Multi-element evaluation method, system and device based on multi-scene education information analysis

Abstract

The invention discloses a multivariate evaluation method, system and device based on multi-scene education information analysis. The method comprises the following steps: acquiring classroom interaction audio data, after-class voice comment data, roll book image data, non-teaching scene voice data and third-party operation data; through voice preprocessing and image preprocessing, classroom analysis data, after-class analysis data, subject information analysis data and non-teaching scene analysis data are obtained; combining the after-class analysis data and the subject information analysis data to obtain stage feedback data; performing matching analysis on the classroom interaction audio data, the after-class voice comment data and the non-teaching scene voice data, and obtaining behavior analysis data through evaluation analysis; and performing optimization and correction by combining with the third-party operation behavior data, and further obtaining student multivariate evaluation data through multivariate analysis. According to the method, the problem that the evaluation method has defects in comprehensiveness and accuracy is solved, and meanwhile, the manual workload is reduced through automatic evaluation.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a multi-evaluation method, system and device based on multi-scenario educational information analysis. Background Art

[0002] In the current school education scenario, students need to be systematically and comprehensively evaluated at important time points in each semester, such as midterm or final exams.

[0003] At present, teachers can only evaluate students by referring to limited and scattered test scores and homework correction records, combined with their memory of daily classroom impressions of students. Since this evaluation method is a manual evaluation method, it is mainly based on students' usual subjective performance and teachers' subjective views. It is highly subjective and random. There are great limitations in the evaluation content and planning for students, and it is impossible to provide good suggestions for students' all-round development. So far, it is not possible to combine students' daily homework, exams, classroom performance, extracurricular activities, non-classroom performance and related evaluation information in a diversified way to conduct a comprehensive and accurate evaluation of students. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a multi-evaluation method, system and device based on multi-scenario educational information analysis.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions: A multi-evaluation method based on multi-scenario educational information analysis includes the following steps: Obtain classroom interaction audio data, after-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; Perform voice preprocessing on classroom interactive audio data, after-class voice comment data, and non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; Establish an initial behavior event library, combine classroom analysis data, after-class analysis data and non-teaching scenario analysis data, match the initial behavior event library through sentence matching, obtain specific behavior events, and conduct evaluation and analysis based on specific behavior events in different scenarios to obtain behavior analysis data; Perform image preprocessing on the roll call image data to obtain subject information analysis data, and combine the after-class analysis data and subject information analysis data to obtain stage feedback data; Analyze and process the third-party operation behavior data to obtain operation analysis data, and use the operation analysis data to correct and optimize the behavior analysis data and stage feedback data to obtain optimization analysis data; Multivariate analysis is performed on the optimized analysis data to obtain students' multivariate evaluation data.

[0006] As an implementable method, the speech preprocessing of the classroom interactive audio data to obtain classroom analysis data includes the following steps: Split and value analyze the classroom interactive audio data to obtain the classroom interactive audio data after value analysis; By using speech recognition technology, the classroom interaction audio data after value analysis is converted to obtain converted classroom interaction audio data; Conduct preliminary analysis and text extraction of the converted classroom interactive audio data to obtain key information data; Conduct deep semantic analysis on key information data to obtain semantic positive and negative expression data, behavior description data and corresponding relationship data, and then obtain classroom analysis data through behavior classification label matching.

[0007] As an implementable method, the voice preprocessing of the after-class voice comment data to obtain the after-class evaluation data includes the following steps: By using speech recognition technology, the after-class speech comment data is converted into text to obtain the after-class comment text data; The post-class review text data is subjected to deep semantic analysis to obtain positive and negative review data, review behavior data, and review correspondence data, and then the post-class evaluation data is obtained through behavioral classification label matching.

[0008] As an implementable method, the non-teaching scene voice data is subjected to voice preprocessing to obtain the non-teaching scene parsed data, including the following steps: Through data analysis and data matching, the non-teaching scene voice data is extracted to obtain non-teaching voice segment data; Deep semantic analysis is performed on non-teaching voice segment data to obtain non-teaching positive and negative data, non-teaching behavior data, and non-teaching corresponding relationship data, and then non-teaching scene analysis data is obtained through behavior classification label matching.

