KR20210006723A - Method and apparatus for determining ratio of negligence based on big data and machine learning - Google Patents

Abstract

A method for determining a fault ratio performed by a device for determining a fault ratio may comprise the steps of: obtaining accident-related information including image information before and after the accident and location information of the accident site; obtaining information on surrounding environment of a location of an accident based on the location information; obtaining driving information when the accident occurs based on the image information; deriving addition and subtraction factor information based on the surrounding environment information and the driving information; determining an error rate through an artificial neural network based on the surrounding environment information, the driving information, and the addition and subtraction factor information; and providing information on a fault ratio to a user.

Description

Big data and machine learning based fruit ratio determination method and apparatus {METHOD AND APPARATUS FOR DETERMINING RATIO OF NEGLIGENCE BASED ON BIG DATA AND MACHINE LEARNING}

The present invention relates to a method and apparatus for determining an error rate in case of an accident or when determining damage, and more particularly, to a method and apparatus for automatically determining the rate of error in an accident for dispute resolution and damage assessment.

If an accident occurs on the road, etc., the perpetrator and the victim can be distinguished, but it takes a considerable amount of time before the rate of negligence is determined. In this case, it is difficult to resolve disputes between the accident parties, and the vehicle is left on the site until the insurance company employee and the police arrive, thereby disturbing the flow of the vehicle and increasing the risk of a secondary accident.

In addition, if an objection is raised even if the negligence (%) is determined, the division cannot be resolved, and the automobile dispute deliberation committee or lawsuit proceeds, resulting in unnecessary time and economic waste.

Therefore, it is very important to quickly determine the negligence because it can help the perpetrator and the victim economically and mentally, and it can help smooth traffic flow, thereby reducing the risk of secondary accidents. However, judging negligence requires related expertise, so the general public cannot easily decide and has no choice but to seek help from experts. Therefore, there is a need and increasing demand for a technology for determining the percentage of errors based on accident-related information.

Registered Patent Publication No. 10-1302011, 2013.08.26

The problem to be solved by the present invention is to provide a method for determining fruit ratio.

Another problem to be solved by the present invention is to provide a computer-readable recording medium in which a program for performing a method for determining a fruit ratio is recorded.

Another problem to be solved by the present invention is to provide an apparatus for determining fruit ratio.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems that are 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-described problems, the method for determining the ratio of errors according to an embodiment of the present invention includes the steps of acquiring accident-related information including image information before and after the accident and location information of the accident site, and the accident location based on the location information. Acquiring surrounding environment information of, acquiring driving information at the time of an accident based on the image information, deriving additive and subtractive factor information based on the surrounding environment information and the driving information, the surrounding environment information, It may include determining a fruit ratio through an artificial neural network based on the driving information and the additive and subtractive factor information, and providing information on the fruit ratio to a user.

Here, the surrounding environment information may include road type information of the accident place, speed limit information of the road, state information of the road, and building information within a predetermined distance from the accident place.

Here, the state information of the road may include at least one of lane information of the road, curvature information of the road, longitudinal slope information of the road, and cross slope information of the road.

Here, the driving information includes speed information of the accident vehicle at the time of the accident, driving direction information of the accident vehicle, speed information of nearby vehicles within a certain distance from the accident vehicle, driving direction information of the surrounding vehicle, vehicle and surrounding vehicles It may include at least one of distance information and signal information when the accident occurs.

Here, the acceleration/decrement factor information is at least one of information on whether the accident vehicle complies with the speed limit when the accident occurs, information on whether to comply with the signal, information on whether to comply with the safety distance, information on whether to comply with the lane, and information on the interruption. It can contain one.

In this case, the artificial neural network may be learned based on at least one of error chart data, opinion data of a loss adjuster for each case, and precedent data for each case.

Here, the artificial neural network may include an artificial neural network learned by a supervised learning method.

