KR102549230B1 - Method, apparatus and program for providing attorney work analysis service using ai-based big data analysis - Google Patents

Abstract

Disclosed is a method of providing a lawyer's work analysis service through artificial intelligence-based big data analysis according to various embodiments of the present invention. The method includes: obtaining attorney work data from a lawyer work support platform; Acquiring big data of lawyer work by pre-processing the lawyer work data through a pre-learned neural network model; Generating analysis information based on the lawyer's business big data; and providing the analysis information to at least one lawyer through the lawyer service support platform, wherein the pretrained neural network model may include a data conversion model that converts unstructured data into structured data.

Description

Lawyer business analysis service provision method, apparatus and program through artificial intelligence-based big data analysis

The present invention relates to a method, apparatus, and program for providing a lawyer's business analysis service through artificial intelligence-based big data analysis, and more specifically, to a service that collects lawyer's business data and provides various analysis information based thereon.

Lawyers are sharing various representations according to limitations such as travel distance or business hours for business processing. For example, a lawyer may obtain a proxy to attend a trial in a district court far from his office and conduct business. In addition, various tasks are shared, such as interview agency, investigation agency, investigation participation agency, record copying agency, content certification preparation agency, and written agency agency.

In this way, despite the fact that there are many cases in which work needs to be shared between lawyers, there is no special method and system for finding a lawyer who is located in the region and will perform the proxy work. For example, in the prior art, when a lawyer seeks a legal representation, a lawyer in the vicinity of each district court makes a direct call to inquire about the possibility of representation.

Therefore, there is a demand for a platform capable of sharing various lawyer services in the industry. In addition, if an analysis service for lawyer work is provided on a platform that can share lawyer work, it is expected that a platform service with higher satisfaction can be provided.

Regarding lawyer work support service, Patent Publication No. 10-2012-0123001 discloses a system and method for mediating legal work such as litigation through the Internet.

The present invention has been devised in response to the above background art, and is intended to provide a lawyer business analysis service through a lawyer business support platform service.

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

According to an embodiment of the present invention for solving the above problems, a method for providing a lawyer's business analysis service through artificial intelligence-based big data analysis is disclosed. The method includes: obtaining attorney work data from a lawyer work support platform; Acquiring big data of lawyer work by pre-processing the lawyer work data through a pre-learned neural network model; Generating analysis information based on the lawyer's business big data; and providing the analysis information to at least one lawyer through the lawyer service support platform, wherein the pretrained neural network model may include a data conversion model that converts unstructured data into structured data.

In an alternative embodiment, the legal practice data includes first text data, image data, video data, and audio data, and the neural network model comprises a first neural network for extracting text from the image data or the video data. Model; and a second neural network model for extracting text from the voice data.

In an alternative embodiment, the step of preprocessing the lawyer work data through the pre-learned neural network model to obtain the lawyer work big data, when the lawyer work data is composed of the image data, the video data, or the audio data. , obtaining second text data by inputting the lawyer work data into any one of the first neural network model and the second neural network model, wherein the lawyer work big data includes the first text data data and the second text data.

In an alternative embodiment, the generating of the analysis information based on the lawyer's practice big data may include generating a plurality of data sets corresponding to a preset time unit based on an initial creation time of the data; and generating a scenario group by grouping the plurality of data sets according to event types, and the analysis information may include the scenario group.

In an alternative embodiment, the step of grouping the plurality of data sets by event type and generating a scenario group may include recognizing evaluation information of the event or result information of the event for generating the scenario group. ; and generating the scenario group when the evaluation information of the event is equal to or higher than a preset score or when the result of the event corresponds to a preset result as a positive result.

In an alternative embodiment, the step of providing the analysis information to at least one lawyer through the lawyer work support platform, when a request for confirmation of work order for a specific case is received through the lawyer work support platform, the specific case recognizing a specific scenario group corresponding to; Recognizing the current processing status of the specific case; recognizing a first data set corresponding to a current processing state of the specific event in the specific scenario group; recognizing a second data set corresponding to a second time unit that is a time unit following the first time unit corresponding to the first data set; and providing the second data set in the next order of work.

In an alternative embodiment, the method may include receiving precedent data including a decision result from an external server; extracting, as precedent keywords, words appearing more than a predetermined number of times among words included in the precedent data; recognizing a specific field of the case based on the precedent keyword; Transmitting the precedent data to a terminal of a lawyer whose professional field previously set on the lawyer business support platform is the same as the specific field; Receiving an additional keyword from at least one terminal presetting the same specialized field as the specific field; generating training data for training a decision result prediction model using the precedent data, the decision result, the precedent keyword, and the additional keyword; and training the decision result prediction model using the training data, wherein the decision result prediction model is trained to output a prediction result for the specific event when a keyword related to the specific event is input. It can be.

In an alternative embodiment, the method may further include receiving a request for predicting an outcome of the specific case through the attorney practice support platform; obtaining a prediction result for the specific event by inputting information on the specific event into the decision result prediction model; and providing the prediction result through the lawyer work support platform.

In an alternative embodiment, the method may further include receiving case law data including legal costs from an external server; extracting, as precedent keywords, words appearing more than a predetermined number of times among words included in the precedent data; generating training data for training a legal cost prediction model using the legal cost and the precedent keyword; and training the legal cost prediction model using the learning data, wherein the legal cost prediction model is trained to output a predicted cost for the specific case when a keyword for the specific case is input. It can be.

In an alternative embodiment, the method may further include receiving a cost estimate request for a particular case through the attorney practice support platform; obtaining a predicted cost for the specific case by inputting information on the specific case into the legal cost prediction model; and providing the predicted cost through the lawyer work support platform.

In an alternative embodiment, the step of providing the analysis information to at least one lawyer through the attorney business support platform includes: receiving a reading request signal for the analysis information from the terminal of the attorney requesting reading; Recognizing the use level of the reading request lawyer; And based on the usage level, outputting at least a portion of the analysis information or the entirety of the analysis information from the terminal of the reading request lawyer; may include.

In an alternative embodiment, the usage level includes at least one of a first subscription level that allows viewing of the entire content of the analysis information and a second subscription level that allows viewing of part of the content of the analysis information, and the second subscription level A user of may be requested to pay additionally if he/she wants to view the entire contents of the analysis information.

In an alternative embodiment, the lawyer service support platform obtains multiple attorney entrusted tasks, posts the multiple attorney entrusted tasks, obtains an intention to accept a specific task from at least one attorney terminal, and performs the task. Obtaining a score value of each of the at least one lawyer by inputting the specific task to a neural network model pretrained to output a score value proportional to suitability, and corresponding to the highest value among the score values of each of the at least one lawyer An attorney may be determined as an entrusted attorney, and the specific task may be matched to the entrusted attorney.

According to one embodiment of the present invention for solving the above problems, an apparatus is disclosed. The device includes: a memory for storing one or more instructions; and a processor that executes the one or more instructions stored in the memory, wherein the processor executes the one or more instructions to perform the methods described above.

According to one embodiment of the present invention for solving the above problems, a computer program stored in a computer-readable recording medium to perform the above methods by being combined with a computer as hardware is disclosed.

Other specific details of the invention are included in the detailed description and drawings.

The method, apparatus, and program for providing a lawyer's work analysis service through artificial intelligence-based big data analysis of the present invention can provide analysis information on various work of a lawyer.