[0009] As an implementable method, obtaining a specific behavior event includes the following steps: Based on students' daily behavior events, daily behavior data is obtained, and a basic event library, namely, an initial behavior event library, is established through the daily behavior data; Through semantic understanding, classroom analysis data, after-class analysis data, and non-teaching scenario analysis data are matched with daily behavior data to obtain specific behavior events, specifically: Based on the classroom analysis data, after-class analysis data and non-teaching scenario analysis data to form a text library, the text library is corrected to obtain a text library after correction; Through text matching and name entity recognition, the behavior events and subject names existing in the corrected text library are identified to obtain the behavior events and name entities; Through the name entity of the behavior event, the behavior events in the initial behavior event library are extracted and identified, the matching behavior events are obtained and associated with the name entity, and the behavior events corresponding to the name entity are obtained.

[0010] As an implementable method, the image preprocessing of the roll call image data to obtain the subject information analysis data includes the following steps: Performing corner point detection on the point list image data to obtain corner point position information, correcting the point list image data using the corner point position information to obtain corrected image data, and obtaining identification code area data using the relative position of the corner point position information; Based on the roll call image data, the row and column information data is obtained, and the subject information position data is obtained by combining the corner point position information and the detection and positioning model; By combining the character recognition model and the subject information location data, the subject information recognition data is obtained, and then character correction and character proofreading are performed on the subject information recognition data. Combined with the identification code area data, the subject information analysis data is obtained.

[0011] As an implementable embodiment, the character recognition model is obtained by: Acquire an original data set and preprocess the original data set to obtain a training data set, wherein the training data set is a grayscale image, and the preprocessing includes at least data enhancement and data synthesis; Construct a character recognition pre-training model and train it through the training data set to obtain a character recognition model; Among them, the character recognition pre-training model is implemented through the Beam Search algorithm. During decoding, the first K characters with the highest probability of the current decoded character are screened and saved. Specifically, the first list is constructed to store the largest K results obtained each time, and the decoding length S is traversed; the first list is traversed to decode the candidate set for each of the largest K results so far; each decoded K result is stored in the second list; the first K are selected as the first list according to the confidence level; and the traversal is continued until the decoding length S is obtained.

[0012] As an implementable method, obtaining the stage feedback data includes the following steps: Based on the preset subject understanding threshold, the subject information analysis data is analyzed and processed to obtain understanding data; By analyzing and summarizing the after-class analysis data and subject information analysis data, the evaluation data is obtained; The evaluation data is adjusted and optimized to obtain stage feedback data.

[0013] As an implementable method, the multivariate analysis of the optimization analysis data includes the following steps: Slice the behavior analysis data in the optimization analysis data to obtain short word data, remove short words and matching hot words from the short word data, and generate a student hot word portrait; Summarize the behavior analysis data in the optimization analysis data, analyze the behavior characteristics and student types, and obtain behavior characteristic data and student type data; Analyze the behavioral analysis data in the optimization analysis data and combine it with expert advice to obtain targeted guidance and suggestions; The stage feedback data in the optimization analysis data are summarized, and the learning behavior characteristics are analyzed to obtain the learning behavior data.

[0014] As an implementable method, it also includes the following steps: displaying the students' multi-evaluation data through an interface display module, wherein the displayed content at least includes students' hot word portraits, behavioral characteristic data, student type data, targeted guidance suggestions and learning behavior data.

[0015] A multivariate evaluation system based on multi-scenario educational information analysis, including a data acquisition module, a voice preprocessing module, an event library establishment module, an image preprocessing module, a correction optimization module and a multivariate analysis module; The data acquisition module acquires classroom interactive audio data, post-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; The speech preprocessing module performs speech preprocessing on the classroom interactive audio data, the after-class speech commentary data, and the non-teaching scene speech data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; The event library establishment module establishes an initial behavior event library, combines classroom analysis data, after-class analysis data and non-teaching scenario analysis data, matches the initial behavior event library through sentence matching, obtains specific behavior events, and performs evaluation and analysis in different scenarios based on the specific behavior events to obtain behavior analysis data; The image preprocessing module performs image preprocessing on the roll call image data to obtain subject information analysis data, and combines the after-class analysis data and the subject information analysis data to obtain stage feedback data; The correction and optimization module analyzes and processes the third-party operation behavior data to obtain operation analysis data, and corrects and optimizes the behavior analysis data and stage feedback data through the operation analysis data to obtain optimization analysis data; The multivariate analysis module performs multivariate analysis on the optimized analysis data to obtain multivariate evaluation data of students.

