34results about How to "Automate assessment" patented technology

The invention discloses a safety evaluation system and method of live-line work equipotential entry paths. According to the system and method, the whole process of equipotential entry is displayed in a three-dimensional scenario; safety distance between a body of an operator and a live part, smallest distance between the equipotential work operator and adjacent-phase wires and a combined interval of the equipotential work operator entering and leaving an electric field are dynamically calculated; safety evaluation on equipotential entry paths is achieved. The safety evaluation system and method of live-line work equipotential entry paths has the advantages that entering equipotential paths in live-line work can be visually and automatically evaluated, work of hand computation is reduced, efficiency is improved, and better visual is achieved.

The embodiment of the invention provides a human body motion posture evaluation method and system. The method is based on the system and includes the steps that pressure induction values induced by a pressure sensor, displacement values induced by a displacement sensor and measurement values induced by an attitude measurement sensor are obtained; when the gravity center of the human body is adjusted horizontally in situ, the gravity center supporting foot of the human body is determined according to one pressure induction value; the corresponding measurement value and the corresponding displacement value are determined; the inclining condition of the upper half trunk of the human body and the displacement direction of the crotch are determined; if the inclining condition includes that the upper half trunk of the human body inclines, and / or the displacement direction of the crotch is inconsistent with the direction where the gravity center supporting foot is located, it is determined that the movement mode of the gravity center is abnormal; if the inclining condition includes that upper half trunk of the human body does not incline, and the displacement direction of the crotch is consistent with the direction where the gravity center supporting foot is located, it is determined that the movement mode of the gravity center is normal. Evaluation results are more objective and accurate, and automatic evaluation is achieved.

The invention provides a Java unit test teaching feedback method based on program static analysis, comprising the following steps: 1) source program code static structure analysis; 2) source program test requirement generation; 3) Java unit test case writing; 4) Test case coverage data collection; 5) Summary statistics of test cases and coverage data; 6) Visual display of source program static structure and coverage data; 7) Execution process display of a single test case on source program static structure. The present invention solves the problem that the Java unit test teaching task is difficult to practice and evaluate in the current software test course, provides a platform for programming practice and automatic evaluation and visual display of the Java unit test, and greatly improves the practice and evaluation efficiency of the teaching task. It helps teachers improve teaching content based on practice feedback, and helps students continuously improve their ability to write test cases based on practice feedback.

The invention discloses a bone age evaluation method based on a convolutional neural network and a multiple attention mechanism. The method comprises the following steps: in a training stage, taking ametacarpal bone image as the input of a backbone network, obtaining a feature map F through a feature extractor, and obtaining a bone age regression value; taking the input of a multi-attention module as a feature map F, obtaining M sub-attention maps through compression operation and attention map splitting operation, conducting point multiplication of each sub-attention map with the feature mapF, and then obtaining a corresponding bone age regression value; combining a backbone network with the bone age regression value obtained by the multiple attention module, and training a neural network by adopting a multi-task learning strategy; and in a test stage: inputting a to-be-tested metacarpal bone image into the trained neural network, and obtaining a bone age evaluation value through the backbone network. The model can be trained end to end; meanwhile, an attention distribution diagram can be automatically generated, and better generalization is achieved; and in addition, based on the 2D convolutional neural network, the speed is high, the precision is high, and an average evaluation error is within 4.1 months.

The invention belongs to the technical field of network security application, in particular to a web landmark reliability evaluation method and device based on multi-level decision. The method includes: parsing an IP address in a candidate landmark; for the parsed candidate landmarks, the filter is used to filter the candidate landmarks and delete the invalid data. The filtered candidate landmarksare evaluated to obtain their credibility values. On the premise of not relying on path detection, Making full use of Internet public service, classifying and filtering invalid Web landmarks with different characteristics, quantitatively evaluating the credibility of landmarks, realizing automatic evaluation of large-scale Web landmarks, and solving the problems of low accuracy, low efficiency and automatic quantitative operation of large-scale Web landmarks. Realizing invalid landmark filtering and effective landmark credibility quantitative evaluation, and effectively improving the accuracyof landmark acquisition and positioning results, has important guiding significance for the accurate acquisition technology of Web server-like entity landmarks.

The invention provides a construction quality evaluation cloud platform which includes a platform docking module, a front end collection module, a data receiving and saving module, a cloud computing service module and a big data visual display module, wherein the cloud computing service module is connected with the big data visual display module; the front end collection module collects index information data of all the flows of the constructional engineering and sends the index information data to the data receiving and saving module; the data receiving and saving module receives the index information data and sends the data to the cloud computing service module; the cloud computing service module compares the index information data with data in the interior technical index standard library to obtain the deviation value of each piece of index information; the big data visual display module is used for displaying the index information data and deviation values. The construction quality evaluation cloud platform provided by the invention realizes the automatic evaluation on construction quality as well as informatization and automation of evaluation on construction quality, and reduces workload and error in manual evaluation.

