KR102486208B1 - User customized welfare curation service server, method and program based on artificial intelligence - Google Patents

Abstract

Disclosed are a server, a method, and a program for providing a user-customized welfare curation service based on artificial intelligence (AI). The method for providing a welfare curation service according to one embodiment of the present invention comprises the steps of: performing processing of subscription based on information on disability of a user, which includes first information obtained when an image of a welfare card is inputted into a learning model and second information inputted by the user, wherein the information on disability of the user is collected by adjusting a data recognition field in the image of the welfare card according to a kind of the welfare card; extracting information on welfare benefits matched with the information on disability of the user, and generating welfare service information including the extracted information on welfare benefits and an expected benefit amount calculated based on the information on welfare benefits; outputting the welfare service information according to output criteria including a disability type of the corresponding user; and providing an extra service matched with the information on disability of the user.

Description

Artificial intelligence-based user-customized welfare curation service server, its method and program

The present disclosure relates to an AI-based user-customized welfare curation service server, a method and a program therefor.

Currently, the government implements various welfare projects for the disabled and increases the welfare budget every year for this, but about 70% of registered disabled people recognize that the benefits of the welfare programs are not sufficient.

Meanwhile, since there are many institutions or servers that provide welfare benefit information, welfare benefit information is also distributed and provided through various methods or servers. Accordingly, there may be cases in which disabled people do not recognize welfare benefit information.

In addition, since the acquisition and utilization of digital information using wireless communication devices such as smart phones is lower than that of non-disabled people, it is found that it is more difficult for people with disabilities to recognize welfare benefit information provided through various sources.

Republic of Korea Patent Registration No. 10-1982525 (2019. 05. 21.)

Embodiments disclosed in the present disclosure provide an artificial intelligence-based user-customized welfare curation service server, method, and program for providing a service so that the disabled can easily check distributed welfare benefit information by utilizing artificial intelligence technology. .

Embodiments disclosed in this disclosure provide user-customized welfare services that people with disabilities can easily join and use, and community services that enable communication between people with disabilities.

Embodiments disclosed in this disclosure provide product information such as assistive devices suitable for the disabled.

The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

In the welfare curation service method according to an aspect of the present disclosure for achieving the above-described technical problem, in the method performed by the welfare curation service server, the first information identified by inputting the welfare card image into the learning model And performing subscription processing based on the user's disability information including the second information input by the user, but collecting the user's disability information by adjusting the data recognition field in the welfare card image according to the type of welfare card. doing; extracting welfare benefit information matched with disability information of the user and generating welfare service information including the extracted welfare benefit information and an expected benefit amount calculated based on the welfare benefit information; outputting the welfare service information according to an output criterion including a disability type of a corresponding user; and providing an additional service matching the disability information of the user, wherein the output criterion may be a condition for differentiated provision of the welfare service information for each user based on the user's disability type.

The collecting of disability information of the user may include inputting the scanned welfare card image into the learning model; recognizing the type of the welfare card; setting a data recognition field in the welfare card image according to the type of the recognized welfare card; extracting the first information from the set data recognition field; receiving the second information input according to the user's manipulation; and processing and storing the disability information of the user according to a first data format.

Prior to the collecting of disability information of the user, the welfare curation service method may include collecting a plurality of welfare benefit information from a plurality of welfare information providing servers; extracting disability keywords from welfare service-related information and substituting similar terms among the extracted disability keywords with a preset representative disability keyword; classifying the plurality of welfare benefit information into corresponding categories according to a classification criterion based on a representative disability keyword of the collected plurality of welfare benefit information; deleting identical redundant data by comparing similarities between the plurality of pieces of collected welfare benefit information; and processing the welfare benefit information in different formats according to a second data format and storing the same format.

In the step of deleting the redundant data, the welfare curation service method may maintain welfare benefit information of a source with the highest priority based on the priority of the plurality of welfare benefit information sources and delete welfare benefit information of the remaining sources. there is.

The generating of the welfare service information may include extracting the plurality of welfare benefit information that matches disability information of the user; determining whether or not the plurality of welfare benefit information is duplicated and support priority based on the disability information of the user; Calculating an expected benefit amount based on whether the plurality of welfare benefit information is identified and whether or not the plurality of welfare benefit information is duplicated and the priority of support; and generating the welfare service information including at least one of the welfare benefit information, the priority of support, whether or not the support is duplicated, and the expected benefit amount.

In the step of performing the subscription process, a group including similar objects is determined based on the user's disability information, and among the disability information of other users who have previously joined, other users whose residence area, disability type, disability degree, and gender are matched. After classifying users as the highest priority, determining a group based on household members' income and date of birth; may further include.

The providing of the additional service may include forming a community meeting for each same group based on the determined group.

The step of providing the additional service includes selecting and providing a community meeting or community counterpart in consideration of the user's date of birth, type of disability, degree of disability, gender, residential area, and date of registration of the disabled person among the disability information of the user, Among the user's disability information, the community meeting or community partner may be selected by reflecting the weight of the user's disability information according to the community priority set by the user.

The providing of the additional service may include recommending activity assistants for each group based on the determined group, providing encyclopedia information related to welfare, or recommending a product including an auxiliary device matched to the group; can include

The providing of the supplementary service may include providing auxiliary device information and purchase function matched based on the type and degree of disability among the disability information of the user, but when providing the auxiliary device information, the plurality of benefit information is provided. providing a government subsidy and a method of applying for the government subsidy when purchasing the auxiliary device by using the auxiliary device; If the auxiliary device is purchased, monitoring whether it is time to purchase a new auxiliary device based on the type of disability, the degree of the disorder, the purchased auxiliary device, and the date of purchase of the auxiliary device; and product information including at least one of a notification of the purchase time of the new auxiliary device, recommendation information on the new auxiliary device, government subsidy for the new auxiliary device, and a method of applying for the government subsidy, if the monitoring result indicates the purchase time of the new auxiliary device. It may include; transmitting a notification to a terminal of a corresponding user.

