Abstract:
Proposed is a digital system and robust expert method for accuracy-enhanced expert forecasting based on a digital audit-linked best-estimation framework, wherein the audit-based best-estimation framework comprises two or more execution member executing at least the steps of (i) determining a forecasted value for a definable future time window benchmarking the audit-based best-estimation framework to a starting point value based on one or more historical databases, (ii) determining a 90% confidence interval range for the determined starting point value by a lower bund value and an upper bond value of the interval range, wherein the starting point value is part of the confidence interval value range, and wherein an actually measured value of the forecasted value in the future time window is forecasted to measurably deviate with a 90% probability within the 90% confidence interval range, and (iii) selecting one or more possible scenarios each having a definable probability distribution and applying a sensitivity analysis by at least varying a time-based range of an observation window, wherein if the forecasted value deviates further from the starting point value as a predefined threshold value by the variation, the starting point value is adjusted. The forecasted values of the at least two execution member are transmitted and captured by a best-estimation engine determining a best-estimation forecasted value based on the captured forecasted values of the at least two execution member.
Abstract:
Proposed is an automated maximum impact measurand forecasting system (1) for measuring an impact of an explosion of an explosive (3) in open steel and/or concrete and/or reinforced concrete structures (2), wherein at least loading (311) and/or resistance (211) measuring parameter (21/31) values are measured and/or captured by the automated forecasting system (1).
Abstract:
Proposed is an automated automobile claims fraud detector and method for automatically evaluating validity and extent of at least one damaged object from image data and detect possible fraud, the automated automobile claims fraud detector comprising the processing steps of: (a) receiving image data comprising one or more images of at least one damaged object; (b) processing said one or more images for existing image alteration using unusual pattern identification and providing a first fraud detection; ( c) processing said one or more images for fraud detection using RGB image input, wherein the RGB values are used for (i) CNN-based pre-existing damage detection, (ii) parallel CNN-based color matching, and (iii) double JPEG compression (DJCD) detection using custom CNN; (d) processing output of (i) CNN- based pre-existing damage detection, (ii) parallel CNN-based color matching, and (iii) double JPEG compression detection using custom CNN as input for ML-based fraud identifier providing a second fraud detection; and (e) generating fraud signaling output, if the first or second fraud detection indicates fraud.
Abstract:
Proposed are an automated real-time fraud monitoring and detection system (1) for detecting unusual and/or suspicious activities within a network of nodes (41) interconnected by edges (42) triggered by captured synthetic forms of social data, in particular social networking and/or linkage and/or relationship data) and social metadata comprising at least data from microblogging services and/or social networking services by means of pattern recognition and matching.
Abstract:
Proposed is an automated measuring system (1) for progress monitoring and steering of impacts of a complex system (2) to world environment and ecosystem (3) induced by environmental-human linkages (21) and for quantitative measuring of effects of applied risk-transfer structures (4) to said environmental-human linkages (21) induced by risk-transfer–SDG linkages (41/411,…41x) measuring quantifying distances (11/111, 112, …, 11x) of progresses toward at least one of a predefined sustainable development goal (SDG/12) with and without applying said risk-transfer structures (4).
Abstract:
Proposed is a digital channel for automated risk-transfer underwriting in fragmented, unstructured data environments covering heterogenous risk sources (1142) and risk-exposure classes (1141) associated with assets (2i1) of small and/or medium size enterprises (21,22,…,2i). The digital channel is provided by a digital platform (1) for the risk-exposed units (2, 21,22,…,2i) assessing the digital platform (1) by means of network- enabled devices (2i2) via a data transmission network (4). Risk-transfer portfolio data (101, 102, …, 10i) are held in a persistence storage (10) of the digital platform (1). The digital platform (1) comprises a risk advisory module (11) for automated asset classification (1262), risk scoring (1263) and interactive risk-transfer and risk-exposure steering (1264), wherein asset characteristics parameters (1121) of a unit (21,22,…,2i) are assigned to a risk profile (112) of the unit (21,22,…,2i), and wherein the assets (2i1) of the unit (21,22,…,2i) are classified into predefined asset classes (11211,…,1121i). The digital platform (1) comprises an automated underwriting and pricing module (13), wherein base rates (13412) for applicable risk-transfer covers (13411) are provided and corresponding pricings (13414) are generated based on the base rates (13412), associated rate factors (13413) and value parameters of the asset characteristics parameters (1121), wherein different applicable risk-transfer covers (13411) are generated and are assigned to a profile section (1123) of the risk-exposed unit (21,22,…,2i). A risk score (1124) is generated and assigned to each profile section (1123) of the risk profile (112), wherein the interactive portfolio steering is provided by inter- actively assigning and adjusting risk-transfer covers associated with said portfolio (101, 02, …, 10i).
