WO2020010882A1 - Data processing method, storage medium and electronic device - Google Patents

Data processing method, storage medium and electronic device Download PDF

Info

Publication number
WO2020010882A1
WO2020010882A1 PCT/CN2019/081589 CN2019081589W WO2020010882A1 WO 2020010882 A1 WO2020010882 A1 WO 2020010882A1 CN 2019081589 W CN2019081589 W CN 2019081589W WO 2020010882 A1 WO2020010882 A1 WO 2020010882A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
courseware
operation block
courseware operation
data processing
Prior art date
Application number
PCT/CN2019/081589
Other languages
French (fr)
Chinese (zh)
Inventor
王正博
沈亮
张保福
张连杰
赵明明
Original Assignee
北京大米科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京大米科技有限公司 filed Critical 北京大米科技有限公司
Publication of WO2020010882A1 publication Critical patent/WO2020010882A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/20—Education
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/01—Assessment or evaluation of speech recognition systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals

Definitions

  • the present invention relates to the field of data processing, and particularly to a data processing method, a storage medium, and an electronic device, and more particularly, to a method and a related device for evaluating the content of audio data.
  • Embodiments of the present invention provide a data processing method, a storage medium, and an electronic device to automatically process audio data recorded online and evaluate the situation of online teaching.
  • a data processing method includes:
  • each courseware operation block For each courseware operation block, comparing the mapped speech recognition information with corresponding average state information to obtain comparison parameters, wherein each courseware operation block corresponds to at least one comparison parameter;
  • a computer-readable storage medium on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the method according to the first aspect.
  • an electronic device including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are The processor executes to implement the method according to the first aspect
  • the speech recognition information of the audio data recorded in the online teaching process is mapped to different courseware operation blocks according to the recorded courseware operation data.
  • the corresponding average state information is obtained horizontally to obtain the comparison parameters, and finally the evaluation value is obtained based on the comparison parameters of the courseware operation block.
  • the audio data is processed in conjunction with the recorded courseware operations, so that a relatively accurate automated evaluation of a large amount of online teaching audio data can be performed.
  • FIG. 1 is a schematic diagram of an online teaching system applicable to a data processing method in one or more embodiments
  • FIG. 2 is a schematic diagram of an interface of an online teaching application client in one or more embodiments
  • FIG. 3 is a flowchart of a data processing method in one or more embodiments
  • FIG. 4 is a schematic diagram of an example of a data processing method according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.
  • FIG. 1 is a schematic diagram of an online teaching system applicable to a data processing method in one or more embodiments.
  • the online teaching system includes a first client 1, a second client 2, and a server 3.
  • the first client 1, the second client 2, and the server 3 are connected through a network communication.
  • the first client 1 and the second client 2 can directly or indirectly establish a communication connection through the server 3 to perform online teaching activities after real-time communication.
  • the first client 1 is operated by an instructor.
  • the second client 2 is operated by the learner, and the server 3 forms a communication connection with the first client 1 and the second client 2 at the same time, and stores the data exchanged between the two.
  • the first client 1 and the second client 2 can access the server 3 to obtain courseware data for display, thereby implementing online teaching based on the courseware.
  • the content of the courseware displayed by the first client 1 and the second client 2 changes synchronously, so that the instructor and the learner can synchronize based on the same part of the courseware communicate with.
  • first client 1 and the second client 2 may be any general-purpose data processing device running a predetermined computer application program, such as a desktop computer, a portable computer, a tablet computer, a smart phone, and the like.
  • the server 3 is a high-performance data processing device running a predetermined computer application program.
  • the server 3 may be a server, a server cluster deployed in a distributed manner, or a virtual server cluster deployed in a virtual machine or container manner.
  • a large number of first clients 1 establish a communication connection with the second client 2 in a one-to-one, one-to-many, or many-to-many manner to communicate.
  • FIG. 2 is a schematic diagram of an interface of an online teaching application client in one or more embodiments.
  • the online teaching application client can display the courseware in the main window 21 of the application interface, and display the real-time image collected by the image acquisition device of the counterpart in the sub-window 22 of the application interface.
  • a video of the upper body of the other party is displayed in the sub-window 22 of the application interface.
  • the content of the courseware displayed in the main window is controlled by the operation of the teacher to switch or display the track.
  • the instructor performs page switching (ie, page turning) on the courseware on the first client 1 or performs a track operation on the content of the courseware.
  • the trajectory operation refers to identifying content or drawing an image through a trajectory on a courseware.
  • the instructor can highlight certain content of the courseware through lines or circles, and can also draw graphics or text by trajectory through handwriting or mouse operation.
  • the server 3 can record all courseware operations (including page switching operations and trajectory operations) applied by the teacher on the first client 1 during the teaching process.
  • the server 3 may also record audio data of the learner during the entire teaching process and audio data of the learner during the teaching process.
  • the audio data includes corresponding voice information.
  • the above two types of audio data are stored in the same audio file in a divided audio track manner.
  • the audio data recorded by the server 3 and the courseware operation data are processed to automatically evaluate the teaching process.
  • FIG. 3 is a flowchart of a data processing method in one or more embodiments. As shown in Figure 3, the data processing method includes the following steps:
  • step S100 the time axis is divided into a plurality of courseware operation blocks according to courseware operation data.
  • courseware operation data is recorded for each teaching based on the online teaching system.
  • the timeline information of each courseware operation is acquired based on the courseware operation data, that is, at which point in time each courseware operation occurs.
  • the timeline information of courseware operation is used to divide the teaching process into different courseware operation blocks.
  • the courseware operations may include page switching operations and track operations. Based on the above two different operations, the teaching process can be divided into multiple courseware operation blocks in two different dimensions.
  • the courseware operation block refers to a time interval corresponding to a certain courseware operation.
  • the timeline of the entire teaching process is divided into first-type operation blocks that explain each page of the courseware.
  • the first type of operation block covers the time axis between two adjacent page switching operations, that is, the first type of operation block can be characterized as being obtained by the instructor for each page of courseware. Describe the time interval information.
  • a second type of operation block corresponding to each trajectory operation may be obtained.
  • the second type of operation block covers the time axis of one trajectory operation.
  • a second type of operation block is the time interval for which the corresponding trajectory operation lasts.
  • a second type of operation block is a time interval from a predetermined time before the start of the track operation to a predetermined time after the end of the track operation. Therefore, each time a trajectory operation occurs, a corresponding second-type operation interval is obtained.
  • the teaching timeline is 20 minutes long.
  • the instructor performed 5 page switching operations (including the end operation) during the teaching process.
  • one line drawing operation was performed to emphasize the content. Therefore, as shown in FIG. 4, according to the page switching operation, the time axis can be divided into five first-type operation blocks A1-A5.
  • Each operation block of the first type corresponds to a teaching time interval of a page of courseware.
  • two second-type operation blocks B1 and B2 can be obtained.
  • Each second-type operation block contains the trajectory operation. Time interval.
  • the voice information in the time period may be further processed.
  • Step S200 Acquire speech recognition information corresponding to the speech information in the audio data.
  • the speech recognition technology is a technology that processes audio data containing speech information to obtain information related to speech content.
  • the voice recognition information obtained through voice recognition is voice duration information.
  • the voice recognition information obtained through voice recognition is text information corresponding to the voice information.
  • the text information can reflect the specific content explained by the teacher during the teaching process, which can be used as the basis for subsequent evaluation.
  • the speech duration information refers to time axis information of the detected speech in the audio data.
  • the teacher may not be continuously explaining, and the speech duration information may reflect the intensity of the communication between the teacher and the learner to a certain extent.
  • the acquired speech recognition information also carries time axis information.
  • the time axis information characterizes the text content in the text corresponding to the time on the time axis.
  • the time axis information represents a start time and an end time of the speech duration.
  • At least one of text information and speech duration information is extracted from audio data as a basis for evaluation.
  • the time axis of the audio data processed in this step should be synchronized with the time axis of the courseware operation data in advance to ensure the accuracy of subsequent processing.
  • step S200 may be performed sequentially with step S100 in any order. In one or more embodiments, step S200 may be performed simultaneously with step S100.
  • step S300 the speech recognition information is mapped into the corresponding courseware operation block according to the timeline information of the courseware operation.
  • mapping refers to extracting the speech recognition information corresponding to the time interval involved in the courseware operation block according to the time axis information carried by the speech recognition signal, and establishing association with the courseware operation block. process.
  • the speech recognition information includes text information and speech duration information.
  • the text information is mapped twice, and the text information is mapped to each first-type operation block according to its corresponding time axis, which makes the text information divided into multiple parts, each Part corresponds to a first type of operation block.
  • the text information is also mapped to each second-type operation block, so that the part of the text information related to the time interval where the trajectory operation occurs is extracted and related to the corresponding trajectory operation (or the first The second type of operation block) establishes an association. For example, in a certain teaching process, for page 5 of the courseware, the instructor performed a 30-second trajectory operation.
  • the corresponding text information will be extracted and associated with the trajectory operation within the 30-second time interval or within the time interval of 30 seconds before and after the total of 90 seconds.
  • all text information (including text information during the 30-second trajectory operation process) on page 5 of the entire courseware will be mapped to the corresponding first-type operation block, that is, the courseware corresponding to page 5 Operation block.
  • the speech duration information is also mapped twice.
  • the speech duration information is mapped into each first-type operation block according to the time axis distribution, which allows each first-type operation block to have a speech duration attribute, which can be identified in the The length of time the educator is explaining during the course of the page courseware.
  • the speech duration information is also mapped into each second-type operation block, which enables each second-type operation block (that is, each trajectory operation) to perform trajectory with the instructor.
  • the voice duration information during operation is associated.
  • mapping ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇ ⁇
