TWM580835U - Fraud detection system for financial transaction - Google Patents
Fraud detection system for financial transaction Download PDFInfo
- Publication number
- TWM580835U TWM580835U TW108205037U TW108205037U TWM580835U TW M580835 U TWM580835 U TW M580835U TW 108205037 U TW108205037 U TW 108205037U TW 108205037 U TW108205037 U TW 108205037U TW M580835 U TWM580835 U TW M580835U
- Authority
- TW
- Taiwan
- Prior art keywords
- user
- module
- fingerprint
- financial transaction
- prevention system
- Prior art date
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
本創作提供一種金融交易詐騙偵測防範系統，其在觸控式面板中設置一指紋掃描模組，當使用者在觸控式面板上輸入交易密碼時可掃描手指並得到指紋，同時利用一影像擷取裝置擷取使用者之影音，利用一分析模組判斷相同指紋是否有過多筆不同帳號的提款交易，及依據影像擷取裝置所擷取之影音判斷該使用者之臉部影像及肢體動作是否符合至少一受詐騙行為特徵、聲音是否中是否包含受詐騙相關字眼或指示操作字眼等，以利用一警示模組發出警示通知，告知金融機構人員有詐騙份子或受害者正在提款。The present invention provides a financial transaction fraud detection prevention system, which sets a fingerprint scanning module in the touch panel, and when the user inputs a transaction password on the touch panel, the user can scan the finger and obtain the fingerprint, and simultaneously utilize an image. The capturing device captures the user's video and audio, and uses an analysis module to determine whether the same fingerprint has a plurality of withdrawal transactions of different accounts, and determines the facial image and limb of the user according to the video captured by the image capturing device. Whether the action meets at least one of the characteristics of the fraud, whether the voice contains the fraud-related word or the instruction operation word, etc., uses a warning module to issue a warning notice to inform the financial institution that the fraudulent person or the victim is withdrawing money.
Description
本創作係有關一種金融交易系統，特別是指一種金融交易詐騙偵測防範系統。This creation is about a financial transaction system, especially a financial transaction fraud detection and prevention system.
目前詐騙案件層出不窮，民眾往往會因為緊張、害怕及擔心等因素，造成錯誤及令人懊悔的決定，進而將辛苦賺來得錢財雙手奉上給不法得利之人，然現行銀行員於客戶臨櫃取款或匯款無相關明確判斷其是否被詐騙之依據，只能口頭詢問，反而可能使客戶不耐煩，或是在客戶被詐騙後反而將矛頭指向銀行員。At present, fraudulent cases are emerging one after another. People often make mistakes and regrettable decisions because of factors such as tension, fear and worry, and then they will make their hard-earned money and hands to those who are unlawful, but the current bankers are at the customer's counter. Withdrawals or remittances are not based on a clear basis for determining whether they are being scammed. They can only ask questions verbally. Instead, they may be impatient, or they may point their finger at bankers after they have been defrauded.
此外，在自動櫃員機部份，現行以非約定轉帳及提款有限額制度，惟詐騙車手使用多張不法獲得之金融卡提領現金，只要沒有超過限制額度，無法阻止其提領現金或轉帳，也無法警示同一人於同一時間操作自動櫃員機之異常情況，甚至換了其他台自動櫃員機、甚至換到其他分行提領，也極難被發現。In addition, in the ATM section, the current non-contracted transfer and withdrawal system has a quota system. However, fraudulent drivers use a number of unlawful financial cards to withdraw cash. As long as they do not exceed the limit, they cannot prevent them from withdrawing cash or transfer money. It is also impossible to warn the same person to operate the ATM at the same time, or even change to another ATM, or even to other branches to withdraw, it is extremely difficult to find.
因此，本創作即提出一種金融交易詐騙偵測防範系統，有效解決上述該等問題，具體架構及其實施方式將詳述於下：Therefore, this creation proposes a financial transaction fraud detection and prevention system to effectively solve the above problems. The specific architecture and its implementation will be detailed below:
本創作之主要目的在提供一種金融交易詐騙偵測防範系統，於輸入交易密碼之一觸控式面板中設置一指紋掃描模組，擷取使用者的指紋，以判斷該使用者是否進行多筆不同帳號之提款，以早期發現詐騙車手，阻止犯罪繼續發生。The main purpose of this creation is to provide a financial transaction fraud detection and prevention system. A fingerprint scanning module is set in one of the input transaction passwords, and the fingerprint of the user is captured to determine whether the user performs multiple strokes. Withdrawals from different accounts are used to detect fraud drivers early and prevent crime from continuing.
