KR102617635B1 - System for providing public contract platform service connecting public and company - Google Patents

Abstract

A public contract platform service provision system that connects government offices and companies is provided. A government office terminal registers at least one task information and requests contracts and documents, registers participation in at least one task information, and registers as participation. In this case, a posting department that receives and posts at least one task information from corporate terminals and government office terminals that register quotations, a reception department that registers participation in at least one task information from corporate terminals, and registers quotations from at least one corporate terminal. When a contract and document is requested from a government office terminal, the Quotation Comparison Department, which provides quotation comparison, the Administrative Simplification Department, which prepares documents according to the administrative simplification service already established by a corporate terminal selected from a government office terminal, a corporate terminal It includes a platform service providing server that includes a transmission unit that transmits the prepared documents to government office terminals.

Description

Public contract platform service provision system that connects government offices and companies {SYSTEM FOR PROVIDING PUBLIC CONTRACT PLATFORM SERVICE CONNECTING PUBLIC AND COMPANY}

The present invention relates to a public contract platform service provision system that connects government offices and companies, and provides a platform that can reduce the decision-making costs of government offices and help companies participate in public contracts.

Government procurement or public procurement refers to a procurement process carried out to meet public demand such as goods, construction, and services required by administrative entities such as the state or local governments. The public procurement market is not only gradually increasing in size around the world, but is also an important policy tool in major countries. In order to prevent corruption in the public procurement market, improvements in public procurement legislation and public procurement that effectively guarantee transparency and cost efficiency are needed. The importance of follow-up audits of procurement is also growing. The laws that form the core of the public procurement legal system in the public procurement market include the Act on Contracts to which the State is a Party, the Act to Contracts to which Local Governments are a Party, the Procurement Project Act, the Defense Acquisition Program Act, and the Act on the Management of Public Institutions. There is a law regarding this. In cases where public enterprises, quasi-governmental organizations, and other public organizations do not have provisions related to contract affairs rules or operating regulations, the National Contract Act has been applied mutatis mutandis to establish a national comprehensive e-procurement system and provide a basis for use, and the e-procurement system stipulated in various laws and regulations has been established. Related matters were systematically legislated so that electronic procurement could be actively utilized.

At this time, methods for computerizing administrative work or predicting the results of public procurement bidding were researched and developed. In this regard, the prior art, Korea Registered Patent No. 10-1869653 (announced on June 20, 2018) and Korea Registered Patent No. In No. 10-2370969 (announced on March 10, 2022), a document form is provided when administrative work is requested from the user terminal, and when the document is created on the user terminal, it is forwarded to the responsible terminal to create an approval file and a draft file. A configuration that requests storage and payment and a configuration that calculates the qualitative evaluation, quantitative evaluation, success rate, and procurement performance of the procuring company to predict the results of public procurement bidding, and then predicts the bidding evaluation results are each disclosed. there is.

However, in the former case, it is only a conversion of administrative work from offline to online and is not a structure that simplifies administrative work, and in the latter case, it is only a structure that predicts whether or not it will pass the qualification screening for public procurement. When conducting a contract between a government office and a company, rather than considering reasonable price and quality when selecting the company to proceed with the contract, the existing company is selected as is customary by considering external costs and decision-making costs, which are social costs necessary in the decision-making process. In most cases, it is not possible to receive a reasonable price and quality within the budget. In addition, companies that are service providers often need administrative support other than providing services, and they lack the capacity to solve various problems that arise from business start to contract termination on their own, and even companies with sufficient capacity cannot even negotiate private contracts. The current situation is that it is not possible to participate. Accordingly, research and development of a platform that can minimize the decision-making costs of government offices and help companies simplify administrative procedures is required.

In one embodiment of the present invention, task information is registered and posted from a government office terminal so that public contracts between government offices and companies can be smoothly performed, and when the company terminal registers participation and quotation for the task information, it is compared with the government office terminal. We provide estimates, standardize documents requested from government office terminals, and provide administrative simplification services. When signing contracts on corporate terminals, we monitor the progress of each stage of the project corresponding to task information, and after the project is completed. By collecting evaluation information from government offices and governance, it is possible to evaluate and certify each company based on quantitative and qualitative data, database the certification and evaluation information of each company, and automatically update content created as a task. It is possible to provide a public contract platform service provision system connecting government offices and companies that can build an archive by tagging. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes a government office terminal that registers at least one task information and requests contracts and documents, registers participation in at least one task information, and When registering for participation, a posting department that receives and posts at least one task information from corporate terminals and government office terminals that register estimates, a reception department that receives registration of participation in at least one task information from a corporate terminal, and a reception department that receives registration of participation in at least one task information from at least one corporate terminal The Quotation Comparison Department, which registers quotations and provides quotation comparisons; When contracts and documents are requested from government office terminals, the Administrative Simplification Department prepares documents according to the administrative simplification service already established through the corporate terminal selected by the government office terminal; It includes a platform service providing server that includes a transmission unit that transmits documents prepared on a corporate terminal to a government office terminal.

