9results about How to "Reduce rejection rate" patented technology

The invention provides an access control system based on face recognition and a recognition method, and the system comprises a multi-modal image collection subsystem which integrates a visible light camera, a depth camera and an infrared thermal imaging camera and is used for synchronously collecting a visible light image, a depth image and an infrared thermal imaging image of a face; the image preprocessing unit is used for carrying out corresponding preprocessing on the image; the feature extraction network module is used for extracting image features; the multi-modal feature fusion and alignment module is used for calculating a mutual information matrix by adopting a feature fusion strategy based on mutual information maximization and adaptive weighting, determining an adaptive weight and performing weighted summation, and performing feature alignment by applying a method based on canonical correlation analysis; and the face recognition classification and verification module verifies the image by adopting a multi-level fusion strategy. According to the method, the false recognition rate and the rejection rate are effectively reduced, the strong anti-cheating capability is achieved, and cheating attacks of various fake face means can be accurately recognized and resisted.

The invention discloses a customized order receiving method and system for a designated driver based on a saas platform. The invention relates to the technical field of designated driving services. Receiving demand data of a driver, wherein the demand data comprises order receiving preference, a service area and service time; receiving personal information input by a driver, wherein the personal information comprises basic information and order receiving preference setting; wherein the demand data comprises order receiving preferences, service areas and service time of drivers and users; wherein the basic information comprises a name, a driving age and a vehicle type; according to the invention, the driver is allowed to set personalized order receiving conditions according to own order receiving preference, service area and time, so that the working flexibility of the driver is greatly improved. The driver can autonomously select the order suitable for himself / herself, so that the rejection rate of improper orders is reduced, and the working efficiency and the satisfaction degree are improved. And through an intelligent order receiving matching algorithm, the system can quickly match the most appropriate order for the driver, so that the empty driving time and waiting time of the driver are reduced, and the working efficiency and income are further improved.

This application provides a training method for a fingerprint recognition network, a fingerprint recognition method, an apparatus, and a medium. The training method for the fingerprint recognition network includes: determining fingerprint feature matching maps based on a first initial fingerprint image and a second initial fingerprint image; forming a training sample set from multiple fingerprint feature matching maps; and training an original neural network based on the training sample set to obtain a fingerprint recognition network. The technical solution provided by this application solves the problem of difficulty in distinguishing whether two different fingerprint images belong to the same finger, thus reducing the false acceptance and false recognition rates of fingerprint recognition.

The invention provides a small-area fingerprint identification method and system and a storage medium, and the method comprises the steps: obtaining a fingerprint image, and inputting the fingerprint image into a pre-trained fingerprint feature extraction network model; a block-by-block reasoning strategy is adopted for the fingerprint image through the fingerprint feature extraction network model to obtain a fingerprint low-dimensional feature map; obtaining a fingerprint high-dimensional feature map based on the low-dimensional feature map through a layer-by-layer reasoning strategy; processing the fingerprint high-dimensional feature map through a preset two-dimensional convolution layer, an average pooling layer and a full connection layer in sequence to obtain a final fingerprint feature vector; and calculating the similarity between the fingerprint image to be identified and the target fingerprint image through a cosine similarity function based on the final fingerprint feature vector, and completing fingerprint identification when a set threshold value is reached. Wherein the fingerprint feature extraction network model is obtained by training a fingerprint feature extraction neural network through a pre-constructed fingerprint identification data set. The problems that existing small-area fingerprint recognition is low in precision and low in speed are solved.

The application provides a parallel guide rail base mounting method, comprising the following steps: first, providing guide rail base segments, each guide rail base segment comprising a bottom support, a horizontal panel and a fixed base plate connected in sequence; then, making a mounting reference line, determining the mounting position of the parallel guide rail base according to the mounting reference line; then, mounting the parallel guide rail base to a predetermined position, and confirming and processing the position where the mounting allowance of the bottom support is out of tolerance; finally, butting and mounting the parallel guide rail base with the hull plate of the corresponding mounting position, and repairing and replacing the fixed base plate with mounting precision out of tolerance. By controlling the mounting precision of the guide rail base segment, the mounting precision of the parallel guide rail base, and then adjusting the fixed base plate, the parallelism and flatness mounting requirements of the parallel guide rail base can be met, the mounting precision is ensured, the on-site installation difficulty and waste rate are reduced, and the use cost of personnel and materials is greatly saved.

The invention relates to a cloud resource intelligent performance evaluation system and method based on a large model, and belongs to the technical field of IT resource management. The system comprises a front-end interaction layer, a knowledge management layer, an AI evaluation layer and a data support layer. The method comprises the following steps: in an application stage, guiding a user to clarify a demand and extract key parameters through multiple rounds of dialogues, automatically matching a calculation formula template and generating a recommendation configuration report; in the review stage, the application document is automatically analyzed, normalization, accuracy and logic compliance verification is carried out based on the knowledge base, and review suggestions are generated. According to the invention, through fusion of the large model, the RAG and other technologies, intelligence and standardization of the resource application and review process are realized, the process efficiency and decision consistency are significantly improved, the operation cost and dependence on expert experience are reduced, and structured precipitation and reuse of enterprise knowledge are realized.

The invention relates to the technical field of identity recognition, in particular to an identity recognition system based on finger veins and finger creases, and the system comprises a finger vein recognition model which is used for extracting and analyzing finger vein features, a channel importance evaluation method, and distinguishing important channels and unimportant channels in feature mapping by calculating the importance of each channel; according to the two-level fusion method based on the finger creases and the finger veins, the two features of the finger veins and the finger creases are fused from the feature level and the decision-making level for identity recognition, the two biological features of the finger veins and the finger creases are combined, and the identity recognition accuracy can be remarkably improved by means of the uniqueness of the two biological features of the finger veins and the finger creases. The finger vein feature is located in the finger and is difficult to copy, and the finger crease feature has high individual difference, so that the false recognition rate and rejection rate can be greatly reduced by combining the finger vein feature and the finger crease feature, and the safety and reliability of identity recognition are improved.

The invention discloses a risk prevention and control method and device for a financial manual seat and electronic equipment, and relates to the field of financial science and technology or other related technical fields, and the method comprises the steps: collecting a real-time voice signal interacted between the financial manual seat and a customer, and extracting a multi-dimensional dynamic feature from the real-time voice signal, the multi-dimensional dynamic features comprise acoustic features, semantic features and behavior features; matching the multi-dimensional dynamic features with a pre-constructed customer voiceprint model; based on the matching result and the multi-dimensional dynamic characteristics, evaluating the risk level of the real-time voice signal by adopting a risk evaluation algorithm; and under the condition that the risk level is greater than a preset risk threshold value, sending a risk early warning signal to a financial manual seat, and providing prevention and control suggestions and measures. According to the invention, the technical problem of low accuracy of a voiceprint recognition strategy adopted when a financial institution carries out telephone banking service security verification in the prior art is solved.

This application discloses a method, apparatus, device, and storage medium for identifying biological objects. The method includes: identifying a target biological object using a biometric model and determining the identification result. The biometric model is established by using biological sample images as training samples and training the model under a class balance loss function. The class balance loss function includes a first additive term and a second additive term. The first additive term is used to balance the training loss corresponding to the first additive term during model training, and the second additive term is used to balance the training loss corresponding to the second additive term during model training. It is evident that the introduction of a class balance loss function during model training reduces the loss of classes with a larger number of classes and increases the loss of classes with a smaller number of classes, thus relatively balancing the contribution of different classes to the loss. This mitigates the impact of long-tailed data on model performance and reduces the false positive and false negative rates.