350results about How to "Improve quality inspection efficiency" patented technology

The invention discloses a call speech quality inspection method and device, computer equipment and a storage medium, and is applied to the field of artificial intelligence. The method comprises the following steps: acquiring the call recording data in the quality inspection cycle, wherein the call recording data carries the seat person identifier; using the target speech static decoding network toperform text translation of the call recording data so as to obtain the call text data; performing sensitive word verification on the call text data, extracting the target sensitive words and obtaining the first quality inspection score value based on the target sensitive words; using a multi-dimensional quality inspection scoring model corresponding to the quality inspection scoring table to perform quality inspection scoring on the call recording data and the call text data so as to obtain the second quality inspection score value; and obtaining the comprehensive quality inspection result corresponding to the seat person identifier according to the first quality inspection score value and the second quality inspection score value. The method has low cost and high efficiency in call speech quality inspection and has more objective quality inspection result.

The invention discloses an automatic voice quality inspection method, a system thereof, a device and a storage medium. The method includes the following steps: obtaining a voice file to be inspected;processing the voice file to be inspected, and converting the voice file to be inspected into a structured text file; scoring the voice file to be inspected and the structured text file according to apreset quality inspection scoring dimension and a preset score rule, and obtaining the score corresponding to each quality inspection scoring dimension; wherein, the quality inspection scoring dimension includes speech rate and silent analysis scoring, emotional analysis scoring, keyword and sensitive word detection scoring, and quality inspection rule matching scoring; and obtaining the final score of the voice file to be inspected according to the score corresponding to each quality inspection scoring dimension. The method can realize automatic voice quality inspection, and improves qualityinspection efficiency and accuracy.

The invention discloses a recheck platform which is used for rechecking defects in quality inspection of prints and comprises a rack, a working table, an unwinding wheel, a winding wheel, a position detection device, a power device and a microcontroller, wherein, the unwinding wheel and the winding wheel are arranged on the rack; the unwinding wheel transmits the prints to the winding wheel to rewind the prints; the winding wheel is connected with a power device; the position detection device detects the position to which the prints are transmitted and is connected with the microcontroller; the microcontroller stores the position information of defects of the prints and compares with the information of the position when the prints are transmitted to control the power device. The recheck platform can lighten the burden of visual sense detection device, thus the visual sense detection device is only responsible for detection, reconstructs the detection process, separates the process links such as time consuming stopping rejection and label supplementing and the like from the detection process, lowers cost and improves the efficiency of quality detection. The invention also relates to a system adopting the platform to detect the quality of prints.

The invention belongs to the technical field of code automation test, and discloses a continuous integration automated test method.The method includes dividing the project tasks into subtasks, and associating the code under test with a specific task number; The hook script is configured on the SVN service to call the Jenkins service to build automated test, and the continuous integration tool Jenkins is triggered by the SVN hook script every time the code associated with the task number is submitted to schedule the code detection tool to execute the test, and the test is completed automatically from the integration to the test key. Importing preset quality rules and quality thresholds to improve the effectiveness of code quality detection; And it can track and monitor the progress of the task with the help of the project management platform, including the whole process from claim, development, testing to completion, which can not only effectively improve the efficiency of code qualitydetection, but also accurately locate the code problems, making the responsibility of code repair clearer and more specific; Feedback information is sent to the responsible person in the form of e-mail and QQ instant message, so as to effectively guide the improvement of the project.

The invention discloses a device and a method for automatically detecting lens defects through modulation by an optical grating. The device comprises an isolation detecting system, a motion control system and a light source system, wherein the isolation detecting system is arranged in a camera bellows (13); the motion control system is arranged at the bottom of the camera bellows (13) and arranged on one side of the camera bellows (13); the device is characterized in that the optical grating (6) is fixed on a linear lead screw guide rail (5), a planar backlight (10) is fixed below a to-be-detected lens (4) in parallel and connected with a light source controller (11), and a main controller (12) controls the motion control system through a motion control card (9). According to the method, lens images are sampled twice through movement of the optical grating, the lens defects are classified, positioned and measured through analysis of gray values and morphological characteristics of bright and dark field images, and lens detection accuracy and efficiency are greatly improved.

The invention discloses an equipment abnormality detecting method. The equipment abnormality detecting method comprises the steps that first audio information corresponding to current running of to-be-detected equipment is obtained; the first audio information is compared with pre-stored second audio information, and the second audio information is corresponding audio information of the equipmentin the normal running state; and if the first audio information is not matched with the second audio information, equipment abnormality is judged. The invention further discloses an equipment abnormality detecting device and system, an air conditioner and a computer readable storage medium. By means of the equipment abnormality detecting method, device and system, the air conditioner and the computer readable storage medium, the equipment quality checking efficiency is improved.

Embodiments of the invention provide a text data quality check method, apparatus and device, and a computer readable storage medium. The method comprises the steps of obtaining message-level dialoguetext data and conversation-level conversation text data, and performing preprocessing; according to preset quality check points and rules corresponding to the quality check points, marking out the quality check points in the preprocessed dialogue text data and conversation text data; according to the preset rules, integrating quality check point results marked out by a full text search engine andquality check point results marked out by a preset neural network model to serve as a final quality check point result. The quality check results obtained by matching of the full text search engine and the quality check results classified by the preset neural network model can be combined according to the preset rules, so that the text data quality check efficiency and accuracy are improved.