According to one of the above-described problem-solving means of the present invention, task information is registered and posted from a government office terminal so that public contracts between government offices and companies can be smoothly performed, and participation in the task information and estimates are registered on the company terminal. In this case, comparative estimates are provided through government office terminals, standardization is performed on documents requested by government office terminals, and administrative simplification services are provided. When a contract is concluded through a corporate terminal, the progress of each step is monitored for the project corresponding to the task information. After the project is completed, evaluation information by government offices and governance is collected to evaluate and certify each company based on quantitative and qualitative data, and each company's certification and evaluation information is made into a database and tasks are completed. You can build an archive by automatically tagging content created with .

Figure 1 is a diagram for explaining a public contract platform service provision system connecting government offices and companies according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a platform service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a public contract platform service connecting government offices and companies according to an embodiment of the present invention is implemented.
Figure 5 is an operation flowchart illustrating a method of providing a public contract platform service connecting government offices and companies according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

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

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram for explaining a public contract platform service provision system connecting government offices and companies according to an embodiment of the present invention. Referring to Figure 1, the public contract platform service provision system 1 connecting government offices and companies includes at least one government office terminal 100, a platform service provision server 300, and at least one company terminal 400. It can be included. However, since the public contract platform service provision system 1 of FIG. 1 connecting government offices and companies is only an embodiment of the present invention, the present invention is not limited to FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one government office terminal 100 may be connected to the platform service providing server 300 through the network 200. In addition, the platform service providing server 300 may be connected to at least one government office terminal 100 and at least one enterprise terminal 400 through the network 200. Additionally, at least one enterprise terminal 400 may be connected to the platform service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one government office terminal 100 uses a web page, app page, program, or application related to the public contract platform service connecting government offices and companies to upload task information, request a quote, receive documents, and compare quotes. It may be a terminal in a government office that selects and contracts with a company to perform a task, monitors the status of each stage of the project, and evaluates the results.

Here, at least one government office terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one government office terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one government office terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), 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) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The platform service providing server 300 may be a server that provides a public contract platform service web page, app page, program, or application that connects government offices and companies. In addition, the platform service providing server 300 uploads task information from the government office terminal 100, receives participation of the corporate terminal 400, and then provides an administrative simplification service for documents to be filled out in the corporate terminal 400. It may be a server that helps prepare documents by providing . In addition, the platform service providing server 300 monitors the progress of each stage of the project and guides it to the government office terminal 100, and after the project is completed, qualitative evaluation is performed from the government office terminal 100 and the evaluator terminal (not shown). And it may be a server that collects quantitative evaluations and then accumulates and stores them as qualitative and quantitative data for each company.

Here, the platform service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one corporate terminal 400 participates in government office tasks using a web page, app page, program, or application related to the public contract platform service that connects government offices and companies, and sends related documents to the platform service providing server 300. It is prepared and submitted according to the administrative simplification service of , and may be a corporate terminal that provides an estimate and receives the evaluation results and settlement of the payment after proceeding with the project when a contract is concluded.

Here, at least one enterprise terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one enterprise terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one enterprise terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), 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) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the platform service providing server included in the system of Figure 1, and Figures 3 and 4 are implementations of a public contract platform service connecting government offices and companies according to an embodiment of the present invention. This is a drawing to explain one embodiment.

Referring to FIG. 2, the platform service providing server 300 includes a posting unit 310, a reception unit 320, a quote comparison unit 330, an administrative simplification unit 340, a transmission unit 350, and a digitization unit 360. ), including real-time quotation department (370), promotion certification department (380), archive department (391), matching department (393), monitoring department (395), contract database department (397), and evaluation and certification department (399). can do.