Here, the supervised learning method includes training data on the surrounding environment information, the driving information, and the addition/deduction factor information, and result data on the fruit ratio based on the error chart data, opinion data of the damage adjuster for each case, and case-by-case precedent data. And learning by changing weights of nodes included in the artificial neural network based on the training data and the result data.

Here, the information on the fruit ratio includes a first percentage value for the user's fruit and a second percentage value for the other person's fruit, and the sum of the first percentage value and the second percentage value is 100, and the The first percent value and the second percent value may be represented as a multiple of 0 or 100 or less, respectively.

Here, the information on the fruit ratio further includes reliability information according to the artificial neural network, the reliability information includes a reliability value in units of percent, and the reliability value may be rounded off from the first decimal place.

In a computer-readable recording medium according to an embodiment of the present invention for solving the above-described other problems, a program for performing the above-described method for determining the fruit ratio may be recorded.

An apparatus for determining an error ratio according to an embodiment of the present invention for solving the above-described other problems includes at least one processor and a memory storing at least one instruction executed by the at least one processor, The at least one command is executed to obtain accident-related information including image information before and after the accident and location information of the accident site, and is executed to obtain information on the surrounding environment of the accident site based on the location information, and the image information It is executed to obtain driving information at the time of an accident based on, and is executed to derive additive and subtractive factor information based on the surrounding environment information and the driving information, and based on the surrounding environment information, the driving information, and the additive and subtractive factor information. As a result, the fruit ratio may be determined through an artificial neural network, and information on the fruit ratio may be provided to the user.

Here, the surrounding environment information may include road type information of the accident place, speed limit information of the road, state information of the road, and building information within a predetermined distance from the accident place.

Here, the state information of the road may include at least one of lane information of the road, curvature information of the road, longitudinal slope information of the road, and cross slope information of the road.

Here, the driving information includes speed information of the accident vehicle at the time of the accident, driving direction information of the accident vehicle, speed information of nearby vehicles within a certain distance from the accident vehicle, driving direction information of the surrounding vehicle, vehicle and surrounding vehicles It may include at least one of distance information and signal information when the accident occurs.

Here, the acceleration/decrement factor information is at least one of information on whether the accident vehicle complies with the speed limit when the accident occurs, information on whether to comply with the signal, information on whether to comply with the safety distance, information on whether to comply with the lane, and information on the interruption. It can contain one.

In this case, the artificial neural network may be learned based on at least one of error chart data, opinion data of a loss adjuster for each case, and precedent data for each case.

Here, the artificial neural network may include an artificial neural network learned by a supervised learning method.

Here, the supervised learning method includes training data on the surrounding environment information, the driving information, and the addition/deduction factor information, and result data on the fruit ratio based on the error chart data, opinion data of the damage adjuster for each case, and case-by-case precedent data. And learning by changing weights of nodes included in the artificial neural network based on the training data and the result data.

Here, the information on the fruit ratio includes a first percentage value for the user's fruit and a second percentage value for the other person's fruit, and the sum of the first percentage value and the second percentage value is 100, and the The first percent value and the second percent value may be represented as a multiple of 0 or 100 or less, respectively.

Here, the information on the fruit ratio further includes reliability information according to the artificial neural network, the reliability information includes a reliability value in units of percent, and the reliability value may be rounded off from the first decimal place.

According to the disclosed embodiment, it is possible to automatically determine the fruit ratio within a short time based on an image of a black box or a picture of a mobile phone and provide it to a user.

In addition, it is possible to conduct effective consultation through direct matching with experts based on the primary determined fruit ratio or images stored (transmitted) on mobile devices.

In addition, since the primary negligence rate can be confirmed within a short time based on the accident site information instead of a third party's confirmation procedure, it is possible to get out of the accident site on the road within a relatively short time, thereby preventing traffic flow on the road. have.

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 following description.