In addition, the welfare curation service server according to another aspect of the present disclosure includes an information registration unit; Department of Welfare Information; and a processor for controlling the operation of the additional service provider, wherein the processor includes the user's disability information including the first information identified as inputting the welfare card image into the learning model and the second information input by the user. Performs subscription processing based on, but collects disability information of the user by adjusting a data recognition field in the welfare card image according to the type of welfare card; extracting welfare benefit information matched with disability information of the user and generating welfare service information including the extracted welfare benefit information and an expected benefit amount calculated based on the welfare benefit information; outputting the welfare service information according to an output criterion including a disability type of the corresponding user; and providing an additional service matching the disability information of the user, and the output criterion may be a condition that differentiates and provides the welfare service information for each user based on the user's disability type.

In addition to this, a computer program stored in a computer readable recording medium for execution to implement the present disclosure may be further provided.

In addition to this, a computer readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

According to the above-described problem solving means of the present disclosure, since distributed welfare benefit information is collected and provided using artificial intelligence technology, the welfare benefit information can be provided without omission from the viewpoint of the disabled, and thus the welfare benefit application rate is also increased. It provides an effect that can be improved.

According to the above-described problem solving means of the present disclosure, a user-customized welfare curation service that a person with a disability can easily join and use can be provided.

According to the above-mentioned problem solving means of the present disclosure, it is possible to provide welfare benefit information that matches the condition of each person with a disability, so that the person with a disability can receive only high-quality information related to themselves.

According to the above-described problem-solving means of the present disclosure, product information including assistive devices can be provided in a customized manner by matching the condition of the disabled person, thereby improving the life convenience of the disabled person.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram showing a connection relationship between a welfare curation service server and other components of the present disclosure;
2 is a block diagram of a welfare curation service server according to the present disclosure;
3 to 15 are exemplary diagrams for explaining the welfare curation service method of the present disclosure.
16 is a flowchart for explaining the welfare curation service method of the present disclosure
17 to 19 are flowcharts for explaining the welfare curation service method of FIG. 16 in more detail.

Like reference numbers designate like elements throughout this disclosure. The present disclosure does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present disclosure belongs is omitted. The term 'unit, module, member, or block' used in the specification may be implemented as software or hardware, and according to embodiments, a plurality of 'units, modules, members, or blocks' may be implemented as one component, It is also possible that one 'part, module, member, block' includes a plurality of components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case of being directly connected but also the case of being indirectly connected, and indirect connection includes being connected through a wireless communication network. do.

In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

Throughout the specification, when a member is said to be located “on” another member, this includes not only a case where a member is in contact with another member, but also a case where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

Expressions in the singular number include plural expressions unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of description, and the identification code does not explain the order of each step, and each step may be performed in a different order from the specified order unless a specific order is clearly described in context. there is.

Hereinafter, the working principle and embodiments of the present disclosure will be described with reference to the accompanying drawings.

In this specification, the 'welfare curation service server according to the present disclosure' includes all various devices capable of providing results to users by performing calculation processing. For example, a welfare curation service server according to the present disclosure may include a computer, a server device, and a portable terminal, or may be in any one form.

Here, the computer may include, for example, a laptop computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, and the like equipped with a web browser.

The server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

The portable terminal is, for example, a wireless communication device that ensures portability and mobility, and includes a Personal Communication System (PCS), a Global System for Mobile communications (GSM), a Personal Digital Cellular (PDC), a Personal Handyphone System (PHS), and a PDA. (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smart phone ) and wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted-devices (HMD). device may be included.

Users of the present disclosure may include persons with disabilities, and guardians and family members of persons with disabilities.

1 is a diagram showing a connection relationship between a welfare curation service server and other components according to the present disclosure, and FIG. 2 is a block diagram of the welfare curation service server according to the present disclosure.

Referring to FIG. 1 , the welfare curation service system may include a welfare curation service server 100 , a user terminal 200 , and a plurality of welfare information providing servers 300 .

The above-described plurality of welfare information providing servers 300 refer to servers providing welfare benefit information, and may be, for example, a welfare portal server such as a welfare road.

Referring to FIG. 2, the welfare information providing server 300 is a server for creating, managing, and providing welfare benefit information, and includes a plurality of servers for providing portal sites operated by central government departments, local governments, and the private sector. can do. In this case, since the welfare benefit information has a different announcement form for each support project, the provided form may also be different.

Referring to FIG. 2 , the welfare curation service server 100 includes a processor 110 , a memory 150 and a communication unit 160 . At this time, the processor 110 may include the information registration unit 120, the welfare information providing unit 130, and the additional service providing unit 140 to control the operation of each component. The components shown in FIG. 1 are not essential in implementing the welfare curation service server 100 according to the present disclosure, so the welfare curation service server 100 described in this specification has more components than those listed above. or may have fewer components.

Processor 110 may collect and store welfare benefit information.

Specifically, the processor 110 may collect a plurality of welfare benefit information from the plurality of welfare information providing servers 300 . At this time, the processor 110 may collect welfare benefit information from the distributed welfare information providing server 300 through web crawling, but is not limited thereto, and the welfare information providing server 300 is not limited thereto according to a preset period. ), various methods such as requesting and receiving welfare benefit information can be applied.

The processor 110 may process welfare benefit information in different formats according to a second data format through the information registration unit 120 and store them in the same format.

The processor 110 performs subscription processing based on the user's disability information including the first information identified by inputting the welfare card image into the learning model and the second information input by the user, but depending on the type of welfare card. Accordingly, the disability information of the user may be collected by adjusting the data recognition field in the welfare card image.

