TWI760747B - Liability judgment and claim system and method thereof for traffic accident - Google Patents
Liability judgment and claim system and method thereof for traffic accident Download PDFInfo
- Publication number
- TWI760747B TWI760747B TW109116209A TW109116209A TWI760747B TW I760747 B TWI760747 B TW I760747B TW 109116209 A TW109116209 A TW 109116209A TW 109116209 A TW109116209 A TW 109116209A TW I760747 B TWI760747 B TW I760747B
- Authority
- TW
- Taiwan
- Prior art keywords
- accident
- injury
- traffic accident
- traffic
- feature
- Prior art date
Links
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
Description
本發明關於一種交通事故之肇責判斷與理賠系統及方法,並且特別地,關於一種協助保險人員判斷肇責比例及傷害等級的系統及方法。 The present invention relates to a system and method for judging liability for a traffic accident and a claim settlement, and in particular, to a system and method for assisting insurance personnel in judging liability ratio and injury level.
車輛的發展至今已有數百年,而隨著科技不斷地進步,車輛已成為人們的代步工具,也成為人們不可或缺的交通工具。由於車輛的普及化,因此擁有車輛的人也越來越多。然而,在這個車輛數量眾多的時代中,交通的問題也日益顯著。 Vehicles have been developed for hundreds of years, and with the continuous advancement of technology, vehicles have become people's means of transportation and an indispensable means of transportation. Due to the popularity of vehicles, more and more people own vehicles. However, in this era of a large number of vehicles, the problem of traffic is also becoming more and more prominent.
在天氣狀況不佳、車輛的駕駛人不熟悉路況、不遵守交通規則等的因素下,經常會導致交通事故的發生,尤其是在車潮最多的時間(如上、下班)中,更容易發生交通事故。一般來說,當交通事故發生時,車輛的駕駛人會打電話報警並通知保險業者至現場評估與處理事故。由於交通事故可能發生在任何地點,警察或保險業者仍需花費一些時間才到達事故現場,因此,駕駛人需在事故現場等待相關處理人員。而為了讓保險業者釐清並判斷肇事責任,車輛需停留在事故現場。然而,事故現場往往因肇事責任不易立即判定,交通事故的當事人難以第一時間於事故現場達成和 解。進一步地,當交通事故發生在道路中央或十字路口時,停留在事故現場的車輛則會造成交通擁塞,若又在車潮最多的時間發生事故,則會嚴重地影響交通。 Under such factors as poor weather conditions, unfamiliar road conditions, non-compliance with traffic rules, etc., traffic accidents are often caused, especially during the most crowded times (such as commuting and commuting), traffic is more likely to occur ACCIDENT. Generally speaking, when a traffic accident occurs, the driver of the vehicle will call the police and notify the insurance company to go to the scene to assess and deal with the accident. Since a traffic accident can happen anywhere, it still takes some time for the police or insurance company to arrive at the accident scene, so the driver needs to wait at the accident scene for the relevant handlers. In order for the insurance company to clarify and determine the responsibility for the accident, the vehicle needs to stay at the scene of the accident. However, it is often difficult to immediately determine the responsibility of the accident at the accident scene, and it is difficult for the parties involved in the traffic accident to reach an agreement at the accident scene as soon as possible. untie. Further, when a traffic accident occurs in the middle of a road or at an intersection, vehicles staying at the accident site will cause traffic congestion, and if the accident occurs at the time when the traffic is most crowded, the traffic will be seriously affected.
一般來說,保險人員係根據交通事故初判表以及汽車肇事責任分攤處理原則判斷事故類型,以判斷事故的肇事責任比例。然而,由於汽車肇事責任分攤處理原則所記載的事故類型甚多,保險人員或社會大眾需查閱汽車肇事責任分攤處理原則的內容以找出對應的事故類型,進而得知肇事責任比例。此外,當交通事故發生駕駛或人員傷害時,保險人員亦需根據醫療診斷表以判斷傷害類型。因此,現行的車輛事故肇責及事故所造成的傷害的處理方式不僅降低效率並且提高成本。 Generally speaking, insurance personnel judge the type of accident according to the preliminary judgment table of traffic accident and the principle of sharing and handling the responsibility of automobile accident, so as to determine the proportion of responsibility for the accident. However, since there are many types of accidents recorded in the principle of sharing responsibility for auto accidents, insurance personnel or the general public need to check the content of the principle of sharing responsibility for vehicle accidents to find out the corresponding type of accident, and then know the proportion of responsibility for accidents. In addition, when driving or personal injury occurs in a traffic accident, insurance personnel also need to judge the type of injury based on the medical diagnosis table. Therefore, the current handling of vehicle accident liability and injuries caused by the accident not only reduces efficiency but also increases costs.
有鑑於此,本發明之一範疇在於提供一種交通事故之肇責判斷與理賠系統,以解決先前技術的問題。 In view of this, one of the scopes of the present invention is to provide a system for judging liability for traffic accidents and for settlement of claims, so as to solve the problems of the prior art.