1 is a block diagram of an apparatus according to an embodiment.
2 is a diagram schematically illustrating a first environment in which a method for determining a fruit ratio according to an exemplary embodiment can be used.
3 is a diagram schematically illustrating a second environment in which a method for determining a fruit ratio according to an exemplary embodiment can be used.
4 is a diagram schematically illustrating a method of determining a fruit ratio according to an exemplary embodiment.
5 is a flowchart illustrating a method of determining a fruit ratio according to an embodiment.

Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in a variety of different forms, only the present embodiments are intended to complete the disclosure of the present invention, It is provided to fully inform the technician of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. As used in the specification, “comprises” and/or “comprising” do not exclude the presence or addition of one or more other elements other than the mentioned elements. Throughout the specification, the same reference numerals refer to the same elements, and “and/or” includes each and all combinations of one or more of the mentioned elements. Although "first", "second", and the like are used to describe various elements, it goes without saying that these elements are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical idea of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically.

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

In the present specification, a computer refers to all kinds of hardware devices including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to embodiments. For example, the computer may be understood as including all of a smartphone, a tablet PC, a desktop, a laptop, and a user client and an application running on each device, but is not limited thereto.

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

Each of the steps described herein is described as being performed by a computer, but the subject of each step is not limited thereto, and according to embodiments, at least some of the steps may be performed in different devices.

1 is a block diagram of an apparatus according to an embodiment.

The processor 102 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals with other components. .

The processor 102 according to an embodiment may perform a method described later with reference to FIGS. 2 to 5 by executing one or more instructions or instructions stored in the memory 104.

For example, the processor 102 may execute one or more instructions stored in the memory, and the one or more instructions are instructions for obtaining accident-related information including image information before and after the accident and location information of the accident site, and the location information. Based on a command for acquiring surrounding environment information of the accident place, a command for acquiring driving information at the time of an accident based on the image information, a command for deriving additive and subtractive factor information based on the surrounding environment information and the driving information, the It may include a command for determining a fruit rate through an artificial neural network based on surrounding environment information, the driving information, and the additive/deducting factor information, and a command for providing information on the fruit rate to the user.

Here, the surrounding environment information may include road type information of the accident place, speed limit information of the road, state information of the road, and building information within a certain distance from the accident place, and the state information of the road It may include at least one of lane information of the road, curvature information of the road, longitudinal slope information of the road, and cross slope information of the road.

Here, the driving information includes speed information of the accident vehicle at the time of the accident, driving direction information of the accident vehicle, speed information of nearby vehicles within a certain distance from the accident vehicle, driving direction information of the surrounding vehicle, vehicle and surrounding vehicles It may include at least one of distance information and signal information when the accident occurs.

Here, the information on the acceleration and deduction factors includes information on whether or not the accident vehicle complies with the speed limit when the accident occurs, information on whether or not to comply with the signal, information on whether to comply with the safety distance, information on whether to comply with the lane, and information on interception. It may include at least one.

Here, the artificial neural network may be learned based on at least one of fruit chart data, opinion data of a loss adjuster for each case, and precedent data for each case, and may include an artificial neural network learned by a supervised learning method. . In addition, the supervised learning method includes training data on the surrounding environment information, the driving information, and the addition/deduction factor information, and result data on the fruit ratio based on the error chart data, opinion data of the damage adjuster for each case, and case-by-case precedent data. And learning by changing weights of nodes included in the artificial neural network based on the training data and the result data.

Here, the information on the fruit ratio may include a first percentage value for the user's fruit and a second percentage value for the other's fruit, and the sum of the first percentage value and the second percentage value is 100 , The first percent value and the second percent value may be represented as a multiple of 0 or 100 or less, respectively.

Here, the information on the fruit ratio may further include reliability information according to the artificial neural network, and the reliability information may include a reliability value in units of percent, and the reliability value is rounded off from the first decimal place. Can be.

Meanwhile, the processor 102 temporarily and/or permanently stores a signal (or data) processed inside the processor 102, a RAM (Random Access Memory, not shown) and a ROM (Read-Only Memory). , Not shown) may further include. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, RAM, and ROM.