本創作之另一目的在提供一種金融交易詐騙偵測防範系統，擷取使用者之交易影音，分析判斷使用者之臉部表情、肢體動作是否符合多項受詐騙常見行為特徵，若是，則可阻止受害人繼續被詐騙轉帳出去。Another purpose of the present invention is to provide a financial transaction fraud detection and prevention system, which captures the user's transaction video and audio, analyzes and determines whether the user's facial expressions and physical movements meet the characteristics of multiple fraudulent common behaviors, and if so, can prevent The victim continues to be transferred by fraud.
本創作之再一目的在提供一種金融交易詐騙偵測防範系統，其在觸控式面板上更設置一脈搏偵測模組，從手指上取得使用者的脈搏頻率，以判斷使用者的緊張程度。A further object of the present invention is to provide a financial transaction fraud detection prevention system, which further sets a pulse detection module on the touch panel to obtain the user's pulse frequency from the finger to determine the user's nervousness. .
為達上述目的，本創作提供一種金融交易詐騙偵測防範系統，包括：一觸控式面板，以供一使用者輸入提款交易之一交易密碼，該觸控式面板中更包括一指紋掃描模組，於該使用者之手指按壓該觸控式面板時掃描該手指並得到一指紋；一影像擷取裝置，擷取該使用者之影音，包括臉部影像及肢體動作；分析模組，與該觸控式面板及該影像擷取裝置電性連接，包括一指紋比對模組及一影像分析模組，該指紋比對模組判斷當有複數不同帳號之提款交易時，該指紋掃描模組所掃描之指紋是否相同，該影像分析模組判斷該使用者之該臉部影像及該肢體動作是否符合至少一受詐騙行為特徵；以及一警示模組，電性連接該分析模組，當該分析模組之判斷結果為複數不同帳號之提款交易掃描到相同指紋時，發出一第一警示通知，及當該分析模組判斷該使用者之該臉部影像或該肢體動作符合該受詐騙行為特徵時，發出一第二警示通知。To achieve the above objective, the present invention provides a financial transaction fraud detection prevention system, comprising: a touch panel for a user to input a transaction password of a withdrawal transaction, and the touch panel further includes a fingerprint scan The module scans the finger and obtains a fingerprint when the user's finger presses the touch panel; an image capturing device captures the user's audio and video, including facial images and limb movements; and the analysis module, Electrically connecting with the touch panel and the image capturing device, comprising a fingerprint matching module and an image analyzing module, the fingerprint matching module determining that when there are multiple withdrawal transactions of different accounts, the fingerprint Whether the fingerprint scanned by the scanning module is the same, the image analysis module determines whether the facial image of the user and the motion of the limb meet at least one fraudulent behavior feature; and a warning module electrically connected to the analysis module When the judgment result of the analysis module is that the withdrawal transaction of the plurality of different accounts scans to the same fingerprint, a first warning notice is issued, and when the analysis module determines that the user When the image or portion of the body movement matches the characteristics of fraud by issuing a second warning notification.
根據本創作之實施例，該觸控式面板中更包括一脈搏偵測模組，以從該使用者按壓該觸控式面板之該手指上偵測一脈搏頻率。According to an embodiment of the present invention, the touch panel further includes a pulse detection module for detecting a pulse frequency from the finger of the user pressing the touch panel.
承上，該分析模組中更包括一脈搏判斷模組，用以判斷該脈搏頻率是否超過一預設值，若超過則要求該警示模組發出一第四警示通知。該預設值為每分鐘脈搏頻率大於100下。The analysis module further includes a pulse judgment module for determining whether the pulse frequency exceeds a preset value, and if the parameter is exceeded, the warning module is required to issue a fourth alert notification. The preset value is greater than 100 pulses per minute.
根據本創作之實施例，該受詐騙行為特徵包括眉頭緊皺、眼睛睜大、東張西望、擦汗、深呼吸、動作匆忙、頻繁講電話、邊使用手機邊操作機台等。According to an embodiment of the present invention, the fraudulent behavior features include brow wrinkles, wide eyes, squinting, sweating, deep breathing, rushing, frequent phone calls, and operating the machine while using the mobile phone.
根據本創作之實施例，更包括一儲存模組，電性連接該觸控式面板、該影像擷取裝置及該分析模組，暫存該指紋及該影音。According to an embodiment of the present invention, a storage module is electrically connected to the touch panel, the image capturing device and the analysis module, and the fingerprint and the audio and video are temporarily stored.
