58results about How to "Improve scoring efficiency" patented technology

The invention discloses a high-speed cap separating mechanism, which comprises a cap bin, transmission components and cap separating components, wherein the cap bin is placed vertically; at least 2 cap separating components are arranged at the bottom of the cap bin; each cap separating component consists of double layers of shifting wheels and is formed by connecting an upper wheel (13) and a lower wheel (15) through a central shaft sleeve (16), the projection of the lower wheel (15) is in a shape of sector of which central angle is less than 180 degrees, the upper surface of the lower wheel (15) is a plane, the projection of the upper wheel (13) is in a shape of sector of which central angle is 180+ / -10 degrees, the lower surface of the upper wheel (13) is a plane, the edge of the upper surface of the upper wheel (13) is provided with a spiral face (14), the directions of the symmetric lines of the sectors of the upper wheel (13) and the lower wheel (15) are opposite, and the distance between the lower surface of the upper wheel (13) and the upper surface of the lower wheel (15) is the thickness of a tank cap; and the central shaft sleeve (16) of each cap separating component is in transmission connection with the transmission component. The high-speed cap separating mechanism enables the easily nested tank cap to be automatically separated at a high speed, and has high cap separating efficiency.

The embodiment of the invention provides a subjective question evaluation method and device, and the method comprises the steps: receiving the score associated data of a subjective question; calculating semantic similarity values of the standard answer data and the test paper answer data; calculating a basic score coefficient of the subjective question by utilizing a basic score equation corresponding to the question stem data and the semantic similarity value; calculating an additional score coefficient corresponding to the test paper answer data and a preset additional score dimension; calculating a final score coefficient corresponding to the ontology vector by utilizing a final score model, and obtaining a final score by calculating the product of the final score coefficient and the total score of the subjective question. The final score obtained by the invention comprises evaluation of multiple dimensions on subjective questions, so that the score is closer to real demands and higher in accuracy, thereby greatly reducing the workload of manual rechecking, improving the scoring efficiency, and effectively solving the problems of low accuracy and low efficiency when the subjective questions are scored by an existing system automatic paper scoring mode.

The invention provides an electronic grading system and a grade summing system. An image scanner is used for reading a plurality of answer sheets, a plurality of answer images on one answer sheet are extracted, the answer images are converted into a file, the file is sent to a grading server, if a question number is input at the client for judging, the answer images of the file of the question is displayed on a display device of the client, a grader make correct or error judgment by observing the display, and the judgment results are summed in the grading server examinee by examinee.

The embodiment of the invention provides a performance evaluation method and device based on artificial intelligence. The invention relates to the field of artificial intelligence. The method comprises the steps of determining K evaluation indexes according to an instruction of a user; determining the weight of each evaluation index in the K evaluation indexes according to the instruction of the user; screening K deep neural network models from the plurality of deep neural network models, wherein each deep neural network model in the K deep neural network models has a mapping relationship withone evaluation index in the K evaluation indexes; respectively inputting the to-be-evaluated performance text into each deep neural network model in the K deep neural network models; and adding the scores of the evaluation indexes output by each deep neural network model in the K deep neural network models according to a preset weight to obtain a performance score of the target employee. According to the technical scheme provided by the embodiment of the invention, the problem of low scoring efficiency of the performance text in related technologies can be solved.

The invention relates to a CTG fetal heart rate scoring method and system. The CTG fetal heart rate scoring method comprises the following steps that fetal heart data processing is carried out, specifically, signal acquisition and calculation of a fetal heart rate and uterine contraction values are conducted to obtain fetal heart rate data, uterine contraction pressure data and fetal movement data; and fetal heart scoring is carried out, specifically, the fetal heart rate data and the uterine contraction pressure data obtained in the fetal heart data processing step are received, interferenceremoval and noise processing are sequentially carried out on the received data based on a CTG scoring algorithm, a fetal heart rate baseline is calculated, uterine contraction activity is calculated,acceleration and deceleration activities are analyzed and judged, amplitude variation is calculated and cycle variation is calculated, analysis results are obtained, and corresponding scores are obtained according to the analysis results. The CTG fetal heart rate scoring method and system have the beneficial effects that the analysis and judgment of the fetal heart rate and the uterine contractiondata are more perfect, and the scoring result is more accurate.