The memory 104 may store programs (one or more instructions) for processing and controlling the processor 102. Programs stored in the memory 104 may be divided into a plurality of modules according to functions.

In general, when a vehicle accident occurs, the classification of the perpetrator and the victim may be unclear, and the accident site is left as it is until the insurance company and the police arrive at the accident site. In this case, a problem may occur not only in a complex road environment, but also in a road environment in a remote area, and will be further described with reference to FIGS. 2 and 3.

2 is a diagram schematically illustrating a first environment in which a method for determining a fruit ratio according to an exemplary embodiment can be used.

Referring to FIG. 2, the environment in which the accident has occurred may be an environment in which vehicles are blocked by many vehicles on the road, that is, a complex road environment. In such an environment, a third party, such as an insurance company or police, must arrive, but it may be difficult to arrive due to a complicated road. That is, it may take a long time to arrive. Further, as the arrival of a third party is delayed, accident vehicles may be left at the accident site for a long time, and accordingly, the flow of the vehicle may be further slowed and complicated.

In one embodiment, since accident-related information can be immediately collected and the negligence rate determined in such a situation, it can be immediately used for the classification of perpetrators and victims, and has the effect of reducing the time for the accident parties such as users and counterparts to leave the accident vehicle. There may be. In addition, there is an effect that the user can smoothly consult with a loss adjuster based on the information on the determined fruit ratio.

3 is a diagram schematically illustrating a second environment in which a method for determining a fruit ratio according to an exemplary embodiment can be used.

The above-described problems may occur not only in the complex road environment of FIG. 2 but also in the secluded or remote road environment of FIG. 3. That is, if the accident site is far from a nearby city, the arrival of a third party may be delayed due to the long distance, and there may be cases where it is impossible to contact a third party due to reasons such as injury.

In one embodiment, as described in FIG. 2, since it is possible to immediately collect accident-related information and determine the negligence rate in such a situation, it can be immediately used for the classification of the perpetrator and the victim, so there is no need to wait for the arrival of a third party, and the accident When related information is collected and the damage situation exceeds the threshold, the information can be automatically transferred to a third party set in advance, so it can be effectively utilized even when it is impossible to contact the third party.

Hereinafter, various operations and specific operation methods of an embodiment will be described.

4 is a diagram schematically illustrating a method of determining a fruit ratio according to an exemplary embodiment.

Referring to FIG. 4, in an embodiment, when an accident occurs, accident-related information may be obtained from a photographing device mounted on a user's vehicle.

The accident-related information may include image information, and the image information may include image (still image) information and video (movie) information. Here, the image information may include image information for a certain time immediately before and/or immediately after the accident of the vehicle. The photographing device may be a black box, but is not limited thereto.

In addition, the photographing device may further include a location tracking device or module capable of obtaining location information. Here, the location tracking device or module may include a GPS (Global Postitioning System) device or module, but is not limited thereto. The location information may include absolute location information and/or relative location information, and the absolute location information may be information based on longitude and latitude, and the relative location information is a direction and direction from a location or structure in which absolute location information is stored or set in advance. It may be distance-based information. In other words, the photographing device may provide image information before and after the accident photographed at the time of the accident and location information according to the location tracking module.

In addition, according to an exemplary embodiment, when an accident occurs, accident-related information may be obtained from a photographing device mounted on a user's terminal. Here, the user's terminal may be a mobile terminal such as a smartphone equipped with a photographing device.

The user's terminal may provide an image of the accident site as accident-related information, and the image of the accident site may be an image of the appearance of the user's vehicle after the accident and the appearance of the other's vehicle.

In addition, the user terminal may further include a location tracking device or module capable of obtaining location information, where the location tracking device or module may be as described above. That is, when the user terminal provides location information, the operation of providing the location information of the black box may be omitted, and when the black box provides the location information, the operation of providing the location information of the user terminal may be omitted.