根據本創作之實施例，該提款交易包括於自動櫃員機提款及臨櫃提款。該交易密碼為金融卡密碼或存摺密碼。According to an embodiment of the present creation, the withdrawal transaction includes withdrawals from the ATM and withdrawals from the counter. The transaction password is a financial card password or a passbook password.
本創作提供一種金融交易詐騙偵測防範系統，其利用多重判斷機制分析使用者的生理資訊和表情動作，不但可阻止詐騙車手肆無忌憚的不法得利，還可減少客戶受詐騙發生率，另一方面，也可使金融機構人員增加判斷客戶是否為詐騙份子或被詐騙之依據，以避免遭受客戶的不合理對待。This creation provides a financial transaction fraud detection and prevention system, which uses multiple judgment mechanisms to analyze the user's physiological information and expression actions, which not only prevents fraudulent drivers from unscrupulous gains, but also reduces the incidence of fraudulent customers. It can also enable financial institution personnel to increase the basis for judging whether a customer is a fraudster or being defrauded to avoid unreasonable treatment by customers.
請參考第1圖，其為本創作金融交易詐騙偵測防範系統第一實施例之方塊圖，本創作包括一觸控式面板10、一影像擷取裝置12、一分析模組14及一警示模組16，其中，觸控式面板10用以供一使用者輸入提款交易之一交易密碼，一般而言，提款交易包括臨櫃提款及用自動櫃員機提款，若是臨櫃提款則輸入之交易密碼為存簿密碼或其他客戶設定之密碼，若使用自動櫃員機提款則輸入金融卡密碼，此觸控式面板10中更包括一指紋掃描模組102，當使用者之手指按壓在觸控式面板上輸入交易密碼時，指紋掃描模組102掃描手指並得到一指紋；影像擷取裝置12用以擷取使用者之影音，包括臉部影像、肢體動作及聲音；分析模組14與觸控式面板10及影像擷取裝置12電性連接，此分析模組14可設在金融機構之後端伺服器(圖中未示)中，包括一指紋比對模組142、一影像分析模組144及一語音辨識模組148，指紋比對模組142判斷當有複數不同帳號之提款交易時，指紋掃描模組102所掃描之指紋是否相同，影像分析模組144則判斷使用者之臉部影像及肢體動作是否符合至少一受詐騙行為特徵，例如眉頭緊皺、眼睛睜大、東張西望、擦汗、深呼吸、動作匆忙、頻繁講電話、邊使用手機邊操作機台等代表緊張的微表情和肢體語言；語音辨識模組148對使用者之影音中之聲音進行語音辨識，分析影音中是否包含至少一受詐騙相關字眼或指示操作字眼，例如解除設定、分期付款等；警示模組16電性連接分析模組14，用以發出警示通知，例如當分析模組14之判斷結果為複數不同帳號之提款交易掃描到相同指紋時，代表有詐騙車手在用多張不同金融卡提款，則發出一第一警示通知，當分析模組14判斷使用者之臉部影像或肢體動作符合受詐騙行為特徵時，發出一第二警示通知，告知金融機構人員此使用者疑似被詐騙，將進而進行詐騙相關宣導、提醒使用者及櫃檯人員等措施，以拖延取款及匯款時間，或立即通知相關單位協助處理，當分析模組14分析出影音中包含受詐騙相關字眼或指示操作字眼時，發出一第三警示通知。Please refer to FIG. 1 , which is a block diagram of a first embodiment of a creative financial transaction fraud detection prevention system. The present invention includes a touch panel 10 , an image capturing device 12 , an analysis module 14 , and a warning The module 16 is configured to allow a user to input a transaction password for one of the withdrawal transactions. Generally, the withdrawal transaction includes withdrawal of the counter and withdrawal by the ATM, and if the withdrawal is made by the counter. The input transaction password is a storage password or a password set by another customer. If the ATM is used for withdrawal, the financial card password is input. The touch panel 10 further includes a fingerprint scanning module 102, when the user presses the finger. When the transaction password is input on the touch panel, the fingerprint scanning module 102 scans the finger and obtains a fingerprint; the image capturing device 12 is used to capture the user's audio and video, including facial images, limb movements and sounds; 14 is electrically connected to the touch panel 10 and the image capturing device 12, and the analysis module 14 can be disposed in a rear end server (not shown) of the financial institution, and includes a fingerprint matching module 142 and an image. Analysis module 144 And a voice recognition module 148, the fingerprint comparison module 142 determines whether the fingerprint scanned by the fingerprint scanning module 102 is the same when there are multiple withdrawal transactions of different accounts, and the image analysis module 144 determines the face of the user. Whether the image and limb movements meet at least one characteristic of fraud, such as brow wrinkles, wide eyes, looking around, sweating, deep breathing, rushing, frequent phone calls, operating the machine while using the mobile phone, etc. Body language; the voice recognition module 148 performs voice recognition on the voice in the user's audio and video, and analyzes whether the video and audio contains at least one fraud-related word or instruction operation word, such as canceling setting, installment payment, etc.; The connection analysis module 14 is configured to issue an alert notification. For example, when the judgment result of the analysis module 14 is that the withdrawal transaction of the plurality of different accounts scans to the same fingerprint, the fraud driver is used to withdraw funds from multiple different financial cards. Sending a first warning notice, when the analysis module 14 determines that the user's facial image or limb movement conforms to the fraud feature Issue a second warning notice to inform the financial institution personnel that the user is suspected of being defrauded, and then conduct fraud-related propaganda, reminding users and counter staff and other measures to delay the withdrawal and remittance time, or immediately notify the relevant units to assist in the handling. When the analysis module 14 analyzes that the video contains a fraud-related word or an instruction operation word, a third warning notice is issued.
