Method for providing life-cycle-specific customized welfare and living services

Abstract

A method by which a server provides life-cycle-specific customized welfare and living services, according to one embodiment of the present invention, comprises the steps of: receiving, from a user terminal, personal information including the life cycle of a user and an input for at least one service sector; (b) extracting living welfare information matched to the personal information on the basis of the life cycle, and providing same to the user terminal; (c) providing the personal information and the living welfare information to a company terminal related to the service sector, and receiving product information from the company terminal; and (d) recommending at least some of the product information through the user terminal, wherein the life cycle is pre-classified into a plurality of stages in which at least one from among whether the user is married and has given birth to a child, the age of the child, whether the child is independent, and whether the child is married is reflected.

Description

Methods for providing customized welfare and lifestyle services for each life cycle

[0001] The present invention relates to a method and device for providing customized welfare and lifestyle services according to life cycle, and more specifically, to a technology for identifying welfare and product information matching the user's current life cycle and providing the information to the user.

[0002] A life cycle is a process that divides a person's life into certain stages based on major changes that occur in the life of an individual or a family. Although the degree of change may vary from individual to individual, the order of progression of each stage is generally similar.

[0003] For example, the life cycle can be divided into stages such as family formation, child-rearing, child education, child independence, and old age, depending on the size of the family or changes in lifestyle.

[0004] As people progress through their life cycle, there are expected roles for each stage, known as developmental tasks. For example, during the family formation stage, marriage and childbirth are typically the tasks, and successfully completing these tasks will allow for the smooth progress of subsequent tasks, such as child rearing.

[0005] In this way, in order to lead a satisfactory life, it is very important to correctly recognize and proceed with the developmental tasks for each stage of the life cycle.

[0006] In this regard, in modern society, various public and private service projects are being carried out to assist with developmental tasks at each life stage, and countless products utilized for each task are being distributed in the market.

[0007] Therefore, it is advantageous for individuals and families to manage their capital and time efficiently, such as by applying for and receiving as many welfare services as possible and purchasing the most appropriate products for their circumstances.

[0008] However, most modern people fail to catch up on necessary welfare services or products in their busy daily lives, and many even forget where they fit into their life cycle.

[0009] For example, because different welfare programs are managed by different organizations, policies are introduced or changed constantly, and the procedures required vary depending on individual circumstances, it is difficult to identify and select the services you need.

[0010] Additionally, for newlyweds and those just starting out, there are limitations in identifying the services or products they need, and even for the same type of product, prices and quality can vary greatly depending on the company, often putting a burden on the household budget.

[0011] Meanwhile, the concept of providing customized services by understanding an individual's condition or needs has been recently introduced, and the technical ideas related to this have been disclosed in numerous prior literature.

[0012] Based on this, there is a need for technology that can contribute to improving the quality of life by providing comprehensive information that matches each life cycle, while also identifying optimal services or products by reflecting the user's personal information.

[0013] One embodiment of the present invention aims to recommend welfare services and products that match the user's life cycle to the user by identifying welfare information based on the user's personal information and receiving product information on the service sector desired by the user from a business based on the user's life cycle.

[0014] However, the technical tasks that this embodiment seeks to accomplish are not limited to the technical tasks described above, and other technical tasks may exist.

[0015] According to one embodiment of the present invention, a method for providing customized welfare and living services by life cycle, performed by a server, comprises the steps of: (a) receiving personal information including a user's life cycle from a user terminal and an input for at least one service sector; (b) extracting living welfare information matching the personal information based on the life cycle and providing the same to the user terminal; (c) providing the personal information and the living welfare information to a business terminal related to the service sector and receiving product information from the business terminal; and (d) recommending at least a portion of the product information to the user terminal; wherein the life cycle is pre-classified into a plurality of stages in which at least one of the user's marital status and childbirth status, the age of the children, independence status, and marital status is reflected.

[0016] According to one embodiment of the present invention, the step (a) includes a step of requesting additional information other than the personal information from the user terminal or collecting it in a preset manner, depending on the service sector received from the user terminal.

[0017] According to one embodiment of the present invention, the step (b) includes a step of preprocessing the personal information based on the life cycle and the service sector, extracting at least one piece of information matching the preprocessed personal information from among the life welfare information collected on the server, and providing the extracted information to the user terminal.

[0018] According to one embodiment of the present invention, the step (c) includes a step of processing and analyzing the personal information and the living welfare information based on the service sector, and selecting at least one company among the companies registered in the server based on the analysis results.

[0019] According to one embodiment of the present invention, the step (d) includes a step of sorting or filtering the product information based on at least one of the life cycle, the service sector, and the lifestyle welfare information, and then providing the product information to the user terminal.

[0020] According to one embodiment of the present invention, the step (a), which is the step of self-collecting in the preset manner, includes: a step of collecting lifelog information from the user terminal; a step of performing standardization on unstructured information among the lifelog information to classify the lifelog information based on a service sector; a step of extracting lifelog information belonging to a service sector received from the user terminal based on a classification result; and a step of statistically analyzing the extracted lifelog information to identify a user's area of ​​interest or preference for the service sector and setting it as additional information and storing it.

