12results about How to "Realize choice" patented technology

The invention belongs to the field of artificial intelligence and deep learning, and provides a small sample continuous learning method and system based on adaptive adaptation layer selection. The small sample continuous learning method based on adaptive adaptation layer selection comprises the following steps: pre-training a singular value of a linear weight; freezing a pre-training linear weight matrix corresponding to the knowledge sensitive component; adaptively determining an adaptation layer; multiplying the adapter matrix based on the adaptation layer by the training sample features of the current incremental adaptation training stage to obtain redundancy capacity features; and the small sample playback data is obtained again, singular value decomposition, adaptive layer adaptive determination and incremental adaptive training operation are performed in sequence based on the updated pre-training linear weight matrix, and learning is stopped until the continuous learning model reaches a set requirement, so that the trained continuous learning model is utilized to execute a classification task. According to the method, dynamic adapter selection for minimizing old knowledge interference is realized, and the classification accuracy of a small sample continuous learning model is guaranteed.

The invention discloses an Indel site related to soybean stem diameter, a molecular marker and application of the Indel site and the molecular marker, and belongs to the field of molecular marker assisted breeding. Carrying out PCR (Polymerase Chain Reaction) amplification and detection by using an amplification primer of the molecular marker 17-10.64 by taking the molecular marker 17-10.64 as a template; when the product fragment is 199bp, judging that the soybean to be identified is a soybean strain with thin stalks; and when the product fragment is 255bp, judging that the to-be-identified soybean is a soybean strain with thicker stalks. The molecular marker 17-10.64 contains an Indel site related to the soybean stem diameter, the Indel site is located at the No.17 chromosome 1, 064, 063 bp of the soybean, and the polymorphism is an amplified fragment difference of 56bp. According to the method, the soybean breeding time is shortened, the soybean breeding efficiency is improved, and powerful support is provided for efficiently developing and utilizing wild soybean germplasm resources and rapidly breeding lodging-resistant high-quality soybean varieties with thick and strong stalks.

The utility model provides a cleaning appliance accessory seat with a cleaning function and a cleaning system, which comprise a cleaning module which can be arranged on a horizontal plane and a working module which can be arranged on a horizontal plane, is arranged in parallel with the cleaning module and is connected with the cleaning module, wherein the cleaning module comprises a first base part with a first base part cavity and a first accommodating part which is vertically connected with the first base part and is provided with a first accommodating cavity; the working module comprises a second base part with a second base part cavity and a second accommodating part which is vertically connected with the second base part and is provided with a second accommodating cavity, one end of the first base part cavity is communicated with the second base part cavity, the other end of the first base part cavity is communicated with the first accommodating cavity, and the second base part cavity is communicated with the second accommodating cavity. The multifunctional mop has the advantages that cleaning appliances and accessories can be stored, the accessories can be cleaned, and diversified choices are achieved.

The present invention relates to an end-to-end visualized logistics control system and method, and belongs to the field of logistics management technology. The method includes determining transportation site information according to a transportation origin and a transportation destination, obtaining an optimal transportation site through a transportation planning model according to the transportation site information, obtaining a planned total transportation time and a planned arrival time at the transportation site according to the optimal transportation site, obtaining a planned arrival time according to the transportation start time, obtaining delay warning information according to real-time location information, obtaining a time difference according to the actual arrival time at the site, uploading delay warning information according to the time difference, obtaining an estimated arrival time according to the delay warning information and the delay warning information and uploading it to an administrator for review, uploading external event information to the administrator for review, and updating the estimated arrival time according to the administrator's review result, thereby realizing logistics in-transit transportation management, improving logistics transportation control, and facilitating early intervention of delay risks.

The application relates to a microwave circuit band-stop filtering device based on an artificial magnetic conductor, and belongs to the fields of artificial magnetic conductors and filtering technologies, which solves the problem that a microstrip line causes electromagnetic interference on a circuit board and the surrounding environment in the prior art. The device comprises a shell and a microwave circuit board; the microwave circuit board is arranged in the shell, and a microstrip line is arranged on the microwave circuit board; an artificial magnetic conductor array is arranged on the lower surface of the top cover of the shell, the artificial magnetic conductor array is formed by arranging a plurality of same artificial magnetic conductor structure units, and is used for filtering electromagnetic interference caused by the microstrip line. The microwave circuit band-stop filtering device based on the artificial magnetic conductor is realized.

The invention relates to a cancer prognosis survival analysis method based on a collaborative co-expression network. The invention relates to the technical field of cancer tumor prognosis analysis, and the method comprises the following steps: collecting cancer multi-omics data based on a public database, and preprocessing the data; based on the processed data, constructing a collaborative co-expression network oriented to the cancer multi-omics data; based on the collaborative co-expression network, a prognosis biomarker is extracted; and according to the extracted prognosis biomarker, carrying out sample clustering for survival analysis, and carrying out prognosis survival analysis. According to the invention, accurate prediction of prognosis categories of cancer patients is realized, and statistical support is provided for biologists to reveal molecular mechanisms causing cancer prognosis survival differences and to assist clinicians to finally realize targeted accurate treatment for prognosis biomarkers.