第2圖為本創作金融交易詐騙偵測防範系統第二實施例之方塊圖，本創作之金融交易詐騙偵測防範系統更進一步可在觸控式面板10中設置一脈搏偵測模組104，以從使用者按壓觸控式面板10之手指上偵測一脈搏頻率，因為從脈搏頻率可以推斷使用者的心理狀態是否緊張，緊張時心跳會加快，因此在分析模組14中更包括一脈搏判斷模組146，判斷使用者的脈搏頻率是否超過一預設值，舉例而言，若每分鐘脈搏頻率大於100下，則此使用者很可能就是詐騙份子，或是被詐騙的受害人，分析模組14要求警示模組16發出一第四警示通知給金融機構人員。FIG. 2 is a block diagram of a second embodiment of the fraudulent detection and prevention system for creating a financial transaction. The financial transaction fraud detection and prevention system of the present invention can further provide a pulse detection module 104 in the touch panel 10, The pulse frequency is detected on the finger pressed by the user from the touch panel 10, because it can be inferred from the pulse frequency whether the user's psychological state is tense, and the heartbeat will be accelerated when the tension is increased, so that the analysis module 14 further includes a pulse. The determining module 146 determines whether the pulse frequency of the user exceeds a preset value. For example, if the pulse frequency per minute is greater than 100, the user is likely to be a fraudster or a victim of fraud. The module 14 requires the alert module 16 to issue a fourth alert notification to the financial institution personnel.
此外，本創作更包括一體溫感測器13，其可設置在影像擷取裝置12上或是獨立設置，瞄準使用者的方向偵測使用者的體溫，並在分析模組14中設置一體溫判斷模組149，以判斷體溫感測器13所偵測到之體溫是否高於一預設體溫，此預設體溫為一般人在正常狀態下的體溫，例如攝氏36~37.5度，由於人在緊張的時候體溫會升高，或是在使用手機的時候耳朵溫度也會因手機產生的熱能而升高，或是體溫感測器13可能偵測到有溫度高的物體(如手機)放置於耳朵旁，因此，若體溫判斷模組149判斷偵測到的體溫高於預設體溫，代表有受詐騙者或詐騙車手正在緊張地操作自動櫃員機或臨櫃提款，則警示模組16發出一第五警示通知。In addition, the present invention further includes an integrated temperature sensor 13 which can be disposed on the image capturing device 12 or independently disposed to detect the user's body temperature in the direction of the user, and set the integrated temperature in the analysis module 14. The determining module 149 is configured to determine whether the body temperature detected by the body temperature sensor 13 is higher than a preset body temperature, and the preset body temperature is a body temperature of a normal person in a normal state, for example, 36 to 37.5 degrees Celsius, because the person is nervous The body temperature will rise, or the ear temperature will increase due to the heat generated by the mobile phone when using the mobile phone, or the body temperature sensor 13 may detect that a high temperature object (such as a mobile phone) is placed in the ear. Next, therefore, if the body temperature determining module 149 determines that the detected body temperature is higher than the preset body temperature, indicating that the fraudster or the fraud driver is nervously operating the ATM or the withdrawal of the counter, the warning module 16 issues a Five warning notices.
