KR102432008B1 - Method and Computer-Readable Medium for Providing Legal Services Based on Artificial Intelligence - Google Patents

Abstract

The present invention relates to a method and computer-readable medium for providing legal services based on artificial intelligence, and more particularly, to a case through an artificial intelligence-based model according to one or more case details input by a user. It relates to a method and computer-readable medium for providing legal services based on artificial intelligence, which provide predictive results of

Description

Method and Computer-Readable Medium for Providing Legal Services Based on Artificial Intelligence

The present invention relates to a method and computer-readable medium for providing legal services based on artificial intelligence, and more particularly, to a case through an artificial intelligence-based model according to one or more case details input by a user. It relates to a method and computer-readable medium for providing legal services based on artificial intelligence, which provide predictive results of

In order to improve access to legal services and provide quality legal services, the Law School (Law School) was introduced in 2009. Although this is only the purpose of the introduction, the access to legal services experienced by those who actually use legal services is still not high.

In this situation, various attempts have been made to improve access to legal services, and one of these attempts, Legal Tech service, has recently appeared. Legal Tech refers to a new type of legal service that combines law and technology. Recently, as Internet access through portable devices such as smartphones has greatly improved, and IT technologies such as big data and artificial intelligence have developed, legal tech services have been developed through convergence with IT technologies in the legal service market. Legal Tech has the advantage of providing legal services quickly and at low cost by applying IT technology to the legal service field.

On the other hand, LegalTech is largely responsible for automatic legal writing (Document Automation), lawyer search and mediation (Marketplace), practice management (Practice Management), legal research (Legal Research), legal information analysis (Legal Analytics), and online dispute resolution. (Online Dispute Resolution) provides services in various fields. On the other hand, in order to provide a service for each field as described above, various technologies such as artificial intelligence technology, document search technology, document recognition and discrimination technology, document automatic generation technology, and the like are required.

In the case of legal tech service provided in Korea, the service is provided mainly in the field of automatically generating standardized legal documents, and these services are only to the extent of improving convenience by automating the work process of legal services. There is a problem in that it is difficult to fundamentally improve the accessibility of the aforementioned legal services.

Therefore, as a way to provide high-quality legal services, we provide the results of judgment predictions for users' legal cases based on artificial intelligence to help the users to actually proceed with the legal cases, and to It is necessary to introduce a service that can present methods that can produce favorable results.

The present invention relates to a method and computer-readable medium for providing legal services based on artificial intelligence, and more particularly, to a case through an artificial intelligence-based model according to one or more case details input by a user. An object of the present invention is to provide a method and a computer-readable medium for providing legal services based on artificial intelligence, which provide the prediction results of

In order to solve the above problems, the present invention provides a method for providing a prediction result of a legal case performed in a computing device having one or more processors and one or more memories, and provides a user with one or more case details for a target legal case. an input interface providing step of providing an input interface for a formalization step of deriving input formalized data having a plurality of values from the one or more event detailed information received from a user; a winning probability deriving step of deriving first winning probability information by inputting the input formalized data into a machine-learning model; and a first prediction result providing step of providing a prediction result of a legal case including the first winning probability information to the user;

In an embodiment of the present invention, the one or more case detailed information may include an input for an event category, detailed information input according to the corresponding event category, and evidence information.

In an embodiment of the present invention, the input to the one or more case detailed information includes uploading a file for evidence related to a target legal case, and the input standardized data includes standardized rating information for a file for the evidence. may include

In one embodiment of the present invention, the method for providing the prediction result of the legal case comprises the steps of: generating one or more modified input formalized data obtained by transforming one or more values of the input formalized data; and inputting the one or more modified input formalized data into the machine-learned model to derive one or more second winning probability information; including, wherein the prediction result of the legal case is one of the one or more second winning probability information It may include virtual increase probability information derived based on the above.

In an embodiment of the present invention, the false ascending probability information may include the prevailing probability information predicted when some event details of the one or more event details input by the user are different.

In an embodiment of the present invention, in the method for providing the prediction result of the legal case, after the first prediction result providing step, the input formalized data is updated according to the counterpart's response or the user's response to the target legal case. to do; deriving third winning probability information by inputting the updated input formalized data into the machine-learned model; And it may include a third prediction result providing step of providing the prediction result of the legal case including the third winning probability information to the user.

In an embodiment of the present invention, the input of the one or more case details includes uploading of a file for evidence related to a target legal case, and the input standardized data is additionally input by the user with respect to the file for the evidence. It may include values for one or more admissibility levels.

The present invention for implementing a method for providing a predictive result of a legal case performed in a computing device including one or more processors and one or more memories for storing instructions executable in the processor in order to solve the above problems , A computer-readable medium comprising: an input interface providing step for providing a user with an input interface for one or more case details for a target legal case; a formalization step of deriving input formalized data having a plurality of values from the one or more event detailed information received from a user; a winning probability deriving step of deriving first winning probability information by inputting the input formalized data into a machine-learning model; And it provides a first prediction result providing step for providing a prediction result of a legal case including the first winning probability information to the user; Containing, computer-readable medium is provided.

According to an embodiment of the present invention, the user inputs one or more case details for a target legal case that the user wants to proceed, and derives the first winning probability through a machine-learning model according to the input one or more case detailed information. Since it is provided to the user, the user can exert the effect of recognizing the probability of winning in advance in his or her legal case.

According to an embodiment of the present invention, the prediction result of the legal case including the first probability of winning provided to the user is a substitute for examining the validity of the legal case through consultation with a legal expert in the existing legal service. Therefore, the cost of legal services can be lowered and the quality of legal services can be improved.

According to an embodiment of the present invention, the case detailed information input by the user includes a file of evidence related to a target legal case, and finally derives a standardized value according to the degree of evidence capability for the file for the corresponding evidence. Since the first probability of winning is derived, it is possible to exert the effect of more accurately deriving the probability of winning according to the degree of evidence capacity of the file for evidence.

According to an embodiment of the present invention, transformed input formalized data is generated by transforming one or more input formalized data derived through the formalization step, and a second winning probability is derived based on the transformed input formalized data and provided to the user Therefore, it is possible to exert the effect that the user is provided with a method to improve the probability of winning the target legal case.