The learning model may recognize and receive a welfare card image through an optical character recognition technology to be described later, and output first information through learning. At this time, the learning model may perform processing such as adjusting a data recognition field from the welfare card image and recognizing the first information according to the type of welfare card. In addition, the learning model of the present disclosure may obtain information matched with disability information of a user from a plurality of previously learned and stored welfare benefit information, or may calculate an expected benefit amount for each user.

The above-described first information may refer to disability information of a user identified by scanning a welfare card image. For example, the first information is the name written on the welfare card, the user's identification number (eg, resident registration number, etc.), date of birth, disability type, degree of disability, gender, residential area, disability registration date, issue date, validity It may include at least one of period and issuer. In this case, the degree of disability may mean a degree of disability.

In addition, the second information is information input according to a user's manipulation, and may include income, occupation, etc. of the disabled person and household members.

The processor 110 may obtain the first information by scanning the welfare card using optical character recognition (OCR) technology. The optical character recognition technology may mean that when a character such as a character or shape of a business card is photographed, the character is read and stored as text.

The welfare curation service, including the sign-up procedure of the present disclosure, is performed when a welfare curation service application installed in the user terminal 200 is executed or when the user terminal 200 accesses the welfare curation service server 100. It can be done.

For example, as a welfare curation service application is executed in the user terminal 200, the processor 110 may provide a service so that a photographing and recognizing procedure of a welfare card can be performed on the user terminal 200. A detailed description of this will be described later.

The processor 110 may extract welfare benefit information matched with the user's disability information and generate welfare service information including the extracted welfare benefit information and an expected benefit amount calculated based on the welfare benefit information.

The processor 110 may output welfare service information according to an output criterion including a disability type of a corresponding user.

The processor 110 may provide an additional service matching user's disability information.

The above-described welfare curation service providing method in the welfare curation service server 100 will be described in detail later based on FIGS. 3 to 19 .

The processor 110 of the present disclosure may be composed of one or more cores, such as a central processing unit, a general purpose graphics processing unit, and a tensor processing unit of a computing device. It may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 150 and perform data processing for machine learning according to the present disclosure. According to the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 performs calculations for neural network learning, such as processing input data for learning in deep learning, extracting features from input data, calculating errors, and updating neural network weights using backpropagation. can be done

The neural network model may be a deep neural network. In the present disclosure, a neural network, a network function, and a neural network may be used as the same meaning. A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), and a deep belief network (DBN). , Q network, U network, Siamese network, and the like.

A convolutional neural network is a type of deep neural network and includes a neural network including a convolutional layer. A convolutional neural network is a type of multilayer perceptron designed to use minimal preprocessing. A CNN can consist of one or several convolutional layers and artificial neural network layers combined with them. CNNs can additionally utilize weights and pooling layers. Thanks to this structure, CNN can fully utilize the two-dimensional structure of the input data. Convolutional neural networks can be used to recognize objects in images. A convolutional neural network can represent and process image data as a matrix having dimensions. For example, in the case of image data encoded in RGB (red-green-blue), each R, G, and B color may be represented as a two-dimensional (eg, two-dimensional image) matrix. That is, the color value of each pixel of the image data can be a component of a matrix, and the size of the matrix can be the same as the size of the image. Thus, image data can be represented by three two-dimensional matrices (a three-dimensional data array).

In a convolutional neural network, a convolutional process (input/output of a convolutional layer) can be performed by moving the convolutional filter and multiplying the convolutional filter with matrix components at each position of the image. A convolutional filter may be composed of an n*n matrix. A convolutional filter can consist of a fixed shape filter, which is usually smaller than the total number of pixels in an image. That is, when an m*m image is input to a convolutional layer (for example, a convolutional layer whose size of convolutional filter is n*n), a matrix representing n*n pixels including each pixel of the image It can be component multiplied with this convolutional filter (ie, multiplication of each component of the matrix). A component matching the convolutional filter can be extracted from the image by multiplication with the convolutional filter. For example, a 3*3 convolutional filter to extract top and bottom linear components from an image would be constructed as [[0,1,0], [0,1,0], [0,1,0]] can When the 3*3 convolutional filter for extracting the upper and lower linear components from the image is applied to the input image, the upper and lower linear components matching the convolutional filter may be extracted and output from the image. The convolutional layer may apply a convolutional filter to each matrix for each channel representing an image (ie, R, G, B colors in the case of an R, G, B coded image). A convolutional layer can extract features that match the convolutional filter from the input image by applying a convolutional filter to the input image. The filter value of the convolutional filter (that is, the value of each element of the matrix) may be updated by backpropagation during the learning process of the convolutional neural network.

A subsampling layer is connected to the output of the convolutional layer to simplify the output of the convolutional layer, thereby reducing memory usage and computational complexity. For example, if the output of the convolutional layer is input to a pooling layer with a 2*2 max pooling filter, the image is compressed by outputting the maximum value included in each patch for each 2*2 patch in each pixel of the image. can do. The aforementioned pooling may be a method of outputting a minimum value in a patch or an average value of a patch, and any pooling method may be included in the present disclosure.

A convolutional neural network may include one or more convolutional layers and subsampling layers. A convolutional neural network may extract features from an image by repeatedly performing a convolutional process and a subsampling process (eg, max pooling described above). Through an iterative convolutional process and subsampling process, a neural network can extract global features of an image.

An output of the convolutional layer or the subsampling layer may be input to a fully connected layer. A fully connected layer is a layer in which all neurons in one layer are connected to all neurons in neighboring layers. A fully connected layer may refer to a structure in which all nodes of each layer are connected to all nodes of other layers in a neural network.

