Abstract: An object recognition method is provided. The method includes obtaining speech information of a target object in a current speech environment and position information of the target object; extracting voiceprint feature from the speech information based on a trained voiceprint matching model, to obtain voiceprint feature information; obtaining a voice confidence value corresponding to the voiceprint feature information; and obtaining an object recognition result of the target object based on the voice confidence value, the position information, and the voiceprint feature information.

Abstract: A device control method is described. A processing circuitry of a device obtains a first message that is indicated as from a first device associated with a first device identifier in an instant messaging group and determines, according to the first message, control-related information corresponding to at least a second device associated with a second device identifier in the instant messaging group. The processing circuitry further generates, according to the control-related information, a device control command corresponding to the second device, transmits the device control command to the second device, and receives a second message that is sent by the second device. The second message includes a device control command execution result regarding the second device executing the device control command.

Abstract: A device monitors, by using a microphone array, a sound generated by a monitoring target. In response to detecting a sound signal by the microphone array, the device determines a sound source direction corresponding to detected sound signal according to a sound phase difference obtained by each microphone in the microphone array. The device performs infrared detection in the sound source direction by using the infrared transceiver. The device determines a distance between the monitoring target and the infrared transceiver in the sound source direction according to an infrared detection result obtained by the infrared transceiver. The device generates location information of the monitoring target according to the sound source direction and the distance.

Abstract: Systems and methods are provided for evaluating asset risks using categories of primary loan underwriting factors associated with a pre-selected number of variables. An initial handle-based tree data structure is created based upon primary loan underwriting factors associated with a loan and includes a plurality of handle cells that segment loans according to values of the pre-selected variables. The initial handle-based tree data structure is modified by combining handle cells containing least significant splits and rank ordering of the modified handle-based tree data structure is performed to segment portfolio data.

Abstract: Processing devices and methods for transmitting and receiving data are provided. By performing multiple checks on the downloaded control data packets and the decompressed control data, the data status of each process can be known during the processes from the data packets downloading to decompression. And the correct processing can be performed, thus avoiding loading and running failure caused by incomplete data.

Abstract: Systems and methods are provided for evaluating loan applications. A computer environment can include a loan evaluation system which operates on a processor-based system and which evaluates loan applications. A credit assessment framework is also provided for operating on the processor-based system and has a data connection to the loan evaluation system. The credit assessment framework generates a categorization of credit risk for each of the loan applications to be evaluated.

Abstract: Computer-implemented systems and methods are provided for model validation of a model for compliance and credit risk. Model input, output, and processing validation areas are contained on a computer system. A handle data structure connects the model validation areas with handles that comprise a unified metric. A handle represents combinations of covariate patterns and describes the joint distribution of risk characteristics.

Abstract: Systems and methods are provided for evaluating risks associated with alternative strategies for assessing an entity with respect to a predetermined objective. A system includes an action table that contains a plurality of possible actions that can be taken with respect to the predetermined objective for various entity profiles. One or more statistical data stores are configured to contain risk amounts associated with each entity profile, where the one or more statistical data stores are configured to contain inferred percentage distribution of applicants associated with each entity profile. One or more profile identification data stores contain entity identification information for use in determining an action for the entity. One or more improvement data stores provide an indication in the improvement in risk based upon a change in one or more characteristics for an entity profile.

Abstract: Processing devices and methods for transmitting and receiving data are provided. By performing multiple checks on the downloaded control data packets and the decompressed control data, the data status of each process can be known during the processes from the data packets downloading to decompression. And the correct processing can be performed, thus avoiding loading and running failure caused by incomplete data.

Abstract: Systems and methods are provided for evaluating risks associated with alternative strategies for assessing an entity with respect to a predetermined objective. A system includes an action table that contains a plurality of possible actions that can be taken with respect to the predetermined objective for various entity profiles. One or more statistical data stores are configured to contain risk amounts associated with each entity profile, where the one or more statistical data stores are configured to contain inferred percentage distribution of applicants associated with each entity profile. One or more profile identification data stores contain entity identification information for use in determining an action for the entity. One or more improvement data stores provide an indication in the improvement in risk based upon a change in one or more characteristics for an entity profile.