  • the above information is compared horizontally with corresponding information of other instructors when teaching the same courseware.
  • the same lecturer's information on the same courseware can also be used as a basis for horizontal comparison.
  • the comparison can identify whether the content of the currently processed audio data is significantly different from other teachers or other teaching processes in the above four dimensions, or that it deviates significantly. average value.
  • the second type of operation block may not be mapped. In one or more embodiments, only one of the above-mentioned speech recognition information is mapped to reduce the calculation load and speed up the data processing speed.
  • Step S400 Compare the speech recognition information in each courseware operation block with corresponding average state information to obtain corresponding comparison parameters.
  • each courseware operation block corresponds to at least one comparison parameter.
  • the average state information is used to characterize the average state of the above-mentioned different dimension information in other teaching processes for the same courseware.
  • the average state information of the text information is obtained as follows.
  • a vector space model (VSM) is often used to identify text.
  • the vector space model uses a vector to represent a piece of text information, and each item in the vector is the weight of the feature item.
  • Feature items can be words, words, or phrases of information in the text.
  • word segmentation and statistical word frequency operations the feature terms of the text and their weights can be obtained.
  • feature extraction can be performed on the vector to reduce the dimensionality of the vector to reduce the amount of data processing calculations.
  • the extracted feature vector is a mapping of text information in a predetermined feature space, which can uniquely characterize the text information.
  • a feature vector corresponding to each text can be obtained.
  • the average of these feature vectors can be used as the average state information of this type of text information.
  • the word segmentation, word frequency statistics, vectorized expression of text, and feature extraction in the above process can be implemented using various existing text processing technologies.
  • the operation of comparing the text information with the average state information may be performed by calculating the distance between the feature vector corresponding to the text information and the average state information in the feature space or the included angle on a certain projection plane. achieve.
  • the values of the distance and the included angle can represent the degree of difference between the text information and the average state information, so as to serve as the comparison parameter.
  • the average state information of the voice duration information is obtained in the following manner. Since the speech duration information is actually a numerical value, an average value can be directly obtained as the average state information of the speech duration information. In one or more embodiments, by comparing the speech duration information and the average value, the degree of difference between the speech duration information and the average state information can be characterized. This degree of difference can be used as the comparison parameter.
  • Step S500 Obtain an evaluation value according to the comparison parameter of the courseware operation block.
  • the evaluation value is obtained according to comparison parameters of all courseware operation blocks.
  • only a part of the comparison parameters of courseware operation blocks is selectively selected to obtain the evaluation value.
  • the evaluation value may be obtained by weighted summation of comparison parameters of different courseware operation blocks.
  • Different courseware operation blocks can have different weights, and different contrast parameters can also have different weights.
  • step S500 includes the following sub-steps:
  • step S510 a plurality of comparison parameters corresponding to each courseware operation block are weighted and summed to obtain an evaluation index of the courseware operation block.
  • Step S520 Calculate a weighted sum of evaluation indexes of all courseware operation blocks according to the weight of each courseware operation block as the evaluation value.
  • step S200 the voice information in the audio data is identified, thereby obtaining corresponding text information and voice duration information.
  • the above information has timeline related information.
  • step S300 the text information and speech duration information with the lecturer's explanation for each page of courseware are mapped to the first-type operation blocks A1-A5, respectively.
  • the text information (corresponding to its voice information) and voice duration information during the two trajectory operations of the teacher are mapped to the operation blocks B1 and B2, respectively.
  • step S400 the text information X1-X5 of the first-type operation blocks A1-A5 are respectively compared with the corresponding average state information Y1-Y5, thereby obtaining the text of each first-type operation block A1-A5.
  • Information comparison parameters a1-a5. Compare the speech duration information T1-T5 of the first type of operation blocks A1-A5 with the corresponding average state information Q1-Q5, thereby obtaining the speech duration information comparison parameter b1- of each first type of operation block A1-A5 b5.
  • the text information X6 and X7 of the second type of operation blocks B1 and B2 are compared with the corresponding average state information Y6 and Y7, respectively, thereby obtaining the text information comparison parameter c1 of each second type of operation blocks B1 and B2.
  • c2 Compare the speech duration information T6 and T7 of the second type of operation blocks B1 and B2 with the corresponding average state information Q6 and Q7 respectively, thereby obtaining the speech duration comparison parameters d1 and d2.
  • the first-type operation blocks A1-A5 are respectively given weights w1-w5 in advance
  • the second-type operation blocks B1-B2 are respectively given weights bw1 and bw2.
  • the evaluation value is calculated by the following weighted calculation formula:
  • W1 ⁇ ai + W2 ⁇ bi is the evaluation index of the first type of operation block Ai
  • W1 ⁇ ci + W2 ⁇ di is the evaluation index of the second type of operation block Bi.
  • the foregoing weights may be set by an operator based on the knowledge and experience of the courseware. For example, you can set a higher weight for more important courseware pages. As another example, when the narrative content is more important, the text information is given a higher weight.
  • the process described above is merely an example.
  • a part of the data processing process is reduced to reduce the calculation amount.
  • the trajectory operation may not be mapped, and only mapping, comparison, and evaluation value calculation may be performed for each first-type operation block.
  • whether or not there is a trajectory operation in the first-type operation block is taken as additional information of each first-type operation block, and is considered in calculating the evaluation value.
  • the data processing method may further include step S600, displaying an evaluation value obtained in step S500 or displaying a comparison parameter of each courseware operation block.
  • step S600 displaying an evaluation value obtained in step S500 or displaying a comparison parameter of each courseware operation block.
  • radar charts can be used to show evaluations in different dimensions. As a result, you can understand the teaching process based on the evaluation value or the display of comparative parameters. At the same time, it also provides a more objective evaluation basis for the evaluation of teaching quality.
  • the speech recognition information of the audio data recorded in the online teaching process is mapped to different courseware operation blocks according to the recorded courseware operation data.
  • the corresponding average state information is obtained horizontally to obtain the comparison parameters, and finally the evaluation value is obtained based on the comparison parameters of the courseware operation block.
  • the audio data is processed in conjunction with the recorded courseware operations, so that a relatively accurate automated evaluation of a large amount of online teaching audio data can be performed.
  • FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.
  • the electronic device shown in FIG. 5 is a general-purpose data processing apparatus including a general-purpose computer hardware structure including at least a processor 51 and a memory 52.
  • the processor 51 and the memory 52 are connected via a bus 53.
  • the memory 52 is adapted to store instructions or programs executable by the processor 51.
  • the processor 51 may be an independent microprocessor or a collection of multiple microprocessors. Therefore, the processor 51 executes the commands stored in the memory 52, thereby executing the method flow of the embodiment of the present invention as described above to implement data processing and control on other devices.
  • the bus 53 connects the above-mentioned multiple components together, and simultaneously connects the above-mentioned components to the display controller 54 and the display device, and an input / output (I / O) device 55.
  • the input / output (I / O) device 55 may be a mouse, keyboard, modem, network interface, touch input device, somatosensory input device, printer, and other devices known in the art.
  • an input / output (I / O) device 55 is connected to the system through an input / output (I / O) controller 56.
  • the memory 52 may store software components, such as an operating system, a communication module, an interaction module, and an application program. Each module and application described above corresponds to a set of executable program instructions that perform one or more functions and methods described in the embodiments of the invention.
  • aspects of the embodiments of the present invention may be implemented as a system, method or computer program product. Therefore, various aspects of the embodiments of the present invention may take the following forms: a completely hardware implementation, a completely software implementation (including firmware, resident software, microcode, etc.) or may generally be referred to herein as “circuits", “modules” “Or” system “implementations that combine software and hardware aspects. Furthermore, aspects of the invention may take the form of a computer program product implemented in one or more computer-readable media, the computer-readable medium having computer-readable program code implemented thereon.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.
  • a computer-readable storage medium may be any tangible medium capable of containing or storing a program used by or in conjunction with an instruction execution system, device, or device.
  • the computer-readable signal medium may include a propagated data signal having computer-readable program code implemented therein, such as in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof.
  • the computer-readable signal medium may be any of the following computer-readable media: not a computer-readable storage medium, and may communicate and propagate a program used by or in conjunction with an instruction execution system, device, or device Or transmission.
  • Computer program code for performing operations directed to aspects of the present invention may be written in any combination of one or more programming languages, including: object-oriented programming languages such as Java, Smalltalk, C ++, PHP, Python Etc .; and conventional procedural programming languages such as the "C" programming language or similar programming languages.
  • the program code can be executed entirely on the user's computer as a stand-alone software package, and partially on the user's computer. Performed partially on the user's computer and partially on the remote computer; or entirely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (for example, by using the Internet of an Internet service provider) .
  • LAN local area network
  • WAN wide area network
  • Internet service provider for example, by using the Internet of an Internet service provider

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Technology (AREA)
  • Marketing (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Educational Administration (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Electrically Operated Instructional Devices (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

Disclosed are a data processing method, a storage medium, and an electronic device. The method comprises the following steps: dividing a timeline into multiple courseware operation blocks according to courseware operation data (S100); acquiring speech recognition information corresponding to speech information in audio data (S200); mapping the speech recognition information to corresponding courseware operation blocks according to information of the timeline (S300); comparing, in each of the courseware operation blocks, the mapped speech recognition information with corresponding average state information to acquire a comparison parameter, wherein each of the courseware operation blocks corresponds to at least one comparison parameter (S400); and acquiring an evaluation value based on the comparison parameter of the courseware operation block (S500). By means of the method, relatively accurate automated evaluation can be performed on a large amount of online teaching audio data.