[0016] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented: Obtain classroom interaction audio data, after-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; Perform voice preprocessing on classroom interactive audio data, after-class voice comment data, and non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; Establish an initial behavior event library, combine classroom analysis data, after-class analysis data and non-teaching scenario analysis data, match the initial behavior event library through sentence matching, obtain specific behavior events, and conduct evaluation and analysis based on specific behavior events in different scenarios to obtain behavior analysis data; Perform image preprocessing on the roll call image data to obtain subject information analysis data, and combine the after-class analysis data and subject information analysis data to obtain stage feedback data; Analyze and process the third-party operation behavior data to obtain operation analysis data, and use the operation analysis data to correct and optimize the behavior analysis data and stage feedback data to obtain optimization analysis data; Multivariate analysis is performed on the optimized analysis data to obtain students' multivariate evaluation data.

[0017] A multi-evaluation device based on multi-scenario educational information analysis includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the following method is implemented: Obtain classroom interaction audio data, after-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; Perform voice preprocessing on classroom interactive audio data, after-class voice comment data, and non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; Establish an initial behavior event library, combine classroom analysis data, after-class analysis data and non-teaching scenario analysis data, match the initial behavior event library through sentence matching, obtain specific behavior events, and conduct evaluation and analysis based on specific behavior events in different scenarios to obtain behavior analysis data; Perform image preprocessing on the roll call image data to obtain subject information analysis data, and combine the after-class analysis data and subject information analysis data to obtain stage feedback data; Analyze and process the third-party operation behavior data to obtain operation analysis data, and use the operation analysis data to correct and optimize the behavior analysis data and stage feedback data to obtain optimization analysis data; Multivariate analysis is performed on the optimized analysis data to obtain students' multivariate evaluation data.

[0018] The present invention has significant technical effects due to the adoption of the above technical solution: The method of the present invention realizes the collection of educational data in multiple scenarios, and by comprehensively recording and analyzing the performance of students inside and outside the classroom, and combining the operation analysis data obtained after analyzing the third-party operation behavior data, a secondary data analysis and correction is performed, so as to comprehensively and scientifically analyze the students' actual learning ability and personal characteristics. At the same time, combined with artificial intelligence algorithms, targeted suggestions are provided for the subsequent development direction and personal improvement of students, providing help and guidance for students' learning career. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a schematic flow diagram of the method of the present invention; Figure 2 It is an overall schematic diagram of the system of the present invention; Figure 3 It is a schematic diagram of the student portrait result data of the present invention. DETAILED DESCRIPTION

[0021] The present invention is further described in detail below in conjunction with embodiments. The following embodiments are for explanation of the present invention but the present invention is not limited to the following embodiments.

[0022] Embodiment 1: A multi-evaluation method based on multi-scenario educational information analysis, such as Figure 1 As shown, the following steps are included: S100, obtaining classroom interaction audio data, after-class voice comment data, roll call image data, non-teaching scene voice data and third-party operation behavior data; S200, performing voice preprocessing on the classroom interactive audio data, the after-class voice comment data, and the non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; S300, establishing an initial behavior event library, combining classroom analysis data, after-class analysis data and non-teaching scenario analysis data, matching the initial behavior event library through sentence matching, obtaining specific behavior events, and performing evaluation and analysis in different scenarios based on the specific behavior events to obtain behavior analysis data; S400, performing image preprocessing on the roll call image data to obtain subject information analysis data, and combining the after-class analysis data and the subject information analysis data to obtain stage feedback data; S500, analyzing and processing the third-party operation behavior data to obtain operation analysis data, and correcting and optimizing the behavior analysis data and stage feedback data through the operation analysis data to obtain optimization analysis data; S600, performing multivariate analysis on the optimized analysis data to obtain multivariate evaluation data of students.

[0023] The method of the present invention solves the problem that the existing student evaluation methods only rely on students' classroom performance, test records and teachers' subjective evaluation. Data is collected from multiple scenarios such as classroom and after-class, and then the data is analyzed and processed to evaluate and analyze students in multiple scenarios. At the same time, career analysis guidance and suggestions are provided to students. Through comprehensive analysis of multi-scenario data, the problem of insufficient comprehensiveness and accuracy in student evaluation is avoided.

[0024] In order to ensure the diversity of data, the data obtained are classroom interactive audio data, post-class voice comment data, roll call image data, non-teaching scene voice data and third-party operation behavior data. In other words, during the school's classroom time and teaching activities, the teacher can use the teacher's microphone or the camera installed in the classroom and other equipment to collect the data of the teacher's interaction with the students, including the teacher's roll call on students to answer questions, students' replies and teachers' comments, and obtain the classroom voice data by collecting the complete data of the entire interactive learning time, and upload it to the server in real time or with delay through the APP to obtain the classroom interactive audio data.