Abstract:
Proposed are a system (1) and a method for the determination and forecast of absolute and relative risks for car accidents based on exclusively non-insurance related measuring data and based on automated traffic pattern recognition, wherein data records of accident events are generated and location-dependent probability values for specific accident conditions associated with the risk of car accident are determined. Thus, the proposed system (1) provides a grid-based (2121, 2122, 2123, 2124), technically new way of automation of risk-prediction related to motor accidents using environment based factors (elevation, road network, traffic data, weather conditions) including socio-economic factors that are impacting motor traffic and are location dependent received from appropriate measuring devices and systems (41,...,45). In this way, predictions of the accident risk for arbitrary areas can be provided. The system is calibrated by comparing features of areas or road segments with the number and type of accidents that have measured or registered there, linking the features and accident data e.g. using the below discussed machine learning techniques.
Abstract:
Proposed is a secure key management, peer-to-peer transmission system (6), and method thereof, based on a controlled, double-tier cryptographic key structure (2), providing a closed cryptosystem for secure content distribution and further processing within a provided, secured network environment (11). Individual, user- specific data (331) are captured by means of capturing device (33) associated with a user network node (3). Based on the individual, user-specific data (331), data services (101) are requested from and provided to the user network node (3), by means of a data consumer network node (4). The captured individual, user-specific data (331) are transmitted from the user network node (3) to a central P2P transmission system (1) and are processed by a non-storage-based processing unit (10), providing the requested data service (101) of the data consumer network node (4) requested by the user network node (3). A first cryptographic key (21) is generated by the non-storage-based processing unit (10), wherein service response data (211) of the requested service (101) are encrypted, by means of the first cryptographic key (21), to single encrypted service response data (212) and transmitted to the user network node (3), in response to the requested service (101). The received single encrypted service response data (212) are double encrypted, by means of a generated second cryptographic key (22), to double encrypted service response data (221) by the user network node (3) and transmitted back and stored in the central, P2P transmission system (1). The first cryptographic key (21) is transmitted and/or made accessible to the user network node (3), if predefined authorization-parameters (102) are triggered, by means of the central, P2P transmission system (1).
Abstract:
Proposed is a mobile automotive car system (1), and method thereof, for a dynamic, telematics-based connection search engine and telematics data aggregator, wherein risk-transfer profiles (124) are captured and categorized in a results list (118) from a plurality of first risk-transfer systems (12) based on dynamically generated driving score parameters (10131 /1111..... 1117) by means of appropriately triggered automotive data (3). As a variant, during a predefined trial period (e.g. 1 -2 months), the automotive and driving behavior data (3) can be collected, which are transmitted together with the generated driving score parameters (10131 /1111..... 1117) to multiple automated first risk-transfer systems (12) for quotation. The user is able to dynamically select the best-fitting first risk-transfer system (12) for risk-transfer by means of the results list (118), which is provided and updated in real-time for display to and selection by a user of a mobile telecommunication apparatus (10) by means of a mobile telematics application (101) of the mobile telecommunications apparatus (10).
Abstract:
Proposed is an automotive car system (1), and method thereof, associated with a plurality of autonomous or partially autonomous driving motor vehicles (41,...,45). The autonomous or partially autonomous motor vehicles (41,...,45) comprise exteroceptive sensors (4011) for sensing environmental parameters (40111), and proprioceptive sensors (4012) for sensing operating parameters of the motor vehicles (41,...,45). The motor vehicles (41,...,45) further comprise an autonomous or partially autonomous driving control system (461 465) interpreting the sensory data (40111 /40121) of the exteroceptive and proprioceptive sensors (4011 /4012) and identifying appropriate navigation paths and/or obstacles and/or relevant signage. The motor vehicles (41,...,45) or the automotive control systems (461 465) are connected to a central, expert-system based circuit (11) by means of a data link (21) transmitting at least usage-based (31) and/or user-based (32) and/or operating (33) automotive data (3) to the central, expert-system based circuit (11), and wherein the usage-based (31) and/or user-based (32) and/or operational (33) automotive data (3) are based on the sensory data (40111 /40121) and/or operating parameters (4611) of the automotive control system (461,...,465). The automotive car system (1) provides an automated first and/or second risk-transfer based on dynamic generated first and/or second risk transfer parameters (501,..., 505/1021,...,1025) from the motor vehicles (41,...,45), wherein by means of the central, expert-system based circuit (11) the first and/or second risk transfer parameters (501,...,505/1021,...,1025) and correlated first and/or second payment transfer parameters (1021,...,1025/1221,...,1225) are dynamically generated, adapted and/or optimized, wherein, in the case of triggering the occurrence of one of defined risk events (61 63), the occurred loss (71,..., 75) is automatically covered by the automotive car system (1).