本創作更包括一儲存模組18，其電性連接觸控式面板10、影像擷取裝置12及分析模組14，用以暫存指紋及影音，若使用者不是連續提款，同樣可藉由儲存模組18中暫存之指紋判斷其是否有提領過不同帳戶，或是依據暫存的影音加強判斷使用者是否為詐騙車手的可能性。The present invention further includes a storage module 18 electrically connected to the touch panel 10, the image capturing device 12 and the analysis module 14 for temporarily storing fingerprints and audio and video. If the user does not continuously withdraw money, the present invention can also be borrowed. The fingerprint stored in the storage module 18 determines whether it has picked up a different account, or enhances the possibility of determining whether the user is a fraud driver based on the temporarily stored video.
接著請參考第3圖，其為應用本創作金融交易詐騙偵測防範系統第一實施例之流程圖。首先步驟S10中，使用者於一觸控式面板上輸入提款交易之一交易密碼；步驟S12中，當使用者之手指按壓觸控式面板時，觸控式面板中之指紋掃描模組掃描手指並得到一指紋，及影像擷取裝置擷取該使用者之影音，此影音包括使用者之臉部影像及肢體動作；接著於步驟S14中利用分析模組中之影像分析模組判斷該使用者之該臉部影像及該肢體動作是否符合至少一受詐騙行為特徵，若是，代表使用者可能被詐騙，則於步驟S16發出一第二警示通知給金融機構人員，以阻止使用者繼續進行提款或轉帳交易；若否，則繼續步驟S18，利用語音辨識模組對影音中之聲音部分進行語音辨識，分析該影音中是否包含至少一受詐騙相關字眼或指示操作字眼，若是，代表使用者可能是被詐騙的受害者，於步驟S20中發出一第三警示通知；若否，再繼續步驟S22利用分析模組中之指紋比對模組判斷是否為複數不同帳號之提款交易但掃描到相同指紋，若是，則於步驟S24中發出一第一警示通知給金融機構人員，告知可能是詐騙車手出沒，反之，若否，則使用者可繼續交易，提領現金或轉帳，如步驟S26所述。Next, please refer to FIG. 3, which is a flowchart of the first embodiment of the application financial transaction fraud detection prevention system. First, in step S10, the user inputs a transaction password of the withdrawal transaction on a touch panel; in step S12, when the user's finger presses the touch panel, the fingerprint scanning module in the touch panel scans. Fingers get a fingerprint, and the image capturing device captures the user's video and audio, the video audio includes the user's facial image and limb motion; and then uses the image analysis module in the analysis module to determine the use in step S14. Whether the facial image and the movement of the limb meet at least one fraudulent behavior feature, and if the representative user may be defrauded, a second warning notification is sent to the financial institution personnel in step S16 to prevent the user from continuing to mention And the transfer transaction; if not, proceeding to step S18, using the speech recognition module to perform speech recognition on the sound portion of the audio and video, and analyzing whether the audio and video includes at least one fraud-related word or instruction operation word, and if so, on behalf of the user It may be a victim of fraud, and a third warning notification is sent in step S20; if not, proceed to step S22 to use the analysis module. The pattern matching module determines whether it is a withdrawal transaction of a plurality of different accounts but scans the same fingerprint, and if so, sends a first warning notice to the financial institution personnel in step S24, indicating that the fraudulent driver may be present, otherwise, if not , the user can continue to trade, withdraw cash or transfer, as described in step S26.