The platform service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention provides information between a government office and a company using at least one government office terminal 100 and at least one company terminal 400. When transmitting a connecting public contract platform service application, program, app page, web page, etc., at least one government office terminal 100 and at least one corporate terminal 400 are public contract platforms connecting government offices and companies. You can install or open service applications, programs, app pages, web pages, etc. Additionally, a service program may be run on at least one government office terminal 100 and at least one corporate terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the posting unit 310 may receive at least one task information registered from the government office terminal 100 and post it. The government office terminal 100 can register at least one task information and request contracts and documents. For example, task information may be in the form of task instructions, but is not limited to this. Taking the Korea Tourism Organization domestic tourism media wall content production delivery and experience space creation project conducted by the Korea Tourism Organization in 2021 as an example, the task instruction has a table of contents such as task performance period, task target status, task details, etc., and task contents. And the detailed guidelines explain what tasks should be performed according to the 6th principle. This task instruction is a massive 23 pages, and when uploading task information, you can upload all of this task instruction and provide summary information along with it. For example, by extracting and providing keywords, a summary can also be provided to easily understand the conditions for which companies can participate. In addition, taking the 2022 Gangnam Ingang promotional video production task instruction as an example, information such as project period, project budget, contract method, production content, and production format is provided, and detailed task content includes various tasks such as planning and scenario, filming, and editing. Conditions are posted. This text information can be provided as infographics, and each task instruction can be re-visualized based on standardized tags. Alternatively, you can create a preset standardized format, assign a unique identification code to each coordinate and frame within the standardized format, automatically extract information by mapping it to the items in the task instruction, and provide only keywords in the standardized format to create the file. It can also be provided so that information can be viewed on an Internet web page at a glance without having to open it or understand all the various task instructions. At this time, when using TF-IDF to extract keywords, only frequencies are considered, so a domain library is built according to the type of each task instruction, and Instruction-Focused Summarization is used to extract only keywords containing instructions related to the task instruction. Available. For this purpose, SBERT with Extractive Summarizer or BERTSum based on BERT (Bidirectional Encoder Representations from Transformers) can be used. Of course, keywords related to task instructions can be extracted and provided using various other methods.

The reception unit 320 may receive registration of participation in at least one task information from the enterprise terminal 400. The enterprise terminal 400 can register participation in at least one task information and, if participation is registered, register an estimate. At this time, the task instructions include details about which camera should be used and which personnel should participate. Accordingly, it is possible to determine whether the estimate is appropriate. The production of the promotional video for Gangnam Ingang ordered by Gangnam-gu Office (Education Support Division) as described above. Looking at the task instructions, the production content and production format are as shown in Table 1, and the necessary filming equipment, manpower, experience of the manpower, final result range, etc. can be extracted, and a margin of error for the average price is set for this and submitted by the company. You can determine whether the quote is appropriate.

business budget Gold 22,000,000 won (VAT included) Production details -1 official promotional video (approximately 2 minutes, length confirmed after discussion of plan)
-1 short form video (approximately 15 seconds, length confirmed after discussion of plan)
- Shortened official promotional video
-You can request that the edited 30-second edited version be completed through consultation prior to the production end date. Production format Full HD or higher or 4K or higher video for broadcasting Applied technology- -Produce novel and high-quality videos by reflecting the latest video shooting and editing trends such as CG, sound, and special effects
-Use special effects only to improve the quality of the video, and avoid using them to lower the quality of the video, such as replacing on-site filming.
-Utilize various filming equipment such as drones, cinema cameras, electric sliders, jimbos, gimbals, etc. scenario Written by a professional writer with over 10 years of experience Scope of performance Includes the entire production process, including planning, directing, composition, storyboard, scenario, filming, recording, music, CG, translation, and editing. DB construction A systematic database work on the original footage must be conducted and delivered as part of the final product, and must be provided in the file format desired by Gangnam Ingang. performance report Performance must be reported regularly during the task performance period, and progress must be reported frequently as requested by Gangnam In-Lecture. Copyright Copyright for all materials, including productions, copyrights, other rights, and intermediate results developed in connection with the performance of this task, belongs to the ordering agency.

The quote comparison unit 330 can receive quotes from at least one enterprise terminal 400 and provide quote comparison. In the case of architecture, the standard product price is announced, so the price of each person can be roughly determined. However, in the case of video production, the quality can be different even for people with the same experience, so by grading and standardizing the quality, a database similar to the standard product price in the architectural field is created. You can also build . In addition, it may be determined whether the quotation of the corporate terminal 400 is appropriate based on contract data accumulated and stored according to various conditions such as the contract quotation and the latest quotation stored in the contract database unit 397, which will be described later, and whether the quotation of the corporate terminal 400 is appropriate, which will be described later in real time. Estimates can also be calculated and compared in real time using the BEP reverse calculation method of the estimator unit 370.

When a contract and document is requested from the government office terminal 100, the Administrative Simplification Department 340 will proceed with the preparation of documents according to the administrative simplification service already established with the corporate terminal 400 selected from the government office terminal 100. You can. At this time, the administrative simplification service is a service that standardizes and digitizes 9 to 10 various documents prepared at the time of a negotiated contract so that they can be easily prepared.

The transmission unit 350 may transmit documents prepared in the corporate terminal 400 to the government office terminal 100. At this time, a cloud server can be established so that various documents can be accessed and searched whenever necessary from the government office terminal 100. In one embodiment of the present invention, a service that verifies the authenticity of a document at each institution before transmitting or uploading the document to the cloud can be used to provide a tag indicating whether or not the document has been verified.