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

1 is a diagram illustrating a system according to an embodiment of the present invention.
2 is a hardware configuration diagram of a computing device according to an embodiment of the present invention.
3 is a schematic diagram showing a network function according to an embodiment of the present invention.
4 is a flowchart illustrating a process of a lawyer work support platform service according to an embodiment of the present invention.
5 and 6 are flowcharts for explaining an example of a method of providing a service support platform service of a lawyer of the present invention.
7 and 8 are flowcharts for explaining an example of a method of providing a lawyer's business analysis service through artificial intelligence-based big data analysis of the present invention.
9 and 10 are flowcharts for explaining various examples of a method of providing a lawyer's business analysis service through artificial intelligence-based big data analysis of the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and "units" or "modules" may be combined into smaller numbers of components and "units" or "modules" or may be combined into additional components and "units" or "modules". can be further separated.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least a part of each step may be performed in different devices according to embodiments.

Due to the nature of the lawyer's work, it is necessary to find a sub-representative (attorney) to attend the trial of each district court located far from each office, or to find a lawyer who can perform tasks in a remote place such as interview agency, investigation agency, investigation participation agency, etc. often do In addition, there are many cases in which collaboration between lawyers is necessary depending on the location, field of expertise, and workload, such as finding a lawyer who will perform paperwork such as record copying, content certification preparation, and document preparation.

However, in this case, there is no special means to find a lawyer to act as an agent, so lawyers find lawyers near each district court and make inquiries by phone or through internet bulletin boards, SNS, messengers, etc. is in need of finding.

Accordingly, the present invention proposes a lawyer work sharing platform service using a smartphone application to solve the problems of the existing work method. According to the present invention, it is possible to match an attorney who wants to delegate agency work with an attorney who wants to take over, and to easily negotiate costs and trade services.

In addition, by using the service proposed according to the present invention, data necessary for work can be safely and conveniently shared, and work performance results can be inspected and supplemented through feedback. It is possible to provide a safe payment service that pays for expenses without delay or omission through the cache.

Furthermore, by using the service proposed according to the present invention, you can easily check, manage, and share the progress of your work, provide timely information necessary for your work, safely store your work history and related data, You can conveniently search for the information you need.

In addition, it is possible to provide various convenient services required for business operations, such as searching for legal documents, reading documents, and authenticating digital evidence, so that not only the delegation of agency business but also the overall business performance can be performed on the service proposed according to the present invention.

Through this, in the present invention, various data generated according to service execution can be collected. When data is collected above a certain level, various functions can be developed and services can be provided using big data analysis techniques.

Furthermore, it is possible to acquire AI models that can be used for legal services by learning various AI models based on the collected data. For example, a model capable of presenting a legal strategy, predicting the winning rate and expected risk, and predicting litigation costs may be provided.

Through this, the service according to the present invention can be developed into a comprehensive legal platform, and based on this, it can be expanded to various affiliate businesses and service platforms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating a system according to an embodiment of the present invention.

Referring to FIG. 1 , a system according to an embodiment of the present invention may include a computing device 100 , a lawyer terminal 200 and an external server 300 .

Here, the system shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added, changed, or deleted as necessary.

According to one embodiment, the computing device 100 may be a server for providing a platform service for supporting lawyer work. Computing device 100 may include any type of computer system or computer device, such as, for example, microprocessors, mainframe computers, digital processors, portable devices and device controllers, and the like. However, it is not limited thereto.

The terms "entrusted person", "entrusted attorney" and "entrusted attorney" used in the following description are used interchangeably in consideration of only the ease of preparation of the specification, and do not have a meaning or role distinct from each other by themselves, and do not have a distinct meaning or role, and the lawyer of the present invention It may refer to a user who provides lawyer work on the business support platform.

In addition, the terms “mandator,” “entrusted attorney,” and “entrusted attorney” used in the following description are used interchangeably in consideration of only the ease of writing the specification, and do not have a meaning or role that are distinct from each other in themselves, and do not have a distinct meaning or role in the present invention. It may refer to a user who handles the lawyer service provided by the platform for supporting the lawyer service of .

In one embodiment, the computing device 100 may provide a lawyer's work sharing service when providing a lawyer's work support platform service.

Specifically, a delegator who wishes to delegate work may register idle work, which is a lawyer's work to be entrusted to another lawyer, through the attorney's work support platform. On the other hand, a person in charge who wants to accept a task can search for shared tasks through the platform, and can apply for the task they want to accept. If a mandate has applied for a task, the mandator may review the applicant's information and select a mandate to delegate the dual task. The selected mandate can decide whether to accept the sharing of work.

More specifically, the computing device 100 may acquire a plurality of attorney entrusted tasks (or idle tasks) from a plurality of attorneys (or delegators) registered in the attorney task support platform. In addition, the computing device 100 may post a plurality of lawyer entrusted tasks to the lawyer task support platform, and obtain an intention to accept a specific task from at least one attorney terminal. In addition, the computing device 100 obtains a score value of each of the at least one lawyer by inputting a specific task to a neural network model assigned to each of the at least one lawyer and pretrained to output a score value proportional to suitability for performing the job. can In addition, the computing device 100 may determine an attorney corresponding to the highest value among the score values of each of the at least one attorney as an entrusted attorney (or an entrusted person), and match the specific task to the entrusted attorney.

Meanwhile, when matching between the delegator and the entrusted person is completed, task information may be shared with the matched entrusted person. The entrusted person performs the delegated tasks, and the entrusted person can inspect the completed tasks. When the inspection by the entrusting person is completed, the cost settlement for the work may be provided to the entrusting person.

Hereinafter, an example of a method for the computing device 100 to provide a lawyer's work sharing service through a lawyer's work support platform service will be described later with reference to FIGS. 4 to 6 .

In addition, a description of the network function constituting the neural network model mentioned in the present invention will be described later with reference to FIG. 3 .

In various embodiments, the computing device 100 may provide a lawyer's business analysis service when providing a lawyer's business support platform service.

Specifically, the computing device 100 may obtain attorney work data from a lawyer work support platform. In addition, the computing device 100 may obtain lawyer business big data by pre-processing the lawyer business data through a pre-learned neural network model. In addition, the computing device 100 may generate analysis information based on lawyer business big data. In addition, the computing device 100 may provide analysis information to at least one lawyer through a lawyer business support platform.

Hereinafter, an example of a method in which the computing device 100 provides a lawyer's business analysis service through the lawyer's business support platform service will be described later with reference to FIGS. 7 and 8 .

In one embodiment, the computing device 100 may be connected to the lawyer terminal 200 through the network 400, and a web or application for providing a lawyer business support platform to the lawyer terminal 200 based services can be provided. However, it is not limited thereto.

Specifically, the computing device 100 may provide a lawyer business support platform web or a lawyer business support platform application accessible from the lawyer terminal 200 . Here, the attorney terminal 200 may include, for example, various types of computer devices. For example, the attorney terminal 200 may refer to various terminal devices such as smart phones, tablet PCs, desktops, and laptops.

The lawyer terminal 200 includes a display on at least a portion of the lawyer terminal 200 and may include an operating system for driving an application or extension program-based service provided from the computing device 100 . For example, the lawyer terminal 200 may be a smart phone (Smart-phone), but is not limited thereto, and the lawyer terminal 200 is a wireless communication device that ensures portability and mobility, navigation, 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 (Wireless Broadband Internet) terminal, smart pad (Smartpad), tablet PC (Tablet PC), and all kinds of handheld-based wireless communication devices can include

The network 400 may refer to a connection structure capable of exchanging information between nodes such as a computing device, a plurality of terminals, and servers. For example, the network 400 includes a local area network (LAN), a wide area network (WAN), a world wide web (WWW), a wired and wireless data communication network, a telephone network, a wired and wireless television communication network, and the like. do.

Wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet (Internet), LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth (Bluetooth) network, NFC (Near- Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

In one embodiment, the external server 300 may be connected to the computing device 100 through the network 400 and allow the computing device 100 to transmit/receive various information/data required to provide a lawyer business support platform service. and store and manage various types of information/data generated as the computing device 100 provides services.

For example, the external server 300 may be a server of a national institution (eg, the Supreme Court) that provides information (eg, precedent) used in a lawyer business support platform. For another example, the external server 300 may be a server of a law firm or a law office that provides information about lawyers used in a lawyer business support platform or lawyer consignment business.

Hereinafter, with reference to FIG. 2 , the hardware configuration of the computing device 100 will be described.

2 is a hardware configuration diagram of a computing device according to an embodiment of the present invention.

Referring to FIG. 2, a computing device 100 according to an embodiment of the present invention includes one or more processors 110 and a memory 120 that loads a computer program 151 executed by the processor 110. , a bus 130, a communication interface 140, and a storage 150 for storing the computer program 151. Here, in FIG. 2, only components related to the embodiment of the present invention are shown. Therefore, those skilled in the art to which the present invention pertains can know that other general-purpose components may be further included in addition to the components shown in FIG. 2 .

The processor 110 controls the overall operation of each component of the computing device 100 . The processor 110 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present invention. It can be.

Also, the processor 110 may perform an operation for at least one application or program for executing a method according to embodiments of the present invention, and the computing device 100 may include one or more processors.

In various embodiments, the processor 110 may temporarily and/or permanently store signals (or data) processed in the processor 110 (RAM: Random Access Memory, not shown) and ROM (ROM: Read -Only Memory, not shown) may be further included. In addition, the processor 110 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

The bus 130 provides a communication function between components of the computing device 100 . The bus 130 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the computing device 100 . Also, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may include a communication module well known in the art. In some embodiments, communication interface 140 may be omitted.

The storage 150 may non-temporarily store the computer program 151 . When the detailed diagnosis module proposal process is performed through the computing device 100, the storage 150 may store various types of information required to perform analysis according to the disclosed embodiment.

The storage 150 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or the like, a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 151 may include one or more instructions that when loaded into memory 120 cause processor 110 to perform methods/operations in accordance with various embodiments of the invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present disclosure by executing the one or more instructions.

In one embodiment, the computer program 151 may include one or more instructions to perform various methods related to the attorney's work support platform service.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements; similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors.

3 is a schematic diagram showing a network function according to an embodiment of the present invention.

Throughout this specification, the terms computational model, neural network, network function, and neural network may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network includes one or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, an input node to output node relationship may be created around a link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of data of the output node may be determined based on data input to the input node. Here, a link interconnecting an input node and an output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order to perform a function desired by the neural network. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in the neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values of the links, the two neural networks may be recognized as different from each other.

A neural network may be composed of a set of one or more nodes. A subset of nodes constituting a neural network may constitute a layer. Some of the nodes constituting the neural network may form one layer based on distances from the first input node. For example, a set of nodes having a distance of n from the first input node may constitute n layers. The distance from the first input node may be defined by the minimum number of links that must be passed through to reach the corresponding node from the first input node. However, the definition of such a layer is arbitrary for explanation, and the order of a layer in a neural network may be defined in a method different from the above. For example, a layer of nodes may be defined by a distance from a final output node.

An initial input node may refer to one or more nodes to which data is directly input without going through a link in relation to other nodes among nodes in the neural network. Alternatively, in a relationship between nodes based on a link in a neural network, it may mean nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in relation to other nodes among nodes in the neural network. Also, the hidden node may refer to nodes constituting the neural network other than the first input node and the last output node.

In the neural network according to an embodiment of the present invention, the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as the number of nodes progresses from the input layer to the hidden layer. can In addition, the neural network according to another embodiment of the present invention may be a neural network in which the number of nodes of the input layer may be less than the number of nodes of the output layer, and the number of nodes decreases as the number of nodes increases from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present invention is a type of neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as the number of nodes progresses from the input layer to the hidden layer. can A neural network according to another embodiment of the present invention may be a neural network in the form of a combination of the aforementioned neural networks.

A deep neural network (DNN) may refer to a neural network including a plurality of hidden layers in addition to an input layer and an output layer. Deep neural networks can reveal latent structures in data. In other words, it can identify the latent structure of a photo, text, video, sound, or music (e.g., what objects are in the photo, what the content and emotion of the text are, what the content and emotion of the audio are, etc.). . Deep neural networks include convolutional neural networks (CNNs), recurrent neural networks (RNNs), auto encoders, generative adversarial networks (GANs), and restricted boltzmann machines (RBMs). machine), a deep belief network (DBN), a Q network, a U network, a Siamese network, a Generative Adversarial Network (GAN), and the like. The description of the deep neural network described above is only an example, and the present invention is not limited thereto.

In one embodiment of the present invention, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network for outputting output data similar to input data. An auto-encoder may include at least one hidden layer, and an odd number of hidden layers may be disposed between input and output layers. The number of nodes of each layer may be reduced from the number of nodes of the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically with the reduction from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform non-linear dimensionality reduction. The number of input layers and output layers may correspond to dimensions after preprocessing of input data. In the auto-encoder structure, the number of hidden layer nodes included in the encoder may decrease as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, a sufficient amount of information may not be conveyed, so more than a certain number (e.g., more than half of the input layer, etc.) ) may be maintained.

The neural network may be trained using at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Learning of the neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

A neural network can be trained in a way that minimizes output errors. In the learning of the neural network, the learning data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. It is a process of updating the weight of each node of the neural network by backpropagating in the same direction. In the case of teacher learning, the learning data in which the correct answer is labeled is used for each learning data (ie, the labeled learning data), and in the case of comparative teacher learning, the correct answer may not be labeled in each learning data. That is, for example, learning data in the case of teacher learning regarding data classification may be data in which each learning data is labeled with a category. Labeled training data is input to a neural network, and an error may be calculated by comparing an output (category) of the neural network and a label of the training data. As another example, in the case of comparative history learning for data classification, an error may be calculated by comparing input learning data with a neural network output. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation. The amount of change in the connection weight of each updated node may be determined according to a learning rate. The neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate may be used in the early stage of neural network training to increase efficiency by allowing the neural network to quickly obtain a certain level of performance, and a low learning rate may be used in the late stage to increase accuracy.

In neural network learning, generally, training data can be a subset of real data (ie, data to be processed using the trained neural network), and therefore, errors for training data are reduced, but errors for real data are reduced. There may be incremental learning cycles. Overfitting is a phenomenon in which errors for actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that has learned a cat by showing a yellow cat does not recognize that it is a cat when it sees a cat other than yellow may be a type of overfitting. Overfitting can act as a cause of increasing the error of machine learning algorithms. Various optimization methods can be used to prevent such overfitting. To prevent overfitting, methods such as increasing the training data, regularization, inactivating some nodes in the network during learning, and using a batch normalization layer should be applied. can

4 is a flowchart illustrating a process of a lawyer work support platform service according to an embodiment of the present invention.

Referring to FIG. 4 , in step S110, a delegator who wants to delegate a task may register an idle task. The type of idle task is not limited, and the delegator can register by writing information on the idle task to be delegated. Here, the delegator may include a lawyer, and the idle task may have the same meaning as the attorney entrusted task.

Depending on the embodiment, a category or detailed information on an idle task to be delegated may be input according to a predetermined criterion.

For example, information about the type of work, detailed field of expertise, location, etc. may be input. In addition, information on application deadline, business deadline, business processing cost, etc. may be input, but is not limited thereto.