[0025] In addition, in after-class scenarios, for some teaching occasions that are not suitable for real-time voice collection, the teacher can use the teaching computer equipped by the teacher or the mobile phone used by the teacher and other terminal devices with audio data collection function. After class, the teacher can comment on the follow-up homework, daily behavior and activities related to the classroom teaching content through the WeChat public account, such as the correction of paper homework or online homework, and also include the voice evaluation of students' classroom performance, and obtain the after-class voice comment data.

[0026] The roll call image data is obtained by designing a roll call on the platform. The process is as follows: Combined with the teacher-student management system, the teacher-student relationship and the student list corresponding to each teacher are obtained. The teacher can obtain targeted content to be counted by editing the content of the table to be counted. After completing the design of the roll call, the upper right corner of the roll call automatically generates a corresponding identification code containing the teacher and class subject information. The teacher can print it and use it in the teaching process. In daily teaching work, after correcting homework or filling in the roll call content after class, take a photo with a mobile phone and upload the roll call photo based on the WeChat enterprise account to obtain the roll call image data.

[0027] Non-teaching scene voice data can include relevant data provided by students themselves and their peers during the non-teaching process of the school; or in classrooms and other areas, students use fixed classroom hardware recording equipment to input voice-related evaluation content about themselves or their classmates. These contents include peer interaction data, personal psychological change data, and daily behavior performance data. In addition, relevant data in the home environment will also be included. For example, after students go home from school, parents can upload student-related evaluation data to the platform through WeChat voice or taking photos, and the platform will summarize these data.

[0028] The third-party operation behavior data is obtained through the products of third-party authoritative institutions. The products of third-party authoritative institutions can be tablet devices or other hardware devices. Students conduct human-computer dialogue through hardware devices. During the human-computer dialogue, a variety of concrete "life scenes" are set rather than abstract "questions". Through concrete "life scenes", more emphasis is placed on examining students' life experience, thinking quality, problem-solving ability, rapid learning ability, sociality and emotional expression, etc. The products of third-party authoritative institutions obtain third-party operation behavior data by collecting students' operation data, etc.

[0029] In step S200, voice preprocessing is performed on classroom interactive audio data, after-class voice comment data, and non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data, including the following steps: S210: performing voice preprocessing on the classroom interaction audio data, including the following steps: Step 1: Split the classroom interactive audio data and retain the parts with analysis value. In this embodiment, the meaningless noise part with low volume and the external interference that cannot be accurately determined are eliminated to obtain the classroom interactive audio data after value analysis; Step 2: Convert the classroom interactive audio data after value analysis into text to obtain converted classroom interactive audio data. The text conversion can be performed using speech recognition technology, such as speech recognition products provided by Tencent, iFLYTEK, Huawei and Alibaba Cloud. Step 3: Based on the preliminary analysis of natural semantics and text interception, extract the key text information of the sentences with evaluation nature and the content describing the students to obtain the key information data; Step 4: Perform deep natural semantic analysis on key information data to obtain the positive and negative expressions in the key information data, as well as the corresponding relationship between the behaviors of the corresponding semantic descriptions and the students. Specifically, it can be accurate to which student a certain description is directed at, which can be done through OpenAI or other natural semantic understanding models; Step 5: Match the behavior classification labels on the semantic positive and negative expression data, behavior description data, and corresponding relationship data to obtain classroom analysis data.

[0030] S220: Performing voice preprocessing on the after-class voice comment data, including the following steps: S221: Using speech recognition technology, convert the after-class speech comment data into text to obtain after-class comment text data. In this embodiment, the speech recognition technology can be provided by speech recognition products provided by Tencent, iFLYTEK, Huawei, Alibaba Cloud, etc.; S222: Performing deep natural semantic analysis on the post-class comment text data, analyzing the student name analysis in the semantics, the positive and negative expressions of the evaluation, the corresponding relationship between the behavior described in the semantics and the student, and obtaining the positive and negative comment data, comment behavior data and comment corresponding relationship data, wherein the obtained data is accurate enough to obtain a description of a certain sentence for a certain student; S223: Match the positive and negative comment data, comment behavior data, and comment correspondence data with behavior classification labels to obtain post-class evaluation data.

[0031] S230: performing speech preprocessing on the non-teaching scene speech data, including the following steps: S231: extracting and matching the non-teaching scene voice data, extracting the student's name and the corresponding evaluation content, and obtaining the non-teaching voice segment data; S232: Perform deep natural semantic analysis on non-teaching voice segment data to obtain positive and negative expressions of semantics, as well as the corresponding relationship between behaviors and students corresponding to semantic descriptions, and then obtain non-teaching positive and negative data, non-teaching behavior data, and non-teaching corresponding relationship data, which is accurate enough to determine the corresponding description relationship between a certain sentence and a certain classmate. This can be done through OpenAI or other natural language understanding models; S233: Classify and label match the non-teaching positive and negative data, non-teaching behavior data, and non-teaching corresponding relationship data to obtain non-teaching scenario analysis data.