According to an embodiment of the present invention, when a response is made according to the legal procedure for the target legal case, the input formalized data is updated according to the corresponding response, and the third winning probability is derived based on the updated input formalized data and provided to the user, it is possible to exert the effect of providing the user with the result of the prediction of the judgment of the target legal case in accordance with the legal response in real time.

According to an embodiment of the present invention, since it is provided to the user by predicting the possibility of winning the target legal case in advance, it is possible to significantly lower the cost of legal services and to prevent in advance the number of legal cases with high validity. Therefore, it is possible to exert the effect of providing high-quality services for the legal cases that the lawyer is entrusted with.

1 schematically shows the configuration of a system including a computing device according to an embodiment of the present invention.
Figure 2 schematically shows the steps of providing a prediction result of a legal case including the first winning probability according to an embodiment of the present invention.
3 schematically shows an input interface for event details according to an embodiment of the present invention.
4 schematically illustrates a first detailed input interface included in the input interface for event detailed information according to an embodiment of the present invention.
5 schematically illustrates a second detailed input interface included in the input interface for event detailed information according to an embodiment of the present invention.
6 schematically shows the steps of providing a prediction result of a legal case including pseudo-increasing probability information according to an embodiment of the present invention.
7 schematically shows the steps of providing a prediction result of a legal case including a third winning probability according to the update of the input formalized data according to an embodiment of the present invention.
8 schematically shows input normalized data according to an embodiment of the present invention.
9 schematically illustrates an internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are now disclosed with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of one or more aspects. However, it will also be recognized by one of ordinary skill in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings set forth in detail certain illustrative aspects of one or more aspects. These aspects are illustrative, however, and some of the various methods in principles of various aspects may be employed, and the descriptions set forth are intended to include all such aspects and their equivalents.

Further, various aspects and features will be presented by a system that may include a number of devices, components and/or modules, and the like. It is also noted that various systems may include additional apparatuses, components, and/or modules, etc. and/or may not include all of the apparatuses, components, modules, etc. discussed with respect to the drawings. must be understood and recognized.

As used herein, “embodiment”, “example”, “aspect”, “exemplary”, etc. may not be construed as an advantage or an advantage in any aspect or design described above over other aspects or designs. . The terms '~part', 'component', 'module', 'system', 'interface', etc. used below generally mean a computer-related entity, for example, hardware, hardware A combination of and software may mean software.

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. should be understood as not

Also, terms including an ordinal number such as first, second, etc. may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are generally understood by those of ordinary skill in the art to which the present invention belongs. have the same meaning as Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in an embodiment of the present invention, an ideal or excessively formal meaning is not interpreted as

On the other hand, 'manager terminal' and 'user terminal' mentioned below are a computing device or a separate computer device that can connect to other servers or other terminals through a network, or a server system including a service server implemented by the computing device. It may be implemented as a portable terminal. Here, the separate computer device includes, for example, a laptop, a desktop, and a laptop equipped with a web browser, and the portable terminal has, for example, portability and mobility. As a guaranteed wireless communication device, PCS (Personal Communication System), GSM (Global System for Mobile Communications), PDC (Personal Digital Cellular), 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 (Wibro (Wireless Broadband Internet)) terminal, such as all kinds of handheld (Handheld) based wireless communication devices, such as can "Network" also means a wired network, such as a Local Area Network (LAN), Wide Area Network (WAN), or Value Added Network (VAN), or a Mobile Radio Communication Network (SAT) or satellite network. It can be implemented with all kinds of wireless networks, such as In addition, the cases described in the present invention correspond to all kinds of cases that can be concluded or a result can be derived by being carried out by a series of legal procedures.

1 schematically shows the configuration of a system including a computing device according to an embodiment of the present invention.

As shown in (A) of FIG. 1, the computing device 100 performs communication with one or more user terminals 200 and one or more administrator terminals 300 by wire or wirelessly, and the electronic litigation court server ( 400), it communicates with one or more externally provided servers by wire or wirelessly.

Specifically, the computing device 100 includes one or more processors and one or more memories to perform a series of steps for providing the aforementioned artificial intelligence-based legal services. On the other hand, the computing device 100 provides the user with an input interface for receiving one or more case details about a target legal case for which the user wants to request a service from the user in order to perform the series of steps. Meanwhile, in the present invention, the user includes a party to the case who wants to receive the service for the target legal case.

More specifically, the computing device 100 provides the input interface to the user terminal 200 or the manager terminal 300 of the corresponding user, and the user according to the input interface displayed on the user terminal 200. One or more event details are input, and the user terminal 200 may transmit the inputted one or more event details to the computing device 100 .

In addition, the user provides information on one or more case details through the computing device 100 or an administrator who manages the provision of legal services performed in the computing device 100, and the administrator is the administrator terminal 300 ), input the one or more event details according to the input interface, and the manager terminal 300 may transmit the inputted one or more event details to the computing device 100 .

More specifically, the manager using the manager terminal 300 is an expert with professional knowledge about the law, such as a lawyer, or a subject that can be appointed as a legal representative for the user, or a company such as a law firm (Law Firm). Including all entities capable of managing legal services provided through the computing device 100 , such as a subject managing legal services in .

The electronic litigation court server 400 receives a complaint generated based on one or more case details for the target legal case input through the input interface in a legal institution such as a court, and responds to the case specified in the complaint. The processed information is stored. The electronic litigation court server 400 may transmit the stored processed information to the computing device 100 . Preferably, the electronic litigation court server 400 transmits the processed information in the form of an email or text message to a separate email server (not shown) or a separate text message server (not shown) capable of processing text messages from a mobile communication company. ) to the corresponding manager terminal 300 , and the computing device 100 may collect or receive the processed information based on an email or text message transmitted to the corresponding manager terminal 300 .

Separately, the computing device 100 may collect the information stored in the electronic litigation court server 400 in a macro, crawling or API method, and the electronic litigation court server 400 is an electronic litigation court operated by the Ministry of Justice. In addition to the server that processes the , it may include all one or more servers that process information on legal cases in a legal institution.

Meanwhile, although FIG. 1 shows the user terminal 200 and the manager terminal 300 separately, in another embodiment of the present invention, the manager terminal 300 may be included in the user terminal 200, and In the same case, the subject using the user terminal 200 may include both a party to a case who wishes to request a corresponding target legal case and an administrator who manages the case or manages the computing device 100 .

