return, and the selection of the online seller 110 or the offline warehouse 130 according to the search result provision Efficiency can be further increased by reflecting and updating learning.

If the fulfillment service server 120 has information of an online seller or an offline warehouse terminal, it is possible to search for and provide a personalized item customized to the terminal through learning. In this way, if the personalization is performed, the factor values of the various models described above can be more simply configured, and the efficiency can be further improved through learning, and a result for a desired article can be provided quickly.

Meanwhile, in relation to the present invention, the database 350 stores the above-described various data, such as the received image, the information of the possessed product, and the above-described logistics ontology. Meanwhile, the database 350 is not necessarily built in the computing device 120 (or the online seller terminal 110 ). The database 350 also stores data in a cloud form, and returns a uniform resource locator (url) as necessary by accessing the url returned from the fulfillment service server 120 or the online seller terminal 110 and related It may also be built to acquire data.

The control unit 340 controls the entire process of the fulfillment service server 120 as a whole, and can appropriately control each configuration as necessary.

On the other hand, in the case of the image comparison method described above, in general, it is possible to increase the accuracy of calculation or determination by collecting and referencing various 3D information about an article. For example, referring to images acquired for various viewing angles or angles, such as the front, rear, upper, lower, and side surfaces of the article, it can contribute to fast calculation and accurate decision making in the decision process for the article.

Although not shown, when the order information received from the online seller 110 in the fulfillment service server 120 does not contain text or images alone, but is combined, the above-described contents may be appropriately combined to solve the problem. Accordingly, it can be considered that such a case is also included in the embodiment of the present invention. For example, if the data extracted and classified or cropped from the order information is text, a natural language processing method is used according to the text processing method, and if it is an image, an image processing method is used, and finally obtained from the data processed according to each method A fulfillment service can be provided based on one data.

In addition, in the above case, if the information on the same article or the final fulfillment service search data obtained therefrom do not match each other, the process is repeated or the fulfillment service data about the articles based on different data can be generated and transmitted to the online seller 110 to receive confirmation and proceed. Relevant data, such as experiences acquired in this process, may be used as learning materials for artificial intelligence-based data according to the present invention and updated later.

The fulfillment service process in the fulfillment service system 100 shown in FIG. 9 will be described with reference to FIGS. 10 and 11 .

Referring to FIG. 10 , the online seller 110 stocks the items available for sale in the offline warehouse 130 in advance ( S201 ).

When a customer places an order for a specific product with the online seller 110 (S202), the online seller 110 uploads order information to the fulfillment service server 120 (S203).

The fulfillment service server 120 converts the order information into a database and transmits it to the offline warehouse 130 (S204).

The offline warehouse 130 picks up, packages, and releases the product based on the transmitted order information (S205/S206).

The offline warehouse 130 uploads the invoice information to the fulfillment service server 120 after the goods are shipped (S207).

The fulfillment service server 120 provides the uploaded product invoice information to the online seller 110 (S208).

Referring to FIG. 11 , a detailed processing process for CS processing and return operation will be described after FIG. 10 .

When a customer requests a CS processing or return operation to the online seller 110 (S301), the online seller 110 transmits it to the fulfillment service server 120 (S302).

The fulfillment service server 120 determines the customer's CS processing/return operation request information and delivers it to the offline warehouse 130 (S303).

After confirming this, the offline warehouse 130 transmits the feedback information to the online seller 110 through the fulfillment service server 120 (S304, S305). In this case, the feedback information may include various data such as a restocking request due to insufficient quantity of goods, confirmation of whether another product has been shipped, and data of a process of sending out goods according to a previous request.

At the same time, the offline warehouse 130 releases other goods and delivers them to the customer (S306).

The offline warehouse 130 returns the information on the restocking to the online seller 110 through the fulfillment service server 120 (S307, S308).

Thereafter, the online seller 110 receives the customer's feedback again. If the feedback is affirmative, the process is terminated. However, if the feedback is negative, the above-described procedure may be repeated or another procedure may be performed. The above other procedures may include bringing in and compensating for outgoing goods.

Meanwhile, in the above process, the fulfillment service server 120 may continuously manage and control the fulfillment service by databaseizing and updating various types of data in the form shown in FIG. 12 .

Meanwhile, 　the method described above can be written as a program that can be executed on a computer, and 　 can be implemented in a general-purpose digital computer that operates the program using a computer-readable medium. In addition, the structure of data used in the above-described method may be recorded in a computer-readable medium through various means. A computer readable medium storing executable computer code for performing various methods of the present invention is a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.), an optical readable medium (eg, a CD-ROM, a DVD) storage media, such as).

A person of ordinary skill in the art related to the embodiments of the present invention will understand that it can be implemented in a modified form without departing from the essential characteristics of the description. Therefore, the disclosed methods should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the detailed description of the invention, and all differences within the scope equivalent thereto should be construed as being included in the scope of the present invention.