At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, the CPU and GPGPU can process learning of network functions and data classification using network functions. In addition, in an embodiment of the present disclosure, the learning of a network function and data classification using a network function may be processed by using processors of a plurality of computing devices together. In addition, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU or TPU executable program.

The memory 150 may store a computer program for providing a welfare curation service method, and the stored computer program may be read and driven by the processor 110 . The memory 150 may store any type of information generated or determined by the processor 110 and any type of information received by the communication unit 160 .

The memory 150 may store data supporting various functions of the welfare curation service server 100 and a program for operating the processor 110, and input/output data (eg, welfare card image). , welfare benefit information, welfare service information, additional service information, etc.) are stored, and a plurality of applications (application programs or applications) running on the welfare curation service server 100, the welfare curation service server 100 ) can store data and instructions for operation. At least some of these application programs may be downloaded from an external server through wireless communication.

The memory 150 may be a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, or a multimedia card micro type. micro type), card-type memory (for example, SD or XD memory, etc.), RAM (Random access memory; RAM), SRAM (Static random access memory), ROM (Read-only memory; ROM), EEPROM (Electrically erasable It may include a storage medium of at least one type of a programmable read-only memory (PROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. In addition, the memory is separate from the present device, but may be a database connected by wire or wireless.

The communication unit 160 may include one or more components enabling communication with an external device, and for example, at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-distance communication module, and a location information module. can include

Although not shown, the welfare curation service server 100 of the present disclosure may further include an output unit and an input unit.

The output unit may display a user interface (UI) for providing label noise selection results and learning results. The output unit may output any type of information generated or determined by the processor 110 and any type of information received by the communication unit 160 .

The output unit includes a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, 3 At least one of 3D displays may be included. Some of these display modules may be of a transparent type or a light transmissive type so that the outside can be seen through them. This may be referred to as a transparent display module, and a representative example of the transparent display module is TOLED (Transparent OLED) and the like.

The input unit may receive information input by a user. The input unit may include keys and/or buttons on a user interface or physical keys and/or buttons for receiving information input by a user. A computer program for controlling a display according to embodiments of the present disclosure may be executed according to a user input through an input unit.

16 is a flowchart illustrating a welfare curation service method of the present disclosure.

Hereinafter, the welfare curation service method of the present disclosure will be described with reference to FIGS. 3 to 15, which are exemplary diagrams for explaining the method.

The processor 110 of the welfare curation service server 100 may collect and store welfare benefit information through the information register 120 (410).

Specifically, the processor 110 may collect a plurality of welfare benefit information from the plurality of welfare information providing servers 300 through the information registration unit 120 . In this case, the welfare benefit information may refer to welfare information provided to the disabled.

Referring to FIG. 2, the welfare information providing server 300 is a server for creating, managing, and providing welfare benefit information, and includes a plurality of servers for providing portal sites operated by central government departments, local governments, and the private sector. can do. In this case, since the welfare benefit information has a different announcement form for each support project, the provided form may also be different.

The processor 110 may process welfare benefit information in different formats according to a second data format through the information registration unit 120 and store them in the same format. In this case, the second data format may refer to a format for unifying welfare benefit information of different formats, including information items, the order of listing information items, and contents included in each information item.

The above-mentioned welfare benefit information includes information items depending on the source (welfare name, welfare provider, support target, support content, application method, documents submitted, application date, payment date, support cycle, provision type, person in charge name, contact information, etc.) and information display formats may be provided in different formats.

For example, welfare benefit information 1 includes the items of welfare name, welfare provider, provision type, support cycle, support target, service content, application method, and additional information, and welfare benefit information 2 includes welfare name, provision type, application Items such as method, support cycle, support target, selection criteria, and service contents can be included. At this time, not only the information items but also the contents included in each item of the different welfare benefit information may be different, and the method of arranging the information items may also be different.

The processor 110 may process different welfare benefit information into the same format according to the second data format through the information registration unit 120 and store it in the memory 150 .

Next, the processor 110 may perform a user subscription process through the information registration unit 120 (420). In this case, the user may include the disabled person, the guardian of the disabled person, and the disabled family member.

Specifically, the processor 110 subscribes based on the user's disability information including the first information identified as inputting the welfare card image into the learning model through the information registration unit 120 and the second information input by the user. Processing is performed, but the disability information of the user may be collected by adjusting the data recognition field in the welfare card image according to the type of welfare card.

Hereinafter, a user subscription procedure and a user disability information acquisition method will be described with reference to drawings.

Referring to FIG. 3 , when the user is in a pre-subscription (or non-login) state, the processor 110 may output a subscription guidance message on the home screen through the information registration unit 120 as shown in ①. If the user is an existing subscriber, the processor 110 may output the number of welfare benefit information that can be supported and the expected benefit amount on the home screen, as shown in ②.

Referring to FIG. 4, when the user is in a pre-registration (or non-login) state, the processor 110 provides welfare benefit information of the entire support project by preset category (for example, as shown in ③) through the information registration unit 120. For example, health, life, work, culture, education and others) can be displayed on the home screen. In addition, if the user is an existing subscriber, the processor 110, through the information registration unit 120, divides welfare benefit information filtered based on disability information of the previously subscribed user into categories (eg, health, life, work, culture, education, etc.) can be displayed on the home screen.

In addition, the processor 110 may display a banner area including notifications, marketing news, etc. on the home screen through the information registration unit 120 as shown in ⑤.

Referring to FIG. 5 , the processor 110 first selects a subscription target, whether a person with a disability or a guardian or family member, in order to perform a subscription procedure according to the user's manipulation through the information register 120, and selects the selected subscription target. Based on this, it may be guided to take a picture of the user's welfare card.

The processor 110 of the present disclosure may allow only the disabled person, the guardian of the disabled person, and the disabled family member to perform membership registration through an authentication procedure during the user registration process through the information registration unit 120 .