In step S120, an entrusted person who wants to accept a task may search for a shared task. Task search may be performed according to keyword input or filter input of the entrusted person, or may be performed in a form in which recommended tasks corresponding to information already registered by the entrusted person are listed and provided. In addition, information on available working hours, costs, etc. set by the mandator may also be input in advance and used to recommend work to the mandator.

In various embodiments, a notification may be provided to an entrusted person when a recommended task corresponding to information pre-registered by the entrusted person is registered.

In addition, the mandated person can apply for the job he or she wants to be entrusted with. The support information may be delivered to the entrusting person in real time or together with a predetermined deadline.

In various embodiments, the mandator and the mandator may register their own profile information on the lawyer's work support platform and determine whether or not to disclose it. Through this, the delegator and the entrusted person can check each other's information and refer to the delegation or acceptance of tasks.

In step S130, the entrusting person may review the applicant's information and select an entrusting person to delegate the dual task. During the selection process, the entrusting person may select a plurality of mandated persons, request consultations or bids on costs, and may select a final mandated person according to the result.

Depending on the embodiment, the entrustor may request delegation by searching for and selecting a desired entrustee instead of conducting open bidding. In another embodiment, the delegator may open bid for the task but solicit bids from the desired delegator.

In step S140, the selected mandator may decide whether to accept work sharing. Depending on the embodiment, the matching may be completed automatically without a step of determining whether to accept or not to accept the person selected through the bidding, or after being selected, the final decision may be reviewed to determine final acceptance.

In various embodiments, if the selected trustee does not accept the share of work, the trustee may select another applicant again and notify them of their selection. Depending on the embodiment, a runner-up may be automatically selected based on a score previously determined by the applicant.

In step S150, matching is completed, and task information may be shared with the matched person in charge. For example, detailed information about the contents of the work, customer information, and various data related to the work may be delivered to the mandator.

The transmitted information is safely managed through the server, and can be managed so that only authorized users can view it. In addition, depending on the setting, some sensitive information may be deleted after the task is completed and restricted so that the entrusted person cannot read it again.

The data delivered to the entrusted person may be what the entrusted person has registered at the time of task registration, or may be newly registered by the entrusted person after successful matching. In the subsequent process of performing the task, the delegator may deliver necessary information to the mandator.

In the matching process, the entrusting person and the entrusting person may discuss business conditions or share business contents through a messenger provided by the service according to the disclosed embodiment.

In addition, the delegator may pay the agreed business cost. Cost payment may be performed through an escrow service provided by the service according to the disclosed embodiment, or may be performed through a cache pre-charged by the entrustor.

The payment amount is managed by the platform and can be paid to the person in charge after the work is completed.

In step S160, the entrusted person may perform the delegated task. In various embodiments, necessary documents and a power of attorney required for the mandator to perform his/her duties may be automatically generated and provided to the mandator and the mandator. A power of attorney may be prepared through an electronic signature on the platform, but is not limited thereto.

In the process of performing the task, the entrusted person can upload the task progress at a preset time. The task progress sharing time point may be determined according to a request of the delegater or may be determined according to a preset template according to the type of task. Through this, the delegator can track the progress of the task in real time.

The delegator can check the progress of the task and provide feedback to guide the delegator to perform the task accordingly.

When the task is complete, the delegate can upload a completion report. The completion report may be provided in a form for each task type or automatically generated according to the task content. The person in charge can review the generated report, revise and supplement necessary information and submit the report.

In various embodiments, information and services necessary for the mandator to perform his or her duties may be provided. For example, services such as Supreme Court case search, notification provision, deadline management, etc. may be provided, but are not limited thereto. In addition, a cloud or local server-based business data backup service may be provided.

In addition, a task support function may be provided for an entrusted person performing the task and an entrusted person who manages the task. The task support function may provide information for task schedule management (for example, person in charge information, task progress information, task progress rate information) or may provide a messenger or video conference function for task execution. In addition, a function for electronic signature or electronic contract of necessary documents such as a power of attorney may be provided.

In addition, case precedent search function, document security and management function, certificate management function and other security services can be provided for business execution.

In various embodiments, evidence verification functions such as document reading, digital evidence data authentication, and data forgery verification may be provided, and a service for computerizing non-computerized documents using a technology such as OCR may be provided.

In step S170, the delegator may inspect the completed task. If there is no abnormality as a result of the inspection, the entrustor can approve it or request supplementation.

In step S180, cost settlement may be performed for tasks that have been inspected. The cost is provided to the mandator using the amount paid by the delegator or cash, and in this process, the platform may deduct a certain percentage of the fee and provide it to the mandator, but is not limited thereto.

Delegators and delegates can check information on tasks delegated or accepted on the platform, and through this, the delegator can request new tasks from the delegates who have previously entrusted tasks.

Delegators and delegates can leave feedback on completed tasks after task completion. Feedback information can be made public so that other users can refer to it, or it can be recorded privately and used only for data analysis on the platform.

Profile information, job performance information, and feedback information of the mandator and mandator may be disclosed according to settings, and through this, services for lawyer recruitment and job search may be provided. For example, information on a job offer or a lawyer with an intention to seek a job may be disclosed, or a recommendation service may be provided based on job offer and job search information and information on each lawyer. Such information may be provided to headhunters in addition to job seekers and job seekers.

During this process, the platform may charge a fee for reading information, charge a fee for sending a job offer or job offer request, or charge a fee if the job offer or job search is successful.

In various embodiments, a function of collecting and analyzing big data generated in a business process may be provided. Various legal data can be generated in the process of performing the delegated task, and the platform can perform the process of selecting the data necessary for analysis, removing noise data, and preprocessing.

In various embodiments, the platform may transform unstructured legal data into structured data. In addition, the platform can analyze the generated legal data in real time or post to extract necessary information or process data for learning or analysis.

The collected data may be processed into various statistical data or data for AI model learning. In this process, necessary preprocessing processes such as deletion of sensitive information and de-identification of personal information may be performed.

In various embodiments, artificial intelligence model learning using the collected big data may be performed. For example, an artificial intelligence model may be trained to suggest a strategy for a legal case by learning information about a legal case and information on performance of the case.

As another example, an artificial intelligence model may be trained to analyze a winning rate or a risk factor for a legal case by obtaining information and judgment information on the legal case.

As another example, the artificial intelligence model may be trained to automatically generate a written document by learning written data, detect an error in the written written document, or verify it.

As another example, the artificial intelligence model may be trained to predict the cost of a legal case based on information about the legal case and information about the cost paid for the case.

The artificial intelligence models created through this can be applied to platform services and used to provide lawyer work support platform services, or provide services in the form of APIs to various related organizations or companies.

Through this, the platform according to the disclosed embodiment may provide a contract or document automatic writing service or API, and may have a revenue model selling generated legal content.

In addition, the platform according to the disclosed embodiment can be extended to a subscription service that provides information on generated legal content or real-time legal events.

Hereinafter, with reference to FIGS. 5 to 10, embodiments that can be provided by the above-described lawyer work support platform will be described in more detail.

5 and 6 are flowcharts for explaining an example of a method of providing a service support platform service of a lawyer of the present invention.

According to an embodiment of the present invention, the computing device 100 of the present invention may provide a service for sharing lawyer's work through a lawyer's work support platform.

Referring to FIG. 5 , the computing device 100 may acquire a plurality of attorney entrusted services from a plurality of attorneys registered in the attorney service support platform (S210).

A plurality of lawyers using the lawyer work support platform of the present invention can provide work that needs help to the platform and entrust their work to other lawyers.