The invention relates to the technical field of software testing, in particular to a workload evaluation method and device, electronic equipment and a readable storage medium. The method comprises thesteps of obtaining a target test log in a target workday; obtaining test service data of a determined dimension of the target user from the target test log, wherein the target user is a target tester, and the determined dimensions include but are not limited to the number of test associated systems, the number of test schedules, the number of test interfaces and the number of test scenes; and inputting the test service data into a pre-constructed workload evaluation model to calculate the target daily test workload of the target user. According to the scheme disclosed by the invention, the software test workload evaluation efficiency and accuracy are improved.

The embodiment of the invention discloses an audio call assessment method, assessment equipment and a computer storage medium. The audio call assessment method is applied to the assessment equipment,and comprises the following steps: a recognition text of received audio is obtained, wherein the recognition text is a recognition result of the received audio after transmission of reference audio attransmit-receive dual ends; and by combining the recognition text and a reference text corresponding to the reference audio, an effect assessment value of the audio call is obtained.

The invention discloses a distribution transformer risk assessment model construction method and risk assessment method and system. The method comprises steps of constructing a service time dimensionmodel according to the service time dimension characteristic quantity, constructing an environment climate dimension model according to the environment climate dimension characteristic quantity, and constructing a monitoring data dimension model according to the monitoring data dimension characteristic quantity; finally, according to the service time dimension model, the environmental climate dimension model and the monitoring data dimension model, a transformer risk assessment model based on multi-dimensional feature fusion is constructed, and compared with a traditional risk assessment method which only considers a single-dimensional model and manual intervention, the model comprehensively considers multi-dimensional risk influence factors, and the risk assessment accuracy is improved. According to the risk assessment method and system, automatic risk assessment and active risk prevention and control are achieved, and the risk assessment method and system have important significancein prolonging the service life of the distribution transformer, reducing the potential risk of operation of a power distribution network and guaranteeing safe and reliable operation of a power distribution system.

The invention discloses an application deployment method based on a multi-inference engine system. The method can automatically achieve the conversion from a source model to different inference engines for a given source model, carries out the inference evaluation of the model obtained through conversion, and finally selects an optimal inference engine for subsequent application deployment according to the inference evaluation result . According to the invention, automatic evaluation of each inference engine in the system is achieved, the professional threshold and workload of the inference engine selection process are reduced, the situation that developers spend a large amount of time and energy to select the inference engines due to the fact that the developers are not familiar with the inference engines is avoided, and application deployment efficiency can be improved. In addition, the invention further provides an application deployment device based on the multi-inference engine system, equipment and a readable storage medium, and the technical effects correspond to the technical effects of the method.

Embodiments of the invention disclose a design drawing assessment method and apparatus, and a computer readable storage medium. The method comprises the steps of obtaining a plurality of to-be-assessed design drawings; According to a preset assembly type splitting scheme, splitting each to-be-evaluated design drawing into a plurality of components; Matching each component in each to-be-evaluated design drawing with each standard component in a pre-established standard drawing library, and calculating a component reuse rate and a component coincidence rate of each to-be-evaluated design drawing; The component reuse rate and the component coincidence rate reflect the project cost, and the higher the component reuse rate of the to-be-evaluated design drawing is, the higher the component coincidence rate is, the lower the project cost generated when construction is carried out according to the to-be-evaluated design drawing is. Therefore, the to-be-evaluated design drawings can be sorted according to the component reuse rate and the component coincidence rate of the to-be-evaluated design drawings. According to the technical scheme, automatic assessment of the design drawing is achieved, and due to the fact that assessment standards are consistent, objectivity and reliability of assessment of the design drawing are improved.

The invention discloses a distribution line risk assessment model construction method and a risk assessment method and system, and the method comprises the steps: constructing a service time dimensionmodel according to the service time dimension characteristic quantity, constructing an environment climate dimension model according to the environment climate dimension characteristic quantity, constructing a monitoring data dimension model according to the monitoring data dimension characteristic quantity, and finally, according to the service time dimension model, the environmental climate dimension model and the monitoring data dimension model, constructing a distribution line risk assessment model based on multi-dimensional feature fusion. Compared with an existing single-dimensional model, the model comprehensively considers multi-dimensional factors having important influence on the risk state of the distribution line, and the risk state of the distribution line can be reflected more scientifically and accurately; according to the risk assessment method and system, automatic assessment of the distribution line risk and active prevention and control of the risk are achieved, andthe risk assessment method and system have important significance for prolonging the service life of the distribution line, reducing the potential risk of power distribution network operation and guaranteeing the safety and stability of the distribution system.

