CN112365106A - Student comprehensive quality analysis system based on long-time sequence multi-source data - Google Patents
Student comprehensive quality analysis system based on long-time sequence multi-source data Download PDFInfo
- Publication number
- CN112365106A CN112365106A CN202011480695.XA CN202011480695A CN112365106A CN 112365106 A CN112365106 A CN 112365106A CN 202011480695 A CN202011480695 A CN 202011480695A CN 112365106 A CN112365106 A CN 112365106A
- Authority
- CN
- China
- Prior art keywords
- target object
- analysis
- data
- comprehensive
- audio
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 192
- 238000012360 testing method Methods 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 230000003238 somatosensory effect Effects 0.000 claims abstract description 21
- 238000007619 statistical method Methods 0.000 claims abstract description 6
- 230000014509 gene expression Effects 0.000 claims description 91
- 238000011161 development Methods 0.000 claims description 37
- 238000000034 method Methods 0.000 claims description 22
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 description 9
- 230000004630 mental health Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 230000004044 response Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013441 quality evaluation Methods 0.000 description 3
- 206010034960 Photophobia Diseases 0.000 description 2
- 238000013475 authorization Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003930 cognitive ability Effects 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 206010063659 Aversion Diseases 0.000 description 1
- 241001672694 Citrus reticulata Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000000088 lip Anatomy 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000036630 mental development Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 210000001331 nose Anatomy 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The application provides a student synthesizes quality analysis system based on long chronogenesis multisource data, includes: the audio and video data acquisition equipment is used for acquiring video data information and audio data information of the target object; the wearable data acquisition equipment is used for acquiring somatosensory information of the target object; the input type data acquisition equipment is used for acquiring offline reference information related to the target object; the external data acquisition equipment is used for providing a test environment and acquiring test data corresponding to the target object and the test environment; the data special analysis modules are respectively used for analyzing data acquired by at least one device in the data acquisition device to generate a special analysis result; and the comprehensive analysis module is used for carrying out statistical analysis according to the analysis result of the preset analysis and evaluation system to obtain the comprehensive analysis result of the target object. The invention can not only obtain the special analysis result of the target object from a single angle, but also obtain the comprehensive analysis result of the target object.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a student comprehensive quality analysis system based on long-time-sequence multi-source data.
Background
In order to guide the students to develop in a better direction, it is necessary to perform sufficient observation and analysis on the states of the students and then give development advice suitable for the students based on the results of the observation and analysis. However, in the prior art, the observation and analysis of students are difficult to be comprehensively analyzed, and the development suggestions obtained according to the one-sided analysis result are often not accurate enough, even contradictory. Therefore, in order to make appropriate suggestions for the overall development of students, it is highly desirable to provide a system capable of performing an overall analysis of students.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defect that the students cannot be comprehensively analyzed in the prior art, so that a student comprehensive quality analysis system based on long-time-series multi-source data is provided.
The invention provides a student comprehensive quality analysis system based on long-time sequence multi-source data, which comprises: the audio and video data acquisition equipment is used for acquiring video data information and audio data information of target objects in different scenes; the wearable data acquisition equipment is used for acquiring somatosensory information of the target object; the input type data acquisition equipment is used for acquiring offline reference information which is input by a user and is related to the target object; the external data acquisition equipment is used for providing a test environment and acquiring test data corresponding to the target object and the test environment according to the behavior of the target object in the test environment; the system comprises a plurality of special analysis modules, a plurality of data analysis modules and a plurality of data analysis modules, wherein each data analysis module is respectively used for analyzing data acquired by at least one of audio and video data acquisition equipment, wearable data acquisition equipment, input type data acquisition equipment and external type data acquisition equipment to generate a special analysis result; and the comprehensive analysis module is used for carrying out statistical analysis on the analysis results obtained by the plurality of special analysis modules according to a preset analysis and evaluation system to obtain the comprehensive analysis result of the target object.