The digitization unit 360 standardizes at least one type of document required according to the type of at least one contract, and collects at least one information to be entered into the document from the enterprise terminal 400 and automatically inputs it or enters it into the enterprise terminal 400. The terminal 400 may provide a guide for manual input. For example, when conducting a private contract in a national marketplace, business register, certified copy of register, performance bond insurance policy, certificate of full payment of local taxes, certificate of full payment of national taxes, copy of bankbook, certificate of experience for each participant, copy of resume and qualifications, and copies of qualifications held by the company. There are so many and various documents, including various certificates, confirmations, reports, fair contract pledge, integrity contract implementation memorandum, integrity contract special conditions, retiree recruitment confirmation, start-up report, participating personnel security pledge, service process schedule, personal information provision agreement, and employment certificate. You must fill out, obtain and submit documents. Since the organizations that issue each document are different and there are many documents that need to be prepared, one embodiment of the present invention can help users easily issue documents by using a standardized process that performs this on their behalf or creates standardized documents. To this end, you can register documents in advance or obtain various necessary documents from each institution through a document issuance agency. To this end, each company can apply for issuance agency after authenticating with authentication documents such as a joint certificate, and related personnel information can be automatically uploaded by linking with each company's database or personnel ERP.

The real-time estimate unit 370 can calculate and provide an estimate for the task requested by the government office terminal 100 in real time by applying the Break-Even Point (BEP) reverse calculation method. A method of reverse calculating the quotation by applying the project cost to the actual task using a cost analysis model to analyze the break-even point so that a real-time quotation is possible before the quotation is provided by the corporate terminal 400. can be used.

The verification unit 380 may verify the creator by accumulating and storing quantitative and qualitative data about the creator of at least one creator terminal (not shown). When performing verification for at least one creator terminal, the promotion authentication unit 390 sets the standard for project success difficulty, then grants performance points according to the degree of completeness of completing the project, and quantitatively evaluates the project according to the quantitative evaluation of the project. Promotion certification can be confirmed by accumulating qualitative data based on data and qualitative evaluation.

<Quantitative analysis>

Quantitative data can analyze the amount of mentions of at least one keyword, the trend of at least one keyword, and the trend of the amount of mentions of at least one keyword. For efficient analysis of content keyword data, GLM with Gamma Distribution as the link function can be used. Additionally, a two-mode network based on graph theory is constructed to visualize the relationships between keywords. You can use a content keyword analysis method that determines the regression equation from the 2-mode network visualization results and estimates the parameters of the regression equation using GLM based on the gamma distribution.

Content data must be preprocessed into a standardized data structure for analysis. In one embodiment of the present invention, a preprocessing process using text mining techniques is performed. First, a text database is built by extracting title and summary data from the searched content data, and a corpus is created based on this. Keywords are extracted from the generated corpus, and standardized data consisting of content data and keywords are constructed to finally obtain a content-keyword matrix. The rows of the matrix represent n content data and the columns represent m keywords. Each element of this matrix is the frequency value of a specific keyword included in each content data. The range of values that a frequency value can have is from 0 to positive infinity. For analysis, q keywords to be used as response variables and p keywords to be used as explanatory variables are selected from m keywords. To visualize a 2-mode network, the correlation coefficient matrix between explanatory variables and response variables is obtained. In one embodiment of the present invention, the 2-mode network has a social network structure using connection relationships between p row and q column nodes. In other words, the correlation between p description keywords and q response keywords is visualized. To create a 2-mode network, first create an input matrix as shown in Equation 1. ???梡煬?

Here, C is an association matrix consisting of a (p×q) correlation coefficient matrix. On and 0m are zero matrices of (n×n) and (m×m), respectively. Finally, the regression equation to be used in the gamma distribution-based GLM is determined using the results of visualizing the matrix M. GLM consists of three components: response variable, linear predictor, and link function. Response variables (Y1, Y2,...,Yq), which are independent of each other, follow a distribution belonging to the exponential family. In one embodiment of the present invention, gamma distribution is used. In other words, the random variable Y following the gamma distribution has the probability density function of Equation 2.

The values that the random variable Y can have are positive real numbers greater than 0. Equation 3 below, which is a linear combination of X1, X2,...,Xp, is called a linear predictor. When the average of Yi is μi, g(.), which has the relationship in Equation 4, becomes the connection function.

In one embodiment of the present invention, since the frequency of content keywords theoretically has a large spread from 0 to positive infinity, the logarithm of the link function is used. Table 2 below shows the content keyword analysis procedure according to an embodiment of the present invention.