Description

数据处理方法、存储介质和电子设备Data processing method, storage medium and electronic equipment
本申请要求了2018年7月11日提交的、申请号为2018107582209、发明名称为“数据处理方法、存储介质和电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed on July 11, 2018, with application number 2018107582209, and the invention name is "data processing method, storage medium and electronic device", the entire contents of which are incorporated herein by reference. .
技术领域Technical field
本发明涉及数据处理领域，具体涉及一种数据处理方法、存储介质和电子设备，更具体地，涉及对于音频数据的内容进行评价的方法和相关装置。The present invention relates to the field of data processing, and particularly to a data processing method, a storage medium, and an electronic device, and more particularly, to a method and a related device for evaluating the content of audio data.
背景技术Background technique
随着互联网技术的发展，基于网络的在线教学得到越来越广泛的应用。知识服务者或知识分享者(也可称为教学者)可以通过网络与学习者进行实时的交流和沟通。为了对于在线教学的讲解情况进行了解和评估，需要进行录像回看或进行在线监督。但是，如果在线教学的数量较大，会涉及大量的音视频数据，如果采用人工方式会需要消耗大量的人力资源。With the development of Internet technology, web-based online teaching has become more and more widely used. Knowledge servers or knowledge sharers (also known as educators) can communicate and communicate with learners in real time through the network. In order to understand and evaluate the explanation of online teaching, you need to review the video or conduct online supervision. However, if the amount of online teaching is large, a large amount of audio and video data will be involved, and if manual methods are used, a lot of human resources will be consumed.
发明内容Summary of the invention
本发明实施例提供一种数据处理方法、存储介质和电子设备，以自动化地对于在线录制的音频数据进行处理，对在线教学的情况进行评估。Embodiments of the present invention provide a data processing method, a storage medium, and an electronic device to automatically process audio data recorded online and evaluate the situation of online teaching.
根据本发明实施例的第一方面，提供一种数据处理方法，其中，所述方法包括：According to a first aspect of the embodiments of the present invention, a data processing method is provided, wherein the method includes:
根据课件操作数据将时间轴划分为多个课件操作区块；Divide the timeline into multiple courseware operation blocks according to courseware operation data;
获取音频数据中的语音信息对应的语音识别信息；Obtaining speech recognition information corresponding to the speech information in the audio data;
根据时间轴信息将所述语音识别信息映射到对应的课件操作区块；Map the speech recognition information to the corresponding courseware operation block according to the time axis information;
对于每个课件操作区块，将映射后的所述语音识别信息与对应的平均状态信息比较以获取对比参数，其中，每个课件操作区块对应于至少一个对比参数；For each courseware operation block, comparing the mapped speech recognition information with corresponding average state information to obtain comparison parameters, wherein each courseware operation block corresponds to at least one comparison parameter;
根据所述课件操作区块的所述对比参数获取评价值。Obtain an evaluation value according to the comparison parameter of the courseware operation block.
根据本发明实施例的第二方面，提供一种计算机可读存储介质，其上存储计算机程序指令，其中，所述计算机程序指令在被处理器执行时实现如第一方面所述的方法。According to a second aspect of the embodiments of the present invention, a computer-readable storage medium is provided on which computer program instructions are stored, wherein the computer program instructions, when executed by a processor, implement the method according to the first aspect.
根据本发明实施例的第三方面，提供一种电子设备，包括存储器和处理器，其中，所述存储器用于存储一条或多条计算机程序指令，其中，所述一条或多条计算机程序指令被所述处理器执行以实现如第一方面所述的方法According to a third aspect of the embodiments of the present invention, there is provided an electronic device including a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are The processor executes to implement the method according to the first aspect
在一个或多个实施例中，根据所记录的课件操作数据来将在线教学过程中记录的音频数据的语音识别信息映射到不同的课件操作区块，进一步对于课件操作区块的语音识别信息与对应的平均状态信息进行横向来获取对比参数，最后基于课件操作区块的对比参数来获取评价值。在一个或多个实施例中，结合记录的课件操作来对音频数据进行处理，由此，可以对大量的在线教学音频数据进行较为准确的自动化评价。In one or more embodiments, the speech recognition information of the audio data recorded in the online teaching process is mapped to different courseware operation blocks according to the recorded courseware operation data. The corresponding average state information is obtained horizontally to obtain the comparison parameters, and finally the evaluation value is obtained based on the comparison parameters of the courseware operation block. In one or more embodiments, the audio data is processed in conjunction with the recorded courseware operations, so that a relatively accurate automated evaluation of a large amount of online teaching audio data can be performed.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
通过以下参照附图对本发明实施例的描述，本发明的上述以及其它目的、特征和优点将更为清楚，在附图中：The above and other objects, features, and advantages of the present invention will be more apparent from the following description of embodiments of the present invention with reference to the accompanying drawings, in which:
图1是一个或多个实施例中数据处理方法所适用的在线教学***的示意图；FIG. 1 is a schematic diagram of an online teaching system applicable to a data processing method in one or more embodiments; FIG.
图2是一个或多个实施例中在线教学应用客户端的界面示意图；2 is a schematic diagram of an interface of an online teaching application client in one or more embodiments;
图3是一个或多个实施例中数据处理方法的流程图；3 is a flowchart of a data processing method in one or more embodiments;
图4是本发明实施例的数据处理方法的一个示例的示意图；4 is a schematic diagram of an example of a data processing method according to an embodiment of the present invention;
图5是本发明实施例的电子设备的示意图。FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.
具体实施方式detailed description
以下基于实施例对本发明进行描述，但是本发明并不仅仅限于这些实施例。在下文对本发明的细节描述中，详尽描述了一些特定的细节部分。对本领域技术人员来说没有这些细节部分的描述也可以完全理解本发明。为了避免混淆本发明的实质，公知的方法、过程、流程、元件和电路并没有详细叙述。The present invention is described below based on examples, but the present invention is not limited to these examples. In the following detailed description of the present invention, some specific details are described in detail. To those skilled in the art, the present invention can be fully understood without the description of these details. In order to avoid obscuring the essence of the present invention, well-known methods, procedures, processes, components, and circuits have not been described in detail.
此外，本领域普通技术人员应当理解，在此提供的附图都是为了说明的目的，并且附图不一定是按比例绘制的。In addition, those of ordinary skill in the art should understand that the drawings provided herein are for the purpose of illustration, and the drawings are not necessarily drawn to scale.
除非上下文明确要求，否则整个说明书和权利要求书中的“包括”、“包含”等类似词语应当解释为包含的含义而不是排他或穷举的含义；也就是说，是“包括但不限于”的含义。Unless the context clearly requires otherwise, the words "including", "comprising" and the like throughout the specification and claims should be interpreted as inclusive rather than exclusive or exhaustive; that is, "including but not limited to" Meaning.
在本发明的描述中，需要理解的是，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。此外，在本发明的描述中，除非另有说明，“多 个”的含义是两个或两个以上。In the description of the present invention, it should be understood that the terms “first”, “second”, and the like are used for descriptive purposes only, and cannot be understood to indicate or imply relative importance. In addition, in the description of the present invention, unless otherwise stated, "multiple" means two or more.
一个或多个实施例中，数据处理方法适用于基于预定的课件进行在线音视频教学的场景。图1是一个或多个实施例中数据处理方法所适用的在线教学***的示意图。如图1所示，所述在线教学***包括第一客户端1、第二客户端2和服务器3。其中，第一客户端1、第二客户端2和服务器3通过网络通信连接。第一客户端1和第二客户端2可以直接或通过服务器3间接地建立通信连接后实时通信进行在线教学的活动。一个或多个实施例中，第一客户端1由教学者操作。第二客户端2由学***板计算机、智能手机等。服务器3为运行有预定计算机应用程序的高性能数据处理设备，其可以是一台服务器，也可以分布式部署的服务器集群，还可以是以虚拟机或容器方式部署虚拟服务器集群。一个或多个实施例中，在线教学***中，大量的第一客户端1以一对一、一对多、或多对多的方式与第二客户端2建立通信连接进行通信。In one or more embodiments, the data processing method is applicable to a scenario where online audio and video teaching is performed based on a predetermined courseware. FIG. 1 is a schematic diagram of an online teaching system applicable to a data processing method in one or more embodiments. As shown in FIG. 1, the online teaching system includes a first client 1, a second client 2, and a server 3. The first client 1, the second client 2, and the server 3 are connected through a network communication. The first client 1 and the second client 2 can directly or indirectly establish a communication connection through the server 3 to perform online teaching activities after real-time communication. In one or more embodiments, the first client 1 is operated by an instructor. The second client 2 is operated by the learner, and the server 3 forms a communication connection with the first client 1 and the second client 2 at the same time, and stores the data exchanged between the two. The first client 1 and the second client 2 can access the server 3 to obtain courseware data for display, thereby implementing online teaching based on the courseware. In one or more embodiments, in the used online teaching system, the content of the courseware displayed by the first client 1 and the second client 2 changes synchronously, so that the instructor and the learner can synchronize based on the same part of the courseware communicate with. It should be understood that the first client 1 and the second client 2 may be any general-purpose data processing device running a predetermined computer application program, such as a desktop computer, a portable computer, a tablet computer, a smart phone, and the like. The server 3 is a high-performance data processing device running a predetermined computer application program. The server 3 may be a server, a server cluster deployed in a distributed manner, or a virtual server cluster deployed in a virtual machine or container manner. In one or more embodiments, in the online teaching system, a large number of first clients 1 establish a communication connection with the second client 2 in a one-to-one, one-to-many, or many-to-many manner to communicate.
图2是一个或多个实施例中在线教学应用客户端的界面示意图。如图2所示，在线教学应用客户端可以在应用界面的主窗口21显示课件，并在应用界面的子窗口22显示对方的图像采集装置采集的实时图像。一个或多个实施例中，在应用界面的子窗口22中显示的对方的上半身的视频。由此，通信的双方可以同时看到课件和对方的状态。FIG. 2 is a schematic diagram of an interface of an online teaching application client in one or more embodiments. As shown in FIG. 2, the online teaching application client can display the courseware in the main window 21 of the application interface, and display the real-time image collected by the image acquisition device of the counterpart in the sub-window 22 of the application interface. In one or more embodiments, a video of the upper body of the other party is displayed in the sub-window 22 of the application interface. As a result, both communicating parties can see the status of the courseware and the other party at the same time.