Specifically, the processor 110 allows the disabled person, the guardian of the disabled person, and the disabled family member to perform a membership sign-up process through a process of registering a welfare card for the disabled person, as shown in FIG. 5 . In addition to this, the processor 110 may additionally perform an authentication procedure through the user terminal 200 of the person with a disability for all users requesting membership registration. For example, when the object of membership registration is a guardian of a disabled person and a family member of a disabled person, the processor 110 transmits a subscription attempt confirmation request message to the user terminal 200 of the disabled person concerned, and upon receiving a reply thereto, Additional authentication procedures can be completed. In addition, the processor 110 of the present disclosure may match, store, and manage the disabled person, the guardian of the disabled person, and the disabled family member.

The processor 110 may check whether the welfare card scanned through the information registration unit 120 is stolen or falsified. For example, the processor 110 identifies forgery based on the counterfeit information processed in the welfare card through the information registration unit 120, and compares the disabled information recognized from the welfare card with the previously registered disabled information to correct the user. You can check whether it is. To this end, the processor 110 requests confirmation of whether the disabled information is correct from a server (not shown) that registers and manages disabled information, or collects and previously stores all registered disabled information, and then authenticates using the stored information. can do.

As shown in FIG. 6 , the processor 110 can pop up a guide screen for photographing and recognizing a welfare card through the information registration unit 120, thereby increasing user convenience.

Since the present disclosure acquires the first information by scanning the welfare card through optical character recognition technology, it is possible to adjust data recognition fields (D1 and D2 in FIG. 6) in the welfare card image according to the type of welfare card.

Specifically, as shown in Figure 7, the welfare card (disability registration certificate) can be classified into two types of type 1 and type 2, and can be further subdivided without being limited thereto.

In this case, the first type may be an ID type, and the second type may be a credit card type (including financial and transportation types).

As a result of recognizing the front and back sides of the welfare card through the information registration unit 120, the processor 110 classifies the type of the welfare card according to the position of the recognized data field and adjusts the data recognition field.

Specifically, the processor 110 may search for the keyword 'welfare card' in the image of the welfare card scanned through the information registration unit 120 . At this time, a space that may exist between letters of the welfare card may be considered. At this time, the processor 110 may output a keyword by inputting an image of a welfare card to the learning model. The learning model may be a pre-learned model using various welfare card images and data recorded on welfare cards as input data.

As a result of the search, if the keyword 'welfare card' is not searched, the processor 110 may output an error display through the information registration unit 120 . In this case, the error display may be a display indicating that the corresponding welfare card image is not a welfare card.

Next, the processor 110 classifies whether the welfare card is type 1 or type 2 based on the difference between the disabled information recorded on the front and the back according to the type of welfare card through the information registration unit 120, and distinguishes According to the result, the disabled information of the user of the welfare card can be recognized.

Specifically, as a result of recognizing the front side of the welfare card through the information registration unit 120, the processor 110 recognizes the 'initial registration date' or 'type of disability (including keywords such as delay and time)' field, the corresponding Welfare card can be recognized as a credit card-type welfare card, otherwise it can be recognized as an ID-type welfare card.

Next, the processor 110 may extract and obtain disability information of the user from the data recognition field of the welfare card image through the information registration unit 120 .

For example, if the welfare card is an identification type, the processor 110 sets the 'disability' keyword in the front of the welfare card image scanned through the information registration unit 120 as a reference point, name, social security number, gender, disability grade and address can be extracted. In addition, the processor 110 may set a 'disability type' keyword as a reference point on the back of the welfare card image scanned through the information registration unit 120, and extract the disability type and registration date.

At this time, the processor 110 may process and store the user's disability information extracted by the above method according to the first data format, and a detailed description thereof will be described later.

As another example, if the welfare card is a credit card type, the processor 110 retrieves the date of birth, name, disability type, gender, disability level, first registration date and address from the back of the welfare card image scanned through the information registration unit 120. can be extracted.

At this time, the processor 110 may determine the date of birth from an area in the form of a social security number such as 931022 or an area in the form of a date of birth such as 93.10.22 through the information registration unit 120.

The user's disability information obtained from the welfare card image is not limited to the above-described information, and may be added or changed according to changes in information described in the welfare card.

Referring to FIG. 8 , the processor 110 recognizes the welfare card through the information registration unit 120 and extracts and recognizes the user's disability information from the welfare card (eg, name (or name, name), date of birth, Gender, degree of disability, residential area (address), registration date of disability, and type of disability) can be displayed on the screen of the user terminal 200 so that the user in the process of signing up can check it.

In addition, the processor 110 may receive second information including income of household members according to a user's manipulation through the information registration unit 120 . As shown in FIG. 9 , the processor 110 may receive input of the number of household members and income of household members through the information registration unit 120 .

In addition to this, the processor 110 may additionally receive a nickname (eg, pleasant coffee, etc.) as shown in FIG. 10 .

The processor 110 may store and manage user disability information obtained through the information registration unit 120 in the memory 150 .

Next, the processor 110 extracts welfare benefit information matching the user's disability information through the welfare information providing unit 130, and includes the extracted welfare benefit information and the expected benefit amount calculated based on the welfare benefit information. Welfare service information may be generated (430).

Next, the processor 110 may output welfare service information through the welfare information providing unit 130 according to an output criterion including the disability type of the corresponding user (440).

As shown in FIGS. 11 to 15 , the processor 110 may provide welfare service information searched for and created based on disability information of the user through the welfare information providing unit 130 in various ways. For example, the processor 110 may provide, through the welfare information providing unit 130, a higher level item and a lower level item including specific details for each higher level item. In this case, the processor 110 may support a call connection with a person in charge of welfare service information selected by the user through the welfare information providing unit 130 . To this end, when collecting and storing welfare benefit information through the information registration unit 120, the processor 110 may match and store information of a person in charge of each welfare benefit information.