<Step 1>
Collection and preprocessing of content data ① Search content data related to target content or artist ② Preprocessing of content data using text mining techniques ③ Building a content-keyword matrix ④ Select keywords to be used as response variables and explanatory variables <Step 2>
Two-mode network visualization ① Construction of description-response keyword matrix ② Calculate the correlation coefficient between description and response keywords ③ Generate input matrix using zero matrix and association matrix ④ 2-mode network visualization <Step 3>
Perform GLM based on gamma distribution ① Specify the distribution of response keywords as a gamma probability distribution ② Define linear predictor for descriptive keywords ③ Perform final GLM using log link function ④ Model evaluation

In one embodiment of the present invention, Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Log Likelihood are used to evaluate the performance of the finally constructed model. First, AIC is defined as Equation 5.

Here, log is the log likelihood and k represents the number of parameters to be estimated. The smaller the AIC value, the better the model's performance. BIC, which is mainly used in evaluating model performance along with AIC, is defined as Equation 6.

Here N is the size of data. In other words, when the given data is large, BIC imposes a larger penalty on each parameter than AIC. Like AIC, the smaller the BIC value, the better the model performance. The third performance evaluation measure used in one embodiment of the present invention is log likelihood defined in Equation 7.

Log likelihood represents the sum of the logarithm of the probability function of the parameter for given data. In other words, since log likelihood represents the likelihood of a parameter, the larger the value, the better the model's performance. In an experiment of an embodiment of the present invention using actual content data, AIC, BIC, and log-likelihood values can be used to evaluate performance between comparative models. Through the performance evaluation results, the best model can be set as a model according to an embodiment of the present invention.

<Qualitative evaluation>

In the case of qualitative evaluation, positive, negative, and neutral emotions regarding content data can be analyzed using a previously constructed emotional vocabulary dictionary. Sentiment analysis refers to the task of determining subjective elements such as opinions and evaluations contained in text and quantifying them in numbers, diagrams, or ratings. Rather than simply determining positive and negative emotions, it extracts target attributes and analyzes the emotions, attitudes, and positions of opinion holders. The main purpose of sentiment analysis is to analyze large amounts of text to understand customers or audiences' perspectives on target items, and to extract subjective data from text by combining statistics, natural language processing, and machine learning techniques. Traditional sentiment analysis aims to classify whether a document or sentence is positive or negative when viewed overall. However, in order to utilize the sentiment analysis results, information is needed on why consumers are satisfied or dissatisfied with a specific part of the content rather than simply evaluating it positively or negatively.

Deriving these various attributes and performing sentiment analysis for each attribute is called attribute-based sentiment analysis (Aspect-Based Sentiment Analysis, ABSA). The reason why attribute-level emotional analysis has recently received attention is because it can identify customer preferences by attribute and increase the usability of analysis results by deriving more precise and accurate insights. In addition, companies may be more likely to gain more marketing-related insights through analysis and comparison of major competitors. It has the advantage of being able to easily check which attributes are superior to competing content and which attributes are evaluated relatively low. Traditional attribute-based sentiment analysis has been performed using topic classification or dependent syntax analysis, but in one embodiment of the present invention, attribute-based sentiment analysis can be performed using the BERT model, which provides high performance based on a transformer architecture.

<BERT model>

As described above, BERT is a pre-trained language model composed of transformer encoder blocks stacked on top of each other. Through learning tasks such as mask language model and guessing whether the next sentence is the next sentence, the model can see both forward and backward context. It uses token embedding, segment embedding that separates sentences, and position embedding that corresponds to the location of the token. The pre-trained model shows excellent performance in natural language processing fields such as entity name recognition and question answering through fine tuning. The RoBERT-a model is an application model of BERT, and has the characteristics of learning longer than BERT, utilizing more data with a larger batch size, and not utilizing the NSP (Next Sentence Prediction) methodology. In addition, by using longer sentences and dynamically changing masking in the pre-training stage, the results exceed the existing BERT methodology.

<ABSA>

Attribute-based sentiment analysis, for example, when given reviews of computers and restaurants, extracts attributes for each review and assigns a sentiment polarity to the extracted attributes. Traditional sentiment analysis considers only the emotional polarity of the entire sentence and is appropriate when there is only one feature or emotion in a sentence, but ABSA is a more sophisticated method that focuses on the features or attributes of the target. As an example of a restaurant review, when given the sentence [the ambience is good, but the food is horrible], it can be seen that it expresses positive feelings about the atmosphere, but negative feelings about the food. On the other hand, in traditional emotion analysis methods, the word [horrible] is given a probability higher weight than the positive word [good], so the positive part is ignored and the entire sentence is classified as negative. In this way, attribute-based sentiment analysis has the advantage of being able to better understand specific attributes mentioned in a sentence through more detailed sentiment analysis. Of course, qualitative and quantitative evaluations can be performed in a variety of ways in addition to the methods described above.