The invention discloses an evaluation method for a shipboard aircraft autonomous landing guide information fusion algorithm. The evaluation method comprises the steps of 1, obtaining indexes of a plurality of fusion algorithms of shipboard aircraft autonomous landing guide information; step 2, establishing a comment set corresponding to indexes of each fusion algorithm; 3, obtaining a single-factor membership degree matrix of the shipboard aircraft autonomous landing guide information fusion algorithm by using a single-factor fuzzy evaluation method according to the weight distribution set and the comment set of the indexes of each fusion algorithm; 4, performing fuzzy synthesis on the single-factor membership degree matrix, and evaluating the advantages and disadvantages of each algorithm according to a score value; according to the method, the performance of the shipboard aircraft autonomous landing guide information fusion algorithm based on different technical principles can be effectively analyzed and evaluated, and the optimal scheme of the shipboard aircraft autonomous landing guide information fusion algorithm is selected.

The utility model discloses a kind of damping devices with multi-section damping travel, including damping frame, pusher, damper and damping travel adjusting mechanism;The pusher includes first push block and second push block;The damping frame is respectively connected with first push block and second push block through first sliding structure between them, and it includes first slider and first sliding slot;The damping travel adjusting mechanism includes locking structure and travel selection mechanism;The locking structure includes multiple sets of first locking slot and first locking block;The travel selection mechanism includes bridge slider and travel selection drive mechanism;When first push block moves to the top of bridge slider, the bottom of first push block is supported by bridge slider;When first push block passes bridge slider, this first push block swings downward into corresponding first locking slot.This damping device of the utility model can realize the adjustment to damping travel, so as to be suitable for different application occasions.

The application provides a packaging bag film blowing system, which comprises a fan, a wind ring assembly and a discharge die head, the wind ring assembly comprises a base and an upper air disc, the base is installed on the discharge die head, the upper air disc covers the base, and a lower air lip is fixedly connected to the upper air disc; a main air channel is formed between the base, the upper air disc and the lower air lip, a lower air channel is formed between the base and the lower air lip, and the lower air channel communicates with the main air channel; a first upper air channel and a second upper air channel are arranged on the lower air lip, an annular groove is arranged on the lower air lip, a first air hole is arranged on the annular groove, a blocking ring is slidably installed in the annular groove, and a second air hole is arranged on the blocking ring; the application can solve the problem that the air port of the wind ring in the prior art is in an open state for a long time, dust in the air easily enters the inside of the wind ring device through the air port, the dust is blown to the film tube which has not been completely cooled by the cooling air, and the film quality is seriously affected.

The present invention discloses an array-type flexible temperature sensor wireless acquisition system, wherein the flexible temperature sensor array is used to acquire temperature field signals, the analog switch module is used to switch the column leads in the temperature sensor array to ground or to a reference voltage, the channel selection module is used to select the row leads in the temperature sensor array to be grounded, the A / D conversion module is used to amplify the voltage signal output by the temperature sensor array and convert it into a digital signal, the MCU module is used to control the analog switch module, the channel selection module, and the A / D conversion module to acquire sensor signals, perform analytical calculations on the acquired data, and the line transmission module is used to wirelessly transmit the calculated results to a terminal device through a signal antenna. The present invention adopts an analog electronic switch and a channel selection switch, solves the crosstalk problem between sensors through analytical calculations, realizes the gating of the output signals of the n*m-way drive module, and realizes the acquisition of the temperature array sensor unit.

The present disclosure proposes a file annotation method, device, equipment and medium based on AI and RPA, which relates to the field of AI and RPA, wherein the method includes: the RPA system obtains a file annotation request; the RPA system responds to the file annotation request and generates a response result corresponding to the file annotation request; the RPA system draws a target image corresponding to the file to be annotated according to the response result; the RPA system responds to the mouse event and determines the area range of the text annotation in the target image; the RPA system determines the text annotation result within the area range according to the first text information obtained by performing optical character recognition (OCR) on the file to be annotated and the position information corresponding to each text fragment of the first text information. In this way, the extraction of text information in the picture and the selection of discontinuous text in the text can be realized, and at the same time, the text information within the annotated area range and the position information of the text fragments in the text information can be obtained, which can meet the needs of model training.

The present application relates to the field of ultrasonic excitation, and proposes an ultrasonic excitation method, device, system and storage medium. The system includes: a control terminal, a signal generator, a high-frequency electrically controlled switch and a power amplifier, wherein: the control terminal is used to obtain ultrasonic parameters and random parameters, and convert the ultrasonic parameters and random parameters into operation instructions and send them to the signal generator; the signal generator is used to generate ultrasonic signals and level control signals according to the operation instructions; the high-frequency electrically controlled switch selects the ultrasonic signal according to the level control signal, and outputs the selected ultrasonic signal through the high-frequency electrically controlled switch; the power amplifier is used to amplify the ultrasonic signal to output ultrasonic waves through the amplified ultrasonic signal. The embodiment of the present application realizes the random selection of ultrasonic signals by using the level control signal generated by random parameters, which is conducive to reducing the influence of ultrasonic signals executed sequentially on the test results and improving the reliability of the test results.