[0021] According to one embodiment of the present invention, when the life log information is in text form, the step of classifying the life log information based on the service sector includes the step of performing at least one text analysis among sentence analysis, word analysis, and morphological analysis to extract string information in sentence units or word units from the life log information; the step of performing categorization on the extracted string information; the step of identifying a service sector matching each category and matching and storing each string information included in each category with the identified service sector.

[0022] According to one embodiment of the present invention, if the life log information is in text form, the step of setting and storing it as additional information includes the steps of: extracting all string information matching the service sector input from the user terminal; summing the number of repetitions by extracted string information or category and determining them in ascending order; and determining the user's area of ​​interest or preference based on the determination result and setting and storing it as additional information.

[0023] According to one embodiment of the present invention, when the life information is in the form of an image or video, the step of classifying the life log information based on the service sector includes the step of constructing a service sector classification model; and the step of inputting the life log information into the service sector classification model and outputting at least one service sector; wherein the service sector classification model is learned in advance through a machine learning model that is preset so that a specific service sector is output when a specific image or video is input.

[0024] According to one embodiment of the present invention, when the life information is in the form of an image or video, the step of setting and storing it as additional information includes: a step of extracting all images or videos classified in the service sector input from the user terminal; a step of searching the page where each of the extracted images or videos was displayed using a preset search technique; a step of tracking logs and traffic for each searched page, and based on the tracking results, identifying the user's area of ​​interest or preference and setting and storing it as additional information.

[0025] According to one embodiment of the present invention, the step (b) includes: determining a type of welfare service based on the life cycle and service sector; identifying personal information that serves as a criterion for primary filtering based on the type and extracting life welfare information corresponding to the criterion from among previously stored life welfare information; performing secondary filtering to scrape life welfare information corresponding to the type from among the life welfare information extracted by the primary filtering; extracting numerical information based on a preset criterion based on the life cycle and the type; and comparing each extracted numerical information or numerical information combined based on a preset criterion with numerical information included in the life welfare information extracted by the secondary filtering; and specifying life welfare information matching the personal information based on the comparison result.

[0026] According to one embodiment of the present invention, the step (c) includes: a step of building a business selection model that matches a specific user with a specific cluster code through preset machine learning; a step of processing and analyzing the personal information, service sector, and living welfare information to generate input data; and a step of applying the input data to the business selection model to output at least one cluster code; wherein the cluster code is set to be clustered in a preset manner so as to include at least one business among the businesses registered in the server.

[0027] According to one embodiment of the present invention, a method for setting the cluster code includes the steps of: forming a first graph in which one axis is a service sector and the other axis is a life cycle; mapping companies registered in the server to the first graph; connecting companies belonging to the same range on the one axis with nearby locations on the other axis to classify each company into a first cluster; forming a second graph for each first cluster and mapping companies included in each first cluster to each second graph; wherein the second graph is a preset sub-criteria excluding the service sector and the life cycle, and the number of clusterings is determined according to the number of sub-criteria.

[0028] According to one embodiment of the present invention, a method for constructing the above-described business selection model includes: a step of generating training data by performing normalization on personal information and service sectors of predetermined items stored in the server; a step of analyzing the living welfare information stored in the server to determine at least one product or service item corresponding to each living welfare information and setting the determined item as training data; a step of generating input data as a set of training data by differently combining each of the generated or set training data; and a step of repeating learning so that at least one cluster code is output when specific input data is input through a preset machine learning model.

[0029] According to one embodiment of the present invention, the step (d) includes: a step of removing product information unrelated to the life cycle from the received product information; a step of extracting product information corresponding to the life welfare information from the remaining product information after the removal; a step of removing product information not included in the service sector from the extracted product information and then sorting the product information in order of the number of service sectors included; a step of calculating a similarity for each personal information remaining excluding the life cycle for each sorted product information; a step of calculating a matching score by adding up the similarities calculated for each sorted product information; a step of sorting the product information in order of the highest matching score or extracting product information having a matching score higher than a preset reference score and providing the product information to a user terminal.

[0030] One embodiment of the present invention provides users with comprehensive information on welfare services available for each life cycle.

[0031] One embodiment of the present invention recommends a user-tailored welfare service according to the life cycle to the user.

[0032] One embodiment of the present invention provides users with a comprehensive range of products according to their life cycle for a specific service sector.

[0033] One embodiment of the present invention identifies a user-tailored product according to the life cycle for a specific service sector and recommends it to the user.

[0034] Through one embodiment of the present invention, a user can easily recognize welfare services and related products suitable for the current life cycle, and further enjoy services and products optimized for the user.

[0035] Figure 1 is a schematic diagram of a system for providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0036] FIG. 2 is a block diagram showing the configuration of a server providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0037] Figure 3 is a flowchart of a method for providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0038] FIG. 4 is an exemplary diagram of a user interface according to one embodiment of the present invention.

[0039] FIG. 5 is a block diagram of an internal configuration included in a processor of a server according to one embodiment of the present invention.

[0040] Below, with reference to the attached drawings, embodiments of the present invention are described in detail so that those skilled in the art can easily implement them. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, irrelevant parts have been omitted for clarity of description, and similar reference numerals have been used throughout the specification to indicate similar elements.

[0041] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the cases where the parts are "directly connected" but also the cases where the parts are "electrically connected" with other elements intervening. Furthermore, when a part is said to "include" a component, this does not exclude other components, but rather includes other components, unless otherwise stated.