In another embodiment of the present invention, as shown in (B) of FIG. 1 , the computing device 100 is located in a space to which an administrator including a subject providing legal services, such as a law office or a law firm, belongs. can be located In this case, the input interface may be displayed on the computing device 100 without including the separate user terminal 200 and the manager terminal 300 . Accordingly, the user or administrator directly transmits one or more case details about the target legal case to the computing device 100 through the input interface using a separate input device (not shown) included in the computing device 100 . can also be entered as

Figure 2 schematically shows the steps of providing a prediction result of a legal case including the first winning probability according to an embodiment of the present invention.

As shown in FIG. 2 , as a method of providing a prediction result of a legal case performed in a computing device 100 having one or more processors and one or more memories, the user is provided with one or more case details for a target legal case. an input interface providing step of providing an input interface (S10); a formalization step (S20) of deriving standardized input data having a plurality of values from the one or more event details received from a user; a winning probability deriving step (S30) of deriving first winning probability information by inputting the input formalized data into a machine-learning model; and a first prediction result providing step (S40) for providing a prediction result of a legal case including the first winning probability information to the user.

Specifically, in step S10, the computing device 100 provides the input interface to the user terminal 200 or the manager terminal 300, and the user or the manager is connected to the user terminal 200 or the manager terminal 300. According to the displayed input interface, one or more case details for a target legal case are input. Meanwhile, the user terminal 200 or the manager terminal 300 may transmit the received one or more event details to the computing device 100 .

Meanwhile, in another embodiment of the present invention, the input interface may be displayed on the computing device 100, and the input interface may be displayed through a separate input device (not shown) provided in the computing device 100 according to the input interface. One or more event details may be entered directly.

In step S20, input formalized data is derived from one or more case detailed information for the target legal case. The input formalized data may correspond to preset data or dataset that can be used as input data of an artificial intelligence-based model for deriving first winning probability information to be described later.

In step S30, the derived input formalized data is input to the artificial intelligence-based model, and the first winning probability information is derived through the model. Preferably, the model includes a machine learning-based trained model, and more preferably, the model may include one or more deep learning-based trained artificial neural network models. Meanwhile, the model may include a model trained based on machine learning as well as a model based on a rule, and the model may correspond to a form of using a learned model and a model based on a rule in combination.

The first probability of winning information includes quantitative probability information corresponding to 0 to 100% of the victory when the target legal case is a civil lawsuit, or when the target legal case is a legal case such as provisional seizure or administrative trial It may include quantitative citation probability information corresponding to 0 to 100% of the citation of the claim claimed by the party.

On the other hand, the first winning probability information includes information about the probability corresponding to 0 to 100%, as well as information on whether or not to win the corresponding target legal case or information on whether to cite the target legal case. It may include any form of information that can predict the outcome of

Meanwhile, in another embodiment of the present invention, the model may include a plurality of detailed models corresponding to a plurality of event categories. For example, 'Loan Incident', 'Trade Payment Incident', 'Service Expense Case', 'Lease Deposit Case', 'Commitment Money Incident', 'Investment Return Incident', 'Investment Profit Incident', 'Trade Payment Return Incident', ' A case in which a plurality of detailed models corresponding to each of the 'Unfair Profit Incident' and 'Wage (severance pay) case' can be included, and when one event category is selected from among the plurality of event categories in the first detailed input interface to be described later It is also possible to derive the first winning probability information through the detailed model corresponding to the category.

In step S40, the prediction result of the legal case including the first winning probability information derived through the machine-learning model is provided to the user. The prediction result of the legal case including the first winning probability information is not only simply providing the first winning probability information to the user, but also any information that can be provided to the user based on the first winning probability information. may contain information.

Specifically, if the first winning probability information is greater than or equal to the predetermined probability information, it may include information guiding the user to actually proceed with the target legal case, and if it is less than the predetermined probability information, an additional event to the user It may also include a request for details.

On the other hand, in another embodiment of the present invention, the prediction result of the legal case including the first winning probability information may include information for requesting the corresponding user to derive the false increase probability information to be described later.

The prediction result of the legal case including the first winning probability information may be provided to the user through the user terminal 200 or the manager terminal 300 of the user, in another embodiment of the present invention, the computing device The prediction result of the legal case including the first winning probability information is displayed through the display device provided in (100), and may be provided to the user.

Therefore, according to an embodiment of the present invention, the first winning probability is derived through a machine-learning model based on one or more case details for the target legal case input by the user and provided to the user, so that the user It is possible to recognize in advance the probability of winning a legal case of have.

3 schematically shows an input interface for event details according to an embodiment of the present invention.

As shown in FIG. 3 , the one or more case detailed information may include an input for a case category, detailed information input according to the corresponding case category, and evidence information.

Specifically, the computing device 100 provides an input interface to the user terminal 200, and the user terminal 200 displays the input interface to allow the user to obtain one or more case details for a target legal case. can be input.

On the other hand, in another embodiment of the present invention, the input interface is output through a display (not shown) provided separately in the computing device 100, and the computing device 100 uses a separately provided input device (not shown). Through this, a user or an administrator can receive one or more case details for a target legal case.

One or more case details about the target legal case received through the input interface may be used as input of an artificial intelligence-based model for deriving the first winning probability information. Preferably, the input formalized data is generated based on the one or more event details, and the input formalized data can be used as an input of an AI-based model.

Since each model corresponding to the case name (type of event) can be used for the items displayed on the input interface, 'case name (case type)' such as loan case, service cost case, purchase price case, rental deposit case, etc., contract date Since the relevant laws and precedents may differ depending on the 'contract date' and the court's judgment may change depending on the times, the probability of winning may differ depending on the 'application date' and the amount of the claim, so the 'claimed amount' , in addition to 'Date or date information on which money was to be returned', 'Contracted interest rate', 'Date or date of request for refund', 'Whether or not money was received', if there is money received, 'date of receipt' and Items for 'received amount' may be included.

Additionally, the input interface may include items for inputting evidence information. Evidence for 'passbook transfer details or transfer confirmation', 'borrowing certificate', 'messenger conversation history', 'transcript', 'content proof' and 'tax invoice' can be entered in the items that can input the above evidence information. Items may be included. Preferably, the evidence for the item is in the form of an electronic file, and may include all types of files that can be legally effective, such as electronic documents, moving pictures, audio and image files.