In various embodiments, computing device 100 may obtain multiple attorney referrals from external server 300 as well as multiple attorneys.

For example, the computing device 100 may acquire a plurality of attorney referral services from other attorney service support platforms. For another example, the computing device 100 may obtain a plurality of attorney assignments from a law firm or law firm.

When a plurality of attorney entrusted tasks are obtained, the computing device 100 may obtain an intention to accept a specific task from at least one attorney terminal by posting the plurality of attorney entrusted tasks on the attorney task support platform (S220). .

In one embodiment, the computing device 100 may recognize a specific region in which the specific task should be performed when obtaining an intention to commit the specific task. In addition, the computing device 100 may allow specific work to be exposed to a terminal of a lawyer who is accessed in a specific region or has previously set a specific region as a workable region on a lawyer work support platform. In this case, the computing device 100 may acquire an intention to take over from at least one terminal that has been accessed in a specific area or has preset a specific area as a workable area. Here, the computing device 100 may recognize whether or not access to the specific area is limited to terminals that allow sharing of location information.

For example, the computing device 100 recognizes that a specific task needs to be performed in area A, and in area A of a terminal of a lawyer who has set area A as its own business area or a terminal that allows sharing of location information. It is possible to allow the exposure of specific tasks on the connected lawyer's terminal.

In an additional embodiment, the computing device 100 accesses in a specific area or exposes a specific business to a terminal of a lawyer who has preset a specific area as a workable area, and then, if the doctor is not obtained for a predetermined time, An extended area corresponding to a predetermined radius from a specific area may be recognized. In addition, the computing device 100 may additionally allow exposure of a specific task to a terminal that is accessed in the expansion area or has previously set the expansion area as a workable area. In this case, the computing device 100 may obtain an intention to take over from at least one terminal that has been accessed in a specific region or an extended region or has previously set at least one of the specific region and an extended region as a workable region.

In various embodiments, the computing device 100 may proceed with verification of the setting of the lawyer's workable area. For example, the computing device 100 may limit an area located within a predetermined range from the current location of the lawyer to be set as a workable area. As another example, the computing device 100 may allow the lawyer to set the jurisdictional area of the court described in the judgment as a workable area when the lawyer uploads a judgment in which the attorney himself/herself is listed as an agent.

The lawyer's work support platform of the present invention exposes the work to be shared and entrusted to an appropriate user according to the area where the work is performed, thereby increasing the efficiency of work search or work list confirmation.

In another embodiment, the computing device 100 may recognize a specific field corresponding to a specific task when acquiring an intention to commit to a specific task. The computing device 100 may allow exposure of the specific work to a terminal of a lawyer whose field of expertise previously set on the lawyer work support platform is the same as the specific field. In this case, the computing device 100 may obtain an intention to accept the appointment from at least one terminal that has preset the same specialized field as the specific field.

For example, the computing device 100 recognizes that a specific task is in the field of real estate and allows exposure of the specific task to terminals of lawyers who have pre-set their specialties to be in the field of real estate.

In an additional embodiment, the computing device 100 recognizes a similar field corresponding to the specific field when an intention to accept the task is not obtained for a predetermined time after exposing a specific task to a terminal in which the same specialized field as the specific field is set. can do. In addition, the computing device 100 may additionally allow exposure of a specific task to a terminal having the same specialized field as a similar field previously set on the lawyer task support platform. In this case, the computing device 100 may obtain an intention to accept from at least one terminal in which at least one of the specific field and the similar field is the same as a field of expertise previously set in the lawyer's work support platform.

For example, the computing device 100 recognizes that a specific task is in the field of real estate, and if the real estate field is not obtained from an attorney specializing in the field, the terminal of a lawyer in the field of redevelopment and reconstruction or construction field similar to the field of real estate. Exposure of certain tasks may be permitted.

The lawyer's work support platform of the present invention exposes the work to be shared and entrusted to an appropriate user according to the field of work, thereby increasing the quality of the work process result.

In various embodiments, the computing device 100 may recognize an execution time at which the specific task should be performed when obtaining an intention to commit the specific task. In addition, the computing device 100 may allow the exposure of a specific task to the terminal of the attorney whose idle time preset on the attorney task support platform corresponds to the execution time. In this case, the computing device 100 may obtain an intention to take over from at least one terminal for which an idle time including an execution time is previously set.

For example, if a specific task needs to be performed from 10:00 AM to 11:00 AM, exposure of the specific task may be permitted to a lawyer's terminal previously set as idle time from 10:00 AM to 11:00 AM.

As another example, based on the amount of time required to perform a specific task, if it is determined that the task (e.g., writing) will take two days, the attorney's office has more than two days of idle time before the deadline. It is possible to allow the exposure of specific tasks to the terminal.

In various embodiments, idle time may be calculated based on an 8-hour working day. However, the daily working hours may be added according to each user's settings. However, the working hours per day may be restricted so that they cannot be set beyond the preset time (eg, 12 hours). This is because if you set the working hours per day excessively, the time you put into actual work may be reduced or the quality of work may be lowered. In one embodiment, when a user wants to undertake a specific task but lacks idle time (for example, a task that requires 15 hours but idle time is 12 hours by the deadline), the user temporarily idle time limited to a limited number of times. You can request an addition. For example, the user may use the right to request three additional idle hours and to accept a task exceeding the idle time.

At this time, the delegator may approve the use of the request right by comprehensively considering the work history of the corresponding user. In another embodiment, the computing device 100 other than the delegator may approve the use of the request right based on the user's work history, and may indicate to the delegator that the corresponding user has sufficient idle time.

Thereafter, after the user completes the entrusted task, if the evaluation of the entrustor's task performance result is equal to or higher than a predetermined reference value (eg, 90 points), the corresponding user may return the right to request. Conversely, if the evaluation of the entrustor's task performance results is less than a predetermined reference value, the user's right to request may be extinguished. In this case, the lapsed request right may be re-created after a predetermined period (eg, 3 months) has elapsed. Alternatively, the user may use the right to request in return for paying a fee or increasing the commission rate. For example, if the user wants to take on a task that lacks idle time in a situation where the user does not have the right to request, the computing device 100 determines the feasibility of performing the task and delegates the task under the condition of increasing the commission rate for the task. may accept.

In an additional embodiment, the computing device 100 may combine the exposure conditions described above and allow exposure of specific tasks only to several lawyers' terminals.

Specifically, the computing device 100 may allow exposure of a specific task only to an appropriate lawyer's terminal in consideration of a region where a specific task is to be performed, a field of the specific task, and a time when the specific task is to be performed.

The lawyer's work support platform of the present invention not only enhances the quality of work processing results through various exposure conditions, but also can more conveniently check the work to be entrusted.

When obtaining an intention to commit to a specific task from at least one lawyer terminal, the computing device 100 may obtain a score value of each of the at least one attorney by inputting the specific task to a pretrained neural network model (S230). . Here, the pre-trained neural network model is assigned to each of at least one lawyer and may be pre-trained to output a score value proportional to suitability for performing the job.

A pre-trained neural network model to evaluate suitability for job performance may be learned based on a first job history input when at least one lawyer subscribes to the lawyer service support platform. In addition, the neural network model may be updated based on a second work history processed by at least one lawyer through the lawyer work support platform. Here, each of the first business history and the second business history may include at least one of the type of case handled by at least one lawyer, the number of cases handled, the result of case processing, and the evaluation of case processing, but are not limited thereto. don't

Specifically, the computing device 100 may convert at least one of the number of cases processed, the result of processing the case, and the evaluation of the processing of the case into a score value for learning. In addition, the computing device 100 may train the neural network model by labeling the event type with a score value for learning.