根據本發明之一具體實施例,交通事故之肇責判斷與理賠系統用以處理並判定交通事故的事故責任及人員傷害。交通事故之肇責判斷與理賠系統包含事故資料庫、語意分析模組以及判斷模組。事故資料庫用以儲存肇責比例對照表以及傷害等級對照表。其中,肇責比例對照表包含複數個肇責比例且每一個肇責比例對應一事故特徵組合,並且傷害等級對照表包含複數個傷害等級且每一個傷害等級對應一傷害特徵組合。語意分析模組用以接收並分析對應交通事故的交通事故資料以及醫療診斷資料,以產生對應交通事故資料的至少一事故特徵以及對應醫療診斷資料的至少一傷害特徵。判斷模組連接事故資料庫以及語意分析模組。判斷模組以一 判斷模型分析交通事故資料以及醫療診斷資料並產生對應交通事故的肇責比例以及傷害等級。其中,判斷模型根據事故特徵以及傷害特徵分別找出對應交通事故的事故特徵組合以及傷害特徵組合。 According to a specific embodiment of the present invention, the traffic accident liability judgment and claim settlement system is used to process and determine the accident liability and personal injury of the traffic accident. The traffic accident liability judgment and claim settlement system includes an accident database, a semantic analysis module and a judgment module. The accident database is used to store the comparison table of the proportion of culprits and the level of injury. Wherein, the accident-responsibility ratio comparison table includes a plurality of accident-responsibility ratios, and each accident-responsibility ratio corresponds to an accident feature combination, and the injury level comparison table includes a plurality of injury levels, and each injury level corresponds to an injury feature combination. The semantic analysis module is used for receiving and analyzing traffic accident data and medical diagnosis data corresponding to the traffic accident to generate at least one accident feature corresponding to the traffic accident data and at least one injury feature corresponding to the medical diagnosis data. The judgment module is connected to the accident database and the semantic analysis module. The judgment module takes a The judgment model analyzes the traffic accident data and medical diagnosis data, and generates the proportion of responsibility and injury level corresponding to the traffic accident. Among them, the judgment model finds the accident feature combination and the injury feature combination corresponding to the traffic accident according to the accident feature and the injury feature respectively.
其中,語意分析模組為Word2Vec. Among them, the semantic analysis module is Word2Vec.
進一步地,本發明的交通事故之肇責判斷與理賠系統進一步包含學習模組連接事故資料庫以及語意分析模組。學習模組根據事故資料庫的事故特徵組合以及傷害特徵組合產生判斷模型,並且以機器學習的方式將語意分析模組所產生的事故特徵以及傷害特徵回傳至事故資料庫並進行分析以更新判斷模型。 Further, the system for judging responsibility for traffic accidents and claim settlement of the present invention further includes a learning module connected to the accident database and a semantic analysis module. The learning module generates a judgment model according to the accident feature combination and injury feature combination of the accident database, and returns the accident features and injury features generated by the semantic analysis module to the accident database by means of machine learning and analyzes to update the judgment Model.
其中,判斷模型為貝氏模型。 Among them, the judgment model is the Bayesian model.
在一具體實施例中,本發明的交通事故之肇責判斷與理賠系統進一步包含圖像辨識模組連接判斷模組。交通事故資料包含事故圖像資料並且醫療診斷資料包含診斷圖像資料。圖像辨識模組用以接收並分析事故圖像資料以及診斷圖像資料以產生對應交通事故資料的至少一事故特徵以及對應醫療診斷資料的至少一傷害特徵,並且傳送事故特徵及傷害特徵至判斷模組。 In a specific embodiment, the system for judging liability for a traffic accident and claim settlement of the present invention further includes an image recognition module connection judging module. The traffic accident data contains accident image data and the medical diagnosis data contains diagnostic image data. The image recognition module is used for receiving and analyzing the accident image data and the diagnostic image data to generate at least one accident feature corresponding to the traffic accident data and at least one injury feature corresponding to the medical diagnosis data, and transmit the accident feature and the injury feature to the judgment module.
在一具體實施例中,本發明的交通事故之肇責判斷與理賠系統進一步包含保險資料庫以及理算模組。理算模組連接保險資料庫以及判斷模組。保險資料庫用以儲存對應交通事故的交通事故保險以及醫療保險。其中,交通事故保險對應事故保險全額並且醫療保險對應醫療保險金額。理算模組根據對應交通事故的肇責比例以及事故保險金額產生事故理賠金額,並且根據對應交通事故的傷害等級以及醫療保險金額產生醫療理 賠金額。 In a specific embodiment, the traffic accident liability judgment and claim settlement system of the present invention further includes an insurance database and an adjustment module. The adjustment module is connected to the insurance database and the judgment module. The insurance database is used to store traffic accident insurance and medical insurance corresponding to traffic accidents. Among them, the traffic accident insurance corresponds to the full amount of the accident insurance and the medical insurance corresponds to the medical insurance amount. The adjustment module generates the accident compensation amount according to the proportion of liability of the corresponding traffic accident and the amount of accident insurance, and generates medical treatment according to the injury level of the corresponding traffic accident and the amount of medical insurance. compensation amount.
本發明之另一範疇在於提供一種交通事故之肇責判斷與理賠方法,以解決先前技術的問題。 Another scope of the present invention is to provide a method for judging the cause of a traffic accident and settling a claim, so as to solve the problems of the prior art.
