13results about How to "Resolve indistinguishable" patented technology

The invention provides a voice recognition result correction method and device, electronic equipment, a medium and a vehicle, and relates to the technical field of vehicles. The method comprises the following steps: performing voice recognition on input audio information to obtain a first recognition result; in response to input abnormal feedback information, obtaining actual text information corresponding to the audio information; through the actual text information, the first recognition result is corrected to obtain the second recognition result, the second recognition result is the actual recognition result corresponding to the audio information, error results of voice recognition are corrected, the problem that homophones are difficult to distinguish in the voice recognition process is solved, and the accuracy of voice recognition is improved.

The present invention discloses an efficient and rapid method for producing pure-line oyster seeds. It uses tetraploid sperm as a male source to induce gynogeny, which solves the problem that the gynogenetic line and the normal fertilized offspring are both diploid and difficult to distinguish or inaccurate to distinguish, and achieves the purpose of identifying gynogenetic offspring only by ploidy detection. Through ultra-low density culture, true gynogenetic offspring adults are obtained, solving the technical problem of the "bottleneck" of the lack of gynogenetic adults of shellfish in the world, and filling the international gap. Through two consecutive generations of gynogenetic technology, the previous status quo that gynogenetic lines could not survive was reversed, and for the first time in the world, genetically identified pure-line shellfish were obtained, prompting my country to reach the international leading level in this field.

This invention relates to a method for real-time online detection of wastewater indicators. Before detection, a low-concentration water body is injected into the detection chamber to perform micro-dose detection. By observing whether there is a nonlinear shift in the initial response behavior, it is determined whether there is residual response on the inner wall of the detection chamber. If so, a local delayed detection and pre-rinsing operation is performed to suppress interference responses caused by the chemical memory of the detection chamber. After completing the pre-response suppression, a slow-varying physical stimulus process is applied to the wastewater to be tested, stimulating the release of masked pollutants in the wastewater. The pollutant response signals are continuously tracked, and fluctuating behavior is identified. Based on the changing trend of the response curve, a stable response interval is identified as the sampling point for final detection. For cases with superimposed responses from multiple pollutants, the rise rate, fall rate, and tailing characteristics of the response profiles of each indicator are analyzed to identify the physical differences of multiple response signals and perform physical-level decoupling, improving the accuracy of identifying multiple pollutants.

The application discloses a crab apartment inspection method and system based on visual excitation cooperation discrimination, and relates to the technical field of aquatic product breeding automation equipment. The method part comprises the following steps: acquiring a basic frame through visual compensation alignment of an open observation hole; performing passive observation to extract a first displacement area; triggering physical excitation and extracting a secondary stress area when the displacement is lower than a threshold value; and realizing classification evaluation in combination with morphological characteristics. The system part comprises an independent support frame and an inspection mobile terminal carried on a two-dimensional module, and the stroke of a Z-axis feeding assembly is limited outside the independent breeding box. Through active and passive cooperative detection, the application effectively solves the technical problems of easy deviation of multi-layer shelf positioning and high false judgment rate of dormant individuals, and the non-invasive structure ensures the safety of the optical assembly.

The invention relates to the technical field of foramen endoscope operation positioning nails, in particular to a degradable developing positioning nail for a lumbar foramen endoscope operation. According to the technical scheme, the nail comprises a threaded nail body and a nail cap fixedly connected to the end of the threaded nail body, and further comprises a marking structure arranged at the end of the nail cap and used for recognizing a positioning point; the torsion stress groove is formed in the operation end of the nail cap, and a lock rod groove piece is formed in the torsion stress groove; the end of the rectangular rod is connected with a lock head piece connected with the lock rod groove piece in a locked mode, and a springback piece is arranged at the tail end of the transmission rod. The torsion stress groove and the lock rod groove piece are formed in the end of the nail cap, and the lock head piece can be stably connected into the lock rod groove piece under the cooperation of the springback piece; the tapered end piece and the rectangular rod can be withdrawn quickly without loosening the threaded nail body subsequently, so that the positioning stability of the threaded nail body is remarkably improved; and the threaded nail body, the tip part and the nail cap are all made of degradable materials and do not need to be taken out after an operation, so that the operation safety and the patient comfort are improved.

The application is a regional subspace fusion method for infrared images and GM-APD images. The application relates to the technical field of image signal processing. The application obtains a reference segmentation label through a laser image and an infrared image; performs pre-fusion on an unsegmented feature map and a segmented feature map; and finally fuses the segmented fusion map and the unsegmented fusion map. The application adds a regional factor in the whole fusion process, breaks through the limitation that the traditional double-mode whole image feature fusion cannot distinguish regions, and causes differences between regions and insufficient use of information within regions, so as to maximize the target saliency of infrared and the separability between GM-APD targets, successfully solves the problem that similar targets and target backgrounds are difficult to distinguish in the fusion process. This has important significance for realizing accurate target recognition of all-weather detection.

This invention provides a method and apparatus for identifying parameters of a power system node frequency response model, relating to the field of data processing technology. The method includes: acquiring operational data of multiple nodes in a power system under stable operating conditions; constructing an independent disturbance estimation sequence for each of the multiple nodes based on the operational data; wherein the independent disturbance estimation sequence is obtained by minimizing the residual correlation between different nodes; constructing an equivalent input correlation function and an output correlation function for identifying the node frequency response model based on the independent disturbance estimation sequence; establishing an optimization objective function for identifying the parameters of the node frequency response model based on the equivalent input correlation function and the output correlation function; and solving for the parameters of the node frequency response model based on the optimization objective function. The method provided by this invention achieves accurate modeling of the dynamic frequency characteristics of the system without relying on external excitation.