[0032] In step S300, an initial behavior event library is established, and classroom analysis data, after-class analysis data, and non-teaching scenario analysis data are combined to match the initial behavior event library through sentence matching to obtain specific behavior events. Based on the specific behavior events, evaluation and analysis are performed in different scenarios to obtain behavior analysis data, including the following steps: Obtain all behavioral events that will occur during the student's time at school, and establish an initial behavioral event library based on the behavioral events. That is, this initial behavioral event library is a summary of all behavioral events. Perform semantic understanding on classroom analysis data, after-class analysis data, and non-teaching scenario analysis data, and match them with behavioral events in the initial behavioral event library through sentence matching to obtain specific behavioral events. In other words: based on classroom analysis data, after-class analysis data, and non-teaching scenario analysis data to form a text library, perform text correction on the text library to obtain a corrected text library; identify behavioral events and subject names in the corrected text library through text matching and name entity recognition to obtain behavioral events and name entities; extract and identify behavioral events in the initial behavioral event library through the name entity of the behavioral event, obtain matching behavioral events and associate them with the name entity, and obtain behavioral events corresponding to the name entity.

[0033] In addition, as the amount of data increases, the initial behavior event library will also be updated. The specific updating process is as follows: continuously collect user data and establish a basic event library, which is the initial behavior event library; when a new event is added, semantic matching is performed to determine whether it is in the original initial behavior event. If it does not exist, a new initial behavior event is added. If it exists, the definition boundary of the original initial behavior event is expanded to achieve the improvement and expansion of the initial behavior event library.

[0034] In step S400, image preprocessing is performed on the roll call image data to obtain subject information analysis data, and after-class analysis data and subject information analysis data are combined to obtain stage feedback data, including the following steps: S410: In this embodiment, firstly, image tilt correction and identification code detection and recognition are performed on the image data of the roll call list, which is achieved by using a table corner point detection algorithm to obtain corner point position information, obtain identification code area position information according to the relative position of the corner point position information, and perform image tilt correction based on the corner point position information. In this embodiment, the identification code includes but is not limited to a QR code and a bar code; S420: using the corner point position information and the prior information of the table rows and columns in the roll call list, evenly splitting the roll call list table to obtain cells, and then expanding the cells and using the detection and positioning model to obtain subject information position data; S430: Accurately locate the characters by combining the character recognition model with the subject information position data to obtain the character recognition result; S440: According to the actual scenario, the character recognition result is corrected by the model through the column formulation mode, wherein the correction logic corrects and proofreads the character recognition result according to the first k results of the character recognition result and the character column mode to obtain subject information analysis data; S450: Summarize and analyze the subject information analysis data and after-class analysis data to generate evaluation data within the stage, and then adjust and optimize the evaluation data within the stage. In this embodiment, based on the subject information analysis data, classroom performance data, homework data and in-class exercise data are obtained, and a preset subject understanding threshold is set. Based on the preset subject understanding threshold, the subject information analysis data is divided into understanding degrees to obtain understanding data; S460: Summarize and analyze the post-class analysis data, and adjust and optimize the evaluation data to obtain stage feedback data. The feedback data at this stage is adjusted and optimized, and can accurately represent the specific situation of a certain stage. Here, subject understanding refers to the students' mastery of each subject, which is what people usually call the absorption of knowledge. The understanding data can be used to feedback the students' learning situation. Through the understanding data, the students' learning situation can be quickly understood in real time, and the teacher can customize the training plan and related tutoring plan for each student.

[0035] In this embodiment, the character recognition model is obtained by: Acquire an original data set and preprocess the original data set to obtain a training data set, wherein the training data set is a grayscale image, and the preprocessing includes at least data enhancement and data synthesis; Construct a character recognition pre-training model and train it through the training data set to obtain a character recognition model; Among them, the character recognition pre-training model is implemented through the Beam Search algorithm. During decoding, the first K characters with the highest probability of the current decoded character are screened and saved. Specifically, the first list is constructed to store the largest K results obtained each time, and the decoding length S is traversed; the first list is traversed to decode the candidate set for each of the largest K results so far; each decoded K result is stored in the second list; the first K are selected as the first list according to the confidence level; and the traversal is continued until the decoding length S is obtained.