根據本發明之一具體實施例,交通事故之肇責判斷與理賠方法用以處理並判定交通事故的事故責任及人員傷害。交通事故之肇責判斷與理賠方法包含以下步驟:步驟S1:預存肇責比例對照表以及傷害等級對照表,其中肇責比例對照表包含複數個肇責比例且每一個肇責比例對應一事故特徵組合,並且傷害等級對照表包含複數個傷害等級且每一個傷害等級對應一傷害特徵組合;步驟S2:分析對應交通事故的交通事故資料及醫療診斷資料,以產生對應交通事故資料的至少一事故特徵以及對應醫療診斷資料的至少一傷害特徵;以及步驟S3:以判斷模型分析交通事故資料及醫療診斷資料並產生對應交通事故的肇責比例以及傷害等級,其中判斷模型根據事故特徵及傷害特徵分別找出對應交通事故的事故特徵組合以及傷害特徵組合。 According to a specific embodiment of the present invention, a traffic accident liability judgment and claim settlement method is used to process and determine the accident liability and personal injury of the traffic accident. The method for judging and settling a liability for a traffic accident includes the following steps: Step S1: Pre-store a comparison table of the ratio of attribution and a comparison table of injury levels, wherein the comparison table of the ratio of attribution includes a plurality of ratios of attribution and each of the ratios of attribution corresponds to an accident feature combination, and the injury level comparison table includes a plurality of injury levels and each injury level corresponds to a combination of injury characteristics; Step S2: analyze the traffic accident data and medical diagnosis data corresponding to the traffic accident to generate at least one accident feature corresponding to the traffic accident data And at least one injury feature corresponding to the medical diagnosis data; and step S3: analyze the traffic accident data and the medical diagnosis data with a judgment model and generate a liability ratio and an injury level corresponding to the traffic accident, wherein the judgment model finds out respectively according to the accident characteristics and the injury characteristics. The accident feature combination and injury feature combination corresponding to the traffic accident are obtained.
在一具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S41:根據事故特徵組合以及傷害特徵組合產生判斷模型;以及步驟S42:對至少一事故特徵及至少一傷害特徵進行機器學習,以更新判斷模型。 In a specific embodiment, the method for judging liability for a traffic accident and settling a claim further includes the following steps: Step S41 : generating a judgment model according to the accident feature combination and the injury feature combination; and Step S42 : analyzing at least one accident feature and at least one injury feature Machine learning is performed to update the judgment model.
在一具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S6:預存對應交通事故的交通事故保險及醫療保險,交通事故保險對應事故保險金額並且醫療保險對應醫療保險金額;以及步驟S7:根據對應交通事故的肇責比例及事故保險金額產生事故理賠金額, 並且根據對應交通事故的傷害等級及醫療保險金額產生醫療理賠金額。 In a specific embodiment, the method for judging the liability of the traffic accident and the claim settlement method further comprises the following steps: Step S6: Pre-store traffic accident insurance and medical insurance corresponding to the traffic accident, the traffic accident insurance corresponds to the accident insurance amount and the medical insurance corresponds to the medical insurance amount ; And step S7: generate the accident compensation amount according to the proportion of responsibility and the accident insurance amount corresponding to the traffic accident, The amount of medical claims is generated according to the injury level of the corresponding traffic accident and the amount of medical insurance.
在一具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S8:分析對應交通事故資料的事故圖像資料以及對應醫療診斷資料的診斷圖像資料,以產生對應交通事故資料的事故特徵以及對應醫療診斷資料的傷害特徵。 In a specific embodiment, the method for judging liability for a traffic accident and settling a claim further includes the following steps: Step S8: analyzing the accident image data corresponding to the traffic accident data and the diagnostic image data corresponding to the medical diagnosis data to generate the corresponding traffic accident The accident characteristics of the data and the injury characteristics of the corresponding medical diagnosis data.
綜上所述,本發明的交通事故之肇責判斷與理賠系統可藉由語意分析的方式從事故文件中找出事故特徵,以使系統能夠自動判斷交通事故的肇事比例及傷害等級,而不需經由人為進行判斷。並且,本發明的系統也藉由圖像判斷的方式找出事故特徵,並且結合機器學習預測事故類型,以使系統能夠更精準且更快速地判斷出交通事故的肇事比例及傷害等級。此外。本發明的系統結合了保險理賠系統,以使系統除了能夠判斷交通事故的肇事比例及傷害等級之外,也可預先估算車輛或人員的理賠金額,以提高後續理賠的效率。因此,本發明的交通事故之肇責判斷與理賠系統不僅可提高交通事故的處理效率,並且可降低時間以及人力成本。 To sum up, the traffic accident liability judgment and claim settlement system of the present invention can find out the accident characteristics from the accident documents by means of semantic analysis, so that the system can automatically judge the accident proportion and the injury level of the traffic accident without Human judgment is required. In addition, the system of the present invention also finds the accident characteristics by means of image judgment, and combines machine learning to predict the accident type, so that the system can more accurately and quickly determine the accident rate and injury level of the traffic accident. also. The system of the present invention is combined with an insurance claim settlement system, so that the system can not only judge the accident rate and injury level of traffic accidents, but also pre-estimate the claim settlement amount of vehicles or personnel, so as to improve the efficiency of subsequent claim settlement. Therefore, the traffic accident liability judgment and claim settlement system of the present invention can not only improve the processing efficiency of traffic accidents, but also reduce time and labor costs.