在一个或多个实施例中，在主窗口中显示的课件内容受控于教学者一端的操作进行切换或者显示轨迹。在一个或多个实施例中，教学者在第一客户端1上在课件上进行页面切换(也即，翻页)或对课件的内容进行轨迹操作。所述轨迹操作是指在课件上通过轨迹标识内容或绘制图像。例如，教学者可以通过线或者圆圈来突出标识课件的某些内容，也可以通过手写或鼠标操作通过轨迹绘制图形或文字。服务器3可以记录教学过程中教学者在第一客户端1上所施加的所有的课件操作(包括页面切换操作和轨迹操作)。在一个或多个实施例中，服务器3还可以记录教学者在整个教学过程中的音频数据以及学习者在教学过程中的音频数据。所述音频数据包括对应的语音 信息。在一个或多个实施例中，上述两种音频数据以分音轨的方式存储在同一个音频文件中。In one or more embodiments, the content of the courseware displayed in the main window is controlled by the operation of the teacher to switch or display the track. In one or more embodiments, the instructor performs page switching (ie, page turning) on the courseware on the first client 1 or performs a track operation on the content of the courseware. The trajectory operation refers to identifying content or drawing an image through a trajectory on a courseware. For example, the instructor can highlight certain content of the courseware through lines or circles, and can also draw graphics or text by trajectory through handwriting or mouse operation. The server 3 can record all courseware operations (including page switching operations and trajectory operations) applied by the teacher on the first client 1 during the teaching process. In one or more embodiments, the server 3 may also record audio data of the learner during the entire teaching process and audio data of the learner during the teaching process. The audio data includes corresponding voice information. In one or more embodiments, the above two types of audio data are stored in the same audio file in a divided audio track manner.
在一个或多个实施例中，通过对服务器3记录的音频数据以及课件操作数据进行处理，以自动化地评估教学过程。In one or more embodiments, the audio data recorded by the server 3 and the courseware operation data are processed to automatically evaluate the teaching process.
图3是一个或多个实施例中数据处理方法的流程图。如图3所示，数据处理方法包括如下步骤：FIG. 3 is a flowchart of a data processing method in one or more embodiments. As shown in Figure 3, the data processing method includes the following steps:
步骤S100，根据课件操作数据将时间轴划分为多个课件操作区块。In step S100, the time axis is divided into a plurality of courseware operation blocks according to courseware operation data.
在一个或多个实施例中，对于每一次基于在线教学***的教学，记录课件操作数据。在一个或多个实施例中，基于课件操作数据获取各课件操作的时间轴信息，也即，各课件操作在哪个时间点发生。在一个或多个实施例中，利用课件操作的时间轴信息来将教学的过程划分成不同的课件操作区块。In one or more embodiments, for each teaching based on the online teaching system, courseware operation data is recorded. In one or more embodiments, the timeline information of each courseware operation is acquired based on the courseware operation data, that is, at which point in time each courseware operation occurs. In one or more embodiments, the timeline information of courseware operation is used to divide the teaching process into different courseware operation blocks.
在一个或多个实施例中，课件操作可以包括页面切换操作和轨迹操作。基于上述两种不同的操作可以将教学的过程在两个不同的维度上划分为多个课件操作区块。在一个或多个实施例中，课件操作区块是指某一个或某几个课件操作所对应的时间区间。在一个或多个实施例中，基于页面切换操作，将整个教学过程时间轴划分为对于课件的每一页进行讲解的第一类操作区块。在一个或多个实施例中，第一类操作区块覆盖两次相邻的页面切换操作之间的时间轴，也即，第一类操作区块可以表征得到教学者对每一页课件进行讲解的时间区间信息。In one or more embodiments, the courseware operations may include page switching operations and track operations. Based on the above two different operations, the teaching process can be divided into multiple courseware operation blocks in two different dimensions. In one or more embodiments, the courseware operation block refers to a time interval corresponding to a certain courseware operation. In one or more embodiments, based on the page switching operation, the timeline of the entire teaching process is divided into first-type operation blocks that explain each page of the courseware. In one or more embodiments, the first type of operation block covers the time axis between two adjacent page switching operations, that is, the first type of operation block can be characterized as being obtained by the instructor for each page of courseware. Describe the time interval information.
在一个或多个实施例中，基于轨迹操作，可以将划分得到每次轨迹操作所对应的第二类操作区块。在一个或多个实施例中，第二类操作区块覆盖一次轨迹操作的时间轴。一个第二类操作区块为其对应的轨迹操作持续的时间区间。在一个或多个实施例中，一个第二类操作区块为该轨迹操作开始前预定时间至该轨迹操作结束后预定时间的时间区间。由此，每发生一次轨迹操作就会划分得到一个对应的第二类操作区间。In one or more embodiments, based on the trajectory operation, a second type of operation block corresponding to each trajectory operation may be obtained. In one or more embodiments, the second type of operation block covers the time axis of one trajectory operation. A second type of operation block is the time interval for which the corresponding trajectory operation lasts. In one or more embodiments, a second type of operation block is a time interval from a predetermined time before the start of the track operation to a predetermined time after the end of the track operation. Therefore, each time a trajectory operation occurs, a corresponding second-type operation interval is obtained.
例如，对于一个5页的课件，教学时间轴长度为20分钟。教学者在教学过程中进行了5次页面切换操作(包括结束操作)。同时在第4页和第5页课件上分别进行了1次划线操作以强调其中的内容。由此，如图4所示，根据页面切换操作，时间轴可以被划分为5个第一类操作区块A1-A5。每个第一类操作区块对应于教学者对一页课件的讲解时间区间。同时，在另一个维度上，根据讲解第4页和第5页课件时进行的轨迹操作，可以获得两个第二类操作区块B1和B2，每个第二类操作区块包含轨迹操作发生的时间区间。For example, for a 5-page courseware, the teaching timeline is 20 minutes long. The instructor performed 5 page switching operations (including the end operation) during the teaching process. At the same time, on the 4th and 5th courseware, one line drawing operation was performed to emphasize the content. Therefore, as shown in FIG. 4, according to the page switching operation, the time axis can be divided into five first-type operation blocks A1-A5. Each operation block of the first type corresponds to a teaching time interval of a page of courseware. At the same time, in another dimension, according to the trajectory operations performed on the 4th and 5th page of the courseware, two second-type operation blocks B1 and B2 can be obtained. Each second-type operation block contains the trajectory operation. Time interval.
在一个或多个实施例中，基于划分获得的课件操作区块，可以进一步对该时间段内的语音信息进行处理。In one or more embodiments, based on the courseware operation blocks obtained by the division, the voice information in the time period may be further processed.
步骤S200，获取音频数据中的语音信息对应的语音识别信息。Step S200: Acquire speech recognition information corresponding to the speech information in the audio data.
语音识别技术是对于包含语音信息的音频数据进行处理以获取与语音内容相关的信息的技术。在一个或多个实施例中，通过语音识别获得的语音识别信息是语音时长信息。在一个或多个实施例中，过语音识别获得的语音识别信息是语音信息对应的文本信息。The speech recognition technology is a technology that processes audio data containing speech information to obtain information related to speech content. In one or more embodiments, the voice recognition information obtained through voice recognition is voice duration information. In one or more embodiments, the voice recognition information obtained through voice recognition is text information corresponding to the voice information.
在一个或多个实施例中，文本信息可以体现教学过程中教学者讲解的具体内容，其可以作为后续评估的基础。在一个或多个实施例中，语音时长信息是指音频数据中检测到语音的时间轴信息。在一个或多个实施例中，在教学过程中，教学者可能并不是持续地在进行讲解，语音时长信息一定程度上可以反映教学者与学习者交流的强度。在一个或多个实施例中，获取的语音识别信息同时也带有时间轴信息。在一个或多个实施例中，对于文本信息，所述时间轴信息表征文本中的文字内容对应在时间轴上的时间。在一个或多个实施例中，对于语音时长信息，时间轴信息表征语音时长的起点时间和终点时间。In one or more embodiments, the text information can reflect the specific content explained by the teacher during the teaching process, which can be used as the basis for subsequent evaluation. In one or more embodiments, the speech duration information refers to time axis information of the detected speech in the audio data. In one or more embodiments, during the teaching process, the teacher may not be continuously explaining, and the speech duration information may reflect the intensity of the communication between the teacher and the learner to a certain extent. In one or more embodiments, the acquired speech recognition information also carries time axis information. In one or more embodiments, for text information, the time axis information characterizes the text content in the text corresponding to the time on the time axis. In one or more embodiments, for the speech duration information, the time axis information represents a start time and an end time of the speech duration.
在一个或多个实施例中，从音频数据中提取文本信息和语音时长信息中的至少一项作为进行评估的基础。In one or more embodiments, at least one of text information and speech duration information is extracted from audio data as a basis for evaluation.
在一个或多个实施例中，本步骤处理的音频数据的时间轴应预先与课件操作数据的时间轴同步对齐，以保证后续处理的准确性。In one or more embodiments, the time axis of the audio data processed in this step should be synchronized with the time axis of the courseware operation data in advance to ensure the accuracy of subsequent processing.
在一个或多个实施例中，步骤S200可以与步骤S100以任意顺序先后执行，在一个或多个实施例中，步骤S200可以与步骤S100同时执行。In one or more embodiments, step S200 may be performed sequentially with step S100 in any order. In one or more embodiments, step S200 may be performed simultaneously with step S100.
在步骤S300，根据所述课件操作的时间轴信息将所述语音识别信息映射到对应的课件操作区块内。In step S300, the speech recognition information is mapped into the corresponding courseware operation block according to the timeline information of the courseware operation.
在一个或多个实施例中，映射是指根据语音识别信号所带的时间轴信息，将课件操作区块涉及的时间区间所对应的语音识别信息提取出来，并和课件操作区块建立关联的过程。In one or more embodiments, mapping refers to extracting the speech recognition information corresponding to the time interval involved in the courseware operation block according to the time axis information carried by the speech recognition signal, and establishing association with the courseware operation block. process.
在一个或多个实施例中，语音识别信息包括文本信息和语音时长信息。在一个或多个实施例中，对文本信息进行两次映射，将文本信息按照其对应的时间轴映射到各个第一类操作区块中，这使得文本信息被划分为多个部分，每个部分对应一个第一类操作区块。在一个或多个实施例中，文本信息还被映射到各个第二类操作区块中， 这使得文本信息中与轨迹操作发生时间区间相关的部分被提取，并与对应的轨迹操作(或第二类操作区块)建立关联。例如，在某个教学过程中，对于课件第5页，教学者进行了30秒的轨迹操作。则该30秒时间区间内或加上其前后30秒共90秒的时间区间内对应文本信息会被提取并与该轨迹操作建立关联。同时，整个课件第5页讲解过程中的所有文本信息(包括30秒轨迹操作过程中的文本信息)会被映射到对应的第一类操作区块，也即，第5页课件所对应的课件操作区块。在一个或多个实施例中，对于语音时长信息，也进行两次映射。在一个或多个实施例中，语音时长信息根据时间轴分布映射到各个第一类操作区块中，这使得每个第一类操作区块可以具有一个语音时长属性，该属性可以标识在该页课件的讲解过程中教学者进行讲解的时间长度。在一个或多个实施例中，语音时长信息还被映射到各个第二类操作区块中，这使得每个第二类操作区块(也即，每个轨迹操作)与教学者在进行轨迹操作期间的语音时长信息建立关联。In one or more embodiments, the speech recognition information includes text information and speech duration information. In one or more embodiments, the text information is mapped twice, and the text information is mapped to each first-type operation block according to its corresponding time axis, which makes the text information divided into multiple parts, each Part corresponds to a first type of operation block. In one or more embodiments, the text information is also mapped to each second-type operation block, so that the part of the text information related to the time interval where the trajectory operation occurs is extracted and related to the corresponding trajectory operation (or the first The second type of operation block) establishes an association. For example, in a certain teaching process, for page 5 of the courseware, the instructor performed a 30-second trajectory operation. The corresponding text information will be extracted and associated with the trajectory operation within the 30-second time interval or within the time interval of 30 seconds before and after the total of 90 seconds. At the same time, all text information (including text information during the 30-second trajectory operation process) on page 5 of the entire courseware will be mapped to the corresponding first-type operation block, that is, the courseware corresponding to page 5 Operation block. In one or more embodiments, the speech duration information is also mapped twice. In one or more embodiments, the speech duration information is mapped into each first-type operation block according to the time axis distribution, which allows each first-type operation block to have a speech duration attribute, which can be identified in the The length of time the educator is explaining during the course of the page courseware. In one or more embodiments, the speech duration information is also mapped into each second-type operation block, which enables each second-type operation block (that is, each trajectory operation) to perform trajectory with the instructor. The voice duration information during operation is associated.