The present invention relates to the field of image denoising, and in particular to a method for suppressing background noise of a high-sensitivity image of a space target, comprising S1: tracking and imaging the space target using a light measuring device to obtain a continuous high-sensitivity image sequence; S2: counting the grayscale values ​​in the row and column directions in the high-sensitivity image sequence to obtain a brightness distribution; S3: determining the coordinates of the space target in the high-sensitivity image sequence based on the brightness distribution; S4: adjusting the exposure of the high-sensitivity camera in the light measuring device, re-imaging the space target, and obtaining a 16-bit original image, so that the brightness of the pixel points around the space target in the original image reaches a brightness threshold; S5: simultaneously selecting the high 8-bit data of the 16-bit original image and stretching the grayscale at equal intervals to obtain two 8-bit images; S6: fusing the two 8-bit images to obtain a denoised high-sensitivity image. The present invention effectively removes the noise of the high-sensitivity image of the space target.

This invention discloses a TaqMan real-time fluorescent PCR detection primer and probe set, kit, and detection method for Cuscuta pentaphyllum. The primer and probe set includes: an upstream primer C. pan F, whose nucleotide sequence is shown in SEQ ID NO.1; a downstream primer C. pan R, whose nucleotide sequence is shown in SEQ ID NO.2; and a TaqMan probe C. pan P, whose nucleotide sequence is shown in SEQ ID NO.3. The primers and probe target specific fragments of the rbcL gene sequence of Cuscuta pentaphyllum, achieving specific recognition of Cuscuta pentaphyllum through sequence complementarity matching. This avoids false positive results caused by cross-reactions with closely related species and host plants at the molecular targeting level, effectively solving the problem of difficulty in distinguishing closely related species in traditional morphological identification. Compared with traditional morphological identification and conventional PCR, this invention also features high detection efficiency, short processing time, simple operation, and wide applicability. It is suitable for precise identification in professional laboratories and can also meet the practical applications in grassroots quarantine and field monitoring scenarios.

This invention provides a method and apparatus for identifying parameters of a power system node frequency response model, relating to the field of data processing technology. The method includes: acquiring operational data of multiple nodes in a power system under stable operating conditions; constructing an independent disturbance estimation sequence for each of the multiple nodes based on the operational data; wherein the independent disturbance estimation sequence is obtained by minimizing the residual correlation between different nodes; constructing an equivalent input correlation function and an output correlation function for identifying the node frequency response model based on the independent disturbance estimation sequence; establishing an optimization objective function for identifying the parameters of the node frequency response model based on the equivalent input correlation function and the output correlation function; and solving for the parameters of the node frequency response model based on the optimization objective function. The method provided by this invention achieves accurate modeling of the dynamic frequency characteristics of the system without relying on external excitation.

The present invention discloses a method for speech emotion recognition based on supervised contrastive learning, comprising the following steps: obtaining a large-scale speech data set containing multiple emotion categories, systematically preprocessing and emotion labeling the speech data to construct a high-quality training data set; constructing a speech emotion recognition model based on an emotion anchor point generation module, a discourse emotion representation module, a contrastive learning module, and an emotion anchor point adaptation module; using the data set constructed in step 1 to train the emotion recognition model; inputting the target speech to be recognized into the trained model, and calculating the similarity between the discourse emotion representation and the closest emotion anchor point, thereby obtaining the final emotion prediction result. The method proposed by the present invention solves the problem that similar emotions are difficult to distinguish by adopting a supervised contrastive learning method; at the same time, the present invention can not only improve the accuracy of emotion recognition, but also enhance the generalization ability of the model.

The application discloses a probe primer group, a kit and a detection method for detecting European dodder, wherein the probe primer group comprises an upstream primer Ce-rbcL-F, a downstream primer Ce-rbcL-R and a TaqMan probe Ce-rbcL-P; the nucleotide sequence of the upstream primer Ce-rbcL-F is shown as SEQ ID NO. 1; the nucleotide sequence of the downstream primer Ce-rbcL-R is shown as SEQ ID NO. 2; and the nucleotide sequence of the TaqMan probe Ce-rbcL-P is shown as SEQ ID NO. 3. The primer probe group is designed based on a specific region of the rbcL gene of European dodder, and specific identification of European dodder can be realized by combining an optimized real-time fluorescent PCR reaction system and conditions, namely, the application has the characteristics of rapidness, strong specificity, high identification accuracy, effectively solves the problem that near relatives are difficult to distinguish in traditional morphological identification, and avoids false positive misjudgment. Compared with traditional morphological identification and conventional PCR, the application also has the characteristics of high detection efficiency, short time consumption, simple operation and wide applicability, and can be applied to not only professional laboratory accurate identification, but also practical application of scenarios such as primary quarantine and field monitoring.

The invention discloses a SNP molecular marker, an amplification primer and a method for quickly identifying Jian carp varieties. The SNP molecular marker includes SNP 1 to 5; the physical position of SNP 1 is located at the 27079154th base of Chr17 chromosome, and the base is C or T; the physical position of SNP 2 is located at the 27632650th base of Chr17 chromosome, and the base is A or G; the physical position of SNP 3 is located at the 1441950th base of Chr18 chromosome, and the base is T or C; the physical position of SNP 4 is located at the 5857377th base of Chr18 chromosome, and the base is G or C; The physical position of 5 is located at the 23058224th base of the Chr14 chromosome, and its base is C or G; the SNP molecular marker of the present invention can quickly, accurately and batch identify and screen Jian carp seedlings and parents in the seedling stage and parent stage, and is particularly suitable for variety identification of small-sized fry, solving the problem of difficulty in distinguishing varieties with similar appearance.