1:交通事故之肇責判斷與理賠系統 1: Judgment and Claims System for the Cause of Traffic Accidents
11、21:事故資料庫 11, 21: Accident Database
12、22:語意分析模組 12, 22: Semantic Analysis Module
13、23:判斷模組 13, 23: Judgment module
14、24:學習模組 14, 24: Learning modules
16、26:保險資料庫 16, 26: Insurance database
17、27:理算模組 17, 27: Adjustment module
25:圖像辨識模組 25: Image recognition module
S1~S8:步驟 S1~S8: Steps
圖1係繪示根據本發明之一具體實施例之交通事故之肇責判斷與理賠系統的功能方塊圖。 FIG. 1 is a functional block diagram of a traffic accident judging and claim settlement system according to an embodiment of the present invention.
圖2係繪示根據本發明之另一具體實施例之交通事故之肇責判斷與理賠系統的功能方塊圖。 FIG. 2 is a functional block diagram of a traffic accident judging and claim settlement system according to another embodiment of the present invention.
圖3係繪示根據本發明之一具體實施例之交通事故之肇責判斷與理賠方法的步驟流程圖。 FIG. 3 is a flow chart showing the steps of a method for judging responsibility for a traffic accident and making a claim according to an embodiment of the present invention.
圖4係繪示根據圖3之交通事故之肇責判斷與理賠方法進一步的步驟流程圖。 FIG. 4 is a flow chart showing further steps of the method for judging responsibility for a traffic accident and making a claim according to FIG. 3 .
圖5係繪示根據圖3之交通事故之肇責判斷與理賠方法進一步的步驟流程圖。 FIG. 5 is a flow chart showing further steps of the method for judging responsibility for a traffic accident and settling claims according to FIG. 3 .
圖6係繪示根據本發明之另一具體實施例之交通事故之肇責判斷與理賠方法的步驟流程圖。 FIG. 6 is a flowchart showing the steps of a method for judging responsibility for a traffic accident and making a claim according to another embodiment of the present invention.
為了讓本發明的優點,精神與特徵可以更容易且明確地了解,後續將以具體實施例並參照所附圖式進行詳述與討論。值得注意的是,這些具體實施例僅為本發明代表性的具體實施例,其中所舉例的特定方法、系統等並非用以限定本發明或對應的具體實施例。 In order for the advantages, spirit and features of the present invention to be more easily and clearly understood, detailed descriptions and discussions will follow with reference to the accompanying drawings by way of specific embodiments. It should be noted that these specific embodiments are only representative specific embodiments of the present invention, and the specific methods, systems, etc. exemplified therein are not intended to limit the present invention or the corresponding specific embodiments.
在本公開的各種實施例中使用的術語僅用於描述特定實施例的目的並且並非意在限制本公開的各種實施例。如在此所使用,單數形式意在也包括複數形式,除非上下文清楚地另有指示。除非另有限定,否則在這裡使用的所有術語(包括技術術語和科學術語)具有與本公開的各種實施例所屬領域普通技術人員通常理解的含義相同的含義。所述術語(諸如在一般使用的詞典中限定的術語)將被解釋為具有與在相關技術領域中的語境含義相同的含義並且將不被解釋為具有理想化的含義或過於正式的含義,除非在本公開的各種實施例中被清楚地限定。 The terminology used in the various embodiments of the present disclosure is for the purpose of describing particular embodiments only and is not intended to limit the various embodiments of the present disclosure. As used herein, the singular is intended to include the plural as well, unless the context clearly dictates otherwise. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of this disclosure belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning, unless explicitly defined in various embodiments of the present disclosure.
在本說明書的描述中,參考術語“一個實施例、一些實施例、示例、具體示例、或一些示例”等的描述意指結合該實施例或示例描述的具體特徵、結構、材料或者特點包含於本發明的至少一個實施例或示 例中。在本說明書中,對上述術語的示意性表述不一定指的是相同的實施例或示例。而且,描述的具體特徵、結構、材料或者特點可以在任何的一個或多個實施例或示例中以合適的方式結合。 In the description of this specification, a description with reference to the terms "one embodiment, some embodiments, examples, specific examples, or some examples" etc. means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is contained in at least one embodiment or illustration of the present invention example. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
此外,本發明要素或組分前的不定冠詞“一種”和“一個”對要素或組分的數量要求(即出現次數)無限制性。因此“一個”或“一種”應被解讀為包括一個或至少一個,並且單數形式的要素或組分也包括複數形式,除非所述數量明顯旨指單數形式。 Furthermore, the indefinite articles "a" and "an" preceding an element or component of the invention are not limiting on the quantitative requirement (ie, the number of occurrences) of the element or component. Thus "a" or "an" should be read to include one or at least one, and elements or components in the singular also include the plural unless the number is clearly intended to be in the singular.