Abstract: Computer-implemented systems and methods are disclosed herein that relate to processes, which construct an empirically derived and statistically based risk evaluation and policy formulation system. For example, a process can be configured so as to accept as input an information base in computer readable form and produce either a single or multistage system composed of alternative decision making strategies.

Abstract: Systems and methods are provided for evaluating asset risks using categories of primary loan underwriting factors, which are associated with a pre-selected number of variables. An initial handle-based tree data structure is created in a computer memory based upon the primary loan underwriting factors associated with a loan, where the initial handle-based tree data structure includes a plurality of handle cells that segment a population of loans according to values of the pre-selected variables. The depth of the initial handle-based tree data structure is the number of variables associated with the primary loan underwriting factors, and a branch of the initial handle-based tree data structure is based on a value of one of the pre-selected variables. The initial handle-based tree data structure is modified by combining handle cells which contain least significant splits.

Abstract: In accordance with the teachings described herein, computer-implemented lending analysis systems and methods are provided. A pre-processing module may be used to organize loan applicant data into a plurality of applicant groups based on one or more demographic factors, wherein a protected class is identified from the plurality of applicant groups. An index generation module may be used to calculate a plurality of disparity indices for the protected class by comparing lending-related data for the protected class with lending-related data for one or more control groups selected from the applicant groups. An indicator generation module may be used to calculate one or more singular indicators for the protected class by comparing the disparity indices with one or more reference indices. The indicator generation module may be further used to calculate a global indicator as a function of a plurality of singular indicators.

Abstract: Computer-implemented systems and methods are provided for model validation of a model for compliance and credit risk. Model input, output, and processing validation areas are contained on a computer system. A handle data structure connects the model validation areas with handles that comprise a unified metric. A handle represents combinations of covariate patterns and describes the joint distribution of risk characteristics.

Abstract: Systems and methods are provided for evaluating loan applications. A computer environment can include a loan evaluation system which operates on a processor-based system and which evaluates loan applications. A credit assessment framework is also provided for operating on the processor-based system and has a data connection to the loan evaluation system. The credit assessment framework generates a categorization of credit risk for each of the loan applications to be evaluated.

Abstract: Systems and methods are provided for analyzing disparate treatment in financial transactions. Data processing software instructions may be used to process lending-related data to identify a plurality of primary factors and one or more secondary factors for use making a lending-related decision. Model facilitation software instructions may be used to receive one or more relationships between the primary factors and the one or more secondary factors, wherein the relationships define criteria in which one or more positive secondary factors will compensate for a negative primary factor in making the lending-related decision. Model generation software instructions may be used to analyze lending-related data based on the primary factors, secondary factors and the one or more relationships.

Abstract: Systems and methods are provided for analyzing disparate treatment in financial transactions. Data processing software instructions may be used to process lending-related data to identify a plurality of primary factors and one or more secondary factors for use making a lending-related decision. Model facilitation software instructions may be used to receive one or more relationships between the primary factors and the one or more secondary factors, wherein the relationships define criteria in which one or more positive secondary factors will compensate for a negative primary factor in making the lending-related decision. Model generation software instructions may be used to analyze lending-related data based on the primary factors, secondary factors and the one or more relationships.

Abstract: In accordance with the teachings described herein, computer-implemented lending analysis systems and methods are provided. A pre-processing module may be used to organize loan applicant data into a plurality of applicant groups based on one or more demographic factors, wherein a protected class is identified from the plurality of applicant groups. An index generation module may be used to calculate a plurality of disparity indices for the protected class by comparing lending-related data for the protected class with lending-related data for one or more control groups selected from the applicant groups. An indicator generation module may be used to calculate one or more singular indicators for the protected class by comparing the disparity indices with one or more reference indices. The indicator generation module may be further used to calculate a global indicator as a function of a plurality of singular indicators.