In addition, the input interface further includes an item for calculating the winning probability, and when receiving a request for confirmation of the winning probability after receiving one or more case detailed information for the above-described target legal case, the user terminal is computing Transmitting the request to the device, the computing device performs the first prediction result providing step (S40) according to the request, and transmits the prediction result of the legal case including the first winning probability information to the user terminal. Meanwhile, the prediction result of the transmitted legal case may be displayed on the input interface.

In the item for calculating the winning probability shown in FIG. 3, only a quantitative value for the first winning probability is displayed, but it is not limited thereto, and, like information about winning, it can be derived based on the first winning probability information All information may be displayed.

In addition, items displayed on the input interface shown in FIG. 3 correspond to items displayed when a loan event is selected, which is illustrated for ease of explanation, but is not limited thereto. Accordingly, in another embodiment of the present invention, additional additional items displayed when a loan event is selected may be displayed on the input interface, and in the case of items displayed when other events are selected, the input interface shown in FIG. 3 It may be displayed as items different from .

4 schematically illustrates a first detailed input interface included in the input interface for event detailed information according to an embodiment of the present invention.

In another embodiment of the present invention, the input interface shown in FIG. 3 includes a first detailed input interface and a second detailed input interface, and preferentially, the computing device 100 provides a plurality of The first detailed input interface for displaying the item is provided to the user through the user terminal 200 . When the user selects the case category corresponding to the target legal case from among the plurality of items for the case category displayed on the first detailed input interface, the computing device 100 connects the second detailed input interface to the user terminal 200 provided to the user through

Specifically, as shown in FIG. 4, the plurality of items for the event category include 'loan money event', 'sale price event', 'service cost event', 'rent deposit event', 'deposit case', and 'investment return event'. It may include 'cases', 'investment proceeds incident', 'trade return incident', 'unfair profit incident' and 'wage (severance pay) incident'.

Meanwhile, on the second detailed input interface, items for inputting detailed information and evidence information according to a corresponding case category included in the case detailed information are displayed. Preferably, the items displayed on the second detailed input interface may be configured differently depending on the type of the event category selected by the user in the first detailed input interface.

In another embodiment of the present invention, the input interface may be implemented in the form of a single interface. In this case, the first item in the interface is provided with items that can receive an input for an event category, and the user When a specific case category is input in , detailed information input and evidence information input items according to the case category may be displayed in subsequent items of the interface corresponding to the specific case category.

5 schematically illustrates a second detailed input interface included in the input interface for event detailed information according to an embodiment of the present invention.

The diagram shown in FIG. 5 corresponds to a diagram schematically illustrating a second detailed input interface for the 'loan money event' when the user selects 'loan money event' in the first detailed input interface shown in FIG. 4 .

Specifically, the second detailed input interface provides items for inputting detailed information and evidence information according to the corresponding case category selected by the user through the user terminal 200 .

As shown in FIG. 5, detailed information according to the event category includes 'date of loan', 'money loaned', 'interest rate', 'date to receive', 'whether or not to claim overdue interest', 'type of bond', ' You can include information on 'whether money was received', 'date received' and 'money received' if there is money received, 'whether or not billing amount is automatically calculated' and 'charge amount' if you wish to calculate the charge amount. have.

In Fig. 5, '3 million won' was loaned at 'annual interest rate of 10%' on 'March 1, 2019', and it was agreed to be received on 'September 1, 2019', and '50' on 'November 1, 2019' Only '10,000 won' was reimbursed, and '2,732,544 won', the billing amount calculated as of the application date by selecting 'auto calculation of billing amount', is entered as detailed information.

In addition, although not shown in FIG. 5, the second detailed input interface includes an element that can receive an input requesting a winning probability from a user and the first winning probability information derived by the input. Displayed items may be further included.

On the other hand, the input to the one or more case detailed information includes uploading a file for evidence related to a target legal case, and the input formatted data is based on one or more evidence capacity levels additionally input by the user with respect to the file for the evidence. may contain values for

Specifically, through the second detailed input interface, a user or an administrator may upload evidence information, preferably, a file of evidence for the corresponding target legal case, and additionally input the type of the uploaded file.

The file for the evidence may include all types of files that can be legally effective, such as electronic documents, videos, audio and image files, and the types of files uploaded include contracts, bankbook copies, and bankbook transfers. It includes details, deposit history, messenger conversation history, text message history, photos or related data on service completion, judgment, loan certificate, confirmation and tax invoice, etc.

Meanwhile, the second detailed input interface may additionally provide an item for allowing the user to input the evidence capability level of the file for the uploaded evidence. Specifically, the degree of evidence includes standardized values, such as 0 points, 1 points, 2 points, 3 points, 4 points, and 5 points, for example, and the user can arbitrarily according to the level of evidence of the uploaded file. , it is possible to select and input one value among the values of the 0 to 5 points. Meanwhile, the standardized value may consist of discontinuous values or continuous values as in the above example.

For example, when the user uploads an image file in which the bankbook transfer details are captured as a file for evidence, the user can determine the degree of identification according to the image quality and input a value for the level of evidence.

On the other hand, the value for the degree of evidence capability may be directly input by the user through the user terminal 200, but in another embodiment of the present invention, the administrator receives the value for the degree of evidence capability through the corresponding manager terminal 300. may be input, and as described above, even when case detail information is directly input from the computing device 100, the value for the degree of evidence capability may be input by the administrator.

The evidence capacity level includes one or more detailed evidence capacity levels, and a value for each level of detailed evidence capacity may be input by a user or an administrator. Preferably, each detailed evidence capacity level may include the evidence capacity level for the loaned money, the capacity level for the date of repayment and the level of evidence capacity for the interest rate, etc., and based on the uploaded evidence file, the user Alternatively, the administrator may input a value for each level of detailed evidence.

For example, if the user uploads the messenger conversation history as a file for evidence, and the amount of the loaned money is clearly included along with the contents of the loan, the value for the admissibility of the loaned money is 5 If the debtor's promise to repay is included but does not include the date of repayment, enter the value of the admissibility of evidence for the date of repayment as 3 points, and each You can enter a value for

Therefore, according to an embodiment of the present invention, the winning probability can be more accurately calculated because the first winning probability information is derived in consideration of the evidence capability of the file for the uploaded evidence, as well as whether the file is uploaded for the evidence. can have an effect.