在一个或多个实施例中，通过映射可以获得如下数据：In one or more embodiments, the following data can be obtained through mapping:
(1)每个课件页面内教学者讲授内容的文本信息；(1) Text information of the content taught by the instructor on each courseware page;
(2)每个课件页面内教学者讲授内容的语音时长信息；(2) Voice duration information of the lecturer's content on each courseware page;
(3)每次教学者进行轨迹操作期间讲授内容的文本信息；以及(3) text information of the content taught during each trajectory operation by the instructor; and
(4)每次教学者进行轨迹操作期间讲授内容的语音时长信息。(4) Voice duration information of the teaching content during each trajectory operation performed by the instructor.
在一个或多个实施例中，将上述信息与其它教学者在讲授相同的课件时的对应信息进行横向比较。在一个或多个实施例中，相同教学者讲授同一课件的信息也可以作为横向比较的基础。在一个或多个实施例中，该比较可以标识出在上述四个维度中，当前处理的音频数据的内容是否与其他教学者或其它教学过程存在较大的差异，或者说，大幅度地偏离平均值。In one or more embodiments, the above information is compared horizontally with corresponding information of other instructors when teaching the same courseware. In one or more embodiments, the same lecturer's information on the same courseware can also be used as a basis for horizontal comparison. In one or more embodiments, the comparison can identify whether the content of the currently processed audio data is significantly different from other teachers or other teaching processes in the above four dimensions, or that it deviates significantly. average value.
在一个或多个实施例中，在不存在轨迹操作或轨迹操作并不是评估的重点时，可以不对第二类操作区块进行映射。在一个或多个实施例中，仅对上述语音识别信息中的一项进行映射，以减少计算负担，加快数据处理的速度。In one or more embodiments, when there is no trajectory operation or the trajectory operation is not the focus of the evaluation, the second type of operation block may not be mapped. In one or more embodiments, only one of the above-mentioned speech recognition information is mapped to reduce the calculation load and speed up the data processing speed.
步骤S400，将每个课件操作区块内的所述语音识别信息与对应的平均状态信息比较以获取对应的对比参数。在一个或多个实施例中，每个课件操作区块对应于至少一个对比参数。在一个或多个实施例中，所述平均状态信息用于表征其它针对相同课件的教学过程中上述不同维度信息的平均状态。Step S400: Compare the speech recognition information in each courseware operation block with corresponding average state information to obtain corresponding comparison parameters. In one or more embodiments, each courseware operation block corresponds to at least one comparison parameter. In one or more embodiments, the average state information is used to characterize the average state of the above-mentioned different dimension information in other teaching processes for the same courseware.
在一个或多个实施例中，通过如下方式来获取文本信息的平均状态信息。在文 本处理中，通常采用向量空间模型(VSM)来标识文本。向量空间模型以一个向量来表征一段文本信息，向量中的每一项为特征项的权重。特征项可以是文本中信息的字、词或词组。通过分词以及统计词频等操作，就可以获取到文本的特征项以及特征项的权重。如果必要的话，可以对向量进行特征提取，降低向量的维数以降低数据处理的计算量。经过提取后的特征向量为文本信息在一个预定的特征空间中的映射，其可以唯一地表征文本信息。由此，在对于大量的同类文本进行向量化操作以及特征提取后，就可以获得每个文本对应的特征向量。这些特征向量的平均值就可以作为这一类文本信息的平均状态信息。在一个或多个实施例中，上述过程中的分词、词频统计、文本的向量化表达以及特征提取均可以采用现有的各种文本处理技术来实现。In one or more embodiments, the average state information of the text information is obtained as follows. In text processing, a vector space model (VSM) is often used to identify text. The vector space model uses a vector to represent a piece of text information, and each item in the vector is the weight of the feature item. Feature items can be words, words, or phrases of information in the text. Through word segmentation and statistical word frequency operations, the feature terms of the text and their weights can be obtained. If necessary, feature extraction can be performed on the vector to reduce the dimensionality of the vector to reduce the amount of data processing calculations. The extracted feature vector is a mapping of text information in a predetermined feature space, which can uniquely characterize the text information. Therefore, after performing a vectorization operation and feature extraction on a large number of similar texts, a feature vector corresponding to each text can be obtained. The average of these feature vectors can be used as the average state information of this type of text information. In one or more embodiments, the word segmentation, word frequency statistics, vectorized expression of text, and feature extraction in the above process can be implemented using various existing text processing technologies.
在一个或多个实施例中，对文本信息与平均状态信息进行比较的操作可以通过计算文本信息对应的特征向量和平均状态信息在特征空间中的距离或者在某一投影平面上的夹角来实现。所述距离和夹角的数值就可以表征文本信息与平均状态信息之间的差异程度，从而作为所述的对比参数。In one or more embodiments, the operation of comparing the text information with the average state information may be performed by calculating the distance between the feature vector corresponding to the text information and the average state information in the feature space or the included angle on a certain projection plane. achieve. The values of the distance and the included angle can represent the degree of difference between the text information and the average state information, so as to serve as the comparison parameter.
在一个或多个实施例中，通过如下方式来获取语音时长信息的平均状态信息。由于语音时长信息实际上就是一个数值，因此，可以直接求取平均值作为语音时长信息的平均状态信息。在一个或多个实施例中，通过比较语音时长信息和平均值就可以表征语音时长信息与平均状态信息的差异程度。该差异程度可以作为所述的对比参数。In one or more embodiments, the average state information of the voice duration information is obtained in the following manner. Since the speech duration information is actually a numerical value, an average value can be directly obtained as the average state information of the speech duration information. In one or more embodiments, by comparing the speech duration information and the average value, the degree of difference between the speech duration information and the average state information can be characterized. This degree of difference can be used as the comparison parameter.
步骤S500，根据所述课件操作区块的所述对比参数获取评价值。Step S500: Obtain an evaluation value according to the comparison parameter of the courseware operation block.
在一个或多个实施例中，根据所有的课件操作区块的对比参数来获取所述评价值。In one or more embodiments, the evaluation value is obtained according to comparison parameters of all courseware operation blocks.
在一个或多个实施例中，选择性地仅选择一部分课件操作区块的对比参数来获取所述评价值。In one or more embodiments, only a part of the comparison parameters of courseware operation blocks is selectively selected to obtain the evaluation value.
在一个或多个实施例中，所述评价值可以通过对不同的课件操作区块的对比参数加权求和计算获得。不同的课件操作区块可以具有不同的权重，不同的对比参数也可以具有不同的权重。In one or more embodiments, the evaluation value may be obtained by weighted summation of comparison parameters of different courseware operation blocks. Different courseware operation blocks can have different weights, and different contrast parameters can also have different weights.
在一个或多个实施例中，步骤S500包括如下子步骤：In one or more embodiments, step S500 includes the following sub-steps:
步骤S510，对于每个课件操作区块对应的多个对比参数加权求和以获取所述课件操作区块的评价指数。In step S510, a plurality of comparison parameters corresponding to each courseware operation block are weighted and summed to obtain an evaluation index of the courseware operation block.
步骤S520，根据每个课件操作区块的权重计算所有课件操作区块的评价指数的加权和作为所述评价值。Step S520: Calculate a weighted sum of evaluation indexes of all courseware operation blocks according to the weight of each courseware operation block as the evaluation value.
仍然以图4所示的例子为例，对于第一类操作区块A1-A5以及第二类操作区块B1和B2。在步骤S200，音频数据中的语音信息被识别，从而获得对应的文本信息以及语音时长信息。上述信息均带有时间轴相关信息。在步骤S300，带有教学者针对每一页课件讲解的文本信息和语音时长信息被分别映射到第一类操作区块A1-A5。教学者两次轨迹操作期间的文本信息(与其语音信息对应)和语音时长信息被分别映射到操作区块B1和B2。在步骤S400，将第一类操作区块A1-A5的文本信息X1-X5分别与对应的平均状态信息Y1-Y5比较，由此，获取得到每个第一类操作区块A1-A5的文本信息对比参数a1-a5。将第一类操作区块A1-A5的语音时长信息T1-T5与对应的平均状态信息Q1-Q5比较，由此获取每个第一类操作区块A1-A5的语音时长信息对比参数b1-b5。同时，将第二类操作区块B1和B2的文本信息X6和X7分别与对应的平均状态信息Y6和Y7比较，由此获取每个第二类操作区块B1和B2的文本信息对比参数c1和c2。将第二类操作区块B1和B2的语音时长信息T6和T7分别与对应的平均状态信息Q6、Q7比较，由此获取每个第二类操作区块B1和B2的语音时长对比参数d1和d2。在步骤S500,第一类操作区块A1-A5分别被预先赋予权重w1-w5，第二类操作区块B1-B2分别被赋予权重bw1和bw2。由于第二类操作区块具有一定的不确定性，因此，也可以全部赋予相同的权重。同时，文本信息被赋予权重W1，语音时长信息被赋予权重W2。在一个或多个实施例中，通过如下加权计算公式来计算评价值：Still taking the example shown in FIG. 4 as an example, for the first type of operation blocks A1-A5 and the second type of operation blocks B1 and B2. In step S200, the voice information in the audio data is identified, thereby obtaining corresponding text information and voice duration information. The above information has timeline related information. In step S300, the text information and speech duration information with the lecturer's explanation for each page of courseware are mapped to the first-type operation blocks A1-A5, respectively. The text information (corresponding to its voice information) and voice duration information during the two trajectory operations of the teacher are mapped to the operation blocks B1 and B2, respectively. In step S400, the text information X1-X5 of the first-type operation blocks A1-A5 are respectively compared with the corresponding average state information Y1-Y5, thereby obtaining the text of each first-type operation block A1-A5. Information comparison parameters a1-a5. Compare the speech duration information T1-T5 of the first type of operation blocks A1-A5 with the corresponding average state information Q1-Q5, thereby obtaining the speech duration information comparison parameter b1- of each first type of operation block A1-A5 b5. At the same time, the text information X6 and X7 of the second type of operation blocks B1 and B2 are compared with the corresponding average state information Y6 and Y7, respectively, thereby obtaining the text information comparison parameter c1 of each second type of operation blocks B1 and B2. And c2. Compare the speech duration information T6 and T7 of the second type of operation blocks B1 and B2 with the corresponding average state information Q6 and Q7 respectively, thereby obtaining the speech duration comparison parameters d1 and d2. In step S500, the first-type operation blocks A1-A5 are respectively given weights w1-w5 in advance, and the second-type operation blocks B1-B2 are respectively given weights bw1 and bw2. Since the second type of operation block has a certain degree of uncertainty, all of them can be given the same weight. At the same time, text information is given a weight W1, and speech duration information is given a weight W2. In one or more embodiments, the evaluation value is calculated by the following weighted calculation formula:
Figure PCTCN2019081589-appb-000001
Figure PCTCN2019081589-appb-000001
其中，W1·ai+W2·bi为第一类操作区块Ai的评价指标，W1·ci+W2·di为第二类操作区块Bi的评价指标。Among them, W1 · ai + W2 · bi is the evaluation index of the first type of operation block Ai, and W1 · ci + W2 · di is the evaluation index of the second type of operation block Bi.
从另一个角度来说，可以认为：第一类操作区块A1-A5的文本信息被分配了预定的权重W1*wi，i＝1,2,…,5；第一类操作区块A1-A5的语音时长信息被分配了预定的权重W2*wi，i＝1,2,…,5；第二类操作区块B1-B2的文本信息被分配了预定的权重W1*bwi，i＝1或2；第二类操作区块B1-B2的语音时长信息被分配了预定的权重W2*bwi，i＝1或2。From another perspective, it can be considered that the text information of the first type of operation block A1-A5 is assigned a predetermined weight W1 * wi, i = 1, 2, ..., 5; the first type of operation block A1- The voice duration information of A5 is assigned a predetermined weight W2 * wi, i = 1,2, ..., 5; the text information of the second type of operation block B1-B2 is assigned a predetermined weight W1 * bwi, i = 1 Or 2; the voice duration information of the second type of operation blocks B1-B2 is assigned a predetermined weight W2 * bwi, i = 1 or 2.
在一个或多个实施例中，上述权重可以由操作者根据对课件的了解和经验进行设定。例如，可以对比较重要的课件页面设置较高的权重。又例如，在比较重视讲述内容时，对于文本信息赋予较高的权重。In one or more embodiments, the foregoing weights may be set by an operator based on the knowledge and experience of the courseware. For example, you can set a higher weight for more important courseware pages. As another example, when the narrative content is more important, the text information is given a higher weight.
应理解，以上所述的过程仅为示例，在一个或多个实施例中，减少一部分数据处理过程以降低计算量。例如，可以不对轨迹操作进行映射，仅对每个第一类操作区块进行映射、对比以及评价值计算。在一个或多个实施例中，将在第一类操作区块内是否存在轨迹操作作为每个第一类操作区块的附加信息，在计算评价值时予以考虑。It should be understood that the process described above is merely an example. In one or more embodiments, a part of the data processing process is reduced to reduce the calculation amount. For example, the trajectory operation may not be mapped, and only mapping, comparison, and evaluation value calculation may be performed for each first-type operation block. In one or more embodiments, whether or not there is a trajectory operation in the first-type operation block is taken as additional information of each first-type operation block, and is considered in calculating the evaluation value.
在一个或多个实施例中，所述数据处理方法还可以包括步骤S600，展示步骤S500获得的评价值或展示各课件操作区块的对比参数。例如，可以采用雷达图的方式来展示不同维度的评价。由此，可以根据通过评价值或根据对比参数的展示了解教学过程的情况。同时，也为教学质量的评价提供了较为客观的评价依据。In one or more embodiments, the data processing method may further include step S600, displaying an evaluation value obtained in step S500 or displaying a comparison parameter of each courseware operation block. For example, radar charts can be used to show evaluations in different dimensions. As a result, you can understand the teaching process based on the evaluation value or the display of comparative parameters. At the same time, it also provides a more objective evaluation basis for the evaluation of teaching quality.
在一个或多个实施例中，根据所记录的课件操作数据来将在线教学过程中记录的音频数据的语音识别信息映射到不同的课件操作区块，进一步对于课件操作区块的语音识别信息与对应的平均状态信息进行横向来获取对比参数，最后基于课件操作区块的对比参数来获取评价值。在一个或多个实施例中，结合记录的课件操作来对音频数据进行处理，由此，可以对大量的在线教学音频数据进行较为准确的自动化评价。In one or more embodiments, the speech recognition information of the audio data recorded in the online teaching process is mapped to different courseware operation blocks according to the recorded courseware operation data. The corresponding average state information is obtained horizontally to obtain the comparison parameters, and finally the evaluation value is obtained based on the comparison parameters of the courseware operation block. In one or more embodiments, the audio data is processed in conjunction with the recorded courseware operations, so that a relatively accurate automated evaluation of a large amount of online teaching audio data can be performed.
图5是本发明实施例的电子设备的示意图。图5所示的电子设备为通用数据处理装置，其包括通用的计算机硬件结构，其至少包括处理器51和存储器52。处理器51和存储器52通过总线53连接。存储器52适于存储处理器51可执行的指令或程序。处理器51可以是独立的微处理器，也可以是多个微处理器的集合。由此，处理器51通过执行存储器52所存储的命令，从而执行如上所述的本发明实施例的方法流程实现对于数据的处理和对于其他装置的控制。总线53将上述多个组件连接在一起，同时将上述组件连接到显示控制器54和显示装置以及输入/输出(I/O)装置55。输入/输出(I/O)装置55可以是鼠标、键盘、调制解调器、网络接口、触控输入装置、体感输入装置、打印机以及本领域公知的其他装置。典型地，输入/输出(I/O)装置55通过输入/输出(I/O)控制器56与***相连。FIG. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device shown in FIG. 5 is a general-purpose data processing apparatus including a general-purpose computer hardware structure including at least a processor 51 and a memory 52. The processor 51 and the memory 52 are connected via a bus 53. The memory 52 is adapted to store instructions or programs executable by the processor 51. The processor 51 may be an independent microprocessor or a collection of multiple microprocessors. Therefore, the processor 51 executes the commands stored in the memory 52, thereby executing the method flow of the embodiment of the present invention as described above to implement data processing and control on other devices. The bus 53 connects the above-mentioned multiple components together, and simultaneously connects the above-mentioned components to the display controller 54 and the display device, and an input / output (I / O) device 55. The input / output (I / O) device 55 may be a mouse, keyboard, modem, network interface, touch input device, somatosensory input device, printer, and other devices known in the art. Typically, an input / output (I / O) device 55 is connected to the system through an input / output (I / O) controller 56.
其中，存储器52可以存储软件组件，例如操作***、通信模块、交互模块以及应用程序。以上所述的每个模块和应用程序都对应于完成一个或多个功能和在发明实施例中描述的方法的一组可执行程序指令。The memory 52 may store software components, such as an operating system, a communication module, an interaction module, and an application program. Each module and application described above corresponds to a set of executable program instructions that perform one or more functions and methods described in the embodiments of the invention.
上述根据本发明实施例的方法、设备(***)和计算机程序产品的流程图和/或框图描述了本发明的各个方面。应理解，流程图和/或框图的每个块以及流程图图例和/或框图中的块的组合可以由计算机程序指令来实现。这些计算机程序指令可以被提供至通用计算机、专用计算机或其它可编程数据处理设备的处理器，以产生机器，使得 (经由计算机或其它可编程数据处理设备的处理器执行的)指令创建用于实现流程图和/或框图块或块中指定的功能/动作的装置。The above flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present invention describe various aspects of the present invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing device to produce a machine such that the instructions (executed by the processor of the computer or other programmable data processing device) are created for implementation Flowcharts and / or block diagrams or means of functioning specified in a block.
同时，如本领域技术人员将意识到的，本发明实施例的各个方面可以被实现为***、方法或计算机程序产品。因此，本发明实施例的各个方面可以采取如下形式：完全硬件实施方式、完全软件实施方式(包括固件、常驻软件、微代码等)或者在本文中通常可以都称为“电路”、“模块”或“***”的将软件方面与硬件方面相结合的实施方式。此外，本发明的方面可以采取如下形式：在一个或多个计算机可读介质中实现的计算机程序产品，计算机可读介质具有在其上实现的计算机可读程序代码。Meanwhile, as those skilled in the art will appreciate, various aspects of the embodiments of the present invention may be implemented as a system, method or computer program product. Therefore, various aspects of the embodiments of the present invention may take the following forms: a completely hardware implementation, a completely software implementation (including firmware, resident software, microcode, etc.) or may generally be referred to herein as "circuits", "modules" "Or" system "implementations that combine software and hardware aspects. Furthermore, aspects of the invention may take the form of a computer program product implemented in one or more computer-readable media, the computer-readable medium having computer-readable program code implemented thereon.
可以利用一个或多个计算机可读介质的任意组合。计算机可读介质可以是计算机可读信号介质或计算机可读存储介质。计算机可读存储介质可以是如(但不限于)电子的、磁的、光学的、电磁的、红外的或半导体***、设备或装置，或者前述的任意适当的组合。计算机可读存储介质的更具体的示例(非穷尽列举)将包括以下各项：具有一根或多根电线的电气连接、便携式计算机软盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或闪速存储器)、光纤、便携式光盘只读存储器(CD-ROM)、光存储装置、磁存储装置或前述的任意适当的组合。在本发明实施例的上下文中，计算机可读存储介质可以为能够包含或存储由指令执行***、设备或装置使用的程序或结合指令执行***、设备或装置使用的程序的任意有形介质。Any combination of one or more computer-readable media may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media would include the following: electrical connections with one or more wires, portable computer floppy disks, hard disks, random access memory (RAM), read-only memory ( ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the context of embodiments of the present invention, a computer-readable storage medium may be any tangible medium capable of containing or storing a program used by or in conjunction with an instruction execution system, device, or device.
计算机可读信号介质可以包括传播的数据信号，所述传播的数据信号具有在其中如在基带中或作为载波的一部分实现的计算机可读程序代码。这样的传播的信号可以采用多种形式中的任何形式，包括但不限于：电磁的、光学的或其任何适当的组合。计算机可读信号介质可以是以下任意计算机可读介质：不是计算机可读存储介质，并且可以对由指令执行***、设备或装置使用的或结合指令执行***、设备或装置使用的程序进行通信、传播或传输。The computer-readable signal medium may include a propagated data signal having computer-readable program code implemented therein, such as in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. The computer-readable signal medium may be any of the following computer-readable media: not a computer-readable storage medium, and may communicate and propagate a program used by or in conjunction with an instruction execution system, device, or device Or transmission.
用于执行针对本发明各方面的操作的计算机程序代码可以以一种或多种编程语言的任意组合来编写，所述编程语言包括：面向对象的编程语言如Java、Smalltalk、C++、PHP、Python等；以及常规过程编程语言如“C”编程语言或类似的编程语言。程序代码可以作为独立软件包完全地在用户计算机上、部分地在用户计算机上执行。部分地在用户计算机上且部分地在远程计算机上执行；或者完全地在远程计算机或服务器上执行。在后一种情况下，可以将远程计算机通过包括局域网(LAN)或广域网 (WAN)的任意类型的网络连接至用户计算机，或者可以与外部计算机进行连接(例如通过使用因特网服务供应商的因特网)。Computer program code for performing operations directed to aspects of the present invention may be written in any combination of one or more programming languages, including: object-oriented programming languages such as Java, Smalltalk, C ++, PHP, Python Etc .; and conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can be executed entirely on the user's computer as a stand-alone software package, and partially on the user's computer. Performed partially on the user's computer and partially on the remote computer; or entirely on the remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any type of network including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (for example, by using the Internet of an Internet service provider) .
以上所述仅为本发明的优选实施例，并不用于限制本发明，对于本领域技术人员而言，本发明可以有各种改动和变化。凡在本发明的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims (12)