A device of and a method for obtaining thermal images of a living mammal body section. The device comprises a thermal energy storage surface structure for contacting the body section. In a calibration mode of operation, the thermal energy storage surface structure is brought at a reference temperature by transferring thermal energy to the thermal energy storage surface structure from a thermal energy transfer module that is controlled by a control circuit for restraining thermal energy transfer by the thermal energy transfer module in the presence of the body section at the thermal energy storage surface structure. In a registration mode of operation, by a thermal sensor, thermal images reflecting thermal energy storage over at least a portion of the thermal energy storage surface structure are obtained, with the body section contacting the thermal energy storage surface structure. From a series of time consecutive thermal images obtained, a region of interest is determined, based on storage of thermal energy by the thermal energy storage surface structure.

The invention discloses a carbon emission reduction methodology inquiry system, which comprises a keyword storage module used for storing a keyword set for carbon emission reduction items to be inquired, wherein the keyword set comprises a plurality of keywords; a keyword input module is used for inputting the keyword set to the keyword storage module; a keyword dictionary module used for establishing the association between each standard keyword and the corresponding carbon emission reduction methodology; a methodology query module configured to query all carbon emission reduction methodologies associated with the keyword set in the keyword dictionary through matching between any one keyword in the keyword set and a standard keyword in the keyword dictionary module; a methodology screening module used for screening out the target carbon emission reduction methodology of the carbon emission reduction project to be queried among all carbon emission reduction methodologies associated with the keyword set. Correspondingly, the invention also discloses a carbon emission reduction methodology inquiry method.

The embodiment of this specification provides a method and device for evaluating the rationality of buried points. The method includes: obtaining the index data corresponding to multiple evaluation indexes of buried points to be evaluated within the evaluation period, and obtaining each of the above evaluation indexes Then, according to the index data corresponding to each evaluation index and the weight value of each evaluation index, the rationality of the above-mentioned buried points to be evaluated is evaluated; wherein, the above-mentioned evaluation indexes are based on the same buried point The buried point data is set; the weights of the above evaluation indicators are obtained by using multiple sample buried point data to train the buried point rationality evaluation model.

The invention discloses an emergency plan evaluation method and device. The method comprises the steps that preset values of evaluation indexes of an emergency plan are set; an emergency plan maneuveris executed, system operating state data is collected, and actual values of all the evaluation indexes are calculated according to the system operating state data; and whether all the evaluation indexes reach standards is judged according to the preset values and the actual values of the evaluation indexes of the emergency plan, and an evaluation report is obtained according to the judgment result. Through the emergency plan evaluation method, automatic evaluation of the emergency plan can be realized, evaluation cost of the emergency plan is lowered, and evaluation efficiency is improved by90%.

The invention discloses a bone age assessment method based on a convolutional neural network and a multiple attention mechanism, including: in the training stage, the backbone network input is a metacarpal bone image, a feature map F is obtained through a feature extractor, and then a bone age regression value is obtained; multiple The input of the attention module is the feature map F, and M sub-attention maps are obtained through the compression operation and the attention map splitting operation, and each sub-attention map is multiplied by the feature map F to obtain the corresponding bone age regression value; combined with the backbone network and multiple The bone age regression value obtained by the attention module is used to train the neural network with a multi-task learning strategy; in the test phase, the metacarpal image to be tested is input into the trained neural network, and the bone age evaluation value is obtained through the backbone network. The above model can be trained end-to-end; at the same time, it can automatically generate an attention distribution map, which has better generalization; in addition, based on a 2D convolutional neural network, it is fast and accurate, and the average evaluation error is within 4.1 months.

The present disclosure relates to a data analysis method, an apparatus, a storage medium, and an electronic device capable of automatically evaluating a state of a device based on an analysis of historical operational data. The method comprises the following steps: inputting the historical operation data of the target equipment and the data categories to which each historical operation data belongs into a dictionary learning model for training to obtain a dictionary and a classifier; collecting operation data of the target device; calculating a sparse representation of the operation data according to the operation data and the dictionary; based on the sparse representation and the classifier, determining a data class of the operation data to evaluate an operation state of the target device.