On the other hand, in order to prevail in a legal case, the facts required for the legal case must be asserted and proven. For this purpose, the content and evidence related to the legal case must be structured so that the required facts according to the legal case can be clearly described. The items displayed in the second detailed input interface are configured to be

For example, in the case of a request for payment of a sale price that falls under one of the case categories, 'The plaintiff sent the defendant on October 1, 2003 (the date of the contract), The fact of the conclusion of the sale contract is a necessary fact as shown in the above example. ', relevant evidence is required.

Accordingly, the second detailed input interface for the transaction payment request case may be configured so that the user can input detailed event information for the above items.

Additionally, for example, in the case of a rental deposit case that falls under another one of the case categories, 'The plaintiff received a rental agreement from the defendant on January 1, 2002 (contract date), The rental deposit was set at KRW 50 million (the amount of the rental guarantee), and the rental period was set for two years (the rental period), and the rental deposit was paid. The fact that the lease has been terminated after payment is a necessary fact, and as in the above example, information such as the contract date, rental object, rental guarantee amount, rental period and reason for termination must be clearly stated, Relevant evidence corresponding to 'receipt' and 'proof of contents (notice of termination)' is required.

Accordingly, the second detailed input interface for the rental deposit case may be configured so that the user can input the case detailed information for the above items.

6 schematically shows the steps of providing a prediction result of a legal case including pseudo-increasing probability information according to an embodiment of the present invention.

As shown in FIG. 6 , generating ( S50 ) one or more modified input formalized data obtained by transforming one or more values of the input formalized data; and inputting the one or more modified input formalized data into the machine-learned model to derive one or more second winning probability information (S60); the prediction result of the legal case is the one or more second winning probability Includes pseudo-increasing probability information derived based on one or more of the information.

Specifically, the steps of providing a prediction result of a legal case including the pseudo-increasing probability information are a series of steps performed to provide an optimal method to a user or administrator in consideration of methods for increasing the probability of winning of the target legal case. corresponds to the steps of

Through the above-described step S20, the computing device 100 derives input formalized data having a plurality of values, and in step S50, one or more modified inputs obtained by transforming one or more values among a plurality of values in the input formalized data having a plurality of values. Generate standardized data. Preferably, the one or more values modified in step S50 correspond to values for one or more items that can be performed by a user or an administrator.

For example, if a value corresponding to the fact that a specific file for evidence is not uploaded is included in the input formatted data, the modified input formatted data is transformed into a value corresponding to that the specific file has been uploaded in step S50 can create As in the transformation of uploading a specific file that has not been uploaded as described above, the transformed input standardized data can be generated by transforming a value corresponding to an item that a user or an administrator can create and submit a specific file later.

In step S60, the one or more modified input formalized data is input to an artificial intelligence-based model, and second winning probability information is derived through the model. The artificial intelligence-based model may correspond to the artificial intelligence-based model used to derive the first winning probability information in step S30 described above.

On the other hand, the second winning probability information may be derived corresponding to the one or more modified input formalized data, respectively, and the second winning probability information corresponds to 0 to 100% for winning like the above-described first winning probability information. It may include quantitative winning probability information, or it may include information about the increase or decrease of the winning probability in comparison with the first winning probability information.

For example, in the loan case, on March 5, 2017, the plaintiff lent 10 million won to the defendant, did not stipulate a date to receive it, and claimed payment for the money lent on August 5, 2019; If only messenger conversation history exists as evidence for this, it is assumed that the first winning probability information for this is derived as 34%, and the above one or more modified input formalized data is transformed to have additional evidence for the borrowing certificate. , In the case where there is additional evidence on the transfer details for the loan of 10 million won, and when the loan amount is divided into several times and there is additional evidence for the loan, one or more transformations for each Input formalized data is generated, and second winning probability information according to each of the modified input formalized data may be derived as follows.

1) If it is modified to have additional evidence for the borrowing certificate, => probability of winning: 94% (increased by 60%)

2) In case there is additional evidence on the transfer history => Probability of winning: 84% (50% increase)

3) If the evidence that was lent over several times is transformed into an additional one, => Probability of winning: 30% (4% decrease)

In this way, the second winning probability information includes quantitative winning probability information corresponding to 0 to 100% and information on the increase or decrease of probability information in contrast to the first winning probability information based on each modified input formalized data. can

On the other hand, when the transformed input formalized data obtained by transforming a plurality of values of the input formalized data is generated, in step S60, second winning probability information for each of the plurality of values is derived, or based on all of the plurality of values Thus, the second winning probability information may be derived.

In step S70, a prediction result of a legal case including pseudo-increasing probability information derived based on the second winning probability information is generated and provided to the user.

The false ascending probability information includes the prevailing probability information predicted when some of the event details of the one or more event details input by the user are different.

Specifically, one or more event details input by the user are formalized, and one or more values in the input standardized data having a plurality of values for the one or more event details are different from the one or more event details input by the user. The artificial intelligence-based model derives second winning probability information based on the transformed input formalized data including one or more values, and the computing device 100 performs step S70 to include the second winning probability information to derive virtual ascending probability information.

Preferably, the false ascending probability information includes not only the second winning probability information, but also guide information for guiding the user or administrator with event details about the modified one or more values corresponding to the second winning probability information. may include more.

For example, if there is additional evidence for the borrowing certificate, the case detailed information is differently transformed to derive the second winning probability information, and when the second winning probability information is included in the virtual ascending probability information, the false ascending probability The information may further include guide information for additionally requesting upload of evidence information for the IOU.

On the other hand, in the step S70, false ascending probability information can be derived based on all the derived second winning probability information, and in another embodiment of the present invention, the highest winning probability among the derived one or more second winning probability information The virtual ascending probability information may be derived based on one or more second winning probability information up to a preset rank.

In addition, the false ascending probability information derived in step S70 is included in the prediction result of a legal case including the first winning probability information provided in step S40 described above in FIG. 2, the first winning probability information and the false ascending Probability information may be provided to the corresponding user at the same time.