Optionally, the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention further includes: and the data storage module is used for storing video data information, audio data information, somatosensory information, offline reference information, test data, special analysis results and comprehensive analysis results of the target object and storing analysis templates corresponding to a preset analysis and evaluation system.
Optionally, the student comprehensive quality analysis system based on the long-time-sequence multi-source data further comprises a data transmission module, wherein the data transmission module is respectively connected with the audio and video data acquisition device, the wearable data acquisition device, the input type data acquisition device and the external type data acquisition device, and transmits the video data information, the audio data information, the somatosensory information, the off-line reference information and the test data to the data storage module.
Optionally, the student comprehensive quality analysis system based on the long-time-sequence multi-source data further comprises an alarm module, each special analysis module corresponds to an alarm condition, and if the special analysis result obtained by each special analysis module reaches the alarm condition corresponding to the special analysis module, the alarm module sends an alarm signal.
Optionally, the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention further includes: the development trend analysis module is used for generating the development trend of the target object according to the special analysis result and the comprehensive analysis result of the target object; and the development suggestion module is used for generating development suggestions of the target object according to the development trends of the target object.
Optionally, the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention further includes: and the information pushing module is used for sending the special analysis result and the comprehensive analysis result to the terminal equipment associated with the target object.
Optionally, the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention further includes: the demand receiving module is used for acquiring analysis demands; and the directional analysis module is used for acquiring data related to the analysis requirement from at least one of video data information, audio data information, somatosensory information, offline reference information and test data according to the analysis requirement, and generating a directional analysis result corresponding to the analysis requirement according to the data related to the analysis requirement.
Optionally, in the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention, the special analysis result includes the expression capability of the target object, and the special analysis module obtains the expression capability of the target object through the following steps: acquiring audio data information and video data information of a target object in the same scene and time period; acquiring audio characteristics of the target object according to the audio data information, wherein the audio characteristics at least comprise an audio index; acquiring expression characteristics of the target object according to the video data information, wherein the expression characteristics at least comprise one expression index; respectively determining the comprehensive weight of each audio index and the comprehensive weight of each expression index; calculating the expression ability score of the target object according to the value of each audio index, the value of each expression index and the comprehensive weight of each audio index and each expression index; and calculating the comprehensive expression ability score of the target object in the preset period according to the expression ability scores of the target object in different time periods in the preset period and the time weights of the target object in different time periods in the preset period.
Optionally, in the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention, the step of obtaining the expression ability of the target object by the special analysis module further includes: calculating the increase value of the comprehensive expression ability score of the target object in the target period according to the comprehensive expression ability score of the target object in the target period and the previous period of the target period; calculating a development factor of the target object in the target period according to the increase value of the comprehensive expression ability score of the target object in the target period; and calculating the comprehensive expression ability evaluation result of the target object in the target period according to the development factor and the comprehensive expression ability score of the target object in the target period.
Optionally, in the student comprehensive quality analysis system based on long-time-series multi-source data provided by the invention, the special analysis module determines the comprehensive weight of each audio index and the comprehensive weight of each expression index through the following steps: determining first weights of the audio indexes and the expression indexes through an analytic hierarchy process; determining a second weight of each audio index and each expression index through an entropy weight method; and respectively determining the comprehensive weight of each audio index and each expression index according to the first weight and the second weight.
The technical scheme of the invention has the following advantages:
the student comprehensive quality analysis system based on the long-time sequence multi-source data comprises a plurality of different data acquisition devices, wherein the different data acquisition devices can be used for acquiring different data, after different data of a target object are acquired through the different data acquisition devices, different special analysis results are generated through a plurality of special analysis modules, and finally the comprehensive analysis module carries out statistical analysis on the analysis results obtained by the plurality of special analysis modules according to a preset analysis and evaluation system to obtain the comprehensive analysis result of the target object.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
1-5 are schematic block diagrams of specific examples of student comprehensive quality analysis systems based on long-time multi-source data according to embodiments of the present invention;
fig. 6 is a specific application scene architecture diagram of the student comprehensive quality analysis system based on long-time-series multi-source data according to the embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The embodiment of the invention provides a student comprehensive quality analysis system based on long-time sequence multi-source data, as shown in figure 1, comprising:
and the audio and video data acquisition equipment 11 is used for acquiring video data information and audio data information of target objects in different scenes.