請參考圖1。圖1係繪示根據本發明之一具體實施例之交通事故之肇責判斷與理賠系統1的功能方塊圖。本發明的交通事故之肇責判斷與理賠系統1,用以處理並判定交通事故的事故責任及人員傷害。如圖1所示,交通事故之肇責判斷與理賠系統1包含事故資料庫11、語意分析模組12以及判斷模組13。事故資料庫11用以儲存肇責比例對照表以及傷害等級對照表。其中,肇責比例對照表包含複數個肇責比例且每一個肇責比例對應一事故特徵組合,並且傷害等級對照表包含複數個傷害等級且每一個傷害等級對應一傷害特徵組合。語意分析模組12用以接收並分析對應交通事故的交通事故資料以及醫療診斷資料,以產生對應交通事故資料的至少一事故特徵以及對應醫療診斷資料的至少一傷害特徵。判斷模組13連接事故資料庫11以及語意分析模組12。判斷模組13以一判斷模型分析交通事故資料以及醫療診斷資料並產生對應交通事故的肇責比例以及傷害等級。
Please refer to Figure 1. FIG. 1 is a functional block diagram of a
於實務中,事故資料庫11可為一儲存裝置(如:硬碟),並且可儲存對應各種事故的類型、描述、特徵、責任比例等相關資料的資料庫。而肇責比例對照表以及傷害等級對照表可為由第三方公證機關所提供的對
照表,例如:汽機車肇事責任分攤處理原則、保發中心所制定的殘廢等級表。請參考表1及表2。表1為一具體實施例之肇責比例對照表,表2為一具體實施例之傷害等級對照表。如表1及表2所示,肇責比例對照表包含複數個事故類型以及肇責比例,並且傷害等級對照表包含複數個傷害程度以及傷害等級。每一種肇責比例對應一事故類型,而每一種事故類型對應一事故特徵組合,並且事故特徵組合係由至少一事故特徵所組成;每一種傷害等級對應一傷害程度,而每一種傷害程度係由對應一傷害特徵組合,並且傷害特徵組合係由至少一傷害特徵所組成;而多個事故類型及多個傷害程度可分別對應相同的肇責比例及傷害等級。事故特徵以及傷害特徵可為單字、詞語或由單字及詞語所組合成可作為判斷的句子。舉例來說,事故特徵可為表1中第1項的事故類型中的「未保持」、「安全距離」,也可為表1中第2項的「直行」、「左轉彎」、「碰撞」。而傷害特徵可為表2中第1項的傷害程度中的「一手」、「五指」、「永久喪失機能」,也可為表2中第3項的「中樞神經系統」、「遺存障害」、「無礙勞動」。
In practice, the
交通事故資料可為由第三方公證機關所提供的交通事故初判表,並且醫療診斷資料可為由醫療機構所提供的診斷書。當語意分析模組12接收交通事故資料以及醫療診斷資料後,語意分析模組12可以語意分析的方式分析交通事故資料以及醫療診斷資料,並且提取所對應的事故特徵以及傷害特徵。進一步地,語意分析模組12也可為Word2Vec。當語意分析模組12接收交通事故資料以及醫療診斷資料後,語意分析模組12將交通事故資料以及醫療診斷資料中的文字轉換成向量的形式並進行向量運算,以提取事故特徵以及傷害特徵。舉例來說,當交通事故資料包含「A車於倒車時沒有注意到位於A車後方的B車」時,則語意分析組12可根據交通事故資料判斷出「倒車」的事故特徵,並且根據「沒有注意」判斷出「未注意」的事故特徵。又一例子中,當醫療診斷資料包含「病患的雙手的十指須截肢」時,則語意分析模組12可根據醫療診斷資料並斷出「雙手」及「十指」的傷害特徵,並且根據「截肢」判斷出「永久喪失機能」的傷害特徵。
The traffic accident data can be a preliminary traffic accident judgment form provided by a third-party notary agency, and the medical diagnosis data can be a medical certificate provided by a medical institution. After the
判斷模組13的判斷模型131可根據語意分析模組12所擷取的事故特徵以及傷害特徵分別重新組合成對應交通事故的事故特徵組合以及傷害特徵組合。當判斷模型131將組合事故特徵以及傷害特徵組合成事故特徵組合及傷害特徵組合後,判斷模組13產生對應事故特徵組合及傷害特徵
組合的肇責比例以及傷害等級。舉例來說,當語意分析模組12所擷取的事故特徵為「未保持」、「安全距離」、「追撞」,此時,判斷模型131根據事故特徵組合出表1中第1項的事故類型,接著判斷模組13產生對應表1中第1項的事故類型的肇事責任為100%。又一例子中,當語意分析模組12所擷取的傷害特徵為「雙目」、「視力」、「0.06以下」,此時,判斷模型131根據事故特徵組合出表2中第4項的傷害類型,接著判斷模組13產生對應表2中第4項的傷害類型的傷害等級為5。
The judging model 131 of the judging
進一步地,交通事故之肇責判斷與理賠系統1包含學習模組14連接事故資料庫11以及語意分析模組12。學習模組14根據事故資料庫11的事故特徵組合及該傷害特徵組合產生判斷模型131,並且以機器學習的方式將語意分析模組12所產生的事故特徵及傷害特徵回傳至事故資料庫11以作為歷史資料,並將事故資料庫11中的資料進行分析以更新該判斷模型131。於實務中,學習模組14可整合於一機器學習晶片或程式用以分析語意分析模組12所產生的事故特徵及傷害特徵。詳言之,學習模組14可係根據事故特徵及傷害特徵的出現次數或比例預測事故特徵組合及該傷害特徵組合,並且將出現比例較高的事故特徵組合及該傷害特徵組合優先排列於判斷模型131中,進而更新判斷模型131。因此,當下次判斷模組13接收語意分析模組12所產生的事故特徵及傷害特徵時,判斷模組13可根據更新後的判斷模型131優先判斷比例較高的事故特徵組合及該傷害特徵組合,以減少分析時間,進而提高效率。而判斷模型131也可為貝氏模型。進一步地,學習模組14可透過過採樣(Oversampling)的方式更新判斷組13。由於一個肇責比例及傷害等級可對應多個事故類型及多個傷害程度,並且每一種肇責比
例以及傷害等級的事故類型以及傷害程度的文本數量比不同。因此,判斷模型131可透過過採樣的方式調整每一種肇責比例以及傷害等級的文本數量,以減少判斷模組13偏好分析特定的肇責比例以及傷害等級,進而提高準確性。
Further, the
在本具體實施例中,交通事故之肇責判斷與理賠系統1進一步包含保險資料庫16及理算模組17。理算模組17連接保險資料庫以及判斷模組。保險資料庫用以儲存對應交通事故的交通事故保險以及醫療保險。交通事故保險對應一事故保險金額,並且醫療保險對應一醫療保險金額。於實務中,交通事故保險可為車輛的車輛強制險、車體損失險等,並且醫療保險可為車輛的駕駛或人員的醫療險、意外險等。事故保險金額可為車輛所投保的車體損失險的保障金額,並且醫療保險金額可為駕駛或人員所投保的意外險的保障金額。當判斷模組12產生肇責比例以及傷害等級後,理算模組17可依照肇責比例所對應的理賠比例計算出事故理賠金額,並且可依照傷害等級所對應的理賠比例計算出醫療理賠金額。因此,本發明的交通事故之肇責判斷與理賠系統不僅能夠判斷事故責任之外,也可快速地計算理賠金額,以減少時間成本並提高事故處理效率。