[0036] In this implementation, in order to avoid the influence of other colors, such as background color, font color, etc., the image needs to be grayscaled first. Then the data set is expanded, such as data enhancement or data synthesis; to enhance the robustness of the model, additional data enhancement methods are added, as follows: Font expansion: Opencv is used to randomly perform different levels of expansion operations on the image, mainly to simulate different thicknesses of the font; Scaling: Pillow and Opencv are used to scale the image to different degrees, because scaling may affect the key features and boundaries of the image; Small angle rotation: Randomly generate a smaller rotation angle, and then rotate the target image, mainly to enhance the model's recognition ability at different angles.

[0037] Since the real data collected manually is limited, data synthesis processing is also used. The required characters are randomly selected, and the original images are transformed at different levels, such as size and color. They are then posted at random positions in the cells to achieve the purpose of expanding the data set.

[0038] In addition, during reasoning, the image is expanded to different degrees according to the position where the text is detected, such as 0, 10%, 15%, etc. After obtaining images of different scales, reasoning is performed separately to obtain the results of three different scales of reasoning, providing more selectivity.

[0039] For each column of the table, the pattern is judged and matched. That is, a pattern is formulated for the column according to the occurrence of each character in the column. For example, for column ABCD, the multiple candidates obtained in steps 1 and 2 are combined to select the one with the highest confidence as the final output result of the cell.

[0040] In step S500, the third-party operation behavior data is analyzed and processed to obtain operation analysis data, and then the behavior analysis data is corrected and optimized to obtain optimized analysis data, including the following steps: S510: Based on the operation behavior records of the students on the terminal devices, such as the tablet devices or other hardware devices, third-party operation behavior data is obtained, and operation analysis data is obtained through data analysis and data processing; S520: Combined with the operation analysis data, the behavior analysis data obtained by comprehensive analysis in other scenarios is secondarily corrected and optimized to obtain optimized analysis data.

[0041] In step S600, multivariate analysis is performed on the optimized analysis data to obtain student multivariate evaluation data, including the following steps: S610: Slice the behavior analysis data in the optimization analysis data to obtain short word data, remove short words and matching hot words from the short word data, and generate a student hot word portrait; S620: Summarize the behavior analysis data in the optimization analysis data, analyze the behavior characteristics and student types, and obtain behavior characteristic data and student type data; S630: Analyze the behavior analysis data in the optimization analysis data and combine it with expert suggestions to obtain targeted guidance suggestions; S640: Summarize the stage feedback data in the optimization analysis data, analyze the learning behavior characteristics, and obtain learning behavior data.

[0042] Finally, the student hot word portraits, behavioral characteristics data, student type data, targeted guidance suggestions and learning behavior data are displayed through the interface display module, such as Figure 3 In other words, the whole process can be understood as follows: after obtaining the classroom analysis data, the performance of students in each class is summarized and fed back to the teacher in real time; after obtaining the post-class evaluation data, the voice input by the teacher and the corresponding label information are displayed based on the student dimension and event dimension. During the display process, the teacher can perform secondary editing and correction on the acquired information.

[0043] After obtaining the subject information analysis data, teachers can view the data through the corresponding account through electronic data. The resulting spreadsheet will automatically calculate routine data statistics, including score calculations and quantity statistics. For example, calculate the class average score, or count all students who have received five-pointed stars or honors.

[0044] By obtaining non-classroom analysis data, based on student dimensions and event dimensions, the psychological behavior data is displayed on mobile phones and web pages, and a comprehensive analysis of student status changes is conducted. At the same time, during the data display process, based on the need to protect student data and student privacy, permission control is performed in the data display part. Students can choose to block some data for teachers and parents. At the same time, parents can upload data and view the results of analysis and processing of the relevant data uploaded by themselves. Parent permissions are set so that parents only have viewing permissions for the open parts of data uploaded by some teachers and students.

[0045] After analyzing the third-party operation data to obtain the operation analysis data, the behavior analysis data and stage feedback data will be corrected and optimized to obtain the optimization analysis data. Finally, the optimized analysis data will be used to obtain the student multi-evaluation data. The student multi-evaluation data can be understood as including student hot word portraits, behavior characteristics data, student type data, targeted guidance suggestions and learning behavior data, and of course other related data. These data will eventually be displayed on the interface. This interface can be referred to Figure 3 As shown. It is possible to intuitively know the multiple evaluations and targeted guidance of each student, providing a guidance basis for the next stage.