When the score value is acquired from the pretrained neural network model, the computing device 100 determines the lawyer corresponding to the highest value among the score values of each of the at least one lawyer as the entrusted lawyer, and matches the entrusted lawyer with a specific task. can

For example, when the score value of the first lawyer is 80 and the score value of the second lawyer is 70, a specific task may be matched to the first lawyer having a high score value.

The lawyer task sharing platform of the present invention, when a plurality of lawyers apply for a specific task, utilizes a neural network model to match the task to the most suitable lawyer to improve the quality of the task processing results.

Referring to FIG. 6 , when the entrusted attorney is determined, the computing device 100 may request payment of fees for a specific task to the entrusted attorney terminal entrusted with the specific task (S250).

When the fee payment is completed, the computing device 100 may provide a message to initiate a specific task to the entrusted attorney terminal entrusted with the specific task (S260).

In various embodiments, the computing device 100 may generate information about a performance rate of a specific task after a specific task is matched. Then, the computing device 100 may update information on the performance rate in real time and provide it to the entrusted attorney terminal entrusted with a specific task.

Specifically, the computing device 100 may recognize processing steps for a specific task when generating information on a performance rate of a specific task. In addition, the computing device 100 may obtain whether the processing steps are completed from the entrusted lawyer terminal that has entrusted a specific task. In addition, the computing device 100 may generate and update information about a performance rate based on whether the processing steps are completed.

For example, if the computing device 100 recognizes that the processing step of a specific task includes three steps, it sends a response to the entrusted lawyer terminal indicating which step is the current processing step among steps 1, 2, and 3. can be obtained In addition, the computing device 100 displays the performance rate as '2/3' or '67%' when the entrusted attorney terminal responds that the current processing step of the specific task is step 2, and provides it to the entrusted attorney terminal. It may, but is not limited thereto.

The attorney task sharing platform of the present invention provides a performance rate to the terminal of a lawyer entrusted with a specific task, thereby providing convenience for monitoring the entrusted task.

The computing device 100 may provide the evidence to the entrusted attorney terminal when obtaining the processing evidence of the specific task and the completion signal of the specific task from the entrusted attorney terminal (S270).

For example, the evidence may include at least one of documents, images, audio data, and video data indicating that the processing of a specific task has been completed, but is not limited thereto.

In a further embodiment, the computing device 100 may convert the evidential data into structured data when the evidential data is composed of unstructured data.

Specifically, when the computing device 100 receives evidence consisting of images, audio data, and video data from an entrusted lawyer, the contents included in the image, audio data, and video data are converted into text and stored in the memory 120. can be stored in Here, the text stored in the memory 120 may be used as training data of a neural network model for evaluating job performance suitability in step S230.

On the other hand, the computing device 100 may accumulate at least a portion of the commission fee in the account of the entrusted attorney when obtaining a specific task termination signal from the entrusted attorney terminal (S280).

Specifically, the computing device 100 may obtain evaluation information on a processing result along with a processing completion signal of a specific task from the entrusted lawyer terminal. Also, the computing device 100 may determine a commission rate for a specific task based on the evaluation information. In addition, the computing device 100 may accumulate the remaining amount of the total amount of the fee minus the amount corresponding to the fee rate in the account of the entrusted attorney. Here, the amount of commission for a specific task may be deposited into the account of the attorney instead of being accumulated in the account of the attorney who handled the task according to a setting value previously set by the user.

The evaluation information of the present invention is, for example, 1 grade selected when very satisfied, 2 grade selected when satisfied, 3 grade selected when normal, 4 grade selected when unsatisfied, and selected when very unsatisfactory. 5 grades may be included. In addition, the fee rate corresponding to each grade may be preset and stored in the memory 120 of the computing device 100 .

For example, the computing device 100 may determine a commission rate corresponding to the first grade as 3% when the fee for a specific task is 1 million won and evaluation information of the first grade is obtained. In addition, the computing device 100 may accumulate 970,000 won in the account of the entrusted lawyer who handled the specific task.

For another example, when the commission fee for a specific task is 1 million won and evaluation information of the 5th grade is obtained, the computing device 100 may determine a commission rate corresponding to the 5th grade as 15%. In addition, the computing device 100 may accumulate 850,000 won in the account of the entrusted lawyer who handled the specific task.

The attorney task sharing platform of the present invention can apply different fee rates according to the evaluation of case handling results, causing the entrusted attorney to improve the quality of work. In other words, entrusted lawyers strive to improve the quality of entrusted work, and entrusted lawyers can be expected to receive high-quality results.

In an additional embodiment, the computing device 100 may provide a lawyer recruitment and job search service through a lawyer business support platform.

Specifically, the computing device 100 may obtain at least one of the types of cases handled by each of the plurality of lawyers registered in the lawyer business support platform, the number of cases processed, the results of case processing, and the evaluation of case processing. In addition, the computing device 100 may generate a resume of each of a plurality of lawyers based on at least one of a type of case, the number of cases processed, a result of case processing, and an evaluation of case processing. In addition, the computing device 100 may post the resume of a lawyer who has allowed the disclosure of his or her resume among the plurality of lawyers to the lawyer's work support platform.

For example, a lawyer's resume can be disclosed through a platform to lawyers who are willing to hire, law offices, law firms, etc., or can be provided to headhunters.

The lawyer's business support platform of the present invention can provide various services such as recruitment and job search in addition to sharing the lawyer's work.

In an additional embodiment, the computing device 100 may build a precedent database and provide a precedent search service through a lawyer's work support platform.

Specifically, the computing device 100 uses the case precedent search records processed through the lawyer's business support platform to use the same words among words included in a search sentence and words included in a precedent finally selected as a search result as a search keyword. Can be preset. In addition, the computing device 100 may build a precedent search database by mapping a search keyword and a finally selected precedent.

Meanwhile, the computing device 100 may receive at least one sentence for a lawyer to search for a precedent through a business support platform. In this case, the computing device 100 may recognize a specific search keyword included in at least one sentence. In addition, the computing device 100 may extract a specific precedent mapped to a specific search keyword from the precedent search database and output the extracted precedent through a lawyer work support platform.

The lawyer's work support platform of the present invention can provide various services such as precedent search in addition to sharing the work of lawyers.

7 and 8 are flowcharts for explaining an example of a method of providing a lawyer's business analysis service through artificial intelligence-based big data analysis of the present invention.

According to an embodiment of the present invention, the computing device 100 may generate analysis information by analyzing lawyer work, and provide the analysis information to the lawyer through a lawyer work support platform.

Referring to FIG. 7 , the computing device 100 may acquire attorney work data from the attorney work support platform (S310). Additionally, the computing device 100 may obtain attorney practice data from the external server 300 .

Lawyer's work data of the present invention may include various data related to lawyer's work. Specifically, the attorney's work data may include first text data, image data, video data, and audio data. For example, the lawyer's business data may include business data such as interview, investigation, copying of records, proof of content, and documents.

When obtaining the lawyer work data, the computing device 100 may obtain lawyer work big data by pre-processing the lawyer work data through a pre-learned neural network model (S320). Here, the pre-trained neural network model may include a first neural network model for extracting text from image data or video data included in lawyer work data, and a second neural network model for extracting text from voice data.

Specifically, the computing device 100 inputs the lawyer's work data to any one of the first neural network model and the second neural network model when the lawyer's work data is composed of image data, video data, or audio data, and Text data can be obtained. Here, the lawyer's work big data may include first text data included in the lawyer's work data and second text data obtained using a neural network model, but is not limited thereto.