In this specific embodiment, the
而判斷模組13除了可分析語意分析模組12所提供的事故特徵以及傷害特徵之外,也可接收其他形式所產生的事故特徵以及傷害特徵。請參考圖2,圖2係繪示根據本發明之另一具體實施例之交通事故之肇責判斷與理賠系統2的功能方塊圖。本具體實施例與前述的具體實施例的不同之處係在於本具體實施例的交通事故之肇責判斷與理賠系統2進一步包含圖像辨識模組25。圖像辨識模組25連接判斷模組22。交通事故資料可包
含事故圖像資料,並且醫療診斷資料可包含診斷圖像資料。圖像辨識模組用以接收並分析事故圖像資料及診斷圖像資料以產生對應交通事故資料的事故特徵及對應醫療診斷資料的傷害特徵。於實務中,圖像辨識模組25可為智慧圖像辨識晶片,而事故圖像資料可為交通事故照片(如:碰撞後的照片、車輛碰撞處的照片等),並且診斷圖像資料可為X光片、核磁共振影像(MRI)等。舉例來說,圖像辨識模組25可根據車輛的碰撞位置判斷出「被追撞」的事故特徵,並且可根據姆指截肢的X光片判斷出「手指」、「姆指」、「缺失」的傷害特徵。進一步地,圖像辨識模組25將分析後所產生的事故特徵以及傷害特徵傳送至判斷模組23以供判斷模組23進行判斷。在一具體實施例中,本發明的交通事故之肇責判斷與理賠系統可同時接收語意分析模組以及影像辨識組所產生的事故特徵以及傷害特徵,以提高肇責比例以及傷害等級的準確性,進而提高效率。請注意,本具體實施例中的事故資料庫21、語意分析模組22、學習模組24、判斷模組23、保險資料庫26及理算模組27的功能與前具體實施例所對應的元件的功能大致相同,於此不再贅述。
In addition to analyzing the accident features and injury features provided by the
請參考圖3。圖3係繪示根據本發明之一具體實施例之交通事故之肇責判斷與理賠方法的步驟流程圖。圖3的步驟可由圖1的交通事故之肇責判斷與理賠系統達成。在本具體實施例中,交通事故之肇責判斷與理賠方法用以處理並判定交通事故的事故責任及人員傷害。交通事故之肇責判斷與理賠方法包含以下步驟:步驟S1:於事故資料庫11預存肇責比例對照表以及傷害等級對照表,其中肇責比例對照表包含複數個肇責比例且每一個肇責比例對應一事故特徵組合,並且傷害等級對照表包含複數個傷害等級且每一個傷害等級對應一傷害特徵組合;步驟S2:語意分析模組12分
析對應交通事故的交通事故資料以及醫療診斷資料,以產生對應交通事故資料的事故特徵以及對應該醫療診斷資料的傷害特徵;以及步驟S3:判斷模組13以判斷模型131分析交通事故資料以及醫療診斷資料並產生對應交通事故的肇責比例以及傷害等級,其中判斷模型根據事故特徵及傷害特徵分別找出對應交通事故的事故特徵組合以及傷害特徵組合。
Please refer to Figure 3. FIG. 3 is a flow chart showing the steps of a method for judging responsibility for a traffic accident and making a claim according to an embodiment of the present invention. The steps of FIG. 3 can be achieved by the traffic accident culpability judgment and claim settlement system of FIG. 1 . In this specific embodiment, the traffic accident liability judgment and claim settlement method is used to process and determine the accident liability and personal injury of the traffic accident. The method of judging the liability for a traffic accident and setting up a claim includes the following steps: Step S1: Pre-store the comparison table of the ratio of liability and the comparison table of injury levels in the
請參考圖4。圖4係繪示根據圖3之交通事故之肇責判斷與理賠方法的進階流程圖。在本具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S41:學習模組14根據事故資料庫11中的事故特徵組合以及傷害特徵組合產生判斷模型131;以及步驟S42:學習模組14對事故特徵及傷害特徵進行機器學習,以更新判斷模型131。於實務中,當肇責比對照表以及傷害等級對照表儲存於事故資料庫11後,學習模組14可根據事故資料庫11中的資料產生判斷模型131並傳送判斷模型至判斷模組13。而當語意分析模組12分析出事故特徵及傷害特徵,並且判斷模組13產生對應交通事故的肇責比例及傷害等級後,學習模組14將事故特徵及傷害特徵回傳至事故資料庫11以作為歷史資料,並且再將事故資料庫11內的資料進行機器學習以更新判斷模組131。
Please refer to Figure 4. FIG. 4 is an advanced flow chart of the method for judging responsibility for a traffic accident and making a claim according to FIG. 3 . In this specific embodiment, the method for judging the cause of a traffic accident and settling a claim further includes the following steps: Step S41 : the learning