That is, in an embodiment, accident-related information may be obtained through a photographing device and/or a user terminal mounted on a user's vehicle, and the accident-related information may include image information and location information.

The image information may include driving information, or driving information may be derived according to an embodiment. Here, the driving information includes speed information of the accident vehicle at the time of an accident, driving direction information of the accident vehicle, speed information of surrounding vehicles within a certain distance from the accident vehicle, driving direction information of the surrounding vehicle, distance information between the vehicle and surrounding vehicles, and accidents. It may include at least one of signal information when generated.

The location information may include surrounding environment information, or surrounding environment information may be derived according to an embodiment. Here, the surrounding environment information may include at least one of road type information, road speed limit information, road condition information, and building information within a certain distance from the accident place, and the road condition information Information, curvature information of the road, longitudinal slope information of the road, and cross slope information of the road may be included. That is, an embodiment may derive or obtain information about a surrounding environment of a corresponding location based on location information by interworking with information stored in advance or an external device.

In one embodiment, the additive and subtractive factor information may be derived based on the above-described information, the fruit ratio may be determined based on the above-described information including the additive and subtractive factor information through an artificial neural network, and information on the determined fruit rate Can be provided to the user. A detailed description of this will be described later with reference to FIG. 5.

5 is a flowchart illustrating a method of determining a fruit ratio according to an embodiment.

Referring to FIG. 5, according to an embodiment, accident-related information may be obtained (S510). The accident-related information may include image information and location information, and the image information and location information may be obtained from a user terminal and/or a photographing device mounted on the user's vehicle. A detailed description of this has been described above with reference to FIG. 4.

According to an embodiment, surrounding environment information may be obtained (S520). According to an exemplary embodiment, information on surrounding environments may be obtained based on location information among accident-related information. That is, in an embodiment, information on surrounding environment may be derived from location information, and a detailed description thereof has been described above with reference to FIG. 4.

In an embodiment, driving information may be obtained (S530). According to an exemplary embodiment, driving information may be obtained based on image information among accident-related information. That is, in an embodiment, driving information may be derived from image information, and a detailed description thereof has been described above with reference to FIG. 4.

According to an exemplary embodiment, information on an additive or subtractive factor may be derived (S540). Here, one embodiment may derive the information on the additive and subtractive factors based on the information on the surrounding environment and the driving information. It may include at least one of information on whether to observe the distance, information on whether to comply with lanes, and information on interruption, but is not limited thereto.

For example, information on whether the accident vehicle complies with the speed limit may be derived based on vehicle speed information among driving information and road speed limit information among surrounding environment information. Information on whether to comply with the signal may be derived based on vehicle speed information, vehicle driving direction information and signal information, and lane information of a road among surrounding environment information. Information on whether to comply with the safety distance may be derived based on distance information of the vehicle and surrounding vehicles among driving information. The information on whether to comply with the lane may be derived based on the driving direction information and signal information of the vehicle among the driving information, and the road type information and the lane information of the road among the surrounding environment information.

According to an exemplary embodiment, when there is a violation according to the above-described addition/decrement factor information, it may be considered as a deduction factor and a specific score may be deducted for each violation. Here, the score deducted for each violation may be different, but is not limited thereto.

Here, for example, in an embodiment, after setting a specific reference value, the added or subtracted score may be calculated based on the score deducted. Here, the specific reference value may be 0 points, 50 points, or 100 points, but is not limited thereto.

According to an embodiment, the fruit ratio may be determined (S550). According to an embodiment, an error rate may be determined based on surrounding environment information, driving information, and additive and subtractive factor information, and big data and machine learning techniques may be used. Alternatively, data mining may be performed based on big data, and machine learning may be performed based on rule information or result information derived according to data mining. Here, for machine learning, deep learning may be used, and through this, an artificial neural network may be trained.