  1. 一种数据处理方法，其特征在于，所述方法包括：A data processing method, characterized in that the method includes:
    根据课件操作数据将时间轴划分为多个课件操作区块；Divide the timeline into multiple courseware operation blocks according to courseware operation data;
    获取音频数据中的语音信息对应的语音识别信息；Obtaining speech recognition information corresponding to the speech information in the audio data;
    根据时间轴信息将所述语音识别信息映射到对应的课件操作区块；Map the speech recognition information to the corresponding courseware operation block according to the time axis information;
    对于每个课件操作区块，将映射后的所述语音识别信息与对应的平均状态信息比较以获取对比参数，其中，每个课件操作区块对应于至少一个对比参数；For each courseware operation block, comparing the mapped speech recognition information with corresponding average state information to obtain comparison parameters, wherein each courseware operation block corresponds to at least one comparison parameter;
    根据所述课件操作区块的所述对比参数获取评价值。Obtain an evaluation value according to the comparison parameter of the courseware operation block.
  2. 根据权利要求1所述的数据处理方法，其特征在于，所述方法还包括：The data processing method according to claim 1, wherein the method further comprises:
    展示所述评价值；和/或Display said rating; and / or
    展示各课件操作区块的所述对比参数。The comparison parameters of each courseware operation block are shown.
  3. 根据权利要求1所述的数据处理方法，其特征在于，所述语音识别信息包括所述语音信息对应的文本信息；The data processing method according to claim 1, wherein the voice recognition information includes text information corresponding to the voice information;
    将每个课件操作区块内的所述语音识别信息与对应的平均状态信息比较以获取对应的对比参数包括：Comparing the speech recognition information in each courseware operation block with corresponding average state information to obtain corresponding comparison parameters includes:
    将每个课件操作区块内的所述文本信息与对应的文本平均状态信息比较以获得第一对比参数。The text information in each courseware operation block is compared with corresponding text average state information to obtain a first comparison parameter.
  4. 根据权利要求1所述的数据处理方法，其特征在于，所述语音识别信息包括所述语音信息对应的语音时长信息；The data processing method according to claim 1, wherein the voice recognition information includes voice duration information corresponding to the voice information;
    将每个课件操作区块内的所述语音识别信息与对应的平均状态信息比较以获取对应的对比参数包括：Comparing the speech recognition information in each courseware operation block with corresponding average state information to obtain corresponding comparison parameters includes:
    将每个课件操作区块内的所述语音时长信息与对应的语音时长平均状态信息比较以获得第二对比参数。Compare the speech duration information in each courseware operation block with the corresponding average speech duration status information to obtain a second comparison parameter.
  5. 根据权利要求1所述的数据处理方法，其特征在于，所述语音识别信息包括所述语音信息对应的文本信息和语音时长信息；The data processing method according to claim 1, wherein the voice recognition information includes text information and voice duration information corresponding to the voice information;
    将每个课件操作区块内的所述语音识别信息与对应的平均状态信息比较以获取对应的对比参数包括：Comparing the speech recognition information in each courseware operation block with corresponding average state information to obtain corresponding comparison parameters includes:
    将每个课件操作区块内的所述文本信息与对应的文本平均状态信息比较以获得第一对比参数；Comparing the text information in each courseware operation block with corresponding text average state information to obtain a first comparison parameter;
    将每个课件操作区块内的所述语音时长信息与对应的语音时长平均状态信息比 较以获得第二对比参数。The speech duration information in each courseware operation block is compared with corresponding speech duration average state information to obtain a second comparison parameter.
  6. 根据权利要求1所述的数据处理方法，其特征在于，所述平均状态信息根据对于相同课件的多个课件操作数据以及对应的音频数据获得。The data processing method according to claim 1, wherein the average state information is obtained according to a plurality of courseware operation data and corresponding audio data for the same courseware.
  7. 根据权利要求1所述的数据处理方法，其特征在于，所述课件操作数据包括页面切换操作的记录；所述课件操作区块包括与所述页面切换操作对应的第一类操作区块，其中，所述第一类操作区块覆盖两次相邻的页面切换操作之间的时间轴。The data processing method according to claim 1, wherein the courseware operation data includes a record of a page switching operation; the courseware operation block includes a first type of operation block corresponding to the page switching operation, wherein The first type of operation block covers a time axis between two adjacent page switching operations.
  8. 根据权利要求1所述的数据处理方法，其特征在于，所述课件操作数据包括轨迹操作的记录，所述课件操作区块包括与所述轨迹操作对应的第二类操作区块，其中，所述第二类操作区块覆盖一次轨迹操作的时间轴。The data processing method according to claim 1, wherein the courseware operation data includes a record of a trajectory operation, and the courseware operation block includes a second type of operation block corresponding to the trajectory operation, wherein, all The second type of operation block covers the time axis of a trajectory operation.
  9. 根据权利要求1所述的数据处理方法，其特征在于，至少根据所有课件操作区块的所述对比参数获取评价值包括：The data processing method according to claim 1, wherein obtaining the evaluation value according to at least the comparison parameters of all courseware operation blocks comprises:
    根据每个课件操作区块的权重计算所有课件操作区块对应的对比参数的加权和作为所述评价值。A weighted sum of comparison parameters corresponding to all courseware operation blocks is calculated according to the weight of each courseware operation block as the evaluation value.
  10. 根据权利要求1所述的数据处理方法，其特征在于，根据所述课件操作区块的所述对比参数获取评价值包括：The data processing method according to claim 1, wherein obtaining an evaluation value according to the comparison parameter of the courseware operation block comprises:
    对于每个课件操作区块对应的多个对比参数加权求和以获取所述课件操作区块的评价指数；Weighting and summing a plurality of comparison parameters corresponding to each courseware operation block to obtain an evaluation index of the courseware operation block;
    根据每个课件操作区块的权重计算所有课件操作区块的评价指数的加权和作为所述评价值。A weighted sum of evaluation indexes of all courseware operation blocks is calculated according to the weight of each courseware operation block as the evaluation value.
  11. 一种计算机可读存储介质，其上存储计算机程序指令，其特征在于，所述计算机程序指令在被处理器执行时实现如权利要求1-10中任一项所述的方法。A computer-readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method according to any one of claims 1-10.
  12. 一种电子设备，包括存储器和处理器，其特征在于，所述存储器用于存储一条或多条计算机程序指令，其中，所述一条或多条计算机程序指令被所述处理器执行以实现如权利要求1-10中任一项所述的方法。An electronic device includes a memory and a processor, characterized in that the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement a right The method according to any one of claims 1 to 10.
PCT/CN2019/081589 2018-07-11 2019-04-04 Data processing method, storage medium and electronic device WO2020010882A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810758220.9A CN108877771B (en) 2018-07-11 2018-07-11 Data processing method, storage medium and electronic device
CN201810758220.9 2018-07-11