The archive unit 391 can build a digital archive by supporting automatic tagging of at least one content using at least one deep learning-based image recognition algorithm. At this time, for automatic tagging, an artificial intelligence model that can perform tasks such as preprocessing, classification, and tagging of images must first be built. In order to analyze video content based on deep learning, both theoretically and practically, there are quite a few tasks in the entire process, including collection, preprocessing, analysis, and service. In particular, prior to developing a high-performance deep learning model, it is necessary to secure sufficient quality learning data to train the model. Seven types of AI learning data using video released by the Korea Intelligence and Information Society Agency (NIA) on the AI Hub can be analyzed from a design perspective through documents released on the AI Hub, and standardization measures, especially focusing on classes, can be sought. In the AI Hub, in the video image field, dramas, reports, culture, entertainment, movies, and YouTube collected from 9 broadcasting companies, including KBS, MBN, EBS, SBS, Maeil Business Newspaper, YTN, OBS, tvN, and Maeil Business Newspaper (YouTube). Using videos such as, 7 types of AI learning data totaling 21,804 hours are being constructed and released. The scale of learning data construction is 129,514,816 objects (based on bounding boxes), 124,521 actions (based on clips), 3,136,345 situations (based on clips), 22,099 people (based on bounding boxes and key points), 60,000 shots (based on key shots), etc. The total is close to 132.88 million. In one embodiment of the present invention, various tasks can be organized into objects, actions, and situations, and the format and class of raw data and annotation data can be standardized. For object and action classes, the names can be standardized after unifying the various classification systems into [major classification - medium classification - minor classification]. When a situation is viewed as a combination of object, action, time, place, content (space), and emotion, standardized by detailed unit, and modeled by learning and verifying at least one artificial intelligence algorithm to classify it, just as the dataset was constructed. Automatic tagging of each format, object, behavior class, etc. is possible. Standardization of AI Hub video data sets can become the foundation for the development of integrated DB and archives, enable efficient additional construction and reconstruction, and increase the utilization of built learning data to develop deep learning-based video analysis models and broadcasting fields. can contribute to the AI transition.

In the case of images among content, it may be faster to use reinforcement learning. It may be necessary to initially label content images by hiring a labeler (tagger), but if imitation learning of reinforcement learning is used, automatic labeling similar to human labeling can gradually become possible. In video, an image is a way to express visual information on a two-dimensional plane. In terms of how to process information using images, deep neural networks have recently made rapid progress in object detection and pattern recognition in the image recognition field using convolution, sometimes showing higher reading rates than humans under limited conditions. A convolutional neural network is a type of artificial neural network consisting of several hidden layers between the input layer and the output layer, and learns convolution patterns on its own. Many convolutional neural networks are trained using supervised learning, and are given images as input and labels, which are words or images, as output. For an effective convolutional neural network, high accuracy results can be obtained while effectively solving the overfitting problem when there are many datasets.

For this purpose, the dataset is labeled with the labor of many experts, that is, labelers, and processed in parallel to effectively process many datasets. However, recently, image data is accumulating beyond the capacity that only experts can process. Accordingly, multiple experts need a collaborative method of acquiring datasets. Reinforcement learning is a neural network in which a model defined within an environment recognizes the current state and selects an action or sequence of actions that gives the maximum reward among selectable actions. In one embodiment of the present invention, a group of experts consists of deep learning-based learning image classification and reinforcement learning that imitates experts, performs labeling by experts, and simultaneously performs automated classification through reinforcement learning and records low-accuracy images from experts. A complementary system can be used as labeling.

A deep convolutional neural network is a deep learning neural network dedicated to image processing. An image is given as input and image label data is given as output. Several models are showing very high recognition rates in image classification problems using Imagenet Large Scale Visual Recognition Challenge data. R-CNN (Region-Convolutional Neural Network) is a deep convolutional neural network for use in real-time images such as videos. R-CNN is built around processing time and can compare many images per unit time. Reinforcement learning is a neural network that recognizes states, not inputs and outputs, and selects an action sequence that gives maximum reward from selectable actions. In one embodiment of the present invention, the labeling behavior of the imitation learner can be set to imitate the labeling behavior of an expert in the same form.

<Image labeling>

It can be configured as an imitation learner that collects the expert's labeling and imitates the expert's labeling pattern using reinforcement learning. The storage can be composed of an image and a labeling database. The image database stores images needed for classification, and the labeling database stores data labeled by experts or imitation learners. The labeling unit 330 according to an embodiment of the present invention provides an imitation learner to experts. The imitation learner performs object exploration and labeling using an R-CNN-based neural network based on data labeled by experts. The imitation learner allows reinforcement learning to be performed through reclassification by experts when confidence in the previously classified data for an object is low or there is no data in the classification category.