Here, the artificial neural network may be learned based on at least one of fruit chart data, case-by-case loss adjuster opinion data, and case-by-case precedent data, and may be learned by supervised learning. However, it is not limited thereto because it may be learned by an unsupervised learning method or a reinforcement learning method. In addition, the artificial neural network may include an algorithm based on machine learning or deep learning, and at least one of a deep neural network (DNN), a convolutional neural network (CNN), and a recurrent neural network (RNN). One may be used, but is not limited thereto.

For example, when the artificial neural network is learned according to a supervised learning method, based on the error chart data, the opinion data of the damage adjuster for each case, and the case-by-case precedent data, the surrounding environment information, the driving information, and the additive and subtractive factor information The training data and result data on the fruit ratio may be extracted, and the training may be performed by changing weights of nodes included in the artificial neural network based on the training data and the result data.

Here, the training data and result data may be viewed as a training set, and the training data may be used as a term encompassing the training data and the result data. That is, the artificial neural network can compare the result data according to the input of the training data with the result data in the training set, and can continuously change the weights of the nodes in the artificial neural network so that they become identical, and learning can proceed through this process. have.

For example, in an embodiment, the above-described artificial neural network may be used in a process of deriving surrounding environment information from location information, a process of deriving driving information from image information and/or a process of deriving additive/subtractive factor information.

To this end, in one embodiment, location information and surrounding environment information may be learned as a training set, image information and driving information may be learned as a training set, and surrounding environment information, driving information, and additive/subtractive factor information may be used as a training set. You can also learn.

For example, in an embodiment, the artificial neural network may be trained using the above-described added/subtracted score instead of the subtractive factor information.

In other words, in an embodiment, the fruit ratio may be determined through the artificial neural network described above, and the fruit ratio may be expressed as a percentage value that sums to 100, such as 30 to 70 or 40 to 60. Here, the percentage unit may be omitted. That is, the fruit ratio may be information including a first percentage value for the user's fruit and a second percentage value for the counterpart's fruit, and since it is based on a percentage unit, the sum may be 100.

Further, for example, each percent value of the fruit ratio may be represented as a multiple of 0 or 100 or less. However, here, the fruit ratio may be divided by the greatest common divisor of the first percent value and the second percent value. In this case, 30 to 70 may appear as 3 to 7.

For example, an embodiment may provide reliability information according to the artificial neural network when the fruit ratio is determined through the artificial neural network described above. Here, the reliability information may be information on the determination of the artificial neural network or the reliability of the determination, and may be expressed in a percentage unit. In addition, the reliability value may be rounded to one digit or the first decimal place.

According to an embodiment, information on the fruit ratio may be delivered (S560). The information on the fruit ratio may include the above-described fruit ratio, and may further include reliability information. Here, in an embodiment, information on the fruit ratio including only the fruit ratio may be transmitted to the user terminal, and reliability information or information on the fruit ratio including the reliability information may be transmitted according to an additional request from the user terminal. This is because information on the fruit ratio including the fruit ratio and reliability information may be directly transmitted according to a preset setting, and the present invention is not limited thereto.

In addition, although not shown in the exemplary embodiment, information on the severity of an accident may be derived based on information on surrounding environment, driving information, and additional and subtractive factors, and the artificial neural network described above may be further used. In addition, the severity information may be derived as a severity score having an integer value of 0 or more and 100 or less, and if the derived severity score is higher than a preset threshold or a specific value, the above-described information is automatically delivered to a preset third party. I can. Here, the third party may include the user's family, a police station, a fire station, etc., and may be automatically transferred to their terminals.

In the description of the present invention, an exemplary embodiment has been described based on a user terminal and/or an error rate determination device that transmits and receives information with a photographing device mounted on a user vehicle or a server that performs fruit rate determination. In this case, all of the above-described operations may be performed, and in this case, information transfer operations related to the omitted device may be omitted.