[0046] Embodiment 2: A multi-evaluation system based on multi-scenario educational information analysis, such as Figure 2 As shown, it includes a data acquisition module 100, a speech preprocessing module 200, an event library establishment module 300, an image preprocessing module 400, a correction optimization module 500 and a multivariate analysis module 600; The data acquisition module 100 acquires classroom interactive audio data, after-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; The speech preprocessing module 200 performs speech preprocessing on the classroom interactive audio data, the after-class speech commentary data, and the non-teaching scene speech data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; The event library establishment module 300 establishes an initial behavior event library, combines classroom analysis data, after-class analysis data and non-teaching scenario analysis data, matches the initial behavior event library through sentence matching, obtains specific behavior events, and performs evaluation and analysis in different scenarios based on the specific behavior events to obtain behavior analysis data; The image preprocessing module 400 performs image preprocessing on the roll call image data to obtain subject information analysis data, and combines the after-class analysis data and the subject information analysis data to obtain stage feedback data; The correction and optimization module 500 analyzes and processes the third-party operation behavior data to obtain operation analysis data, and corrects and optimizes the behavior analysis data and the stage feedback data based on the operation analysis data to obtain optimized analysis data; The multivariate analysis module 600 performs multivariate analysis on the optimized analysis data to obtain multivariate evaluation data of students.

[0047] Various changes and modifications can be made without departing from the spirit and scope of the present invention, and all equivalent technical solutions also belong to the scope of the present invention.

[0048] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0049] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0050] The present invention is described with reference to the flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0051] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0052] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0053] It should be noted that: The "one embodiment" or "embodiment" mentioned in the specification means that the specific features, structures or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment" or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0054] In addition, it should be noted that the shapes and names of the parts and components of the specific embodiments described in this specification may be different. Any equivalent or simple changes made based on the structure, features and principles described in the patent concept of the present invention are included in the protection scope of the patent of the present invention. The technicians in the technical field of the present invention can make various modifications or supplements to the specific embodiments described or replace them in a similar manner, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A multi-evaluation method based on multi-scenario educational information analysis, characterized in that: The following steps are involved: Obtain classroom interaction audio data, after-class voice comment data, roll call image data, non-teaching scene voice data, and third-party operation behavior data; Perform voice preprocessing on classroom interactive audio data, after-class voice comment data, and non-teaching scene voice data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; Establish an initial behavior event library, combine classroom analysis data, after-class analysis data and non-teaching scenario analysis data, match the initial behavior event library through sentence matching, obtain specific behavior events, and conduct evaluation and analysis based on specific behavior events in different scenarios to obtain behavior analysis data; Perform image preprocessing on the roll call image data to obtain subject information analysis data, and combine the after-class analysis data and subject information analysis data to obtain stage feedback data; Analyze and process the third-party operation behavior data to obtain operation analysis data, and use the operation analysis data to correct and optimize the behavior analysis data and stage feedback data to obtain optimization analysis data; Multivariate analysis is performed on the optimized analysis data to obtain students' multivariate evaluation data.

2. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The method of performing voice preprocessing on the classroom interactive audio data to obtain classroom analysis data includes the following steps: Split and value analyze the classroom interactive audio data to obtain the classroom interactive audio data after value analysis; By using speech recognition technology, the classroom interaction audio data after value analysis is converted to obtain converted classroom interaction audio data; Conduct preliminary analysis and text extraction of the converted classroom interactive audio data to obtain key information data; Conduct deep semantic analysis on key information data to obtain semantic positive and negative expression data, behavior description data and corresponding relationship data, and then obtain classroom analysis data through behavior classification label matching.

3. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The method of performing voice preprocessing on the after-class voice comment data to obtain the after-class evaluation data includes the following steps: By using speech recognition technology, the after-class speech comment data is converted into text to obtain the after-class comment text data; The post-class review text data is subjected to deep semantic analysis to obtain positive and negative review data, review behavior data, and review correspondence data, and then the post-class evaluation data is obtained through behavioral classification label matching.

4. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The method of performing speech preprocessing on the non-teaching scene speech data to obtain the non-teaching scene parsed data comprises the following steps: Through data analysis and data matching, the non-teaching scene voice data is extracted to obtain non-teaching voice segment data; Deep semantic analysis is performed on non-teaching voice segment data to obtain non-teaching positive and negative data, non-teaching behavior data, and non-teaching corresponding relationship data, and then non-teaching scene analysis data is obtained through behavior classification label matching.

5. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The step of obtaining a specific behavior event comprises the following steps: Based on the daily behavior events of students, daily behavior data are obtained, and a basic event library, namely, an initial behavior event library, is established through the daily behavior data; Through semantic understanding, classroom analysis data, after-class analysis data, and non-teaching scenario analysis data are matched with daily behavior data to obtain specific behavior events, specifically: Based on the classroom analysis data, after-class analysis data and non-teaching scenario analysis data to form a text library, performing text error correction on the text library to obtain a text library after error correction; Through text matching and name entity recognition, the behavior events and subject names existing in the corrected text library are identified to obtain the behavior events and name entities; Through the name entity of the behavior event, the behavior events in the initial behavior event library are extracted and identified, the matching behavior events are obtained and associated with the name entity, and the behavior events corresponding to the name entity are obtained.

6. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The step of performing image preprocessing on the roll call image data to obtain subject information analysis data comprises the following steps: Performing corner point detection on the point list image data to obtain corner point position information, correcting the point list image data using the corner point position information to obtain corrected image data, and obtaining identification code area data using the relative position of the corner point position information; Based on the roll call image data, the row and column information data is obtained, and the subject information position data is obtained by combining the corner point position information and the detection and positioning model; By combining the character recognition model and the subject information location data, the subject information recognition data is obtained, and then character correction and character proofreading are performed on the subject information recognition data. Combined with the identification code area data, the subject information analysis data is obtained.

7. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 6 is characterized in that: The character recognition model is obtained in the following way: Acquire an original data set and preprocess the original data set to obtain a training data set, wherein the training data set is a grayscale image, and the preprocessing includes at least data enhancement and data synthesis; Construct a character recognition pre-training model and train it through the training data set to obtain a character recognition model; Among them, the character recognition pre-training model is implemented through the Beam Search algorithm. During decoding, the first K characters with the highest probability of the current decoded character are screened and saved. Specifically, the first list is constructed to store the largest K results obtained each time, and the decoding length S is traversed; the first list is traversed to decode the candidate set for each of the largest K results so far; each decoded K result is stored in the second list; the first K are selected as the first list according to the confidence level; and the traversal is continued until the decoding length S is obtained.

8. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The step of obtaining the stage feedback data comprises the following steps: Based on the preset subject understanding threshold, the subject information analysis data is analyzed and processed to obtain understanding data; By analyzing and summarizing the after-class analysis data and subject information analysis data, the evaluation data is obtained; The evaluation data is adjusted and optimized to obtain stage feedback data.

9. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The multivariate analysis of the optimization analysis data comprises the following steps: Slice the behavior analysis data in the optimization analysis data to obtain short word data, remove short words and matching hot words from the short word data, and generate a student hot word portrait; Summarize the behavior analysis data in the optimization analysis data, analyze the behavior characteristics and student types, and obtain behavior characteristic data and student type data; Analyze the behavioral analysis data in the optimization analysis data and combine it with expert advice to obtain targeted guidance and suggestions; The stage feedback data in the optimization analysis data are summarized, and the learning behavior characteristics are analyzed to obtain the learning behavior data.

10. The multivariate evaluation method based on multi-scenario educational information analysis according to claim 1 is characterized in that: The following steps are also included: The students' multi-dimensional evaluation data are displayed through an interface display module, wherein the displayed content at least includes students' hot word portraits, behavioral characteristic data, student type data, targeted guidance suggestions and learning behavior data.

11. A multi-evaluation system based on multi-scenario educational information analysis, characterized in that: It includes data acquisition module, speech preprocessing module, event library establishment module, image preprocessing module, correction optimization module and multivariate analysis module; The data acquisition module acquires classroom interactive audio data, after-class voice comment data, roll call image data, non-teaching scene voice data and third-party operation behavior data; The speech preprocessing module performs speech preprocessing on the classroom interactive audio data, the after-class speech commentary data, and the non-teaching scene speech data to obtain classroom analysis data, after-class analysis data, and non-teaching scene analysis data; The event library establishment module establishes an initial behavior event library, combines classroom analysis data, after-class analysis data and non-teaching scenario analysis data, matches the initial behavior event library through sentence matching, obtains specific behavior events, and performs evaluation and analysis in different scenarios based on the specific behavior events to obtain behavior analysis data; The image preprocessing module performs image preprocessing on the roll call image data to obtain subject information analysis data, and combines the after-class analysis data and the subject information analysis data to obtain stage feedback data; The correction and optimization module analyzes and processes the third-party operation behavior data to obtain operation analysis data, and corrects and optimizes the behavior analysis data and stage feedback data through the operation analysis data to obtain optimization analysis data; The multivariate analysis module performs multivariate analysis on the optimized analysis data to obtain multivariate evaluation data of students.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

13. A multi-evaluation device based on multi-scenario educational information analysis, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 10 is implemented.

Images