Claims (19)

A method for providing a fulfillment service in a service server between an online seller and an offline warehouse, the method comprising:
Registering service keywords through artificial intelligence learning;
receiving order information including text data, image data, and audio data for product shipment from the online seller terminal;
extracting search data in the received order information and classifying the extracted search data;
comparing the classified search data with registered service keywords;
as a result of the comparison, if there is no matching service keyword, generating and registering a new service keyword and then updating the service keyword database;
generating first fulfillment service data related to the generated new service keyword;
Confirmation data including the generated first fulfillment service data - The first fulfillment service data and the confirmation data are the service keyword, information on goods stored in an offline warehouse corresponding to the service keyword, and the order information transmitting, to the online seller terminal, item order quantity information extracted from
receiving feedback data for the confirmation data from the online seller terminal;
when the feedback data is received, transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped; and
when the feedback data is received, parsing the feedback data based on the received feedback data, identifying the parsed feedback data content, registering the new service keyword, and updating the service keyword database; and
If the identified feedback data content is a negative message,
re-extracting and re-classifying the search data in the received order information, and re-comparing the re-classified search data with a registered service keyword;
As a result of the re-comparison, if there is no matching service keyword,
generating a new service keyword to generate second fulfillment service data related to the generated new service keyword;
As a result of the re-comparison, if there is a matching service keyword,
As including; generating second fulfillment service data according to the matching service keyword;
When the order information consists of text data including voice data,
Converts voice data into text data according to the STT module,
The natural language processing module receives text data and corresponds to one or more service keywords, the service keywords are determined based on an ontology model, to identify articles corresponding to the service keywords;
When the service keyword according to the received text data is not determined, it can be determined by referring to previous history, online dictionary data, manually entered data, online seller data, and offline warehouse logistics data,
If the determined keyword is different from the logistics-related data of the offline warehouse, the related data is received in advance and processed by referring to the predefined definition of the service keyword,
When determining the service keyword, it calculates the similarity of mapping or matching, and if it is less than a predetermined threshold, it is performed again or returned to the online seller to request confirmation,
When the order information includes an image, but includes a captured or snapshot image, a photographed image, a downloaded image, an image pre-stored in an online seller terminal,
Receive an image to be searched for an item from an online seller terminal,
classifying the received online seller terminal's product search target image,
Recognizing a product-related object from the classified product search target image of the online seller terminal, setting the product-related part in the object as a region of interest, and cropping the set region of interest;
Estimating the image similarity through the operation of the cropped image data and the article image data stored in the database using sub-networks included in the pre-learned network function,
A method for providing a fulfillment service in a service server, comprising transmitting the corresponding article data to the offline warehouse terminal as a result of the search based on the estimated image similarity. delete delete delete delete delete delete delete delete delete In the service server that provides a fulfillment service between an online seller and an offline warehouse,
Registering service keywords through artificial intelligence learning;
receiving order information including text data, image data, and audio data for product shipment from the online seller terminal;
extracting search data in the received order information and classifying the extracted search data;
comparing the classified search data with registered service keywords;
as a result of the comparison, if there is no matching service keyword, generating and registering a new service keyword and then updating the service keyword database;
generating first fulfillment service data related to the generated new service keyword;
Confirmation data including the generated first fulfillment service data - The first fulfillment service data and the confirmation data are the service keyword, information on goods stored in an offline warehouse corresponding to the service keyword, and the order information transmitting, to the online seller terminal, item order quantity information extracted from
receiving feedback data for the confirmation data from the online seller terminal;
when the feedback data is received, transmitting the generated first fulfillment service data to the offline warehouse terminal to control the product to be shipped; and
when the feedback data is received, parsing the feedback data based on the received feedback data, identifying the parsed feedback data content, registering the new service keyword, and updating the service keyword database; and
If the identified feedback data content is a negative message,
re-extracting and re-classifying the search data in the received order information, and re-comparing the re-classified search data with a registered service keyword;
As a result of the re-comparison, if there is no matching service keyword,
generating a new service keyword to generate second fulfillment service data related to the generated new service keyword;
As a result of the re-comparison, if there is a matching service keyword,
As including; generating second fulfillment service data according to the matching service keyword;
When the order information consists of text data including voice data,
Converts voice data to text data according to the STT module,
The natural language processing module receives the text data and corresponds to one or more service keywords, the service keyword being determined based on an ontology model, to identify an article corresponding to the service keyword,
When the service keyword according to the received text data is not determined, it can be determined by referring to previous history, online dictionary data, manually entered data, online seller data, and offline warehouse logistics data,
If the determined keyword is different from the logistics-related data of the offline warehouse, the related data is received in advance and processed by referring to the predefined definition of the service keyword,
When determining the service keyword, it calculates the similarity of mapping or matching, and if it is less than a predetermined threshold, it is performed again or returned to the online seller to request confirmation,
When the order information includes an image, but includes a captured or snapshot image, a photographed image, a downloaded image, an image pre-stored in an online seller terminal,
Receive an image to be searched for an item from an online seller terminal,
classifying the received online seller terminal's item search target image,
Recognizing a product-related object from the classified product search target image of the online seller terminal, setting the product-related part in the object as a region of interest, and cropping the set region of interest;
Estimating the image similarity through the operation of the cropped image data and the article image data stored in the database using sub-networks included in the pre-learned network function,
and transmitting the corresponding article data to the offline warehouse terminal as a result of a search based on the estimated image similarity. delete delete delete delete delete delete delete delete

Images