[0042] In this specification, the term 'unit' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be realized by using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, the '~ unit' is not limited to software or hardware, and the '~ unit' may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, the '~ unit' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and '~sub-units' may be combined into a smaller number of components and '~sub-units' or further separated into additional components and '~sub-units'. Furthermore, the components and '~sub-units' may be implemented to activate one or more CPUs within the device or secure multimedia card.

[0043] The "terminal" mentioned below may be implemented as a computer or portable terminal that can access a server or other terminal via a network. Here, the computer may include, for example, a notebook, desktop, laptop equipped with a web browser, VR HMD (e.g., HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.). Here, the VR HMD includes all of the following: for PC (e.g., HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), for mobile (e.g., GearVR, DayDream, Storm Magic, Google Cardboard, etc.), for console (PSVR), and Stand Alone models (e.g., Deepon, PICO, etc.) that are implemented independently. A portable terminal is, for example, a wireless communication device that ensures portability and mobility, and may include not only a smart phone, a tablet PC, and a wearable device, but also various devices equipped with communication modules such as Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, ultrasonic, infrared, WiFi, and LiFi. In addition, a "network" refers to a connection structure that enables information exchange between each node, such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), the Internet (WWW: World Wide Web), wired and wireless data communication networks, telephone networks, and wired and wireless television communication networks.Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth, infrared, ultrasonic, visible light communication (VLC), and LiFi.

[0044] Hereinafter, an embodiment of the present invention will be described in detail using the attached drawings.

[0045] Figure 1 is a schematic diagram of a system for providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0046] Referring to FIG. 1, a system according to one embodiment includes a server (100), a user terminal (10), and a business terminal (20).

[0047] A user terminal (10) refers to a terminal in which users consume customized welfare services for each life cycle through websites, platforms, applications, etc. provided by a server (100).

[0048] According to one embodiment, the user terminal (10) includes a memory (not shown), a processor (not shown), and a communication module (not shown), and the communication module performs data communication with the server (100) under the control of the processor.

[0049] In one embodiment, the memory stores programs (or applications) for customized welfare and living services for each life cycle.

[0050] The processor executes programs stored in memory and processes a series of operations to provide users with customized welfare and living services for each life cycle.

[0051] As an example of overall operation, the processor transmits customer information and service sector input by the user to the server (100), and then receives lifestyle welfare information and product information corresponding thereto from the server (100), thereby providing the user with customized information for each life cycle.

[0052] The business terminal (20) refers to a terminal of a business that provides products or services utilized to achieve tasks for each life cycle, and may be configured in multiple units corresponding to a single user terminal (10). For example, if the user's life cycle is the family formation period (marriage) and the requested service sector is marriage, the business terminal (20) may be a terminal of a wedding company, a studio company, a makeup company, a dress company, or other various product companies related to newlyweds, and the type of business does not limit the present invention.

[0053] According to one embodiment, the business terminal (20) includes a memory (not shown), a processor (not shown), and a communication module (not shown), and the communication module performs data communication with the server (100) under the control of the processor.

[0054] According to one embodiment, the memory stores a program (or application) for performing a method for providing product information by life cycle.

[0055] The processor executes a program stored in memory and performs a series of operations to provide product information for each life cycle.

[0056] As an example of overall operation, the company terminal (20) receives the user's personal information and lifestyle welfare information from the server (100), extracts product information corresponding thereto, and provides the extracted product information to the server (100), thereby inducing a recommendation of a product suitable for the user's life cycle.

[0057] The server (100) may refer to an operating server of a service provider that provides customized welfare and living services for each life cycle.

[0058] Accordingly, the server (100) can be defined as a server that provides customized welfare and living services for each life cycle.

[0059] FIG. 2 is a block diagram showing the configuration of a server providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0060] According to one embodiment, the server (100) may include a communication module (110), a memory (120), a processor (130), and a database (140).

[0061] The communication module (110) processes data communication with the user terminal (10) and the company terminal (20), respectively.

[0062] The memory (120) stores a program (or application) that provides customized welfare and lifestyle services for each life cycle. For example, the program may be linked to websites, platforms, applications, etc. provided by the server (100) to user terminals (10) and business terminals (20).

[0063] The processor (130) executes a program stored in the memory (120) to process various processes within the program to provide customized welfare and living services for each life cycle.

[0064] As a brief example of the process, the processor (130) receives input for personal information and service sector from a user terminal (10), extracts life welfare information matching the personal information and provides it to the user terminal (10), provides the personal information and life welfare information to a business terminal (20) of the service sector in which it was input, receives product information therefrom, and recommends all or part of the product information to the user terminal (10).

[0065] The database (140) stores users' personal information and can be categorized and stored by life cycle. Furthermore, company information for companies registered on the server (100) can be stored and categorized by service sector. Furthermore, previously collected lifestyle welfare information can be categorized and stored by life cycle. Furthermore, product information received from each company terminal can be matched with company information and stored and categorized and stored by life cycle. Additionally, information generated during various processing processes performed by the server (100) can be stored.

[0066] Hereinafter, with reference to FIGS. 3 and 4, an embodiment of a method for providing customized welfare and living services according to the life cycle of the present invention will be described.

[0067] Figure 3 is a flowchart of a method for providing customized welfare and living services for each life cycle according to one embodiment of the present invention.