In one embodiment, information on the percentage of negligence may be obtained as described above, and based on this, match with at least one loss adjuster (hereinafter, assessor) terminal, or provide it to the user terminal, and the user It may match at least one assessor terminal based on. Alternatively, information on the fruit ratio may be transmitted to the server to match at least one assessor terminal based on a response from the server. That is, it is possible to match with the assessor terminal through the user terminal that has obtained information on the fruit ratio, and it may be directly matched with the assessor terminal through the fruit ratio determination device, but hereinafter, the case of matching with the assessor terminal through the user terminal will be described. Let me explain with an example.

In one embodiment, the user terminal may be matched with one assessor terminal or may be matched with a plurality of assessor terminals. In addition, according to an embodiment, the assessor terminal may be searched based on condition information, and one of the searched at least one loss assessor may be selected and matched. Here, the user terminal may be provided with a matching service such as 1 to 2 or 1 to 3 or more by simultaneously selecting and matching several loss adjusters. Here, the condition information may include location information, field information, and career information, but is not limited thereto.

For example, the user terminal may be matched with a single assessor terminal located closest based on its location information, and may be matched with a plurality of assessor terminals located within a certain radius based on its location information.

For example, when the user terminal inputs location information, field information, and career information as condition information, a loss adjuster that satisfies all three condition information among various damage adjusters may be extracted.

For example, when the user terminal receives three kinds of condition information, it can extract at least one loss adjuster in which all three condition information is established among various damage adjusters, and the extracted damage adjusters can be provided in a list format. I can. Here, the extracted loss adjusters may be listed in the order of the loss adjusters existing at a location close to the user terminal when location information exists among the condition information.

In one embodiment, the specialized field may be classified into a first type, a second type, a third type, and a fourth type, and the third type may be divided into an interpersonal and an object/vehicle.

In this case, the first type may include fields related to fire insurance, liability insurance, technology insurance and credit loss insurance, and the second type is related to marine insurance, including ship insurance, cargo insurance, aviation insurance, and transportation insurance. Fields can be included. Class 3 individuals may include fields related to a person's body due to an automobile accident, and Class III objects/vehicles may include fields related to vehicles and other property due to an automobile accident. Type 4 may include areas related to accident insurance, disease insurance, and nursing care insurance.

Alternatively, specialized fields may be divided into wealth, vehicle, body, and synthesis. In this case, the property may include a field related to insurance contracts, and the vehicle may include a vehicle caused by an automobile accident and other fields related to property. The body may include insurance contracts related to the body, areas related to the human body due to an automobile accident. The synthesis may include all of the above-described property, vehicle, and body.

Here, if the field of expertise is not input by the user, all of the fields may be selected. In addition, in the field of expertise, a choice according to the above-described classification may be provided to the user, and field information may be obtained by selecting one of the options by the user. In addition, when options are provided to the user, description information for each option may be additionally provided.

In one embodiment, the career information may mean information on the career of the loss adjuster, and may be any one of career information for each field or full career information. The career information may be input by the user, and if not input by the user, it may be set as irrelevant. In addition, the career information may be provided to the user with options such as irrelevant, 1 year, 3 years, 5 years, 10 years, etc., and career information may be obtained by selecting one of the options by the user. In an embodiment, the matching service may search and extract a loss adjuster having a career equal to or greater than the acquired career information and provide it to the user.

In an embodiment, other information in addition to the location information, field information, and career information described above may be used as condition information. For example, at least one of the winning rate, age, qualification acquisition date, number of case processing, number of consultations, number of pokes, number of likes, and star score may be used as condition information. For example, the condition information may be set as a 4 or more star score. Alternatively, the winning rate may be set to 80% or more. Alternatively, it can be set to acquire qualifications after 2007.

The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. Software modules 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 on any type 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) and stored in a medium in order to be combined with a computer as hardware to be executed. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments include various algorithms implemented with a combination of data structures, processes, routines or other programming elements, including C, C++ , Java, assembler, or the like may be implemented in a programming or scripting language. Functional aspects can be implemented with an algorithm running on one or more processors.