The above-described output criterion means a condition for differentiated provision of welfare service information for each user based on the user's disability type, and may be arbitrarily set by an operator.

For example, when providing welfare service information through the welfare information providing unit 130, the processor 110 may change and provide a method (voice or text) for outputting the welfare service information based on the disability type. For example, if the user is visually impaired, the processor 110 may provide voice-type welfare service information.

As another example, the processor 110 may convert terms in the welfare service information into easy terms through the welfare information providing unit 130 and provide the converted terms. For example, the welfare service information may be converted and provided in an easy-to-understand manner by reflecting difficult terms, changed terms, and changed policies in the welfare service information. For example, the processor 110 may convert difficult terms in welfare service information into terms that are relatively easy to understand through the welfare information providing unit 130 . In addition, the processor 110 may convert a changed term in the welfare service information into a term before change or display the changed term together with the changed term when displaying the changed term. In addition, the processor 110 may convert the welfare service information to reflect the changed policy when the changed policy is not reflected, or to provide both the case where the changed policy is not reflected and the case where the changed policy is reflected, or to include additional explanation of the changed policy. can

As another example, the processor 110 may translate welfare service information in a first language into a second language through the welfare information providing unit 130 and provide the translated information. For example, welfare service information provided in Korean may be translated into a second language such as English, Thai, or Vietnamese and provided. To this end, the processor 110 may additionally acquire the language or nationality used as second information when processing user registration through the information registration unit 120 .

The output condition of the aforementioned welfare service information may include a single method or a plurality of methods. For example, when providing welfare service information, the processor 110 can apply all output methods, term conversion, and translation into other languages through the welfare information providing unit 130 . That is, the output condition may include an output method of welfare service information, term conversion, and translation into another language.

Next, the processor 110 may provide an additional service matching the disability information of the user through the additional service provider 140 (450).

Meanwhile, the processor 110 determines a group including similar objects based on the user's disability information through the information registration unit 120, but among the disability information of other users who have already joined, the residence area, disability type, degree of disability, and After classifying other users whose gender is matched as the highest priority, a group can be determined based on the income and date of birth of household members.

For example, in step 450, the processor 110 may form a community meeting for each same group based on the determined group through the supplementary service provider 140.

As another example, in step 450, the processor 110 considers the date of birth, type of disability, degree of disability, gender, residence area, and date of registration of the disabled person among the disability information of the user through the supplementary service provider 140, and the community meeting or community counterpart. can be selected and provided. At this time, the processor 110 reflects the weight of the user's disability information according to the community priority set by the user among the user's disability information through the supplementary service provider 140 to select a community meeting or a community counterpart. can At this time, the community priority may be an item to be considered first when selecting a community meeting or a community counterpart among the user's disability information, a family, or a condition arbitrarily input by the user.

As another example, in step 450, the processor 110 recommends activity assistants by the same group based on the determined group through the supplementary service provider 140, provides encyclopedia information related to welfare, or to the corresponding group. It can recommend products including matching assistive devices. At this time, the processor 110 directly implements a function to purchase products related to the disabled, including assistive devices, through the additional service provider 140, or connects with another shopping mall server (not shown) that sells products related to the disabled method can be applied.

As another example, in step 450, the processor 110 may provide auxiliary device information matched based on the type and degree of disability among the disability information of the user through the supplementary service provider 140 and a purchase function. When providing the auxiliary device information, the processor 110 may provide a government subsidy and a method of applying for the government subsidy when purchasing the auxiliary device using a plurality of benefit information through the supplementary service provider 140 .

Meanwhile, when an auxiliary device is purchased by the user, the processor 110, through the supplementary service provider 140, provides a new auxiliary device based on the type of disability, the degree of the disorder, the purchased auxiliary device, and the date of purchase of the auxiliary device. You can monitor whether it is time to buy a device. In this case, the purchase timing of the new auxiliary device may include a case where the life of the existing auxiliary device matches the repurchase condition, an auxiliary device with an upgraded function is released, or an auxiliary device capable of receiving government subsidy occurs.

As a result of the monitoring, when it is time to purchase a new auxiliary device, the processor 110 notifies the purchase time of the new auxiliary device through the supplementary service provider 140, recommends information on the new auxiliary device, and provides government subsidy for the new auxiliary device and the government subsidy. A product information notification including at least one of the application methods may be transmitted to the terminal 200 of the corresponding user.

Although only assistive devices have been described as an example in the above description, it is natural that the above-described configuration can be applied to products necessary for the disabled other than assistive devices.

The welfare curation service, including the above-described subscription procedure, is performed when the welfare curation service application installed in the user terminal 200 is executed or when the user terminal 200 accesses the welfare curation service server 100. can

17 is a flowchart for explaining the welfare curation service method of FIG. 16 in more detail, and step 410 will be described as an example.

In step 410, after the step of collecting welfare benefit information and before the step of storing it, the processor 110 of the welfare curation service server 100 extracts a disability keyword from welfare service related information through the information register 120 and , Similar terms among the extracted disability keywords may be replaced with a preset representative disability keyword (411). In this case, the disability keyword may mean various keywords that may be included in welfare benefit information provided from the welfare information providing server 300 or may be used in relation to welfare for the disabled.

Next, the processor 110 may classify the plurality of welfare benefit information into a corresponding category according to a classification criterion based on a representative disability keyword of the plurality of welfare benefit information collected through the information registration unit 120 (413). . In this case, the category may include a welfare name, a welfare provider, a target of support, and a payment area.

Next, the processor 110 may compare similarities between a plurality of pieces of welfare benefit information collected through the information registration unit 120 and delete identical redundant data (415).