[0068] FIG. 4 is an exemplary diagram of a user interface according to one embodiment of the present invention.

[0069] In step S310, the server (100) receives personal information including the user's life cycle and input for at least one service sector from the user terminal (10).

[0070] According to one embodiment, the server (100) provides a user interface to the user terminal (10), and the user interface may include a service sector selection area (41) and a life cycle selection area (42).

[0071] According to one embodiment, the service sector may be pre-categorized by the server (100) based on life-related factors that may occur in a person's life, and may be pre-classified and stored in the server (100). As illustrated in FIG. 4, the service sectors may be set to include, but are not limited to, health, housing, finance, occupation, culture, leisure, marriage, pregnancy, childbirth, condolence, childcare, education, protection, support, and medical services.

[0072] According to one embodiment, the server (100) displays the classified service sectors in the service sector selection area (41) and can receive at least one selection input from the user terminal (10).

[0073] According to one embodiment, the life cycle may be pre-classified into multiple stages and stored in the server (100). For example, referring to FIG. 4, each stage may be classified into single, married, pregnancy and childbirth, infancy, child education, unmarried children living together, married children living together, children becoming independent, and old age. That is, the server (100) may divide the stages according to preset criteria and set a name representing the life cycle for each stage. Here, the criteria may reflect at least one of the user's marriage and childbirth status, the age of the children, whether the child is independent, and whether the child is married, but is not limited thereto.

[0074] According to one embodiment, the server (100) displays the stages of the classified life cycle in a life cycle selection area (42) and can receive a selection input for at least one of the displayed life cycles from the user terminal (10).

[0075] According to one embodiment, the server (100) can determine the service sectors displayed in the service sector selection area (41) according to the life cycle input from the user terminal (10). For example, if the user's life cycle is old age, the server (100) can filter out sectors that have a low correlation with old age, such as pregnancy, childbirth, and childcare, from all service sectors stored in the server (100), or extract only sectors that have a high correlation with old age, such as health, protection, support, and medical care, from all service sectors. Here, the relationship chart may be stored in the server (100) in the form of a relationship score for each life cycle for each service sector. Accordingly, the server (100) can extract only service sectors in which the relationship score falls within a preset reference range in response to the life cycle input from the user terminal (10) and provide them to the user terminal (10).

[0076] According to one embodiment, the user interface includes a personal information input area (43), and as shown in FIG. 4, the server (100) can display the personal information input area (43) on the user interface in response to input of the service sector and life cycle of the user terminal (10).

[0077] In one embodiment, personal information is information that serves as a basis for user identification, and may include, but is not limited to, items such as life cycle, age, occupation, marital status, presence of children (childbirth), gender, and region.

[0078] According to one embodiment, the server (100) may request additional information required in addition to personal information already received from the user terminal (10) according to the service sector received from the user terminal (10).

[0079] In this regard, the items of personal information to be entered may be preset in the server (100), but may be determined based on the service sector received from the user terminal (10). For example, if the user selects the service sector of "childbirth," the server (100) may perform a process of adding an entry item for whether or not there are children (childbirth) in the input items of personal information set as default if there is no such entry item. Alternatively, if there is an entry item for whether or not there are children in the input items set as default, a more detailed entry may be created and displayed. In this case, the detailed entry may include, but is not limited to, the number of children, pregnancy status, and time of birth, but is merely an example.

[0080] According to one embodiment, the server (100) can collect additional information required in addition to the personal information already received from the user terminal (10) in a preset manner according to the service sector received.

[0081] In this regard, the server (100) can collect the user's lifelog information and obtain the user's additional information through this.

[0082] First, before step S310, the server (100) collects various types of lifelog information generated from the user terminal (10). Here, lifelog information may include, for example, search information, event information, GPS information, image information, video information, exercise information, health information, social network (SNS) information, sleep information, etc., and may be structured or unstructured information, and its types are not limited thereto.

[0083] The server (100) performs standardization on the unstructured information among the collected lifelog information and, based on this, determines which service sector each lifelog information represents. In other words, the server (100) stores each lifelog information by classifying it based on the service sector.

[0084] In the case of life log information in text format, the server (100) performs at least one analysis (text analysis) among sentence analysis, word analysis, and morphological analysis to extract string information in sentence or word units from the life log information. Thereafter, the server (100) performs categorization on the extracted string information. For example, if string information such as "reservation," "game," "ticket," "baseball," "batting average," "soccer," and "tennis" are extracted, they can be classified into a category of the upper concept of "sports." Thereafter, the server (100) identifies the service sector that matches the category. For example, if the categories formed based on the extracted string information are "sports," "movie," and "game," each extracted string information can be matched with and stored in the service sector of "culture."

[0085] In the case of lifelog information in the form of an image or video, the server (100) can classify the lifelog information based on the service sector through a service sector classification model. Here, the service sector classification model is pre-built in the server (100) so that when an image or video frame is input, it is classified into at least one service sector.

[0086] A service sector classification model can be designed by learning from training data using a pre-configured machine learning model. For example, if an image or video containing objects related to a wedding hall, reception hall, wedding photo shoot, dress, invitation, and wedding supplies is input, a function that achieves this can be derived to output the "wedding" service sector. The classification algorithm can then be optimized by repeatedly validating this function using training data.