The invention discloses an automatic marking system of a network attack and defense experiment. The system analyzes and marks based on a data package automatically, and consists of an attack party, a defense party, a core switch, a capture package server and a marking server. The automatic marking system provided by the invention is applied to the network attack and defense experiment in a college information safe and comprehensive practical training laboratory, the system will automatically mark according to the capture package server and the marking server so as to judge winning and losing, after the network attack party and the network defense party finish the experiment. Therefore the two parties are more fair, and the efficiency of the integral experiment can be improved; and meanwhile, the technical requirements on teachers can be reduced, and the experimental requirements on different groups can be met.

The invention discloses a light guide plate scribing machine and a cutting die device of the light guide plate scribing machine. The cutting die device is technically characterized by comprising a cutting die body, blades and elastic components; the cutting die body is provided with a plurality of cutter grooves formed in parallel, one end of each cutter groove is a limiting end, and each cutter groove is further provided with a limiting part; each blade comprises a blade body and a cutting edge connected to the bottom end of the blade body, wherein the blade is inserted into the corresponding cutter groove in a clearance fit mode, and the cutting edge extends out of the corresponding cutter groove; the elastic components are clamped between the blades and the limiting ends of the corresponding cutter grooves, the blades can slide along the corresponding cutter grooves under the action of elastic force of the elastic components, and the limiting parts limit the positions, sliding out of the corresponding cutter grooves, of the corresponding blades. Even if a plate is uneven, the extension length of the blades can be adjusted through the elastic components, and the consistency of scribing depths is guaranteed; the blades are free of swinging by adjusting fit tolerance, and the scribing uniformity can be guaranteed; by means of modularized connection of the cutting die device, lines can be quickly scribed in plates with different areas, and efficiency is very high; compared with a laser scribing device, the cutting die device has the advantage that the equipment cost and power consumption of machining are greatly reduced.

The invention discloses an automatic scoring method based on a virtual experiment platform, which is characterized by comprising the following steps of: 1) inputting text data, namely inputting subjective question text data, 2) preprocessing natural languages, 3) classifying question types, and 4) carrying out a scoring process. The method does not need manual scoring, and can save the scoring time, improve the scoring efficiency and improve the scoring accuracy.

The invention relates to an automatic machined part measuring system and an automatic scoring method. The measuring system comprises a non-contact measuring mechanism and a testing service station, the testing service station is connected with the non-contact measuring mechanism, a numerical control machine tool, a school teaching management system and a mobile phone of a trained student through anetwork and comprises laser, a visual signal processing unit, a numerical control machine tool data acquisition unit, an automatic machined part scoring unit, a school teaching management system interaction unit and a mobile terminal interaction unit, the scoring unit acquires total training score A, A=k1*A1+k2*A2+k3*A3+k4*A4, k1, k2, k3 and k4 are score weighting coefficients which are set according to practical situations by mentors, default values are given by the system, A1 refers to machining dimension precision score, A2 refers to machining technology quality score, A3 refers to machining efficiency score, and A4 refers to attendance discipline score.

The invention discloses an electronic golf scoring system and method. The system comprises a plurality of handheld scoring devices, the handheld scoring devices are provided with a database, and IDs of the handheld scoring devices and score record relationships between the IDs of the handheld scoring devices are stored in the database. At least every three handheld scoring devices form a scoring network according to the corresponding score record relationships, wherein the scoring system comprises the first handheld scoring device, the second handheld scoring device and the third scoring device. Each first handheld scoring device comprises a first input module, a first wireless communication module, a first storage module, a first judgment module, a second judgment module and a first processing module which is connected with the first input module, the first wireless communication module, the first judgment module and the second judgment module. The electronic golf scoring system and method can complete automatic and timely score checking, save time, improve the scoring efficiency and are high in accuracy.

The invention provides a container resource scheduling method, which comprises the following steps that: S1: giving a mark for a node; and S2: selecting a node with a highest score. Through the above setting, on a resource-allowable premise, the bandwidth of a network transmission mirror image and time required for downloading the mirror image can be saved, system operation efficiency is improved, and system service quality is guaranteed.