This imitation learner allows a group of experts to perform mass image labeling through more intensive evaluation and supplementation of the imitation learning results rather than continuous classification. The expert who receives the image obtains the coordinates of the object in the image and assigns a label. Labeled objects are sent to the server and stored in the labeling database. In addition, an expert additionally inputs a new image dataset and performs labeling directly, or specifies that an imitation learner can perform labeling. The imitation learner performs object search on objects obtained based on labeling using R-CNN. If the detected object obtains trust level data, the same label is added. If it is acquired with low accuracy, the object in the image is returned to the expert so that new labeling data for the object can be obtained. Data labeled by experts serves as a reward for reinforcement learning and updates the inference model when updated with new labeling.

If the company of the corporate terminal 400 is a one-person company or a small business that is difficult to participate in an independent bidding, the matching unit 393 can match to correspond to the type and number of personnel required for the project. In the case of video production, various positions and fields such as directing, lighting, shooting, grip, editing, scenario, planning, production, recording, CG, sound, music, art, props, makeup, costume, marketing, etc. Manpower is needed. However, one-person companies or freelancers cannot even participate in private contracts, but by matching these one-person companies, freelancers, or small business owners, we can provide opportunities to participate in public contracts.

The monitoring unit 395 can monitor the project progress of the corporate terminal 400 that has entered into a contract in response to the task information by dividing it into each section in real time. For example, the video production process can be divided into three stages: pre-production, production, and post-production. Pre-production refers to the planning process that develops the initial idea and clarifies the nature, purpose, direction, and strategy of the program. At this time, a composition plan and script are created in consultation with the producer, director, writer, etc., and specific implementation methods are sought to produce an effective video product. In addition, the production stage refers to the production process in which filming and recording are conducted based on the plan and script. The production process is largely divided into a practice process and a filming process. The post-production stage is a post-production process in which recorded screens and sounds are edited to create a complete production, and can be viewed as an editing process. In some cases, 2D or 3D graphics are also included, and sound-related corrections or additional work such as music, recording, and voice acting are required. In this way, the progress of each step can be monitored and the results can be reported to the government office terminal (100).

When a contract between the government office terminal 100 and the corporate terminal 400 is completed, the contract database unit 397 can build a database by mapping contract estimate information to at least one keyword, classifying and storing it. This databaseized contract information can be used by the quotation comparison unit 330 as data to determine whether the quotation is appropriate. In order to use the data, it must first be changed to structured data. To this end, contract information must be standardized for each item and preprocessed and classified first. To achieve this, a database must be established by standardizing each item of contract information and assigning a unique identification code. Contract data that has been changed to structured data in this way can serve as standard data for whether future estimates are appropriate.

When the project corresponding to the task information is completed, the evaluation and certification unit 399 stores the project satisfaction as a client evaluation from the government office terminal 100, collects project evaluation data from at least one evaluator terminal, and stores it as a governance evaluation. You can.

Hereinafter, the operation process according to the configuration of the platform service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to Figure 3a, the platform (tentative name, Public Contract Bridge) according to an embodiment of the present invention allows government offices to make the irrational choice of selecting an existing company according to custom in order to reduce the decision-making costs required for decision-making. We provide services so that companies can proceed without feeling burdened by various documents and estimates required for private contracts, and with a roadmap as shown in Figure 3b, we provide a B2G (Business to Government) or B2B brokerage platform as shown in Figure 4a. We would like to provide. The external API connection details are as shown in Figure 4b, and the menus as shown in Figures 4c and 4d and the manager system as shown in Figure 4e are built. The project (task) request and contract process may be as shown in Figure 4f, and the administrative document simplification service may be carried out as the process in Figure 4g. As shown in Figure 4h, corporate valuation results can also be provided, and keyword notifications are provided as shown in Figure 4i, allowing companies to quickly view information when a desired project is released. As shown in Figure 4j, a contract database can be built to check the market price quote, and as shown in Figure 4k, the company's evaluation can be provided by combining the evaluation results from the client (government office or other company) and governance.

Matters that were not explained about the method of providing public contract platform services connecting government offices and companies in Figures 2 to 4 are explained previously in Figure 1 about the method of providing public contract platform services connecting government offices and companies. Since the content is the same or can be easily inferred from the explained content, the description below will be omitted.

Figure 5 is a diagram showing a process in which data is transmitted and received between each component included in the public contract platform service provision system connecting government offices and companies of Figure 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to Figure 5, the platform service providing server receives and posts at least one task information from a government office terminal (S5100), and registers participation in at least one task information from a corporate terminal (S5200).

In addition, the platform service providing server receives quotations from at least one corporate terminal and provides quotation comparison (S5300), and when a contract and document is requested from a government office terminal, the administrative simplification service already established is provided to the corporate terminal selected from the government office terminal. Proceed with preparing documents according to (S5400).

In addition, the platform service providing server transmits documents prepared on the corporate terminal to the government office terminal (S5500).

The sequence between the above-described steps (S5100 to S5500) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5500) may be changed, and some of the steps may be executed simultaneously or deleted.