[0087] Here, the type of machine learning model does not limit the present invention, but since the purpose is “classification,” the artificial neural network series is preferable, and in particular, it is preferable to adopt a CNN (Convolution Neural Network) optimized for image and video processing.

[0088] As an example of training data, the server (100) can randomly extract a portion of various images and videos stored in the database (140), set them as input data for training, and transmit them to an administrator terminal (not shown). The administrator can verify these and perform labeling to match each image and video with a service sector. Through this, training data, in which a specific image or video is set as input data and a correspondingly labeled service sector is set as output data, can be collected on the server (100).

[0089] Additionally, if the input data is a video, labeling can be done frame by frame, rather than the entire video. Because labeling every frame has its limitations, frame skipping allows for extracting only characteristic frames and setting them as the target for labeling.

[0090] After training data is secured, the server (100) builds a service sector classification model by repeatedly learning through the training data so that labeled output data is accurately output when input data is input.

[0091] Meanwhile, during the learning process, the server (100) may perform a preprocessing process on input data to extract features from images or frames. For example, the server (100) may minimize processing volume and facilitate faster training by identifying objects representing the input data through a preset convolutional filter.

[0092] The server (100) inputs lifelog information in the form of images or videos collected from user terminals (10) into the service sector classification model constructed in this manner. Accordingly, each lifelog information in the form of images or videos can be classified and stored into at least one service sector.

[0093] In this way, when lifelog information is classified by service sector, in step S310, the server (100) can extract lifelog information belonging to the service sector received from the user terminal (10). Thereafter, the server (100) can statistically analyze the extracted lifelog information to identify the user's preferred areas of interest or preferences in the corresponding service sector, and store this as additional information.

[0094] Specifically, when receiving input from a specific service sector from a user terminal (10), the server (100) can extract all string information matching it. The server (100) can determine the number of extracted string information and list them in ascending order. In addition, the number of string information can be added up by category and listed in ascending order. The server (100) can collect additional information, such as the user's area of ​​interest, based on upper string information or categories within a preset range.

[0095] For example, if the service sector of "culture" is input and the most repeated string information extracted is "ticket", "baseball", "stadium", and "reservation", the server (100) can recognize that the user's cultural interest area is "watching baseball" and store this as the user's additional information. Alternatively, if it is difficult to identify the additional information by string information unit, such as "stadium", "performance hall", "baseball", "hip-hop", and "makgeolli", the server (100) can synthesize string information by category, and as a result, if the string information included in the "sports" category is the most, "sports" can be recognized as the user's main area of ​​interest.

[0096] Additionally, when receiving input for a specific service sector from a user terminal (10), the server (100) can extract all images or videos classified into the corresponding service sector through a classification model. The server (100) can search pages where images or videos extracted using crawling techniques or the like are displayed. In addition, the server can track logs and traffic for each page, and based on the tracking results, identify the user's areas of interest or preferences, set them as additional information, and store them.

[0097] In one embodiment, at step S310, the server (100) may provide a preset reward in response to the user's provision of personal information. The preset reward may be implemented in the form of points or commissions for personalized welfare and lifestyle services tailored to each life cycle, but the form and structure of the reward are not limited thereto.

[0098] Referring again to FIG. 3, in step S320, the server (100) can extract life welfare information matching personal information based on the life cycle received from the user terminal (10) and provide it to the user terminal (10).

[0099] In one embodiment, "life welfare information" refers to information on public or private welfare policies, welfare programs, and welfare services that provide physical, psychological, and spiritual support to individuals or families at a specific life stage. For example, if the life stage is marriage, which is a family formation stage, life welfare information may include information on special provisions for newlyweds, jeonse (rental deposit) loans and jeonse loan interest subsidies for newlyweds, health checkup support for newlyweds, and marriage incentives. These are examples and are not intended to be limiting.

[0100] According to one embodiment, the living welfare information may be pre-collected and stored on the server (100). For example, the server (100) may repeatedly collect and update various living welfare information distributed on the Internet using techniques such as crawling, RSS, scraping, and OPEN API. In addition, the server (100) may regularly receive and update living welfare information at preset intervals by linking with various public or private institution servers that provide living welfare information.

[0101] Additionally, the server (100) can store each collected life welfare information by matching it with its corresponding life cycle. In other words, each life welfare information can be classified based on the life cycle.

[0102] In step S330, the server (100) provides the user's personal information and the life welfare information extracted in step S320 to a business terminal (20) related to the service sector entered by the user.

[0103] After this, each company can determine what products or services the user needs based on the information obtained from the server (100) and transmit the product information to the server (100) via the company terminal (20). The server (100) can store each received product information by matching it with each company terminal (20). Here, the product information encompasses products and services, and any information that represents the product, such as the product (service) name, price, quantity, region, and delivery, is sufficient, and the type thereof is not limited.

[0104] In one embodiment, the server (100) may provide a payment interface for selling information to a business terminal (20). That is, the business may pay a prescribed fee and receive information about the user. For example, the business may pay the information provision fee for a prescribed period all at once when registering as a member with the server (100), or may make payments individually each time information about a specific user is received. The server (100) provides personal information and lifestyle welfare information to the business terminal (20) upon confirmation of payment.