The computing device 100 may generate analysis information based on the lawyer business big data when obtaining the lawyer business big data (S330). Then, the computing device 100 may provide the generated analysis information to at least one lawyer through the lawyer work support platform (S340).

In one embodiment, the computing device 100 may generate a scenario for the lawyer's work based on the lawyer's work big data.

Specifically, the computing device 100 may generate a plurality of data sets corresponding to a preset time unit based on an initial creation time of the data. Also, the computing device 100 may create a scenario group by grouping a plurality of data sets according to event types. Here, the scenario group may be included in analysis information.

For example, the computing device 100 may generate lawyer work data generated by date for one legal case as a data set. In detail, for example, the computing device 100 sets each of the first business data processed on the first day, the second business data processed on the second day, and the third business data processed on the third day for one legal case into a data set. can be defined as In addition, the computing device 100 may group the first business data, the second business data, and the third business data to create a scenario group for one legal case.

When the analysis information related to the scenario group is provided, the computing device 100 may receive a request for confirming a work order for a specific case through the lawyer work support platform. In this case, the computing device 100 may recognize a specific scenario group corresponding to a specific event. Also, the computing device 100 may recognize a current processing state of a specific event. Also, the computing device 100 may recognize a first data set corresponding to a current processing state of a specific event in a specific scenario group. In addition, the computing device 100 may recognize a second data set corresponding to a second time unit that is a time unit following the first time unit corresponding to the first data set. And, the computing device 100 may provide the second data set in the following order of work.

The attorney's work analysis service of the present invention can increase the productivity of the attorney's work by providing the next work for a specific case.

In various embodiments, when generating a scenario group, the computing device 100 may recognize event evaluation information or event result information for generating the scenario group. In addition, the computing device 100 may create a scenario group when the evaluation information of the case is equal to or greater than a preset score or the result of the case corresponds to a preset result (eg, winning decision) as a positive result. .

The attorney's work analysis service of the present invention may generate scenario groups only for tasks related to good evaluation results, and may provide analysis information for obtaining good results.

According to various embodiments of the present disclosure, in addition to generating and providing scenario groups, the computing device 100 may obtain judgment information and provide analysis information obtained by analyzing a winning rate or risk factor for a legal case.

According to various embodiments, when providing the analysis information to at least one lawyer in step S340, the computing device 100 may provide differential information according to the usage level of the lawyer registered in the lawyer's work support platform.

Specifically, referring to Figure 8, the computing device 100 may receive a reading request signal for analysis information from the terminal of the reading request lawyer (S341). In this case, the computing device 100 may recognize the use level of the lawyer requesting a view (S342). Then, the computing device 100 may output at least a portion of the analysis information or the entirety of the analysis information from the terminal of the reading request lawyer based on the recognized usage level.

Here, the use level may include at least one of a first subscription level for viewing all of the analysis information and a second subscription level for viewing some of the analysis information. In addition, users of the second subscription level may be requested to pay additionally if they wish to read the entire analysis information, but are not limited thereto.

The attorney's work analysis service of the present invention can provide a subscription-type service that provides various analysis information necessary for attorney's work and classifies and provides free and paid content according to the user's usage level.

In various embodiments, the attorney's work analysis service may provide various auxiliary services while the work is performed through the attorney's work sharing and management platform according to the disclosed embodiment. For example, by comparing the history recorded in the course of the user's work and the recommended work process, if the history and work process are different, or if the work is not recorded at the time when a specific task is to be performed, the user Notifications can be provided for the task.

Users can pay points, fees, cash, etc. to view specific details of the task. Thereafter, when the corresponding user performs a task according to the provided task details and the corresponding task performance record is uploaded to the platform, the computing device 100 may compare the similarity between the recommended task and the corresponding task.

If the corresponding task is not uploaded within a predetermined period, the computing device 100 may return the amount paid for the corresponding task. If the task is uploaded within a preset period of time, the computing device 100 may return some of the cost or pay an additional cost according to the similarity between the recommended task and the uploaded task.

In various embodiments, the computing device 100 may recommend a task to be performed in each step, and automatically generate and provide a draft corresponding to the task. For example, the computing device 100 may automatically generate and provide a corresponding document at the point in time when a specific document needs to be submitted.

Users can review and submit the provided draft, or modify it and submit it. In this case, the computing device 100 may collect information about correction work that occurred between the provided draft and the submitted document. For example, the number of deleted or added characters in a given draft can be counted. The computing device 100 may compare the number of characters in the provided draft with the number of deleted or additionally written characters, and calculate a cost for the provided task based on the ratio. For example, if the price of the provided draft is 100,000 won, the number of characters included in the draft is 1,000, and the number of deleted or added characters is 500, you can charge 50,000 won. However, the specific cost calculation method is not limited thereto.

In various embodiments, the computing device 100 may compare the contents of deleted or added letters. For example, 300 of 1,000 characters are deleted and another 300 are added. As a result of comparing the deleted content with the added content, the content may be the same. In this case, a part in which a difference occurs between the deleted content and the added content may be extracted, and the number of characters according to the corresponding portion may be calculated as the number of modified characters.

9 and 10 are flowcharts for explaining various examples of a method of providing a lawyer's business analysis service through artificial intelligence-based big data analysis of the present invention.

In various embodiments, the computing device 100 may generate case precedent analysis information and provide it through a lawyer's work support platform.

Referring to FIG. 9 , the computing device 100 may receive precedent data including a decision result from the external server 300 (S410). Here, the external server 300 may be a server of the Supreme Court providing precedents, but is not limited thereto.

The computing device 100 may extract, as a precedent keyword, words appearing more than a predetermined number of times among words included in the precedent data (S420). Also, the computing device 100 may recognize a specific field of the case based on the precedent keyword (S430). In addition, the computing device 100 may transmit precedent data to a terminal of a lawyer whose field of expertise previously set on the lawyer's work support platform is the same as that of the specific field (S440). In this case, the computing device 100 may receive an additional keyword from at least one terminal preset for the same specialized field as the specific field (S450).

When the additional keyword is received, the computing device 100 may generate learning data for training a decision result prediction model using the precedent data, the decision result, the precedent keyword, and the additional keyword (S460). Then, the computing device 100 may use the learning data to learn the decision result prediction model (S470). Here, the decision result prediction model may be trained to output a prediction result for a specific event when a keyword related to the specific event is input.

As an example, the computing device 100 may receive a request for predicting a result of a specific case through a lawyer business support platform. In this case, the computing device 100 may obtain a prediction result for the specific event by inputting information on the specific event to the decision result prediction model. Here, information on a specific event may include keywords related to the specific event. That is, when receiving a request for predicting a result of a specific event, the computing device 100 may extract a keyword to be input to the model from information related to the specific event.

In addition, the computing device 100 may provide a prediction result obtained from the judgment result prediction model through the lawyer work support platform. Here, the prediction result may be included in the analysis information provided by the lawyer's work support platform.

In various embodiments, computing device 100 may generate cost estimate information and provide it through an attorney's practice support platform.

Referring to FIG. 10 , the computing device 100 may receive precedent data including legal costs from the external server 300 (S510). In addition, the computing device 100 may extract words that appear more than a predetermined number of times among words included in the precedent data as precedent keywords. In addition, the computing device 100 may generate learning data for training a legal cost prediction model by using legal cost and precedent keywords (S530). Then, the computing device 100 may use the learning data to learn a legal cost prediction model (S540). Here, the legal cost prediction model may be trained to output a predicted cost for a specific case when a keyword for the specific case is input.