In another embodiment of the present invention, the prediction result of the legal case including the first winning probability information through the step S40 is preferentially provided to the user, and the user is the user terminal 200 or directly the computing device 100 ), when a request for the prediction result of a separate legal case is inputted, the above-described steps S50 to S70 are performed, and the prediction result of a separate legal case including the pseudo-increasing probability information may be provided to the user. . In this embodiment, the user may include both the party to the case and the manager, and when the manager inputs a request for a prediction result of a separate legal case, the manager terminal 300 or the computing device 100 directly can be entered through

7 schematically shows the steps of providing a prediction result of a legal case including a third winning probability according to the update of the input formalized data according to an embodiment of the present invention.

As shown in FIG. 7 , in the method of providing the prediction result of the legal case, after the first prediction result providing step, the input formalized data is updated according to the counterpart's response or the user's response to the target legal case. step (S80); deriving third winning probability information by inputting the updated input formalized data into the machine-learned model (S90); And it includes a third prediction result providing step (S100) for providing the prediction result of the legal case including the third winning probability information to the user.

Specifically, the third winning probability information is after the first prediction result providing step is performed, that is, according to one or more case detailed information input by the user, the lawsuit of the target legal case is sent to the court or the electronic litigation court server 400 . It corresponds to the prevailing probability information derived according to the response of the user (plaintiff) or the other party (defendant) to the relevant legal case after receiving the case.

As such, when the relevant documents are submitted as the mutual correspondence is made while the trial is continuously proceeding, the probability of winning may be changed according to each response, and the third winning probability information is the probability of winning according to the mutual correspondence. Since it includes the winning probability information that considers the change, it is possible to exert the effect that the user can recognize the change in the winning probability according to the response.

In step S80, the input formatted data is updated according to the response of the counterpart (defendant) or the response of the user (plaintiff) with respect to the target legal case.

The counterpart's response includes a file of one or more documents or evidence submitted by the other party to the court or the electronic litigation court server 400, and a statement or assertion through pleading in a trial, and the user's response includes the other party's response. In addition to the response to the response, it includes the submission of additional documents or evidence for the subject legal case.

Meanwhile, information related to the counterpart's correspondence and the user's correspondence is transmitted to the computing device 100 by the corresponding user or administrator through the user terminal 200 or the administrator terminal 300 or the computing device 100 It can also be entered directly.

In another embodiment of the present invention, the computing device 100 may receive or collect information related to the counterpart's response and the user's response to the corresponding target legal case directly from the electronic litigation court server 400 . . In this embodiment, the electronic litigation court server 400 stores the information on the corresponding target legal case, so the computing device 100 uses the crawling method, the API method, or the macro method to the electronic litigation court server 400 . ) can receive or collect information related to the counterpart's response to the corresponding target legal case and the user's response stored in the .

On the other hand, in a legal case, information related to the counterpart's response and the user's response is generally responded to by sending a standardized answer including a claim or evidence related to the response to the electronic litigation court server 400 . Accordingly, the computing device 100 may automatically analyze the answer received from the user or administrator or the answer to the corresponding target legal case received or collected from the electronic litigation court server 400 .

More specifically, the computing device 100 performs a character reading step of reading the characters included in the reply, such as an optical character recognition (OCR) method, and based on the read characters, the corresponding Execute the response analysis step to analyze the contents of the response. The answer analysis step can analyze the contents of the answer by inputting the read characters into an artificial intelligence-based model, preferably, the model is one or more deep learning-based trained artificial neural network models or a rule-based model. may include.

Meanwhile, in step S80, the input formatted data may be updated based on the contents of the corresponding answer derived by performing the answer analysis step.

In step S90, the updated input formalized data is input to an artificial intelligence-based model, and third winning probability information is derived through the model. The AI-based model may correspond to the AI-based model used in steps S30 and S60 described above.

On the other hand, the third winning probability information may be repeatedly derived based on the input standardized data updated whenever the counterpart (defendant) or user (plaintiff) responds to the target legal case. In addition, the third winning probability information includes information on the winning probability corresponding to 0 to 100%, as well as information on whether or not to win the target legal case or information on whether to cite the target law. It may include any form of information that can predict the outcome of an event.

In step S100, a prediction result of a legal case including the derived third winning probability information is provided to the user. Since the prediction result of the legal case derived in step S100 is provided separately after providing the user with the prediction result of the legal case including the first winning probability information performed in the above-described step S40, the prediction of each legal case Results may be different.

On the other hand, the prediction result of the legal case including the third winning probability information is not only simply providing the third winning probability information to the user, but also how much the probability of winning is increased or decreased compared with the first winning probability information. Information that can be provided to the corresponding user based on the third winning probability information, such as information on information about or comparison information about the second winning probability information and the third winning probability information similar to the counterpart or user's response. can

On the other hand, the artificial intelligence-based model includes one or more deep learning-based learned artificial neural network models or rules-based models for winning probabilities according to one or more types of protests that the opponent or user can respond to according to the event category. Third winning probability information can be derived.

For example, in the case of a request for payment of a sale price that falls under one of the case categories, the plaintiff told the defendant on October 1, 2003 (the contract date) that he received 1 billion won in gold from Hyundai Apartment Building A, Room B (object) in Seocho-dong, Seocho-gu, Seoul. The other party (defendant) responds to the fact that the sale contract was concluded, 'at the price of the sale.' It is possible to perform a response including a response to a specific item among the 'responses of ', and the artificial intelligence-based model derives third winning probability information for this.

Afterwards, when the user (plaintiff) with respect to the objection of the opponent (defendant) performs a response including a re- defense for a specific item among the midstream of the above-mentioned defense, the artificial intelligence-based model additionally wins the third Probability information is derived.

Therefore, according to an embodiment of the present invention, since the winning probability according to the correspondence between the other party and the user is continuously derived and provided to the user for a legal case, it is possible to exert the effect of providing a quality legal service.

8 schematically shows input normalized data according to an embodiment of the present invention.

The input standardized data shown in FIG. 8 includes a plurality of standardized values for each case detail information based on one or more case details for a target legal case input from a user. In the input standardized data shown in FIG. 8, one row corresponds to one target legal case, and includes a standardized value of one or more detailed case information for a total of 31 target legal cases.

On the other hand, as shown in FIG. 8 , the input formalized data is included in one of the input formalized data by accumulating each target legal case, but in another embodiment of the present invention, individual input for each target legal case Standardized data may be derived.