The invention discloses a voice-based user classification method and device, computer equipment and a storage medium. The method comprises the following steps: recognize speech to be recognized through an N-gram model to acquire a recognition result; extracting keywords from the recognition result to obtain a keyword set corresponding to the recognition result; obtaining a semantic vector of the keyword set, and taking the semantic vector as input of a text emotion classifier to obtain a text emotion recognition result; and converting the keywords of the name part-of-speech into correspondingtags according to a preset tag conversion strategy corresponding to a tag library so as to obtain a user portrait corresponding to the identification result. Speech recognition, emotion recognition and user portrait technologies are adopted. Text emotion recognition and user portrait drawing are carried out after voice recognition is carried out according to the to-be-recognized voice of communication between the seat and the user, various types of customers are effectively classified, spot check of quality inspection posts is facilitated, and the quality inspection efficiency is improved.

The invention relates to a voice quality inspection method and a system and a storage medium. The voice quality inspection method comprises the following steps: acquiring a sound recording file; performing voice recognition conversion on the recording file to obtain a call text; performing multi-dimensional detection on the call text and/or the sound recording file according to a preset voice quality inspection strategy to obtain a detection result, and performing quality inspection scoring on the detection result to obtain a quality inspection scoring result. By performing multi-dimensional detection on the sound recording file and scoring the quality inspection result, the accuracy of the detection result of quality inspection is improved, and the error rate caused by subjective factors is reduced.

The invention provides a method and device for randomly detecting and evaluating navigation electronic map quality, which belong to the technical field of navigation. The method comprises the steps of randomly selecting navigation electronic map information of an area to be detected from a navigation electronic map; obtaining field data of the area to be detected; comparing the selected navigation electronic map information of the area to be detected with the obtained filed data of the area to be detected so as to obtain comparing results; counting the comparing results and calculating an average correct rate of the comparing results according to the count comparing results; and obtaining an integral quality distribution level of the navigation electronic map product through calculating a detecting and evaluating result of a sample area. Therefore, quality detecting efficiency of the navigation electronic map product is effectively increased and the timeliness of the detecting result is assured.

The invention relates to the technical field of display screens, in particular to a large-size display screen defect detection and positioning method. The method comprises the following steps of displaying a screen calibration picture on a reference display screen, and acquiring a screen calibration picture image; acquiring off-line calibration parameters for identifying the reference position information from the screen calibration picture image; sequentially displaying detection pictures on a to-be-detected display screen, and carrying out on-line compensation on the position of the to-be-detected display screen by utilizing the off-line calibration parameters in order to obtain position parameters of the to-be-detected display screen; analyzing the collected detection pictures to obtainimage coordinates of a defect; and converting the image coordinates of the defect into screen coordinates according to the position parameters of the to-be-detected display screen. The display of thescreen calibration picture and the extraction of sub-frame angle point information are not needed, and the first detection picture is compensated through the off-line calibration parameters, so thata to-be-detected area of the screen of a panel in the accurate positioning image can be determined, the method is simple and convenient, and the detection time of an AOI workstation can be effectivelyshortened.

The invention discloses a calligraphy quality detection method and device based on artificial intelligence, and electronic equipment. The method comprises the following steps that: obtaining a writtencharacter to be detected, identifying the written character, searching a copybook database to obtain a copybook character corresponding to the written character; according to a preset quality detection dimension, independently extracting the first character characteristic of the written character and the second character characteristic of the copybook character; comparing the first character characteristic with the second character characteristic to obtain a characteristic diffidence, according to the characteristic different, inquiring preset evaluation information, and obtaining the score result of each quality detection dimension; and according to preset weight corresponding to each quality detection dimension and the score result of each quality detection dimension, generating a quality detection result of the written character. Therefore, the calligraphy quality detection method based on the artificial intelligence is provided so as to conveniently carry out objective evaluationon calligraphy quality, and calligraphy quality detection efficiency is improved.

The invention provides a solar cell defect detection method integrating short-time and long-time depth characteristics. The method comprises the following steps: preprocessing; performing short-time depth feature extraction, including blocking and vectorizing the preprocessed images and then sending the images into a stacked noise reduction automatic encoder to be trained; obtaining a two-dimensional adaptive depth feature matrix learned by all image blocks, and converting the two-dimensional adaptive depth feature matrix into a three-dimensional matrix to obtain a short-time depth feature composed of current image observation information; extracting long-time depth features; integrating and converting the short-time depth feature and the long-time depth feature; and performing low-rank matrix decomposition and post-processing to obtain a final detection result. According to the method, the defect of the solar cell is characterized by using the depth characteristics fusing the currentimage observation information and the priori knowledge, so that the universality and accuracy of the defect detection of the solar cell can be remarkably improved, the calculation amount is small, thedetection efficiency is high, and the positioning precision is relatively high.