The invention discloses an assessment method and device used for a system. The method comprises the steps of: responding to an assessment instruction aiming at a target application system, and reading preset assessment rule parameters, wherein the assessment rule parameters includes projects to be assessed and scoring strategies corresponding to the projects to be assessed; reading state data of the projects to be assessed from a database of the target application system; according to the state data of the projects to be assessed and the scoring strategies corresponding to the projects to be assessed, determining the assessment scores of the projects to be assessed. According to the invention, the projects to be assessed are set on line in advance, and the corresponding scoring strategies aiming the projects to be assessed are configured, so that when the assessment instruction is received, the state data of the projects to be assessed is automatically read, the assessment scores of the projects are determined according to the configured scoring strategies, the automatic scoring process is realized, and the scoring efficiency is improved.

The invention provides an automatic scoring method and an automatic scoring system for translation. The automatic scoring method comprises the following steps: performing text preprocessing on each training translation, each test translation and each standard translation; performing feature extraction on the preprocessed training translation to obtain an X-dimensional feature score of the trainingtranslation; taking the N training translations as training samples, taking the training translation X-dimensional feature score of each training translation as X inputs, taking the final score of the training translation as an output, and respectively training a neural network model, a K-minimum neighbor algorithm model and a support vector machine algorithm model; and inputting the X-dimensional feature score of the test translation into the trained model to obtain a final score of the test translation. According to the automatic scoring method and the automatic scoring system for the translation provided by the invention, the translation can be automatically scored, the scoring efficiency is remarkably improved, and the burden of scoring personnel is reduced.

The invention relates to a data index quantification method and a smart park enterprise value evaluation system, and the method comprises the steps of obtaining smart park enterprise data according to a judgment index system; carrying out numerical processing and normalization processing on the acquired enterprise data of the smart park; multiplying the processed index data by the index weight of the index system to obtain an enterprise value evaluation result, where the index weight obtaining process comprises the steps that a pairwise relative importance judgment matrix is established for each layer of indexes, normalization processing is carried out, the weight of each index is obtained, and the pairwise relative importance judgment matrix represents the relative importance between the two indexes through numerical values; and performing manual marking through an expert method to form training set data, and performing iterative learning training on parameters in a pairwise relative importance judgment matrix in the index system through a regression algorithm to obtain an optimal index weight. Compared with the prior art, the invention has the advantages that subjective judgment is reduced to the minimum, calculation efficiency is high, and the method is more scientific, reasonable and interpretable.

The invention discloses a vocalization scoring method, including the following steps: 1) according to beats of a song, dividing notes of a vocalization into N sections arranged according to time sequence, each section including notes in different numbers, each note being corresponding to a standard pitch value; 2) recording voice data, according to beats of the song, dividing the voice data into Nsections arranged according to time sequence, dividing data in each section into n sampling points whose duration is dj, analyzing the sampling points, to obtain pitch values p of the sampling points; 3) using the following formula to score the pitch values p of the sampling points; 4) counting score of the voice data. The vocalization scoring method is simple and convenient, and scoring efficiency is higher. The voice data is divided into N sections arranged according to time sequence, and each section is scored, so an obtained scoring result is fine and accurate.

The invention provides a multi-modal automatic scoring method, medium and equipment for college English speech. The method comprises the following steps: acquiring historical speech data; extracting text features, audio features and video features, and performing model training to obtain a language use evaluation sub-model, a speech expression evaluation sub-model and a non-language evaluation sub-model; generating a fourth data set according to the output of the three sub-models and the comprehensive score; performing model training to obtain a multi-modal fusion learning model; obtaining a speech video to be scored, extracting corresponding text features, audio features and video features, and outputting corresponding single scores through the three sub-models; inputting the single score into a multi-modal fusion learning model, and outputting a final score result corresponding to the speech video to be scored through the multi-modal fusion learning model; multi-modal scoring can be carried out on the English speech, and the scoring accuracy and the scoring efficiency are improved; and meanwhile, the cost for scoring the English speech is reduced.