Matters that were not explained about the method of providing public contract platform services connecting government offices and companies in Figure 5 are explained previously in Figures 1 to 4 regarding the method of providing public contract platform services connecting government offices and companies. Since the content is the same or can be easily inferred from the explained content, the description below will be omitted.

The method of providing a public contract platform service connecting government offices and companies according to an embodiment described in Figure 5 is in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. It can also be implemented as: Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a public contract platform service connecting government offices and companies according to an embodiment of the present invention described above includes applications installed by default on a terminal (this may include programs included in the platform or operating system, etc., which are installed by default on the terminal). It may be executed by an application (i.e., a program) that the user installs directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a public contract platform service connecting government offices and companies according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default on the terminal or directly installed by the user, and is installed on the terminal. It may be recorded on a computer-readable recording medium, such as a computer-readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

A government office terminal that registers at least one task information in the form of a task instruction and requests contracts and documents;
A corporate terminal that registers participation in the at least one task information and registers an estimate when participation is registered; and
A posting unit that receives and posts at least one task information from the government office terminal, a reception unit that receives registration of participation in the at least one task information from the corporate terminal, and a quotation unit that receives quotations from the at least one corporate terminal and compares quotations. When requesting the contract and documents from the quotation comparison department provided by the government office terminal, the Administrative Simplification Department, which allows documents to be prepared according to the administrative simplification service already established by the corporate terminal selected from the government office terminal, the corporate terminal A transmission unit that transmits the written documents to the government office terminal, a real-time estimate unit that calculates and provides estimates for tasks requested by the government office terminal in real time by applying the BEP (Break-Even Point) reverse calculation method, and the government office terminal When a contract between enterprise terminals is completed, a platform service providing server including a contract database unit that builds a database by mapping contract quote information to at least one keyword, classifying and storing it,
In the above section,
In order to provide a summary to easily understand the conditions for which companies can participate, keywords are extracted from the above task information and provided.
The transmission unit,
Regarding the cloud server that allows various documents to be accessed and searched whenever necessary from the above-mentioned government office terminal, verification is verified using a service that verifies the authenticity of the document at each institution before transmitting or uploading the document to the cloud. Tags are also provided by tagging.
The real-time estimate department,
In order to enable real-time quotation before providing the quotation form on the corporate terminal, the process of analyzing the break-even point is reverse-calculated by applying the project cost to the actual task using a cost analysis model,
The contract database department,
When the contract between the government office terminal and the corporate terminal is completed, the contract information is standardized by item and a unique identification code is assigned to establish a database so that the quotation comparison department can use it as data to determine whether the quotation is appropriate. , A public contract platform service provision system that connects government offices and companies, characterized by providing contract data that has been changed to structured data as standard data for determining whether subsequent estimates are appropriate.
According to claim 1,
The platform service providing server is,
Standardizing at least one type of document required according to the type of at least one contract, and guiding at least one information to be entered in the document to be collected from the enterprise terminal and entered automatically or entered manually in the enterprise terminal A digitalization department that provides;
A public contract platform service provision system that connects government offices and companies, further comprising:
delete According to claim 1,
The platform service providing server is,
A verification unit that verifies the creator by accumulating and storing quantitative and qualitative data about the creator of at least one creator terminal;
A public contract platform service provision system that connects government offices and companies, further comprising:
According to claim 4,
The platform service providing server is,
When performing verification of the at least one creator terminal, a standard for project success difficulty is set, and then performance points are given according to the degree of completion of the project, and quantitative data according to the quantitative evaluation of the project and qualitative evaluation are given. A promotion certification department that accumulates qualitative data and confirms whether or not the promotion is certified;
A public contract platform service provision system that connects government offices and companies, further comprising:
According to claim 1,
The platform service providing server is,
An archive unit that builds a digital archive by supporting automatic tagging of at least one content using at least one deep learning-based image recognition algorithm;
A public contract platform service provision system that connects government offices and companies, further comprising:
According to claim 1,
The platform service providing server is,
If the company of the corporate terminal is a one-person company or a small business that has difficulty participating in individual bidding, a matching unit that matches the type and number of personnel required for the project;
A public contract platform service provision system that connects government offices and companies, further comprising:
According to claim 1,
The platform service providing server is,
A monitoring unit that monitors in real time the project progress of the contracted corporate terminal in response to the task information by dividing it into each section;
A public contract platform service provision system that connects government offices and companies, further comprising:
delete According to claim 1,
The platform service providing server is,
When a project corresponding to the task information is completed, an evaluation and certification unit that stores project satisfaction as a client evaluation from the government office terminal and collects project evaluation data from at least one evaluator terminal and stores it as a governance evaluation;
A public contract platform service provision system that connects government offices and companies, further comprising:

Images