Publications (1)

Publication Number Publication Date
WO2020010882A1 true WO2020010882A1 (en) 2020-01-16

Family

ID=64301076

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/081589 WO2020010882A1 (en) 2018-07-11 2019-04-04 Data processing method, storage medium and electronic device

Country Status (2)

Country Link
CN (1) CN108877771B (en)
WO (1) WO2020010882A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108877771B (en) * 2018-07-11 2021-01-26 北京大米科技有限公司 Data processing method, storage medium and electronic device
CN108962221B (en) * 2018-07-12 2020-08-04 苏州思必驰信息科技有限公司 Optimization method and system of online dialog state tracking model
CN110650369B (en) * 2019-09-29 2021-09-17 北京谦仁科技有限公司 Video processing method and device, storage medium and electronic equipment
CN112735392B (en) * 2020-12-31 2024-04-16 中国科学技术大学 Voice processing method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530837A (en) * 2013-10-28 2014-01-22 苏州市思玛特电力科技有限公司 Teaching evaluation system
CN106851216A (en) * 2017-03-10 2017-06-13 山东师范大学 A kind of classroom behavior monitoring system and method based on face and speech recognition
CN107277598A (en) * 2016-04-07 2017-10-20 北京文香信息技术有限公司 For the net cast VOD system of teaching
CN107609736A (en) * 2017-08-09 2018-01-19 广州思涵信息科技有限公司 A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology
CN107920280A (en) * 2017-03-23 2018-04-17 广州思涵信息科技有限公司 The accurate matched method and system of video, teaching materials PPT and voice content
CN108877771A (en) * 2018-07-11 2018-11-23 北京大米科技有限公司 data processing method, storage medium and electronic equipment

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070124142A1 (en) * 2005-11-25 2007-05-31 Mukherjee Santosh K Voice enabled knowledge system
CN102509482A (en) * 2011-11-15 2012-06-20 北京瑞信在线***技术有限公司 Multimedia teaching system based on mobile terminal framework
CN106127631A (en) * 2016-06-15 2016-11-16 汤美 The teaching-course manager method and system of network courses
CN106228668A (en) * 2016-07-19 2016-12-14 张庆 A kind of hand-held classroom comprehensive data acquisition evaluates scoring device
CN107240047B (en) * 2017-05-05 2020-12-08 广州盈可视电子科技有限公司 Score evaluation method and device for teaching video
CN107545791B (en) * 2017-08-29 2020-03-06 广州思涵信息科技有限公司 System and method for automatically generating classroom teaching knowledge map by courseware

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103530837A (en) * 2013-10-28 2014-01-22 苏州市思玛特电力科技有限公司 Teaching evaluation system
CN107277598A (en) * 2016-04-07 2017-10-20 北京文香信息技术有限公司 For the net cast VOD system of teaching
CN106851216A (en) * 2017-03-10 2017-06-13 山东师范大学 A kind of classroom behavior monitoring system and method based on face and speech recognition
CN107920280A (en) * 2017-03-23 2018-04-17 广州思涵信息科技有限公司 The accurate matched method and system of video, teaching materials PPT and voice content
CN107609736A (en) * 2017-08-09 2018-01-19 广州思涵信息科技有限公司 A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology
CN108877771A (en) * 2018-07-11 2018-11-23 北京大米科技有限公司 data processing method, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN108877771A (en) 2018-11-23
CN108877771B (en) 2021-01-26

Similar Documents

Publication Publication Date Title
WO2020010882A1 (en) Data processing method, storage medium and electronic device
US11908483B2 (en) Inter-channel feature extraction method, audio separation method and apparatus, and computing device
Spikol et al. Estimation of success in collaborative learning based on multimodal learning analytics features
CN109698920A (en) It is a kind of that tutoring system is followed based on internet teaching platform
CN109801194A (en) It is a kind of to follow teaching method with remote evaluation function
CN111027486A (en) Auxiliary analysis and evaluation system and method for big data of teaching effect of primary and secondary school classroom
WO2020007097A1 (en) Data processing method, storage medium and electronic device
WO2022170985A1 (en) Exercise selection method and apparatus, and computer device and storage medium
WO2021047473A1 (en) Semantic classification method and device, neural network training method and device, and medium
CN110246228B (en) Chemical experiment evaluation system and method based on virtual reality technology
CN109697906A (en) It is a kind of that teaching method and system are followed based on internet teaching platform
Rana et al. A taxonomy of various applications of artificial intelligence in education
CN112861809B (en) Classroom head-up detection system based on multi-target video analysis and working method thereof
CN114885216A (en) Exercise pushing method and system, electronic equipment and storage medium
CN110111011A (en) A kind of quality of instruction monitoring and managing method, device and electronic equipment
Villagrán et al. Biomechanical analysis of expert anesthesiologists and novice residents performing a simulated central venous access procedure
CN112990105B (en) Method and device for evaluating user, electronic equipment and storage medium
Caballé et al. Software Data Engineering for Network eLearning Environments
JP7427906B2 (en) Information processing device, control method and program
Bataev et al. Artificial intelligence technologies in higher education institutions: a model of adaptive education
Sankar et al. AI Enabled Educational Bot to Improve Learning Outcomes using Bag of Words Algorithm
Bershadskyy et al. Experimental economics for machine learning-a methodological contribution
Zheng et al. Automated Multi-Mode Teaching Behavior Analysis: A Pipeline Based Event Segmentation and Description
Kheldoun et al. Algsl89: An algerian sign language dataset
Guo et al. [Retracted] Scene Construction and Application of Panoramic Virtual Simulation in Interactive Dance Teaching Based on Artificial Intelligence Technology

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19835201

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19835201

Country of ref document: EP

Kind code of ref document: A1