The invention discloses a Chinese-English spoken language translation question scoring method and system. The method comprises the following steps: preprocessing an obtained voice signal to be scored and extracting voice feature parameters; recognizing the voice feature parameters according to a pre-trained voice recognition model to obtain a voice recognition result; based on a preset scoring mechanism, scoring the voice recognition result to obtain a keyword score, a sentence meaning score, a grammar score and a fluency score; and inputting the keyword score, the sentence meaning score, the grammar score and the fluency score into a pre-trained score fusion model to obtain a comprehensive score of Chinese-English spoken language translation. The embodiment of the invention further discloses a Chinese-English spoken language translation question scoring system. By adopting the embodiment of the invention, the characteristics of the keyword, sentence carelessness, grammar and spoken language fluency of the to-be-scored voice signal are extracted and automatically scored, so that the scoring efficiency and the accuracy of the scoring result are improved, and time and labor are saved.

The invention relates to an automatic assessment scoring method, device and system. The method comprises the steps of obtaining examinee test question information which is submitted by an examinee in advance and carries a test paper identifier; extracting theoretical question answer information and practical operation question answer information from the examinee test question information; comparing the theoretical question answer information with a preset theoretical question answer, and determining a theoretical question score corresponding to the test paper identifier; comparing the practical operation question answer information with a preset practical operation step according to a practical operation question judgment mode corresponding to the practical operation question answer information, and determining a practical operation question score corresponding to the test paper identifier; and determining and outputting a theoretical question score, a practical operation question score and a total score of the examinee according to a pre-stored association relationship between the examinee identifier and the test paper identifier. By the adoption of the scheme, the assessed theoretical questions and practical operation questions are automatically scored, scoring manpower resources are saved, scoring labor cost is reduced, compared with manual scoring, the automatic scoring speed is high, scoring efficiency is improved, the scoring efficiency is not affected by subjective factors of scoring referees, and assessment fairness is improved.

The invention discloses a laser material nicking machine capable of adsorbing and removing scraps. The nicking machine structurally comprises a nicking tool rest, a sliding adjusting rod, an equipmentsupporting table, an intelligent control system and a glass fixing table. The equipment supporting table is horizontally installed on the ground. The sliding adjusting rod is in clearance fit with the equipment supporting table. The intelligent control system is nested on the surface of the equipment supporting table. The laser material nicking machine is provided with a chipping remover. An anti-collision structure promotes a glass cutter to stably get close to laser glass. Glass is prevented from being broken due to too high moving speed. Meanwhile, glass chips are removed thoroughly in a nicking process. Friction generated by the glass chips in the nicking process of the glass cutter is avoided. The glass nicking efficiency is improved, and meanwhile, abrasion of the glass cutter is reduced. The service life of the nicking machine is effectively prolonged.

The present invention is suitable for the technical field of computers, and provides a commercial tenant scoring system. The system comprises: an obtaining unit configured to obtain a first commercialtenant scoring item and a first commercial tenant scoring result corresponding to the first commercial tenant scoring item; a determination unit configured to determine a scoring rule according to the corresponding relation of the first commercial tenant scoring item and the first commercial tenant scoring result; an automatic scoring unit configured to receive a second commercial tenant scoringitem, performing scoring of the commercial tenant according to the commercial tenant scoring rule and output a second commercial tenant scoring result corresponding to the second commercial tenant scoring item. According to the commercial tenant scoring system, the determination unit determines the commercial tenant scoring rule according to the first commercial tenant scoring item and the first commercial tenant scoring result obtained by the obtaining unit, and the automatic scoring unit achieves automatic scoring of the commercial tenants according to the commercial tenant scoring rule so as to improve the efficiency of commercial tenant scoring and achieve precision, automation and intelligence of commercial tenant scoring.

The embodiment of the invention relates to the technical field of family education equipment. The invention discloses a composition scoring method and a family education device. The method comprises the following steps of: obtaining a sample; collecting a large number of compositions under a certain composition topic; analyzing the content of each composition in a large number of compositions; therefore, the writing mode of each composition is obtained; obtaining a target composition submitted by a target user, taking a writing mode as a sample, training to obtain a time sequence corpus model,then obtaining the target composition submitted by the target user, importing the target composition into the time sequence corpus model, obtaining the novelty degree of the target composition judgedby the time sequence corpus model, and scoring the target composition according to the novelty degree of the target composition. The composition scoring efficiency can be improved, and time and laborare saved.