In the above, embodiments of the present invention have been described with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You can understand. Therefore, the embodiments described above are illustrative in all respects, and should be understood as non-limiting.

Claims (12)

In the fruit ratio determination method performed by the fruit ratio determination device,
Acquiring accident-related information including image information before and after the accident and location information of the accident site;
Obtaining information on the surrounding environment of the accident place based on the location information;
Acquiring driving information when an accident occurs based on the image information;
Deriving addition and subtraction factor information based on the surrounding environment information and the driving information;
Determining a fruit ratio through an artificial neural network based on the surrounding environment information, the driving information, and the additive and subtractive factor information; And
Including the step of providing information on the fruit ratio to the user,
How to determine the percentage of fruit.
The method of claim 1,
The surrounding environment information,
Including road type information of the accident place, speed limit information of the road, state information of the road, and building information within a certain distance from the accident place,
How to determine the percentage of fruit.
The method of claim 2,
The road status information,
Including at least one of the lane information of the road, curvature information of the road, longitudinal slope information of the road, and cross slope information of the road,
How to determine the percentage of fruit.
The method of claim 1,
The driving information,
Speed information of the accident vehicle at the time of the accident, driving direction information of the accident vehicle, speed information of surrounding vehicles within a certain distance from the accident vehicle, driving direction information of the surrounding vehicle, distance information between the vehicle and surrounding vehicles, and the accident Including at least one of signal information at the time of occurrence,
How to determine the percentage of fruit.
The method of claim 1,
The above information on the additive and subtractive factors,
Including at least one of information on whether the accident vehicle complies with the speed limit in the event of the accident, information on whether to comply with the signal, information on whether to comply with the safety distance, information on whether to comply with the lane, and information on interruption,
How to determine the percentage of fruit.
The method of claim 1,
The artificial neural network,
Learning based on at least one of negligence chart data, case-by-case damage adjuster opinion data, and case-by-case precedent data,
How to determine the percentage of fruit.
The method of claim 6,
The artificial neural network,
A method of determining the percentage of errors, including an artificial neural network learned by supervised learning.
The method of claim 7,
The supervised learning method,
Based on the error chart data, the opinion data of the damage adjuster for each case, and the case-by-case precedent data, the training data for the surrounding environment information, the driving information, and the additive and subtractive factor information and result data related to the error rate are extracted, and the training data And learning by changing weights for nodes included in the artificial neural network based on the result data.
How to determine the percentage of fruit.
The method of claim 1,
Information on the above fruit ratio,
Including a first percentage value for the user's negligence and a second percentage value for the other's negligence,
The sum of the first percent value and the second percent value is 100, and the first percent value and the second percent value are each represented by a multiple of 0 or 100 or less,
How to determine the percentage of fruit.
The method of claim 9,
Information on the above fruit ratio,
Further comprising reliability information according to the artificial neural network,
The reliability information includes a reliability value in percent,
The confidence value is rounded to the first decimal place,
How to determine the percentage of fruit.
A computer-readable recording medium having a program recorded thereon for performing the method for determining an error rate according to any one of claims 1 to 10.
In the fruit ratio determination apparatus for performing the fruit ratio determination method,
At least one processor; And
A memory for storing at least one instruction executed by the at least one processor,
The at least one command,
It is executed to acquire accident-related information including image information before and after the accident and location information of the accident site,
It is executed to obtain information on the surrounding environment of the accident place based on the location information,
It is executed to acquire driving information when an accident occurs based on the image information,
It is executed to derive addition and subtraction factor information based on the surrounding environment information and the driving information,
It is executed to determine a fruit ratio through an artificial neural network based on the surrounding environment information, the driving information, and the additive and subtractive factor information,
Executed to provide the user with information on the fruit ratio
Fruit ratio judgment device.

Images