第4圖為應用本創作金融交易詐騙偵測防範系統第二實施例之流程圖。步驟S30中，使用者於一觸控式面板上輸入提款交易之一交易密碼；步驟S32中，當使用者之手指按壓觸控式面板時，觸控式面板中之指紋掃描模組掃描手指並得到一指紋，及影像擷取裝置擷取該使用者之影音，此影音包括使用者之臉部影像及肢體動作；接著於步驟S34中判斷使用者之脈搏頻率是否達到一預設值，若是，則於步驟S36發出一第四警示通知給金融機構人員，告知此人為緊張狀態，可能是詐騙車手或詐騙受害人。若脈搏正常，則再於步驟S38偵測使用者的體溫是否超過一預設體溫，若是，則代表使用者正處於緊張狀態，可能是受詐騙的人，因此步驟S40發出一第五警示通知，若否，則接著於步驟S42中利用分析模組中之影像分析模組判斷該使用者之該臉部影像及該肢體動作是否符合至少一受詐騙行為特徵，若是，代表使用者可能被詐騙，則於步驟S44發出一第二警示通知給金融機構人員，以阻止使用者繼續進行提款或轉帳交易；若否，則繼續步驟S46，利用語音辨識判斷使用者在提款時發出的聲音是否包含受詐騙相關字眼或指示操作字眼，前者代表使用者可能為受詐騙者，後者則代表使用者可能為詐騙車手，因此於步驟S48會發出一第三警示通知；若語音辨識結果正常，則步驟S50中，再利用分析模組中之指紋比對模組判斷是否為複數不同帳號之提款交易但掃描到相同指紋，若是，則於步驟S52中發出一第一警示通知給金融機構人員，告知可能是詐騙車手出沒，反之，若否，則使用者可繼續交易，提領現金或轉帳，如步驟S54所述。FIG. 4 is a flow chart of a second embodiment of applying the creative financial transaction fraud detection prevention system. In step S30, the user inputs a transaction password of the withdrawal transaction on a touch panel; in step S32, when the user's finger presses the touch panel, the fingerprint scanning module in the touch panel scans the finger. And obtaining a fingerprint, and the image capturing device captures the video of the user, the audio and video includes the facial image and the limb motion of the user; and then determining whether the pulse frequency of the user reaches a preset value in step S34, if Then, in step S36, a fourth warning notice is sent to the financial institution personnel to inform the person that the person is in a state of tension, which may be a fraud driver or a fraud victim. If the pulse is normal, then in step S38, it is detected whether the user's body temperature exceeds a preset body temperature, and if so, the user is in a state of tension, which may be a fraudulent person, so step S40 issues a fifth warning notice. If not, then in step S42, the image analysis module in the analysis module is used to determine whether the facial image of the user and the motion of the limb meet at least one fraudulent behavior feature. If yes, the representative user may be defrauded. Then, a second alert notification is sent to the financial institution personnel in step S44 to prevent the user from continuing the withdrawal or transfer transaction; if not, proceeding to step S46, using voice recognition to determine whether the voice issued by the user at the time of withdrawal is included The fraudulent related word or the instruction operation word, the former represents the user may be a fraudster, and the latter represents the user may be a fraud driver, so a third warning notice is issued in step S48; if the voice recognition result is normal, step S50 In the middle, the fingerprint comparison module in the analysis module is used to determine whether the withdrawal transaction is a plurality of different accounts but scans to the same Pattern, if yes, in step S52, a first warning notice is sent to the financial institution personnel to inform that the fraudulent driver may be present, and if not, the user may continue to trade, withdraw cash or transfer, as described in step S54. .
舉例而言，若有一使用者在同一間分行的第一台自動櫃員機提款，指紋被暫存在儲存模組中，接著使用者更換其他台自動櫃員機，並使用了多張不同金融卡提款或轉帳，由於所有自動櫃員機的觸控式面板皆連接後端伺服器的儲存模組和分析模組，因此即使使用者更換機台，且沒有連續操作，分析模組仍然可分析出有多筆不同帳號的提款或轉帳交易是相同指紋的人在操作，進而發現詐騙車手，阻止他繼續進行不法行為。For example, if a user withdraws money from the first ATM at the same branch, the fingerprint is temporarily stored in the storage module, and then the user replaces another ATM and uses several different financial cards to withdraw funds or Transfer, since the touch panels of all ATMs are connected to the storage module and analysis module of the back-end server, even if the user changes the machine and there is no continuous operation, the analysis module can still analyze many different ones. The withdrawal or transfer transaction of the account is the same fingerprint of the person operating, and then found the fraud driver to prevent him from continuing the wrongdoing.
再舉例而言，若使用者在提款時不但脈搏頻率快，且臉部表情緊張、有手足無措的肢體表現，甚至還搭配了體溫升高的現象，則代表他極有可能被詐騙要轉帳給詐騙份子，則分析模組還可在其轉帳出去之前阻止其繼續進行交易。For another example, if the user not only has a fast pulse rate, but also has a facial expression, a slap in the face, and even a rise in body temperature, it means that he is most likely to be defrauded to transfer money. For fraudsters, the analysis module can also prevent it from continuing to trade before it is transferred out.