The invention discloses a scoring method and device based on multi-dimensional features, computer equipment and a storage medium, and belongs to the technical field of big data. According to the scoring method based on the multi-dimensional features, historical clients can be divided into a plurality of client sets according to categories of basic attributes in a data set, feature attributes of the clients in all the client sets are analyzed through an initial XGBoost model tree to obtain target feature attributes, and an XGBoost model tree is constructed according to the target feature attributes; a data set is input into an XGBoost model tree for calculation, and a calculation result is analyzed in an equal-frequency binning mode to determine a derogatory threshold. When the data information of the target client is received, the XGBoost model tree is adopted to process the data information to obtain a derogatory probability value, and the score information of the target client is determined based on the derogatory probability value and a derogatory threshold, so that the purpose of quickly, effectively and automatically predicting the score data according to the acquired / acquiredclient data information is achieved.

The invention provides a device for nicking the surface of an injection molded part. The device comprises a first base and a second base arranged on the right side of the first base, wherein a lifting assembly is fixed at the upper end of the second base; a table plate is fixed at the top end of the lifting assembly; a first supporting rod is arranged on the left side of the first base; a first circular truncated cone is connected with the bottom of the first supporting rod; both the upper part and the lower part of the first supporting rod are of a threaded structure; a first recess is formed in the upper surface of the first circular truncated cone; the inner wall of the first recess is of a threaded structure; the bottom of the first supporting rod is rotationally connected to the first recess; a jacking part is rotationally arranged at the top of the first supporting rod and takes the shape of a sphere; a threaded through hole is formed in the jacking part; the top of the jacking part is in contact with the lower surface of the table plate; an injection molded part fixing assembly is placed on the upper surface of the first base; a horizontal moving assembly is fixed on the lower surface of the table plate; and a nicking assembly is connected with the lower end of the horizontal moving assembly.

The invention discloses a high-speed cap separating mechanism, which comprises a cap bin, transmission components and cap separating components, wherein the cap bin is placed vertically; at least 2 cap separating components are arranged at the bottom of the cap bin; each cap separating component consists of double layers of shifting wheels and is formed by connecting an upper wheel (13) and a lower wheel (15) through a central shaft sleeve (16), the projection of the lower wheel (15) is in a shape of sector of which central angle is less than 180 degrees, the upper surface of the lower wheel (15) is a plane, the projection of the upper wheel (13) is in a shape of sector of which central angle is 180+ / -10 degrees, the lower surface of the upper wheel (13) is a plane, the edge of the upper surface of the upper wheel (13) is provided with a spiral face (14), the directions of the symmetric lines of the sectors of the upper wheel (13) and the lower wheel (15) are opposite, and the distance between the lower surface of the upper wheel (13) and the upper surface of the lower wheel (15) is the thickness of a tank cap; and the central shaft sleeve (16) of each cap separating component is in transmission connection with the transmission component. The high-speed cap separating mechanism enables the easily nested tank cap to be automatically separated at a high speed, and has high cap separating efficiency.

The invention relates to the technical field of computer equipment, and particularly discloses an automatic calculation method based on a scoring standard objective score, which comprises the following steps of: importing a bid evaluation data packet which comprises a scoring standard, bidder information and a bidding file; performing data preprocessing on the bid inviting file; obtaining a keyword, calculating a bid inviting file score of the bidder information according to a scoring standard, and updating the score to an index of a corresponding bid inviting system; standardizing the bid inviting file and the score, and performing weighted calculation to obtain a retrieval relevancy score of the bidder information; and performing weighted calculation on the bidder information retrieval relevancy score and the bidder information bidding document score to obtain an objective score. According to the invention, intelligent identification is achieved, each type is automatically distinguished, manual screening is not needed, accurate calculation is also achieved, the scoring time of bidding files is shortened, and the scoring efficiency is improved.

The invention discloses a target practice scoring method based on machine vision. The method comprises the following steps of S1, acquiring a target paper image before shooting, and acquiring a radius value of each target ring line on target paper; S2, acquiring a target paper image after shooting, and determining a radius interval where the center of a circle of a shooting hole is located; and S3, counting the total score of the target practice on the basis of the score value defined by each radius interval. The recognition precision of the target ring where the shooting hole is located is improved, meanwhile, automatic scoring of target practice is achieved, and the scoring efficiency of target practice is improved.