The invention discloses a dual-recorded video quality inspection method and device, equipment and a readable storage medium, and relates to the field of machine learning. The method comprises the following steps: splitting a dual-recorded multimedia file; carrying out keyword monitoring on an audio file to obtain an occurrence moment of a keyword in the audio file; segmenting a video file at the occurrence moment to obtain a key video clip corresponding to the keyword; and performing quality inspection on the image frames in the key video clip in a video quality inspection mode corresponding to the keyword to obtain a quality inspection result of the dual-recorded video. Keyword monitoring is carried out on the audio file in the dual-recorded video, the key video clip is extracted from thevideo file according to the monitored keyword, so that different key video clips are subjected to different quality inspection processing in the quality inspection mode corresponding to the keywords,the quality inspection result is obtained, the quality inspection efficiency is improved, the quality inspection calculation of the dual-recorded video is completed by the server, and the parallel computing capability of the quality inspection calculation is improved.

The invention provides a data achievement information quality intelligent detection method and system based on a task model. According to the method, a plurality of pieces of detection task information corresponding to data achievement multi-dimensional quality detection factors are subjected to detection task computational modelling based on a quality testing algorithm, so as to build a task model; to-be-detected data achievement is recollected and a required detection task is selected to form a task group; the task group is input to a task model; all the detection tasks in the task group areexecuted through a task model so as to obtain a detection task computational result; then, the detection task computational result is subjected to data analytic processing and a data achievement information quality detection report is output to achieve intelligent detection. The method can process mass data; the selected detection task is directly input to the task model for automatic detection,thereby saving time cost and labor cost, and improving the efficiency, accuracy and comprehensiveness of data achievement information detection overall.

The invention discloses a voice quality inspection method and a device, computer equipment and a storage medium. The method comprises the following steps: acquiring service information and voice data;performing text conversion on the voice data to obtain text content; extracting service attribute content from the text content, and verifying whether the service information and the service attribute content are consistent or not to obtain a verification result; matching the text content with the business attribute content removed with preset violation content to obtain a matching result; extracting voice features from the voice data, and performing emotion recognition on the voice features to obtain an emotion recognition result; and if the verification result shows that the verification issuccessful, the matching result shows that the matching fails, and the emotion recognition result belongs to a preset emotion label, determining passing of the quality inspection. According to the voice quality inspection method, comprehensive and objective quality inspection results are obtained through comprehensive analysis in the three aspects of service information verification, violation content matching and emotion recognition, the quality inspection efficiency is improved, and the labor cost is reduced.

The invention discloses a code quality monitoring method, a device, a computer device and a storage medium. The method comprises the following steps: obtaining a code submission log corresponding to the code submission request based on the code submission request; obtaining a code submission log corresponding to the code submission request based on the code submission request; obtaining a code submission log corresponding to the code submission request. The code submission log is monitored by SVN monitoring task process, and the code submission log is arranged according to the sequence of thesubmission time, and the code submission log queue is obtained. Code specification detection tool is used to detect the source code corresponding to the code submission log queue. When the non-standard code is detected by the source code corresponding to the code submission log, the modification prompt information is generated based on the non-standard code, and the modification prompt informationis sent to the SVN client corresponding to the author ID, so that the SVN client displays the modification prompt information. The method improves the efficiency of normative detection of the sourcecode, and realizes the function of quality monitoring for each developer's source code.

The invention provides a voice quality inspection scoring method and device, a terminal and a storage medium, and the method comprises the steps: obtaining recording audio data; converting the acquired recording audio data into data in a text format, the data in the text format comprising seat text data corresponding to the audio data of the seat personnel; and performing matching scoring on the seat text data and a preset scoring index through a cosine similarity algorithm and/or a Hamming distance algorithm to obtain a service quality score of the recording audio data. According to the method, the recorded audio data are automatically identified and scored, excessive manual participation is not needed, intelligent quality inspection is achieved, full coverage quality inspection can be conducted, the quality inspection efficiency is high, the workload of quality inspection workers is reduced, and the quality inspection quality is improved.

The invention discloses a method for filling an aerosol generating product. The method comprises the following steps of (1) preparing a tube body (1) of the aerosol generating product, (2) filling a filtering part (2) in the tube body (1), wherein the filtering part (2) is close to the near lip end of the tube body (1), (3) installing the blocking flow guide part (3) from the far lip end of the tube body (1), (4) installing a fuming unit (4) from the far lip end of the tube body (1), wherein the smoke generating unit (4) is positioned at the far lip end of the tube body (1), and (5) sealing the far lip end of the tube body (1), and forming a sealing piece (5) on the end surface of the far lip end of the tube body (1). Each part is sequentially filled from the near lip end to the far lip end of the aerosol generating product for the first time, so that the pollution to the tube body (1) caused by the fuming unit (4) when the fuming unit (4) is filled is effectively avoided, the appearance qualification rate of the product can reach 100%, the manual quality inspection strength is reduced, the efficiency is improved, the loss is reduced, and the profit margin is increased for enterprises.