TW202345078A - Server for predicting claim amount - Google Patents
Server for predicting claim amount Download PDFInfo
- Publication number
- TW202345078A TW202345078A TW111118135A TW111118135A TW202345078A TW 202345078 A TW202345078 A TW 202345078A TW 111118135 A TW111118135 A TW 111118135A TW 111118135 A TW111118135 A TW 111118135A TW 202345078 A TW202345078 A TW 202345078A
- Authority
- TW
- Taiwan
- Prior art keywords
- training
- processor
- amount
- server
- transceiver
- Prior art date
Links
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 14
- 238000003745 diagnosis Methods 0.000 claims description 10
- 238000003058 natural language processing Methods 0.000 claims description 5
- 238000001356 surgical procedure Methods 0.000 description 7
- 230000015654 memory Effects 0.000 description 4
- 238000000034 method Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Abstract
Description
本揭露是有關於一種用於預測理賠金額的伺服器。This disclosure is about a server used to predict claim amounts.
目前,針對特定保單,由於保單中的保單條款往往過於複雜/瑣碎,用戶通常無法得知此特定保單以及特定診斷書(例如包括診斷證明/手術級別的,醫生診斷書)所能夠獲得的理賠金額。舉例來說,用戶無法基於保單中的保單條款清楚地得知,進行第1級醫療手術能獲得的理賠金額,及/或進行第2級醫療手術能獲得的理賠金額。因此,用戶將難以從眾多保單及/或眾多診斷書中選擇。基此,需要一個用於預測理賠金額的伺服器。Currently, for a specific policy, because the policy terms in the policy are often too complex/trivial, users are usually unable to know the claim amount that can be obtained from this specific policy and a specific diagnosis (for example, including a diagnosis certificate/surgery level, doctor’s diagnosis) . For example, users cannot clearly know the claim amount that can be obtained by performing Level 1 medical surgery and/or the claim amount that can be obtained by performing Level 2 medical surgery based on the policy terms in the policy. Therefore, users will have difficulty choosing from numerous insurance policies and/or numerous medical certificates. Based on this, a server for predicting the claim amount is needed.
本揭露的用於預測理賠金額的伺服器包括儲存媒體、收發器以及處理器。儲存媒體儲存人工智慧模型。收發器通訊連接至用戶電子裝置。處理器耦接儲存媒體以及收發器,其中處理器通過收發器從用戶電子裝置接收保單以及診斷書;處理器將保單以及診斷書輸入至人工智慧模型以預測理賠金額;處理器通過收發器傳送理賠金額至用戶電子裝置。The server disclosed in this disclosure for predicting the claim amount includes a storage medium, a transceiver and a processor. The storage medium stores the artificial intelligence model. The transceiver is communicatively connected to the user electronic device. The processor is coupled to the storage medium and the transceiver, wherein the processor receives the insurance policy and the diagnosis certificate from the user electronic device through the transceiver; the processor inputs the insurance policy and the diagnosis certificate into the artificial intelligence model to predict the claim amount; the processor transmits the claim settlement through the transceiver The amount is transferred to the user's electronic device.
為讓本揭露的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。In order to make the above features and advantages of the present disclosure more obvious and understandable, embodiments are given below and described in detail with reference to the attached drawings.
圖1是根據本揭露的一實施例繪示的用於預測理賠金額的伺服器100的示意圖。伺服器100可包括儲存媒體130、收發器110以及處理器120。FIG. 1 is a schematic diagram of a
儲存媒體130例如是任何型態的固定式或可移動式的隨機存取記憶體(random access memory,RAM)、唯讀記憶體(read-only memory,ROM)、快閃記憶體(flash memory)、硬碟(hard disk drive,HDD)、固態硬碟(solid state drive,SSD)或類似元件或上述元件的組合,而用於儲存可由處理器120執行的多個模組或各種應用程式。儲存媒體130可儲存人工智慧模型。本實施例的人工智慧模型可包括但不限於,時延神經網路(Time Delay Neural Network,TDNN)、最大熵(Maximum Entropy)、支援向量機(Support Vector Machine)、梯度提升決策樹(Gradient Boosting Decision Tree)、卷積神經網路(Convolutional Neural Network,CNN)或者長短期記憶網路(Long Short Term Memory Networks,LSTM)。人工智慧模型的用途將於後續說明。The