At this time, the processor 110 may maintain welfare benefit information from a source with the highest priority based on the priority of the plurality of welfare benefit information sources through the information registration unit 120 and delete welfare benefit information from the remaining sources.

18 is a flowchart for explaining the welfare curation service method of FIG. 16 in more detail, and step 420 will be described as an example.

The processor 110 of the welfare curation service server 100 may recognize the type of welfare card by inputting the welfare card image scanned through the information registration unit 120 to the learning model (421).

For example, a welfare card may be classified into an identification card type (type 1) and a credit card type (type 2) (including a financial type and a transportation type), but is not limited thereto.

The processor 110 may set a data recognition field in the welfare card image according to the type of welfare card recognized through the information registration unit 120 (423).

The processor 110 may extract first information from a data recognition field set through the information registration unit 120 . In this case, the first information may mean disability information of the user identified by scanning the welfare card image. For example, the first information is the name written on the welfare card, the user's identification number (eg, resident registration number, etc.), date of birth, disability type, degree of disability, gender, residential area, disability registration date, issue date, validity It may include at least one of period and issuer. In this case, the degree of disability may mean a degree of disability.

The processor 110 may receive second information input according to a user's manipulation through the information registration unit 120 (425). The second information is information input according to a user's manipulation, and may include income and occupation of the disabled person and household members.

The processor 110 may process and store the user's disability information according to the first data format through the information registration unit 120 (427). The first data format means a format for facilitating a comparison procedure with welfare benefit information for generating welfare service information, and includes information items, information expression methods, the order of information items, and contents included in each information item. can include

For example, the processor 110 may convert and store severe and mild conditions, which are current disability level expression methods, into previous expression methods, which are grades 1 to 6, among the user's disability information through the information registration unit 120 . To this end, the processor 110 may update new information related to welfare of persons with disabilities through the information registration unit 120, store the updated information in the memory 150, and change the first data format based on the updated information.

In addition, the processor 110, through the information registration unit 120, selects the address type of the beggar area among the user's disability information, not the road name address, which is the current method, but the lot address (1) Special city/province, 2) City/County, 3) District, 4) Eup/Myeon/Dong included) can be converted and saved.

At this time, the processor 110 will also be able to store and manage both the original and the modified version of the user's disability information through the information register 120 according to the first data format.

On the other hand, when registering the user's disability information through the information register 120, the processor 110 sets supplementary standards to information requiring security (eg, social security number, photo, name, etc.) among the user's disability information. matching can be applied.

For example, the processor 110 may display only some of information requiring security among the user's disability information through the information registration unit 120 and may mask or de-identify the remaining information so that it can be provided.

For example, the processor 110 maintains only the region indicating gender among the resident registration numbers extracted from the welfare card image through the information registration unit 120, and masks or de-identifies the remaining regions. there is. In addition, the processor 110 may manage the photo area in the welfare card image through the information registration unit 120 by masking or de-identifying the area using the coordinates of the corresponding area. This can be utilized when it is provided to a user requesting to view the user's disability information later.

That is, for the welfare curation service in the processor 110, all security-required information is stored and managed, but when security-required information needs to be displayed on the screen, some of the security information is masked (or non-secured). Identification processing) and provided. To this end, the processor 110 may match and manage the masking area (or non-identification area) when storing the user's disability information.

On the other hand, when the processor 110 sets the masking area (or non-identification area) through the information registration unit 120, the displayed part can be differentiated and provided according to the security level of the object for which the user's disability information is requested to be viewed A plurality of masking areas can be set even in one user's disability information.

For example, if the target of the user's disability information request is a service operator or a person with a disability, the processor 110 may display all of the user's disability information through the information registration unit 120 . If the target of the user's disability information request is not the service operator or the person with a disability, the processor 110 may display only a part of the user's disability information through the information registration unit 120.

19 is a flowchart for explaining the welfare curation service method of FIG. 16 in more detail, and step 430 will be described as an example.

The processor 110 of the welfare curation service server 100 may extract a plurality of welfare benefit information matched with disability information of the user through the welfare information providing unit 130 (431).

The processor 110 may determine whether a plurality of welfare benefit information is duplicated and support priority based on the disability information of the user through the welfare information providing unit 130 (433). At this time, whether or not to provide redundant support may mean whether or not redundant support can be provided to the user among a plurality of welfare benefit information. For example, it may be information indicating that 1 and 3 of welfare benefits 1, 2 and 3 may be supported to the user redundantly. The priority of support may be determined based on a criterion by which a large amount of support money may be paid to a user among a plurality of welfare benefit information and whether or not duplicate support is provided.

The processor 110 may calculate an expected benefit amount based on whether the plurality of welfare benefit information identified through the welfare information providing unit 130 is supported and the priority of support (435).

The processor 110 may generate welfare service information including at least one or more of welfare benefit information, priority of support, whether or not duplicate support is provided, and expected benefit amount through the welfare information providing unit 130 (437).

On the other hand, the method according to the present disclosure described above may be implemented as a program (or application) to be executed in combination with a server, which is hardware, and stored in a medium.

The disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. Instructions may be stored in the form of program codes, and when executed by a processor, create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media in which instructions that can be decoded by a computer are stored. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, and the like.