[0105] In step S340, the server (100) recommends at least some of the product information collected through step S330 to the user terminal (10). That is, the server (100) can induce the user to make an optimal selection by providing the user with information on all or some of the products or services offered by each company.

[0106] As described above, the server (100) can perform various functions to process and analyze collected information to provide users with personalized information tailored to their life cycle. In this regard, referring to FIG. 5, depending on each function, the processor (130) may include components such as a lifestyle welfare information extraction unit (131), a business selection unit (132), and a product recommendation unit (133).

[0107] According to one embodiment, the life welfare information extraction unit (131) may preprocess the user's personal information based on the user's life cycle and service sector, extract at least one piece of information matching the preprocessed personal information from among the stored life welfare information, and provide the extracted information to the user terminal (10).

[0108] Specifically, the Life Welfare Information Extraction Unit (131) determines the type of welfare service corresponding to the combined result by combining life cycle and service sector. For example, if the life cycle is "Pregnancy" and the service sector is "Health," the type may be determined as "Health Care Services for Mothers and Newborns."

[0109] The welfare information extraction unit (131) identifies the personal information that serves as the basis for the primary filtering based on the determined type and extracts information corresponding to the criteria from the stored welfare information. In the example above, since healthcare services are generally under the jurisdiction of local governments, the "region" information should be identified first. In the example above, if the user's region is "Seocho-gu," primary filtering can be performed to extract only welfare information relevant to Seocho-gu and remove the rest.

[0110] The welfare information extraction unit (131) performs a secondary filtering process, scraping information corresponding to a determined type from the primary filtered welfare information. While scraping is typically performed from the database (140), if it is determined that the information has not been collected in advance, scraping can also be performed in real time from a corresponding website. In the example above, the secondary filtered welfare information may refer to a "public notice on health care services for mothers and newborns implemented in Seocho-gu."

[0111] The welfare information extraction unit (131) can extract numerical information based on personal information, such as life cycle and determined type, based on preset criteria. In the example above, numerical information such as "number of children," "date of birth (or expected date)," and "gestational period" can be extracted based on the "pregnancy" life cycle. Furthermore, numerical information such as "number of household members," "health insurance premiums," "income bracket," and "number of family members registered as disabled" can be extracted based on the "health care service" type.

[0112] The welfare information extraction unit (131) compares each extracted numerical information or numerical information combined according to preset criteria with the numerical information included in the secondary filtered welfare information, thereby finally specifying the welfare information that matches the preprocessed personal information. In the example above, among the numerical information included in the notice, the numerical information with the most similar value to "date of birth (or expected date)" or "period of pregnancy" can be identified, and accordingly, the period during which the user can apply for the welfare service can be specified. Alternatively, among the numerical information included in the notice, the numerical information with the most similar value to "number of children", "number of household members", "health insurance premium", or "income level" can be identified, and accordingly, the period of welfare service or whether or not it is provided can be specified.

[0113] In one embodiment, the vendor selection unit (132) processes and analyzes personal information and lifestyle welfare information based on the input service sector, and selects at least one vendor from among the registered vendors based on the analysis results. In other words, the vendor selection unit (132) can select a vendor suitable for the user through data analysis and collect customized product information for the user.

[0114] First, companies registered on the server (100) are assigned to a specific cluster. To this end, the server (100) performs clustering based on each company's business information. Here, the cluster analysis algorithm is not limited, but hierarchical clustering, which allows an upper cluster to be composed of other lower clusters, is preferred.

[0115] Specifically, the server (100) forms a first graph in which one axis represents the service sector (y-axis) and the other axis represents the life cycle (x-axis), and maps each registered company to the graph. Here, the order in which each service sector is listed on the axes can be arbitrarily determined, and the range that each service sector occupies on the y-axis can be equally divided. In addition, each life cycle can be listed on the x-axis in the order of stages pre-classified by the server (100).

[0116] The server (100) measures the similarity of the life cycles of each company based on the service sector. That is, the server (100) connects companies that fall within the same range on the y-axis and are located close to each other on the x-axis, and by repeating this process, classifies each company into a first cluster.

[0117] Next, the server (100) forms a second graph for each first cluster and maps the companies belonging to the first cluster. Here, each axis of the second graph may be a preset sub-criteria excluding the service sector and life cycle, and examples thereof include regions and representative products. In this way, the server (100) can hierarchically cluster each company in a top-down manner starting from a state where all companies are included in one cluster, and n (n is a natural number greater than 1) clusterings may be performed depending on the number of sub-criteria. For example, a cluster code indicating the first to n-th clusters, such as "1-3-11-,,-,,-(- is n-1)", may be set for one company.

[0118] Once clustering of companies is performed, the company selection unit (132) can build a company selection model that matches a specific user with a specific cluster code through preset machine learning.

[0119] Specifically, the vendor selection unit (132) collects training data for building a vendor selection model. First, the vendor selection unit (132) normalizes the data to a pre-defined range for each personal information item and service sector and sets the data as training data. For example, life cycle data can be normalized by categorized stages, age by five-year intervals, and region by city, county, or district.

[0120] Additionally, the vendor selection unit (132) analyzes the living welfare information stored in the server (100), processes each living welfare information into at least one product or service item corresponding to the information, and then sets this as training data. For example, in the case of the living welfare information in the "Public Notice on the Newlyweds' Health Checkup Cost Support Project," training data such as "Health Checkup Center, Health Checkup Product, Hospital" may be set.