收發器110以無線或有線的方式傳送及接收訊號。收發器110可通訊連接至用戶電子裝置200。The
處理器120例如是中央處理單元(central processing unit,CPU),或是其他可程式化之一般用途或特殊用途的微控制單元(micro control unit,MCU)、微處理器(microprocessor)、數位信號處理器(digital signal processor,DSP)、可程式化控制器、特殊應用積體電路(application specific integrated circuit,ASIC)、圖形處理器(graphics processing unit,GPU)、影像訊號處理器(image signal processor,ISP)、影像處理單元(image processing unit,IPU)、算數邏輯單元(arithmetic logic unit,ALU)、複雜可程式邏輯裝置(complex programmable logic device,CPLD)、現場可程式化邏輯閘陣列(field programmable gate array,FPGA)或其他類似元件或上述元件的組合。處理器120可耦接儲存媒體130以及收發器110。The
為了提高後續人工智慧模型預測理賠金額的準確度,處理器120可預先利用包括多個訓練保單、多個訓練診斷書以及多個訓練理賠金額的訓練資料集來訓練人工智慧模型。詳細而言,此處的「多個訓練保單」可為,「對應於用戶識別1的,包括保單條款1的訓練保單1」以及「對應於用戶識別2的,包括保單條款2的訓練保單2」等多個訓練保單,且此處的「多個訓練診斷書」可為,「對應於用戶識別1的,包括診斷證明/手術級別1的訓練診斷書1」以及「對應於用戶識別2的,包括診斷證明/手術級別2的訓練診斷書2」等多個訓練診斷書,且此處的「多個訓練理賠金額」可為,「用戶識別1取得訓練診斷書1後,經由訓練保單1所獲得的訓練理賠金額1」以及「用戶識別2取得訓練診斷書2後,經由訓練保單2所獲得的訓練理賠金額2」。換言之,前述的多個訓練保單、多個訓練診斷書以及多個訓練理賠金額可以是伺服器100預先從不同的用戶(用戶識別)分別獲得的。In order to improve the accuracy of the subsequent artificial intelligence model in predicting the claim amount, the
此外,為了擷取前述多個訓練保單以及多個訓練診斷書的關鍵字(義),處理器120可對多個訓練保單以及多個訓練診斷書執行自然語言處理(Natural Language Processing,NLP),以訓練人工智慧模型。In addition, in order to retrieve the keywords (meanings) of the aforementioned multiple training policies and multiple training medical certificates, the
圖2是根據本揭露的一實施例繪示的預測理賠金額的方法的流程圖,其中預測理賠金額的方法可由圖1所示伺服器100實施。FIG. 2 is a flowchart of a method for predicting a claim amount according to an embodiment of the present disclosure. The method for predicting a claim amount can be implemented by the
請參照圖1及圖2。在步驟S201中,當用戶希望從伺服器100得知特定保單A以及特定診斷書A所能夠獲得的理賠金額A時,用戶可操作用戶電子裝置200以傳送保單A以及診斷書A至伺服器100。換言之,處理器120可通過收發器110從用戶電子裝置200接收保單A以及診斷書A。Please refer to Figure 1 and Figure 2. In step S201, when the user wishes to know the claim amount A that can be obtained from a specific policy A and a specific medical certificate A from the
接著,在步驟S202中,處理器120可將保單A以及診斷書A輸入至人工智慧模型以預測(出)理賠金額A。進一步而言,為了擷取保單A以及診斷書A的關鍵字(義),處理器120可對保單A以及診斷書A執行自然語言處理。Next, in step S202, the
在獲得預測的理賠金額A之後,在步驟S203中,處理器120可通過收發器110傳送理賠金額A至用戶電子裝置200。After obtaining the predicted claim amount A, in step S203, the
在用戶利用上述步驟S201~S203獲得理賠金額A之後,用戶也可利用保單B以及診斷書B再次執行上述步驟S201~S203以獲得理賠金額B。換言之,用戶可藉此比較不同的保單及/或診斷書所獲得的理賠金額,以達到比較各保單(保險商品),及/或比較各診斷書(例如,來決定用戶要執行的手術級別)的目的。After the user uses the above steps S201 to S203 to obtain the claim amount A, the user can also use the policy B and the medical certificate B to perform the above steps S201 to S203 again to obtain the claim amount B. In other words, users can use this to compare the claim amounts obtained from different policies and/or medical certificates to compare each policy (insurance product) and/or compare each medical certificate (for example, to determine the level of surgery the user wants to perform) the goal of.
綜上所述,本揭露的用於預測理賠金額的伺服器可利用用戶的保單以及診斷書預測理賠金額。基此,用戶可根據本揭露的用於預測理賠金額的伺服器所預測出的理賠金額,來從眾多保單及/或眾多診斷書中選擇。對用戶來說,除了可比較各保單(保險商品)之外,也可比較各診斷書(例如,來決定用戶要執行的手術級別),從而提高了用戶選擇保單及/或診斷書的準確度和方便性。To sum up, the disclosed server for predicting the claim amount can predict the claim amount using the user's insurance policy and medical certificate. Based on this, the user can choose from many insurance policies and/or many medical certificates based on the claim amount predicted by the server for predicting the claim amount. For users, in addition to comparing various insurance policies (insurance products), they can also compare various medical certificates (for example, to determine the level of surgery the user wants to perform), thereby improving the accuracy of the user's selection of insurance policies and/or medical certificates. and convenience.