As above, the disclosed embodiments have been described with reference to the accompanying drawings. Those skilled in the art to which the present disclosure pertains will understand that the present disclosure may be implemented in a form different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

100: welfare curation service server
110: processor
120: information register
130: replication information providing unit
140: additional service provider
150: memory
160: communication department
200: user terminal
300: Welfare information providing server

Claims (12)

A method performed by a welfare curation service server, comprising: collecting a plurality of welfare benefit information from a plurality of welfare information providing servers through web crawling;
extracting disability keywords from welfare service-related information, and setting a similar term among the extracted disability keywords as a preset representative disability keyword;
Classifying the plurality of welfare benefit information by category including welfare name, welfare provider, support target, and payment area based on a representative disability keyword of the collected plurality of welfare benefit information;
deleting identical redundant data by comparing similarities between the plurality of collected welfare benefit information;
processing the plurality of welfare benefit information in different formats according to a first data format and storing them in the same format;
Subscription processing is performed based on the user's disability information including the first information identified by inputting the welfare card image into the learning model and the second information input by the user, but the welfare card image is selected according to the type of welfare card. Collecting disability information of the user by adjusting a data recognition field in ;
Extracting the plurality of welfare benefit information that matches the disability information of the user, and generating welfare service information including the extracted plurality of welfare benefit information and the expected benefit amount calculated based on the plurality of welfare benefit information doing;
outputting the welfare service information according to an output criterion including a disability type of a corresponding user; and
Including; providing an additional service that matches the disability information of the user;
The collecting of the user's disability information may include processing and storing the user's disability information according to a second data format including an information item, an information expression method, an order of information items, and contents for each information item,
The output criterion is a condition for differentially providing the welfare service information for each user based on the disability type of the user.
According to claim 1,
Collecting the user's disability information,
inputting the scanned welfare card image into the learning model;
recognizing the type of the welfare card;
setting a data recognition field in the welfare card image according to the type of the recognized welfare card;
extracting the first information from the set data recognition field; and
receiving the second information input according to the user's manipulation;
Including, welfare curation service method.
delete According to claim 1,
In the step of deleting the redundant data,
A welfare curation service method, based on the priorities of the sources of the plurality of welfare benefit information, maintaining welfare benefit information from the highest priority source and deleting welfare benefit information from the remaining sources.
According to claim 1,
Generating the welfare service information,
extracting the plurality of welfare benefit information matching the disability information of the user;
determining whether or not the plurality of welfare benefit information is duplicated and support priority based on the disability information of the user;
Calculating an expected benefit amount based on whether the plurality of welfare benefit information is identified and whether or not the plurality of welfare benefit information is duplicated and the priority of support; and
Generating the welfare service information including at least one of the plurality of welfare benefit information, the support priority, whether or not the overlapping support, and the expected benefit amount is generated; Welfare curation service method comprising a.
According to claim 1,
The step of performing the subscription process,
Based on the user's disability information, a group including similar objects is determined, but among the disability information of other users who have already joined, other users matching the residence area, disability type, degree of disability, and gender are classified as the highest priority, and household members Determining a group based on the income and date of birth of; further comprising a welfare curation service method.
According to claim 6,
The step of providing the supplementary service,
Forming a community meeting for each same group based on the determined group; including, Welfare curation service method.
According to claim 6,
The step of providing the supplementary service,
Selecting and providing a community meeting or community counterpart in consideration of the user's date of birth, type of disability, degree of disability, gender, region of residence, and date of registration of the disabled person among the disability information of the user,
The welfare curation service method of selecting the community meeting or community counterpart by reflecting a weight for disability information of the user according to community priorities preset by the user among the disability information of the user.
According to claim 6,
The step of providing the supplementary service,
Based on the determined group, recommending assistants for each same group, providing encyclopedia information related to welfare, or recommending products including assistive devices matched to the group; including, a welfare curation service method .
According to claim 6,
The step of providing the supplementary service,
Assistive device information and purchasing function matched based on the type and degree of disability among the disability information of the user are provided, but when the assistive device information is provided, the government purchases the assistive device using the plurality of benefit information. providing a subsidy and a method of applying for the government subsidy together;
If the auxiliary device is purchased, monitoring whether it is time to purchase a new auxiliary device based on the type of disability, the degree of the disorder, the purchased auxiliary device, and the date of purchase of the auxiliary device; and
As a result of the monitoring, if it is time to purchase the new auxiliary device, product information including at least one of notification of the purchase time of the new auxiliary device, recommendation information on the new auxiliary device, government subsidy for the new auxiliary device, and method of applying for the government subsidy. A welfare curation service method comprising the steps of transmitting a notification to a terminal of a corresponding user.
A program stored in a computer-readable recording medium in order to execute the welfare curation service method of any one of claims 1, 2, and 4 to 10 in combination with a computer.
register of information;
Department of Welfare Information; and
Including; a processor for controlling the operation of the value-added service provider;
the processor,
Collecting a plurality of welfare benefit information from a plurality of welfare information providing servers through web crawling;
extracting disability keywords from welfare service-related information, and setting a similar term among the extracted disability keywords as a preset representative disability keyword;
Classifying the plurality of welfare benefit information by category including welfare name, welfare provider, support target, and payment area based on a representative disability keyword of the plurality of welfare benefit information collected;
comparing similarities between the plurality of collected welfare benefit information and deleting identical redundant data;
processing the plurality of welfare benefit information in different formats according to a first data format and storing them in the same format;
Subscription processing is performed based on the user's disability information including the first information identified by inputting the welfare card image into the learning model and the second information input by the user, but the welfare card image is selected according to the type of welfare card. collecting disability information of the user by adjusting a data recognition field in ;
Extracting the plurality of welfare benefit information matching the disability information of the user, and generating welfare service information including the extracted plurality of welfare benefit information and the expected benefit amount calculated based on the plurality of welfare benefit information and;
outputting the welfare service information according to an output criterion including a disability type of the corresponding user; and
Provides an additional service matching the user's disability information,
When the user's disability information is collected, the user's disability information is processed and stored according to a second data format including information items, information expression methods, order of information items, and content for each information item,
The output criterion is a condition for differentially providing the welfare service information for each user based on the disability type of the user, the welfare curation service server.

Images