請參考圖5。圖5係繪示根據圖3之交通事故之肇責判斷與理賠方法的進階流程圖。在本具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S6:於保險資料庫16預存對應交通事故的交通事故保險以及醫療保險,交通事故保險對應一事故保險金額並且醫療保險對應一醫療保險金額;以及步驟S7:理算模組17根據對應交通事故的肇責比例以及事故保險金額產生事故理賠金額,並且根據對應交通事故的傷
害等級以及醫療保險金額產生醫療理賠金額。於實務中,當判斷模組13產生對應交通事故的肇責比例及傷害等級後,理算模組17再依照肇責比例及傷害等級的理賠比例計算醫療保險金額產生醫療理賠金額。而步驟S1與步驟S6可互相交換,也可同時進行。
Please refer to Figure 5. FIG. 5 is an advanced flow chart of the method for judging responsibility for a traffic accident and making a claim according to FIG. 3 . In this specific embodiment, the method for judging the responsibility of a traffic accident and settling a claim further includes the following steps: Step S6: Pre-store the traffic accident insurance and medical insurance corresponding to the traffic accident in the
請參考圖6。圖6係繪示根據本發明之另一具體實施例之交通事故之肇責判斷與理賠方法的步驟流程圖。圖6的步驟可由圖2的交通事故之肇責判斷與理賠系統達成。在本具體實施例中,交通事故之肇責判斷與理賠方法進一步包含以下步驟:步驟S8:圖像辨識模組25分析對應交通事故資料的事故圖像資料以及對應醫療診斷資料的診斷圖像資料,以產生對應交通事故資料的事故特徵以及對應醫療診斷資料的傷害特徵。於實務中,步驟S2與步驟S8可互相交換,也可同時進行。
Please refer to Figure 6. FIG. 6 is a flowchart showing the steps of a method for judging responsibility for a traffic accident and making a claim according to another embodiment of the present invention. The steps in FIG. 6 can be achieved by the traffic accident determination and claim system of FIG. 2 . In this specific embodiment, the method for judging the responsibility of a traffic accident and settling a claim further includes the following steps: Step S8: the
綜上所述,本發明的交通事故之肇責判斷與理賠系統可藉由語意分析的方式從事故文件中找出事故特徵,以使系統能夠自動判斷交通事故的肇事比例及傷害等級,而不需經由人為進行判斷。並且,本發明的系統也藉由圖像判斷的方式找出事故特徵,並且結合機器學習預測事故類型,以使系統能夠更精準且更快速地判斷出交通事故的肇事比例及傷害等級。此外。本發明的系統結合了保險理賠系統,以使系統除了能夠判斷交通事故的肇事比例及傷害等級之外,也可預先估算車輛或人員的理賠金額,以提高後續理賠的效率。因此,本發明的交通事故之肇責判斷與理賠系統不僅可提高交通事故的處理效率,並且可降低時間以及人力成本。 To sum up, the traffic accident liability judgment and claim settlement system of the present invention can find out the accident characteristics from the accident documents by means of semantic analysis, so that the system can automatically judge the accident proportion and the injury level of the traffic accident without Human judgment is required. In addition, the system of the present invention also finds the accident characteristics by means of image judgment, and combines machine learning to predict the accident type, so that the system can more accurately and quickly determine the accident rate and injury level of the traffic accident. also. The system of the present invention is combined with an insurance claim settlement system, so that the system can not only judge the accident rate and injury level of traffic accidents, but also pre-estimate the claim settlement amount of vehicles or personnel, so as to improve the efficiency of subsequent claim settlement. Therefore, the traffic accident liability judgment and claim settlement system of the present invention can not only improve the processing efficiency of traffic accidents, but also reduce time and labor costs.