The embodiment of the invention provides a human body motion posture evaluation method and system. The method is based on the system and includes the steps that pressure induction values induced by a pressure sensor, displacement values induced by a displacement sensor and measurement values induced by an attitude measurement sensor are obtained; when the gravity center of the human body is adjusted horizontally in situ, the gravity center supporting foot of the human body is determined according to one pressure induction value; the corresponding measurement value and the corresponding displacement value are determined; the inclining condition of the upper half trunk of the human body and the displacement direction of the crotch are determined; if the inclining condition includes that the upper half trunk of the human body inclines, and / or the displacement direction of the crotch is inconsistent with the direction where the gravity center supporting foot is located, it is determined that the movement mode of the gravity center is abnormal; if the inclining condition includes that upper half trunk of the human body does not incline, and the displacement direction of the crotch is consistent with the direction where the gravity center supporting foot is located, it is determined that the movement mode of the gravity center is normal. Evaluation results are more objective and accurate, and automatic evaluation is achieved.

The invention discloses an emergency plan evaluation method and device. The method comprises the steps that for different emergency plans, the following content is performed for at least once. The content comprises the steps of performing emergency plan exercises, and acquiring and recording practical values of evaluation indexes in each exercise, wherein the evaluation indexes comprise timelinessevaluation indexes, monitoring items, fault notification personnel and emergency plan identities; calculating expected values of the timeliness evaluation indexes of the emergency plans, and evaluating the reasonability of the timeliness evaluation indexes according to the expected values and preset values of the evaluation indexes; for the monitoring items, the fault notification personnel and the emergency plan identities, judging the reasonability according to the practical values and the corresponding preset values; and forming an evaluation report based on the evaluation results. According to the method and the device, the evaluation cost of the emergency plans can be reduced, the manpower analysis cost is reduced, the efficiency is improved, and the reliability and continuous optimization capability of the emergency plans are improved.

The invention discloses an important economic target protection construction capability evaluation method. The method comprises the following steps: constructing an index system capable of quantifyingimportant economic target protection construction capability evaluation to represent important economic target protection construction capability; extracting corresponding data from the important economic target protection construction database to calculate values of different evaluation indexes; and calculating to obtain an important economic target protection construction capability value according to the index system and the weights of different evaluation indexes. According to the method, the important economic target protection capability can be quantified and evaluated, and a scientificand visual important economic target protection construction effect is provided for civil defense departments.

The invention discloses a building heritage protection evaluation system constructed based on an intelligent network, and the system comprises a camera whose camera shooting port faces a marker disposed on a building; The humidity sensor is used for detecting the environment humidity of the building; The visible light image detector is used for filtering and imaging the visible light wave band ofthe to-be-detected building exterior wall on the target surface of the visible light image detector through the filtering and imaging effect of the visible light lens to obtain the visible light imageof the to-be-detected building exterior wall and converting the visible light image into image data; And the infrared image detector is used for filtering and imaging the infrared band of the outer wall of the building to be detected on the target surface of the infrared image detector through the filtering and imaging effect of the infrared lens to obtain an infrared image of the outer wall of the building and converting the infrared image into image data. In order to overcome the defects in the prior art, the invention provides the building heritage protection and evaluation system constructed based on the intelligent network, the building quality can be comprehensively detected, and information automatic processing is carried out.

The embodiment of the invention discloses a privacy security assessment method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring assessment interview data for a to-be-assessed object; performing privacy security detection on the to-be-evaluated object to obtain a privacy information set acquired by the to-be-evaluated object; performing data security detection on the to-be-evaluated object to obtain a security detection result of the to-be-evaluated object; and comparing the privacy information set and the security detection result with evaluation interview data to obtain a personal privacy influence evaluation result of the to-be-evaluated object. According to the scheme, the privacy security detection and the data security detection are performed on the to-be-evaluated object, and the detection result is compared with the evaluation interview data, so that the personal privacy influence evaluation result of the to-be-evaluated object is determined, the privacy security of the to-be-evaluated object can be automatically evaluated, and the evaluation efficiency of the privacy security of the to-be-evaluated object is improved. And the accuracy of privacy security evaluation is improved.

The invention discloses an ontology-based highway bridge technical condition inspection and evaluation method, which comprises the following steps of: constructing an ontology knowledge base by introducing bridge engineering basic knowledge, bridge engineering specifications and highway bridge engineering regular inspection data, and achieving knowledge reasoning by combining a semantic network rule and a semantic query rule; and automatically processing bridge disease information to obtain a bridge technical condition grade score.Therefore, automatic evaluation of the technical condition of the highway bridge is achieved, and the efficiency and the intelligent level of highway bridge data processing are greatly improved.