[0121] After this, the vendor selection unit (132) creates input data reflecting various user statuses by combining the training data in different ways. For example, the input data may be comprised of a set of training data such as "Marriage (Life Cycle), 35 years old, Female, Seocho-gu, Office Worker, Housing (Service Sector), Subscription Product (Life Welfare Information), and Secured Loan Product (Life Welfare Information)."

[0122] The company selection unit (132) repeats learning through a preset machine learning model so that at least one cluster code is output when specific input data is entered.

[0123] According to one embodiment, the preset machine learning model may include, but is not limited to, cluster-based unsupervised learning models such as K-Means Clustering, Mean-Shift Clustering, and DBSCAN (DensityBased Spatial Clustering of Applications with Noise).

[0124] In another embodiment, the preset machine learning model may include, but is not limited to, a classification-based supervised learning model that applies techniques such as a Decision Tree, K-Nearest Neighbors (KNN), Naive Bayes, Support Vector Machine (SVM), Random Forest, and Neural Network. In this case, a task of labeling cluster codes for each input data may be performed first.

[0125] Here, the Neural Network may include, but is not limited to, a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Long Short Term Memory (LSTM), and a Generative Adversarial Network (GAN).

[0126] Once the vendor selection model is established in this manner, in step S330, the vendor selection unit (132) processes and analyzes the user's personal information, service sector, and lifestyle welfare information to generate input data. As described above, the input data may be structured as "marriage, 35 years old, female, Seocho-gu, office worker, housing, subscription product, mortgage loan product." The vendor selection unit (132) applies the generated input data to the vendor selection model to output at least one cluster code, and then identifies the vendors belonging to the output cluster code.

[0127] In one embodiment, the vendor selection unit (132) provides personal information and lifestyle welfare information to identified vendors. This information may be anonymized prior to the information being provided. For example, the vendor selection unit (132) may provide input data, processed and analyzed, containing personal information, service sector information, and lifestyle welfare information, to each vendor terminal (20).

[0128] In one embodiment, the product recommendation unit (133) may sort or filter collected product information based on preset criteria and then provide it to the user terminal (10). Accordingly, the user can easily visually recognize products that are more optimal for them.

[0129] In one embodiment, the product recommendation unit (133) may process product information based on the user's life cycle. For example, the product recommendation unit (133) may remove product information unrelated to the user's life cycle from the product information received from each company terminal (20). Alternatively, the product recommendation unit (133) may sort product information in chronological order of the life cycle stages, starting with the user's life cycle.

[0130] In one embodiment, the product recommendation unit (133) can process product information based on the service sector requested by the user. For example, if product information unrelated to the service sector is identified among the received product information, the product recommendation unit (133) can remove it. Alternatively, product information can be classified by service sector and then sorted by life cycle or lifestyle welfare information for each service sector.

[0131] In one embodiment, the product recommendation unit (133) may determine the number of corresponding service sectors for each product information, sort them in descending order of number, or extract product information exceeding a preset number and provide the information to the user terminal (10). For example, if the product is a "postpartum care center service" item, it may correspond to four or more service sectors, such as "childbirth," "education," "support," and "protection."

[0132] In one embodiment, the product recommendation unit (133) may process product information based on the lifestyle welfare information provided to the user terminal (10). For example, the product recommendation unit (133) may extract only product information corresponding to the lifestyle welfare information from the received product information or provide such information to the user terminal (10) by prioritizing such information. For example, if the lifestyle welfare information is "Newlywed Couple Rental Loan Interest Support Project," the product information may be processed to consist only of real estate-related financial products such as rental loan products, secured loan products, and subscription products, or may be arranged at the top.

[0133] Finally, in relation to the above-described embodiments, the product recommendation unit (133) can recommend product information to the user terminal (10) through the following process.

[0134] First, the product recommendation unit (133) removes product information unrelated to the user's life cycle from the received product information. Next, it extracts only product information corresponding to the lifestyle and welfare information provided to the user terminal (10) from the remaining product information. Next, it removes product information not included in the service sector requested by the user, and then sorts the extracted product information in descending order of the number of service sectors included.

[0135] After completing the above process, the product recommendation unit (133) calculates the similarity score for each remaining personal information item, excluding life cycle. The similarity score is preset for each personal information item based on a predetermined range. For example, for the "income" item, if the user's region and product offering area are similar at the neighborhood level, it could be given 5 points, if similar at the city / county level, it could be given 3 points, and if the product offering area is different, it could be given 0 points.

[0136] According to one embodiment, the product recommendation unit (133) may remove any product information that has a similarity score of 0, assuming that the product information is not suitable for the user.

[0137] According to one embodiment, the product recommendation unit (133) may additionally calculate a matching score for additional information collected in step S310 in addition to personal information.

[0138] After this, the product recommendation unit (133) can calculate a matching score by adding up the similarities of each product information. The product recommendation unit (133) can sort the matching scores in descending order or extract product information with a matching score higher than a preset standard score and provide the product information to the user terminal (10).