藉由以上較佳具體實施例之詳述,係希望能更加清楚描述本發明之特徵與精神,而並非以上述所揭露的較佳具體實施例來對本發明之 範疇加以限制。相反地,其目的是希望能涵蓋各種改變及具相等性的安排於本發明所欲申請之專利範圍的範疇內。因此,本發明所申請之專利範圍的範疇應根據上述的說明作最寬廣的解釋,以致使其涵蓋所有可能的改變以及具相等性的安排。 Through the detailed description of the preferred embodiments above, it is hoped that the features and spirit of the present invention can be described more clearly, rather than the preferred embodiments disclosed above to describe the present invention. scope is restricted. On the contrary, the intention is to cover various modifications and equivalent arrangements within the scope of the claimed scope of the present invention. Therefore, the scope of the patentable scope for which the present invention is claimed should be construed in the broadest sense in accordance with the above description so as to encompass all possible modifications and equivalent arrangements.
1、2:交通事故之肇責判斷與理賠系統 1, 2: Judgment and claim settlement system for traffic accidents
11:事故資料庫 11: Accident Database
12:語意分析模組 12: Semantic Analysis Module
13:判斷模組 13: Judgment Module
14:學習模組 14: Learning Modules
16:保險資料庫 16: Insurance Database
17:理算模組 17: Adjustment module
Claims (8)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109116209A TWI760747B (en) | 2020-05-15 | 2020-05-15 | Liability judgment and claim system and method thereof for traffic accident |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109116209A TWI760747B (en) | 2020-05-15 | 2020-05-15 | Liability judgment and claim system and method thereof for traffic accident |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202145122A TW202145122A (en) | 2021-12-01 |
TWI760747B true TWI760747B (en) | 2022-04-11 |
Family
ID=80783900
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109116209A TWI760747B (en) | 2020-05-15 | 2020-05-15 | Liability judgment and claim system and method thereof for traffic accident |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI760747B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9830663B2 (en) * | 2012-11-08 | 2017-11-28 | Hartford Fire Insurance Company | System and method for determination of insurance classification and underwriting determination for entities |
CN109214781A (en) * | 2018-09-12 | 2019-01-15 | 医倍思特(北京)医疗信息技术有限公司 | A kind of people hurts the check method of Claims Resolution setting loss expense |
CN109961056A (en) * | 2019-04-02 | 2019-07-02 | 浙江科技学院 | Traffic accident responsibility identification, system and equipment based on decision Tree algorithms |
TWM591674U (en) * | 2019-10-05 | 2020-03-01 | 業務人資訊有限公司 | Underwriting claims assistance system |
-
2020
- 2020-05-15 TW TW109116209A patent/TWI760747B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9830663B2 (en) * | 2012-11-08 | 2017-11-28 | Hartford Fire Insurance Company | System and method for determination of insurance classification and underwriting determination for entities |
CN109214781A (en) * | 2018-09-12 | 2019-01-15 | 医倍思特(北京)医疗信息技术有限公司 | A kind of people hurts the check method of Claims Resolution setting loss expense |
CN109961056A (en) * | 2019-04-02 | 2019-07-02 | 浙江科技学院 | Traffic accident responsibility identification, system and equipment based on decision Tree algorithms |
TWM591674U (en) * | 2019-10-05 | 2020-03-01 | 業務人資訊有限公司 | Underwriting claims assistance system |
Also Published As
Publication number | Publication date |
---|---|
TW202145122A (en) | 2021-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11664043B2 (en) | Real-time verbal harassment detection system | |
US20180174446A1 (en) | System and method for traffic violation avoidance | |
US9272658B2 (en) | Attention and event management | |
WO2019114805A1 (en) | Method for determining safe speed information of road | |
WO2021012504A1 (en) | Intelligent traffic-based road information prompt method, device, server, and medium | |
DE112016005335T5 (en) | Automated driver assistance device, automated driver assistance system, automated driver assistance procedure, program and recording medium | |
EP2009398A3 (en) | Vehicle-position-recognition apparatus and vehicle-position-recognition program | |
US20170270377A1 (en) | Method and device for recognizing traffic signs | |
EP2798307A1 (en) | Navigation systems that enhance driver awareness | |
Cunningham et al. | A survey of public opinion on automated vehicles in Australia and New Zealand | |
CN102486380A (en) | Vehicle navigation method and device | |
TWI760747B (en) | Liability judgment and claim system and method thereof for traffic accident | |
CN111488792A (en) | System and method for predicting pedestrian behavior | |
Strong | When apps pollute: Regulating transportation network companies to maximize environmental benefits | |
US8378849B2 (en) | Enabling driver communication | |
Hurwitz et al. | Implications of distracted driving on start-up lost time for dual left-turn lanes | |
EP3455097B1 (en) | Method for controlling voice-controlled operating interfaces in motor vehicles and device for performing the method | |
CN114373311B (en) | Vehicle driving guiding method and device | |
Lederman et al. | Fault-y reasoning: navigating the liability terrain in intelligent transportation systems | |
WO2022041971A1 (en) | Positioning reliability test method and related device | |
Puthon et al. | Improvement of multisensor fusion in speed limit determination by quantifying navigation reliability | |
Ali | Traffic accidents and road safety management; a comparative analysis and evaluation in industrial, developing and rich-developing countries | |
US20040236505A1 (en) | Method and device for ouput of data on an attribute on a digital street map | |
WO2019001808A1 (en) | Method for assisting a user of a motor vehicle with travel planning, taking into consideration vehicle-specific attributes, navigation device, storage medium, mobile terminal, server device, and motor vehicle | |
WO2024005160A1 (en) | Image processing device, image processing method, image processing system, and program |