In various embodiments, the computing device 100 may obtain history of each event and fee information of the corresponding event. For example, information on the work cost calculated for the work entrusted may be obtained through the attorney work sharing and management platform according to the disclosed embodiment. Through this, the computing device 100 extracts one or more parameters from the event history and trains a neural network model based on the work cost corresponding to each parameter to learn a model capable of calculating the work cost.

In various embodiments, the parameters extracted from the case history may include, but are not limited to, the type of task, the time required for the task, the number of messages sent and received, the time required for performing the task, the price of the case, judgment information, and the like. don't The computing device 100 may learn a neural network model by taking parameters extracted from the event history as input data and correspondingly using information for calculating a work cost as output data. For example, the output data may be work cost or time information required for work.

For example, a neural network model can be trained to output work costs or intervals of work costs. As another example, the neural network model may be trained to output the time required for a task or a section of the required time. In this case, the business cost may be calculated by multiplying the output time by the business cost per hour of the party to perform the business.

In various embodiments, the work cost calculated through the neural network model may be adjusted based on various conditions. For example, the cost of the work may be adjusted based on a separate assessment of the difficulty of the actual task, the grade and past work history of the party to perform the task, the deadline for the task, and the like.

In various embodiments, the computing device 100 may receive a cost estimation request for a specific case through a lawyer business support platform. In this case, the computing device 100 may input information on a specific case into a legal cost prediction model to obtain a predicted cost for the specific case. Here, information on a specific event may include keywords related to the specific event. That is, when a cost prediction request for a specific event is received, the computing device 100 may extract a keyword to be input to the model from information related to the specific event.

And, the computing device 100 may provide the estimated cost obtained from the cost prediction model to the lawyer through the lawyer's business support platform. Here, the predicted cost may be included in the analysis information provided by the lawyer's work support platform.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (15)

A method for providing a lawyer's business analysis service through artificial intelligence-based big data analysis performed by a computing device including at least one processor,
Acquiring lawyer work data from a lawyer work support platform;
Acquiring big data of lawyer work by pre-processing the lawyer work data through a pre-learned neural network model;
Generating analysis information based on the lawyer's business big data; and
providing the analysis information to at least one lawyer through the lawyer business support platform;
including,
The pretrained neural network model,
Including a data conversion model that converts unstructured data into structured data;
Based on the lawyer's business big data, the step of generating analysis information,
generating a plurality of data sets corresponding to a predetermined time unit based on an initial generation time of data; and
generating the analysis information including a scenario group generated by grouping the plurality of data sets by event type;
including,
Providing the analysis information to at least one lawyer through the lawyer work support platform,
Recognizing a specific scenario group corresponding to the specific case when a request for confirming the order of work for a specific case is received through the lawyer service support platform;
Recognizing the current processing status of the specific case;
recognizing a first data set corresponding to a current processing state of the specific event in the specific scenario group;
recognizing a second data set corresponding to a second time unit that is a time unit following the first time unit corresponding to the first data set;
providing the second data set in a next work order, generating a draft corresponding to the next work order, and providing the draft to the at least one lawyer;
When the task is completed based on the draft, the first number of characters in the draft is compared with the number of second characters deleted or added in the draft, and the ratio calculated by the number of first characters and the number of second characters estimating the corresponding cost; and
billing the at least one attorney for the estimated cost;
including,
When the task is completed based on the draft, the first number of characters in the draft is compared with the number of second characters deleted or added in the draft, and the ratio calculated by the number of first characters and the number of second characters The step of calculating the corresponding cost is,
Recognizing deleted characters in the draft based on the data for which the work has been completed;
Recognizing additionally written letters in the draft based on the data for which the task is completed; and
The difference between the deleted characters and the additionally written characters is recognized as the number of the second characters, and the cost is calculated by multiplying the amount set in the draft by the value of dividing the number of second characters by the number of first characters. doing;
including,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 1,
The lawyer work data,
Including first text data, image data, video data and audio data,
The neural network model,
a first neural network model for extracting text from the image data or the image data; and
a second neural network model for extracting text from the voice data;
including,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 2,
The step of pre-processing the lawyer work data through the pre-learned neural network model to obtain lawyer work big data,
When the lawyer service data is composed of the image data, the video data, or the voice data, the lawyer service data is input to any one of the first neural network model and the second neural network model to obtain second text data. obtaining;
including,
The lawyer business big data,
Including the first text data and the second text data,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
delete According to claim 1,
The step of grouping the plurality of data sets by event type and creating a scenario group,
recognizing evaluation information of the event or result information of the event for generating the scenario group; and
generating the scenario group when the evaluation information of the event is equal to or higher than a preset score or the event result corresponds to a preset result as a positive result;
including,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
delete According to claim 1,
Receiving precedent data including judgment results from an external server;
extracting, as precedent keywords, words appearing more than a predetermined number of times among words included in the precedent data;
recognizing a specific field of the case based on the precedent keyword;
Transmitting the precedent data to a terminal of a lawyer whose professional field previously set on the lawyer business support platform is the same as the specific field;
Receiving an additional keyword from at least one terminal presetting the same specialized field as the specific field;
generating training data for training a decision result prediction model using the precedent data, the decision result, the precedent keyword, and the additional keyword; and
learning the decision result prediction model using the learning data;
Including more,
The decision result prediction model,
When a keyword related to a specific event is input, it is learned to output a prediction result for the specific event.
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 7,
Receiving a result prediction request for the specific case through the lawyer work support platform;
obtaining a prediction result for the specific event by inputting information on the specific event into the decision result prediction model; and
providing the prediction result through the lawyer work support platform;
Including more,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 1,
Receiving precedent data including legal costs from an external server;
extracting, as precedent keywords, words appearing more than a predetermined number of times among words included in the precedent data;
generating training data for training a legal cost prediction model using the legal cost and the precedent keyword; and
learning the legal cost prediction model using the training data;
Including more,
The legal cost prediction model,
When a keyword for a specific event is input, it is learned to output a predicted cost for the specific event.
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 9,
Receiving a request for cost prediction for a specific case through the attorney business support platform;
obtaining a predicted cost for the specific case by inputting information on the specific case into the legal cost prediction model; and
providing the estimated cost through the attorney's work support platform;
Including more,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 1,
Providing the analysis information to at least one lawyer through the lawyer work support platform,
Receiving a reading request signal for the analysis information from the terminal of the reading request lawyer;
Recognizing the use level of the reading request lawyer; and
Based on the level of use, outputting at least a portion of the analysis information or the entirety of the analysis information from the terminal of the reading request lawyer;
including,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 11,
The level of use is
At least one of a first subscription level capable of viewing the entire contents of the analysis information and a second subscription level capable of viewing some contents of the analysis information;
Users of the second subscription level,
If you want to view the entire contents of the analysis information, additional payment is requested,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
According to claim 1,
The lawyer work support platform,
Acquire multiple attorney commissions,
Posting the plurality of lawyer entrusted tasks, obtaining an intention to accept a specific task from at least one lawyer terminal;
Obtaining a score value for each of the at least one attorney by inputting the specific task to a neural network model pretrained to output a score value proportional to suitability for performing the task;
Determining an attorney corresponding to the highest value among the score values of each of the at least one attorney as an entrusted attorney, and matching the specific task to the entrusted attorney,
A method for providing analysis services for lawyers through artificial intelligence-based big data analysis.
a memory that stores one or more instructions; and
a processor executing the one or more instructions stored in the memory;
include,
By executing the one or more instructions, the processor:
An apparatus that performs the method of claim 1 .
A computer program stored in a computer-readable recording medium to be combined with a computer, which is hardware, to perform the method of claim 1.

Images