Specifically, 'CaseTitle' corresponding to the first column in FIG. 8 corresponds to a value for an event category. Case 1 is a loan case, Case 2 is a transaction price case, Case 3 is a service expense case, Case 4 is a rental deposit case, Case 5 is a deposit case, Case 6 is an investment return case, Case 7 is an investment profit case, Case 8 is a transaction refund case, Case 9 is an unfair profit case Case and Case10 correspond to wage cases, and CaseTitle values corresponding to the case category information entered by the user for the target legal case are derived.

'Amount' corresponding to the second row corresponds to the value of the billed amount among the detailed information according to the relevant case category. The billing amount entered by the user as the case detail information is derived from the corresponding row.

'LME' corresponding to the third row corresponds to the value of money paid (loaned) by the user among the detailed information according to the relevant event category. When the user enters the amount of money paid as the event detail information, '1', which is a value corresponding to the payment, is derived. A value of '0' may be derived.

'DDE' corresponding to the fourth row corresponds to the value of the date that the user decided to receive among the detailed information according to the relevant event category. If the user enters the date information for the date of receipt as the event detail information, a value of '1' corresponding to the date of receipt is derived, and if the date of receipt is not entered or entered as none, A value of '0', which is a value corresponding to no date of receipt, may be derived.

'RDE' corresponding to the fifth row corresponds to the value of the requested date among the details according to the relevant case category. If the user inputs date information on the requested date as the case detail information, '1', which is a value corresponding to the existence of the requested date, is derived. A value of '0' corresponding to the absence of '0' may be derived.

'PDE' corresponding to the sixth row corresponds to the value of money received among the details according to the relevant case category. When the user enters the amount of money received as the case detail information, a value of '1' corresponding to the presence of received money is derived. A value of '0' corresponding to no money received may be derived.

Meanwhile, in another embodiment of the present invention, the values corresponding to 'LME', 'DDE', 'RDE', and 'PDE' described above are not derived as values for presence or absence, but amount or date for each item. A value for can be derived, and in this case, the AI-based model can determine a value such as '1' as described above when an amount or a date is derived. Therefore, in this embodiment, it is possible to derive the winning probability more accurately, such as considering that the winning probability fluctuates according to the amount of money.

'E1' to 'E4' corresponding to the seventh to tenth rows correspond to values for each evidence information according to the corresponding case category. More specifically, 'E1' to 'E4' correspond to values for the presence or absence of preset evidence items such as contracts, bank transfer details, messenger conversation details, and pictures of service completion, If uploaded, '1' is derived, and if not uploaded, '0' is derived. The number of evidence items shown in FIG. 8 is only an exemplary embodiment, and may vary according to the number of evidence items that can be uploaded for a corresponding target legal case.

On the other hand, in another embodiment of the present invention, 'E1' to 'E4' may be derived values for the degree of evidence capability of a preset evidence item. For example, when evidence related to an image is uploaded, a standardized value such as 0 to 5 may be derived as a value for the degree of evidence capability according to the degree of identification according to the image quality. Meanwhile, the value for the degree of evidence may be directly input by a user or an administrator.

Finally, 'Output' corresponding to the eleventh row corresponds to the value of whether or not the target legal case prevails. The item is not entered at the beginning of the case, but can be derived when the judgment result of the case is finally released. In case of winning the relevant legal case, '1' is derived, and in case of loss, '0' is derived. The corresponding item is inputted by the user or administrator after the judgment result is released, and the input formatted data is updated, or the input formatted data is updated by receiving or collecting the judgment result of the target legal case from the electronic litigation court server 400 can be

As shown in FIG. 8 , the above-described modified input formalized data can be generated by transforming one or more values in input formalized data having a plurality of standardized values for one or more event details, and can respond to the counterpart or user. The input formalization data can be updated according to the following claims or evidence.

On the other hand, the input formalized data is used as an input to the above-described artificial intelligence-based model, the artificial intelligence-based model can derive the first winning probability information. In addition, the input formalized data may be used as an input for training the AI-based model or as an input for testing the model.

In addition, existing precedents may consist of a dataset having a plurality of standardized values, such as the configuration of the input formalized data shown in FIG. 8, and the dataset will be used as an input for learning an AI-based model. can As for the dataset for the existing precedent, the administrator directly transmits the dataset to the computing device 100 , or the administrator inputs event details about the existing precedent, and the computing device 100 forms a dataset in the form of a dataset. You can also create

On the other hand, the configuration of the input formatted data shown in FIG. 8 corresponds to a form for easy explanation, and the input formatted data may be configured in various ways according to the type of event category, the type and number of detailed information according to the event category, etc. can

In addition, as shown in FIGS. 2 to 8 , the computing device 100 in which steps for providing a prediction result of a legal case are performed, for the purpose of simply deriving a prediction result of a legal case, the above steps and Only the steps described below can be performed, but in another embodiment of the present invention, the computing device 100 performs the step S10 and provides one or more case details for the target legal case input through the input interface provided to the user. Separate steps for managing the target legal case are performed according to the information, and the steps shown in FIGS. 2 to 8 may be included in the separate steps.

9 schematically illustrates an internal configuration of a computing device according to an embodiment of the present invention.

The server system including the computing device 100 shown in FIG. 1 and one or more computing devices 100 may include the components of the computing device shown in FIG. 9 .

9, the computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( I/O subsystem) 11400 , a power circuit 11500 , and a communication circuit 11600 may be included at least. In this case, the computing device 11000 may correspond to the computing device 100 illustrated in FIG. 1 or a server system including one or more computing devices 100 .

The memory 11200 may include, for example, a high-speed random access memory, a magnetic disk, an SRAM, a DRAM, a ROM, a flash memory, or a non-volatile memory. have. The memory 11200 may include a software module, an instruction set, or other various data required for the operation of the computing device 11000 .

In this case, access to the memory 11200 from other components such as the processor 11100 or the peripheral device interface 11300 may be controlled by the processor 11100 .

Peripheral interface 11300 may couple input and/or output peripherals of computing device 11000 to processor 11100 and memory 11200 . The processor 11100 may execute a software module or an instruction set stored in the memory 11200 to perform various functions for the computing device 11000 and process data.

The input/output subsystem may couple various input/output peripherals to the peripheral interface 11300 . For example, the input/output subsystem may include a controller for coupling a peripheral device such as a monitor or keyboard, mouse, printer, or a touch screen or sensor as required to the peripheral interface 11300 . According to another aspect, input/output peripherals may be coupled to peripheral interface 11300 without going through an input/output subsystem.