本創作更可將上述偵測、分析資料套入公式，例如總判斷分數L分為7項評分標準，包含行為a、表情b、心跳c、指紋d、體溫e、詐騙字眼f及欲領取金額g，並在每個評分標準加上權重M，各權重相加為1，即可算出此操作人受詐騙之分數，如下式(1)： L = M1a+ M2b+ M3c+ M4d+ M5e+ M6f+ M7g 其中，M1+ M2+ M3+ M4+ M5+ M6+ M7 = 1，0 ＜ M1 ＜ 1 (1) 其中，各標準均有細項，例如行為a再分為講電話a1、深呼吸a2、擦汗a3、與他人說話a4等固定數量之參數，根據不同評分標準設定不同數量之參數，每個參數皆被偵測到評分標準分數即為100分，如下式(2)： 0 ≦ a = (a1)+(a2)+(a3)+(a4) ≦ 100 (2) This creation can also put the above detection and analysis data into the formula. For example, the total judgment score L is divided into 7 score standards, including behavior a, expression b, heartbeat c, fingerprint d, body temperature e, fraud word f and amount to be collected. g, and add weights M to each scoring standard, and add the weights to 1, to calculate the score of the operator's fraud, as shown in the following formula (1): L = M1a+ M2b+ M3c+ M4d+ M5e+ M6f+ M7g Among them, M1+ M2+ M3+ M4+ M5+ M6+ M7 = 1,0 < M1 < 1 (1) Among them, each standard has a detailed item, for example, the behavior a is divided into a fixed number of parameters such as telephone a1, deep breathing a2, sweating a3, talking with others a4, etc., according to different scoring standards, different numbers of parameters are set, each parameter is The score of the scoring standard is 100 points, as shown in the following formula (2): 0 ≦ a = (a1)+(a2)+(a3)+(a4) ≦ 100 (2)
再由判斷分數Ｌ導入警示級距表，根據不同級距給予不同的警示措施，例如進行詐騙影片相關宣導、行員加強關心、操作畫面提示按鈕確認鍵或立即通知相關單位協助處理等。Then, the judgment score L is introduced into the warning step distance table, and different warning measures are given according to different level intervals, for example, fraudulent film related promotion, pedestrian reinforcement concern, operation screen prompt button confirmation key or immediate notification to the relevant unit for assistance processing.
綜上所述，本創作之金融交易詐騙偵測防範系統係擷取使用者的指紋，以判斷該使用者是否進行多筆不同帳號之提款，可早期發現詐騙車手，阻止犯罪繼續發生。此外，本創作擷取使用者之交易影音，分析判斷使用者之臉部表情、肢體動作是否符合多項受詐騙常見行為特徵，結合語音辨識判斷使用者是否有說出受詐騙相關字眼，若是，則可阻止受害人繼續被詐騙轉帳出去，反之還可加強辨識是否為同一人不斷操作交易。再者，本創作在觸控式面板上更擷取使用者的脈搏頻率，及設有一體溫感測器以偵測使用者的體溫，二者皆可判斷使用者的緊張程度，結合上述指紋辨識、影像辨識、語音辨識等，極大機率可判斷出使用者受詐騙或是詐騙車手，以減少不法交易的發生率。In summary, the financial transaction fraud detection and prevention system of the present invention captures the user's fingerprint to determine whether the user has made multiple withdrawals of different accounts, and can detect fraud drivers early to prevent the crime from continuing. In addition, the author captures the user's transaction video and audio, analyzes and judges whether the user's facial expressions and physical movements meet the characteristics of multiple fraudulent common behaviors, and uses voice recognition to determine whether the user has spoken the fraud-related words, and if so, It can prevent the victim from continuing to be transferred by fraud, and vice versa to enhance the identification of whether the same person is constantly operating the transaction. Furthermore, the present invention captures the user's pulse rate on the touch panel and has an integrated temperature sensor to detect the user's body temperature, both of which can determine the user's nervousness, combined with the above fingerprint identification. , image recognition, speech recognition, etc., a great chance to determine whether the user is defrauded or scam drivers to reduce the incidence of illegal transactions.
唯以上所述者，僅為本創作之較佳實施例而已，並非用來限定本創作實施之範圍。故即凡依本創作申請範圍所述之特徵及精神所為之均等變化或修飾，均應包括於本創作之申請專利範圍內。The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Therefore, any change or modification of the characteristics and spirit described in the scope of this application shall be included in the scope of the patent application for this creation.