雖然本揭露已以實施例揭露如上,然其並非用以限定本揭露,任何所屬技術領域中具有通常知識者,在不脫離本揭露的精神和範圍內,當可作些許的更動與潤飾,故本揭露的保護範圍當視後附的申請專利範圍所界定者為準。Although the disclosure has been disclosed above through embodiments, they are not intended to limit the disclosure. Anyone with ordinary knowledge in the technical field may make slight changes and modifications without departing from the spirit and scope of the disclosure. Therefore, The scope of protection of this disclosure shall be determined by the scope of the appended patent application.
100:用於預測理賠金額的伺服器 110:收發器 120:處理器 130:儲存媒體 200:用戶電子裝置 S201、S202、S203:步驟 100: Server used to predict claim amounts 110:Transceiver 120: Processor 130:Storage media 200: User electronic device S201, S202, S203: steps
圖1是根據本揭露的一實施例繪示的用於預測理賠金額的伺服器的示意圖。 圖2是根據本揭露的一實施例繪示的預測理賠金額的方法的流程圖。 FIG. 1 is a schematic diagram of a server for predicting claim amounts according to an embodiment of the present disclosure. FIG. 2 is a flowchart of a method for predicting a claim amount according to an embodiment of the present disclosure.
100:用於預測理賠金額的伺服器 100: Server used to predict claim amounts
110:收發器 110:Transceiver
120:處理器 120: Processor
130:儲存媒體 130:Storage media
200:用戶電子裝置 200: User electronic device
Claims (5)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111118135A TW202345078A (en) | 2022-05-13 | 2022-05-13 | Server for predicting claim amount |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111118135A TW202345078A (en) | 2022-05-13 | 2022-05-13 | Server for predicting claim amount |
Publications (1)
Publication Number | Publication Date |
---|---|
TW202345078A true TW202345078A (en) | 2023-11-16 |
Family
ID=89720375
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111118135A TW202345078A (en) | 2022-05-13 | 2022-05-13 | Server for predicting claim amount |
Country Status (1)
Country | Link |
---|---|
TW (1) | TW202345078A (en) |
-
2022
- 2022-05-13 TW TW111118135A patent/TW202345078A/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230252327A1 (en) | Neural architecture search for convolutional neural networks | |
CN111126574B (en) | Method, device and storage medium for training machine learning model based on endoscopic image | |
WO2017166449A1 (en) | Method and device for generating machine learning model | |
TWI686819B (en) | Computer aided medical method and medical system for medical prediction | |
WO2019127924A1 (en) | Sample weight allocation method, model training method, electronic device, and storage medium | |
JP7287397B2 (en) | Information processing method, information processing apparatus, and information processing program | |
CN102075352A (en) | Method and device for predicting network user behavior | |
WO2022116502A1 (en) | Model training method and device, data processing method and device, client and storage medium | |
WO2023124296A1 (en) | Knowledge distillation-based joint learning training method and apparatus, device and medium | |
WO2021179625A1 (en) | Smart diagnosis guide method and apparatus, electronic device, and storage medium | |
TW202006738A (en) | Medical image analysis method applying machine learning and system thereof | |
TWI728369B (en) | Method and system for analyzing skin texture and skin lesion using artificial intelligence cloud based platform | |
TW202345078A (en) | Server for predicting claim amount | |
CN113330462A (en) | Neural network training using soft nearest neighbor loss | |
TWM630843U (en) | Server for predicting claim amount | |
WO2021114637A1 (en) | Deep neural network-based method and device for data processing | |
TW202247827A (en) | Electronic device and method of training classification model for age-related macular degeneration | |
WO2017127980A1 (en) | Body weight management method and system for athletes | |
TWI733270B (en) | Training device and training method for optimized hyperparameter configuration of machine learning model | |
TWI826316B (en) | Image segmentation model training method and electronic device | |
TWM586599U (en) | System for analyzing skin texture and skin lesion using artificial intelligence cloud based platform | |
TWI719687B (en) | Ultrasound imaging system and ultrasound imaging method | |
TW202249030A (en) | Electronic device and method of training classification model for age-related macular degeneration | |
TWM632499U (en) | Server for managing recommended product | |
TWI717817B (en) | Prediction model transferring method and prediction model transferring device |