[0139] Although the methods and systems of the present invention have been described with respect to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

[0140] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

[0141] The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

Claims

1. In the method of providing customized welfare and living services for each life cycle, performed by the server, (a) a step of receiving personal information including the user's life cycle and input for at least one service sector from a user terminal; (b) a step of extracting life welfare information matching the personal information based on the life cycle and providing it to the user terminal; (c) a step of providing the personal information and the living welfare information to a company terminal related to the service sector and receiving product information from the company terminal; and (d) a step of recommending at least some of the above product information to the user terminal; including, A method for providing customized welfare and living services by life cycle, wherein the above life cycle is classified into multiple stages that reflect at least one of the following criteria: whether the user is married and has children, the age of the children, whether the user is independent, and whether the user is married.

2. In paragraph 1, The above step (a) comprises a step of requesting additional information other than the personal information from the user terminal or collecting it in a preset manner according to the service sector received from the user terminal; a method for providing customized welfare and living services by life cycle.

3. In paragraph 1, The step (b) above is a method for providing customized welfare and living services by life cycle, including a step of preprocessing the personal information based on the life cycle and the service sector, extracting at least one piece of information matching the preprocessed personal information from the life welfare information already collected on the server, and providing the information to the user terminal.

4. In paragraph 1, The step (c) above is a method for providing customized welfare and living services by life cycle, including a step of processing and analyzing the personal information and the living welfare information based on the service sector, and selecting at least one company among the companies registered in the server based on the analysis results.

5. In paragraph 1, A method for providing customized welfare and living services by life cycle, comprising: the step (d) above, a step of sorting or filtering the product information based on at least one of the life cycle, the service sector, and the living welfare information, and then providing the product information to the user terminal; 6. In paragraph 2, Step (a) above, A step of collecting lifelog information from the user terminal; A step of performing standardization on the non-standard information among the above life log information and classifying the life log information based on the service sector; A step of extracting life log information belonging to the service sector received from the user terminal based on the classification result; and A step of statistically analyzing the extracted life log information to identify the user's areas of interest or preferences in the service sector and storing it as additional information; A method for providing customized welfare and living services for each life cycle, including:

7. In paragraph 6, If the above life log information is in text format, the step of classifying the above life log information based on the service sector is: A step of extracting string information in units of sentences or words from the life log information by performing at least one text analysis among sentence analysis, word analysis, and morphological analysis; A step of performing categorization on the extracted string information; A step of identifying a service sector matching each category and storing the identified service sector by matching each string information included in each category; A method for providing customized welfare and living services for each life cycle, including:

8. In paragraph 6, If the above life log information is in text format, the step of setting it as additional information and saving it is as follows: A step of extracting all string information matching the service sector input from the user terminal; A step of summing the number of repetitions by extracted string information or category and determining them in high order; A step of identifying the user's area of ​​interest or preference based on the identification results and setting it as additional information and saving it; A method for providing customized welfare and living services for each life cycle, including:

9. In paragraph 6, If the above life information is in the form of an image or video, the step of classifying the life log information based on the service sector is as follows: A step of constructing a service sector classification model; and a step of inputting the life log information into the service sector classification model and outputting at least one service sector; including, The above service sector classification model is a method for providing customized welfare and living services by life cycle, which is learned in advance through a machine learning model that is set to output a specific service sector when a specific image or video is input.

10. In paragraph 6, If the above life information is in the form of an image or video, the step of setting it as additional information and saving it is as follows: A step of extracting all images or videos classified into the service sector input from the user terminal; A step of searching the page where each image or video extracted using a preset search technique is displayed; A step of tracking logs and traffic for each page explored, identifying the user's areas of interest or preferences based on the tracking results, and storing them as additional information; A method for providing customized welfare and living services for each life cycle, including:

11. In paragraph 1, Step (b) above, A step of determining the type of welfare service based on the above life cycle and service sector; A step of identifying personal information that serves as the basis for primary filtering based on the above type and extracting living welfare information corresponding to the above criteria from among the previously stored living welfare information; A step of performing a secondary filtering to scrape the living welfare information corresponding to the above type from among the living welfare information extracted by the above primary filtering; A step of extracting numerical information based on the above life cycle and the above type according to preset standards; A step of comparing each extracted numerical information or numerical information combined according to a preset standard with the numerical information included in the living welfare information extracted by the second filtering; and A step of specifying the living welfare information matching the personal information based on the comparison results; A method for providing customized welfare and living services for each life cycle, including:

12. In paragraph 1, Step (c) above, A step of building a vendor selection model that matches specific users with specific cluster codes through pre-configured machine learning; A step of generating input data by processing and analyzing the above personal information, service sector, and living welfare information; and A step of applying the above input data to the above company selection model to output at least one cluster code; including, A method for providing customized welfare and living services by life cycle, wherein the above cluster code is set in a preset manner so that at least one company among the companies registered on the above server is included.

13. In paragraph 1, Step (d) above, A step of removing product information unrelated to the life cycle from the received product information; A step of extracting product information corresponding to the above-mentioned living welfare information from the remaining product information after removal; A step of removing product information that is not included in the service sector from among the extracted product information and then arranging the product information in order of the number of included service sectors; A step of calculating the similarity for each personal information except for the life cycle for each sorted product information; A step of calculating a matching score by adding up the similarities calculated for each sorted product information; A step of sorting the product information in order of the highest matching score or extracting product information having a matching score higher than a preset standard score and providing the product information to a user terminal; A method for providing customized welfare and living services for each life cycle, including:

Images