10‧‧‧觸控式面板 102‧‧‧指紋掃描模組 104‧‧‧脈搏偵測模組 12‧‧‧影像擷取裝置 13‧‧‧體溫感測器 14‧‧‧分析模組 142‧‧‧指紋比對模組 144‧‧‧影像分析模組 146‧‧‧脈搏判斷模組 148‧‧‧語音辨識模組 149‧‧‧體溫判斷模組 16‧‧‧警示模組 18‧‧‧儲存模組 10‧‧‧Touch panel 102‧‧‧Fingerprint scanning module 104‧‧‧ Pulse Detection Module 12‧‧‧Image capture device 13‧‧‧ body temperature sensor 14‧‧‧Analysis module 142‧‧‧Fingerprint comparison module 144‧‧‧Image Analysis Module 146‧‧‧ pulse judgment module 148‧‧‧Voice recognition module 149‧‧‧ Body temperature judgment module 16‧‧‧Warning module 18‧‧‧ storage module
第1圖為本創作金融交易詐騙偵測防範系統第一實施例之方塊圖。 第2圖為本創作金融交易詐騙偵測防範系統第二一實施例之方塊圖。 第3圖為應用本創作金融交易詐騙偵測防範系統第一實施例之流程圖。 第4圖為應用本創作金融交易詐騙偵測防範系統第二實施例之流程圖。 The first figure is a block diagram of the first embodiment of the creative financial transaction fraud detection and prevention system. FIG. 2 is a block diagram of a second embodiment of the creative financial transaction fraud detection and prevention system. FIG. 3 is a flow chart of the first embodiment of applying the creative financial transaction fraud detection prevention system. FIG. 4 is a flow chart of a second embodiment of applying the creative financial transaction fraud detection prevention system.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW108205037U TWM580835U (en) | 2019-04-24 | 2019-04-24 | Fraud detection system for financial transaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW108205037U TWM580835U (en) | 2019-04-24 | 2019-04-24 | Fraud detection system for financial transaction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| TWM580835U true TWM580835U (en) | 2019-07-11 |
Family
ID=68050921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW108205037U TWM580835U (en) | 2019-04-24 | 2019-04-24 | Fraud detection system for financial transaction |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWM580835U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI709100B (en) * | 2019-08-30 | 2020-11-01 | 兆豐國際商業銀行股份有限公司 | Transaction management system |
| TWI730374B (en) * | 2019-08-12 | 2021-06-11 | 華南商業銀行股份有限公司 | Automatic teller machine warning system |
| TWI831596B (en) * | 2023-02-03 | 2024-02-01 | 華南商業銀行股份有限公司 | Mark trading system |
-
2019
- 2019-04-24 TW TW108205037U patent/TWM580835U/en unknown
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI730374B (en) * | 2019-08-12 | 2021-06-11 | 華南商業銀行股份有限公司 | Automatic teller machine warning system |
| TWI709100B (en) * | 2019-08-30 | 2020-11-01 | 兆豐國際商業銀行股份有限公司 | Transaction management system |
| TWI831596B (en) * | 2023-02-03 | 2024-02-01 | 華南商業銀行股份有限公司 | Mark trading system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11100481B2 (en) | Image authentication and security system and method | |
| US10853807B2 (en) | Payment authentication method and apparatus | |
| US9542684B2 (en) | Biometric based authorization systems for electronic fund transfers | |
| JP3612582B2 (en) | Self-service business system and apparatus therefor | |
| TWM580835U (en) | Fraud detection system for financial transaction | |
| US20170337362A1 (en) | Phalangeal authentication device | |
| TWI752312B (en) | Financial transaction fraud detection and prevention system and method | |
| JP2008004006A (en) | Currency exchange processing system | |
| TWM576696U (en) | Machine system with face recognition function | |
| US20220277311A1 (en) | A transaction processing system and a transaction method based on facial recognition | |
| JP2007094588A (en) | Face authentication system | |
| US10846701B1 (en) | Multi-vector authentication unit (MVAU) | |
| TWM590739U (en) | Abnormal transaction auxiliary identification system | |
| TWM607444U (en) | Abnormal transaction determination system | |
| US20210248217A1 (en) | User authentication using primary biometric and concealed markers | |
| TWM582633U (en) | Biometric identification transaction system | |
| TWI745070B (en) | Method and system for judging abnormal transaction | |
| TWI709100B (en) | Transaction management system | |
| JP2003284854A (en) | Game data management method and system | |
| JP5244521B2 (en) | Automatic transaction equipment | |
| TWM645450U (en) | Automatic teller equipment with contactless control unit | |
| TWM639927U (en) | Over-the-counter contact physiological signal detection device | |
| TWM576683U (en) | Automated teller machine system with emotion detection function | |
| TW202407618A (en) | Method for extracting features of users through financial machine and system thereof | |
| TW202044075A (en) | Biometric identification transaction system |