The power circuit 11500 may supply power to all or some of the components of the terminal. For example, the power circuit 11500 may include a power management system, one or more power sources such as batteries or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or a power source. It may include any other components for creation, management, and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, if necessary, the communication circuit 11600 may transmit and receive an RF signal, also known as an electromagnetic signal, including an RF circuit, thereby enabling communication with other computing devices.

This embodiment of FIG. 9 is only an example of the computing device 11000, and the computing device 11000 may omit some components shown in FIG. 9 or further include additional components not shown in FIG. 9, or 2 It may have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. 9 , and may include various communication methods (WiFi, 3G, LTE) in the communication circuit 11600 . , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 11000 may be implemented in hardware, software, or a combination of both hardware and software including an integrated circuit specialized for one or more signal processing or applications.

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. The application to which the present invention is applied may be installed in the user terminal through a file provided by the file distribution system. As an example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to a request of the user terminal.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computing devices, so that it may be stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

According to an embodiment of the present invention, the user inputs one or more case details for a target legal case that the user wants to proceed, and derives the first winning probability through a machine-learning model according to the input one or more case detailed information. Since it is provided to the user, the user can exert the effect of recognizing the probability of winning in advance in his or her legal case.

According to an embodiment of the present invention, the prediction result of the legal case including the first probability of winning provided to the user is a substitute for examining the validity of the legal case through consultation with a legal expert in the existing legal service. Therefore, the cost of legal services can be lowered and the quality of legal services can be improved.

According to an embodiment of the present invention, the case detailed information input by the user includes a file of evidence related to a target legal case, and finally derives a standardized value according to the degree of evidence capability for the file for the corresponding evidence. Since the first probability of winning is derived, it is possible to exert the effect of more accurately deriving the probability of winning according to the degree of evidence capacity of the file for evidence.

According to an embodiment of the present invention, transformed input formalized data is generated by transforming one or more input formalized data derived through the formalization step, and a second winning probability is derived based on the transformed input formalized data and provided to the user Therefore, it is possible to exert the effect that the user can be provided with a method to improve the probability of winning the target legal case.

According to an embodiment of the present invention, when a response is made according to the legal procedure for the target legal case, the input formalized data is updated according to the corresponding response, and the third winning probability is derived based on the updated input formalized data and provided to the user, it is possible to exert the effect of providing the user with the result of the prediction of the judgment of the target legal case in accordance with the legal response in real time.

According to an embodiment of the present invention, since it is provided to the user by predicting the possibility of winning the target legal case in advance, it is possible to significantly lower the cost of legal services and to prevent in advance the number of legal cases with high validity. Therefore, it is possible to exert the effect of providing high-quality services for the legal cases that the lawyer is entrusted with.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (8)

A method of providing a prediction result of a legal case performed on a computing device having one or more processors and one or more memories, the method comprising:
an input interface providing step of providing an input interface for one or more case details of a target legal case to a user online;
a formalization step of deriving input formalized data having a plurality of values from the one or more event detailed information received online from a user;
The winning probability of deriving the first winning probability information by inputting the input formalized data into a machine-learning model that can provide a winning probability through information including one or more event details received through the online-based input interface derivation step; and
A first prediction result providing step of providing a prediction result of a legal case including the first winning probability information to the user;
The method of providing the prediction result of the legal case,
generating one or more modified input formalized data including one or more values obtained by transforming one or more values in the input formalized data to be different from one or more event detailed information input by a user; and
Further comprising; inputting the one or more modified input formalized data into the machine-learned model to derive one or more second winning probability information;
The prediction result of the legal case includes virtual ascending probability information derived based on one or more of the one or more second winning probability information,
One or more values transformed in the step of generating the modified input formalized data are values for one or more items that the user or the manager who manages the target legal case can submit later among the one or more values in the input formalized data. applicable,
The method of providing the prediction result of the legal case,
updating the input formatted data according to a counterpart's response or a user's response as the trial on the target legal case proceeds after the first prediction result providing step;
deriving third winning probability information by inputting the updated input formalized data into the machine-learned model; and
A method of providing a prediction result of a legal case further comprising; a third prediction result providing step of providing the prediction result of the legal case including the third winning probability information to the user.
The method according to claim 1,
The one or more case detailed information includes an input for a case category, detailed information input according to the corresponding case category, and evidence information, a method of providing a prediction result of a legal case.
The method according to claim 1,
The input of the one or more case details includes uploading a file for evidence related to the target legal case,
The method of providing a prediction result of a legal case, wherein the input standardized data includes standardized grade information about the file for the evidence.
delete delete delete The method according to claim 1,
The input of the one or more case details includes uploading a file for evidence related to the target legal case,
The method of providing a predictive result of a legal case, wherein the input formalized data includes a value for one or more degree of evidence capacity additionally input by a user with respect to the file for the evidence.
A computer-readable medium for implementing a method for providing a predictive result of a legal case performed on a computing device comprising one or more processors and one or more memories storing instructions executable in the processor, the method comprising:
an input interface providing step of providing an input interface for one or more case details of a target legal case to a user online;
a formalization step of deriving input formalized data having a plurality of values from the one or more event detailed information received online from a user;
The winning probability of deriving the first winning probability information by inputting the input formalized data into a machine-learning model that can provide a winning probability through information including one or more event details received through the online-based input interface derivation step; and
A first prediction result providing step of providing a prediction result of a legal case including the first winning probability information to the user;
The computer-readable medium comprises:
generating one or more modified input formalized data including one or more values obtained by transforming one or more values in the input formalized data to be different from one or more event detailed information input by a user; and
Further comprising; inputting the one or more modified input formalized data into the machine-learned model to derive one or more second winning probability information;
The prediction result of the legal case includes virtual ascending probability information derived based on one or more of the one or more second winning probability information,
One or more values transformed in the step of generating the modified input formalized data are values for one or more items that the user or the manager who manages the target legal case can submit later among the one or more values in the input formalized data. applicable,
The computer-readable medium comprises:
updating the input formatted data according to a counterpart's response or a user's response as the trial on the target legal case proceeds after the first prediction result providing step;
deriving third winning probability information by inputting the updated input formalized data into the machine-learned model; and
A third prediction result providing step of providing a prediction result of a legal case including the third winning probability information to the user; further comprising, a computer-readable medium.

Images