In a specific embodiment, the video data collecting device may be installed in a place where the target object frequently appears, for example, a classroom, a playground, a restaurant, etc., and it is considered that the states of the target object in different scenes may be different, and therefore, it is necessary to separately store the video data information and the audio data information of the target object in different scenes, and separately analyze the information in different scenes according to the requirements of the analysis content, or analyze the information in a unified manner.
And the wearable data acquisition equipment 12 is used for acquiring the somatosensory information of the target object.
In a specific embodiment, the wearable data acquisition device can be a bracelet and the like equipped on the body of a target object, and can detect the movement track of the target object and data such as the heart rate and the like under specific scenes such as movement, answering questions and the like.
And the recording type data acquisition equipment 13 is used for acquiring offline reference information which is recorded by a user and is related to the target object.
In a specific embodiment, all information of the target object cannot be acquired by the existing device, so the embodiment of the present invention further includes a logging-in data acquisition device 13, and the logging-in data acquisition device may be used to acquire information that cannot be acquired by the monitoring device, such as the achievement of a student, the body test data, the labor situation, and the like.
And the external data acquisition equipment 14 is used for providing a test environment and acquiring test data corresponding to the target object and the test environment according to the behavior of the target object in the test environment.
In the specific embodiment, for the research targets that the learning ability, the mental health state, the reaction ability and the like of the target students are difficult to directly analyze through the data such as the audio and video data and the somatosensory data, the analysis result can be obtained, the external data acquisition equipment 14 is provided in the embodiment of the invention, the external data acquisition equipment 14 provides the test environment, and the test data of the target object in the specific environment is obtained, and the test environment is set based on the research targets, so the response research targets can be accurately analyzed according to the test data of the target object in the specific environment.
The external data acquisition device 14 may be a device having a display screen and a processor, and the external data acquisition device 14 may provide different test environments in response to different test requirements, for example, if the response capability of the target object needs to be tested, the external data acquisition device 14 may display interactive items such as a mini game for testing the response capability of the target object on the display screen, and the target object interacts with the external data acquisition device, and the external data acquisition device may acquire data in an interaction process and determine the data as test data for analyzing the response capability of the target object.
If the mental health state of the target object needs to be tested, the external data acquisition device 14 may display a questionnaire for testing the mental health state of the target object on the display screen, acquire data input by the target object according to the questionnaire, and determine the data as test data for analyzing the mental health state of the target object.
And each data special analysis module 2 is respectively used for analyzing data acquired by at least one of the audio/video data acquisition equipment 11, the wearable data acquisition equipment 12, the input type data acquisition equipment 13 and the external type data acquisition equipment 14 to generate a special analysis result.
In a specific embodiment, one specific analysis module 2 may analyze the target object from one or more angles and obtain corresponding specific analysis results, and when analyzing the target object from different angles, the used data are different, so that each specific analysis module 2 may obtain corresponding data according to actual analysis requirements.
The special analysis module 2 can be used for AI intelligent fusion analysis: by applying technologies such as face recognition, personnel action recognition, action track tracking, behavior analysis and voice recognition, the method can analyze the performance of main activity places such as class behaviors, playground behaviors and dining room behaviors of students and data of families and the like, and can more comprehensively know the individual characteristics of students.
And the comprehensive analysis module 3 is used for performing statistical analysis on the analysis results obtained by the plurality of special analysis modules 2 according to a preset analysis and evaluation system to obtain a comprehensive analysis result of the target object.
In the specific embodiment, the preset analysis and evaluation system is integrated with professional evaluation and evaluation systems of comprehensive quality evaluation, mental health evaluation, competence quality evaluation, professional development, family education measurement and the like of the primary and secondary schools, so that the conditions of personality, psychology, interest, learning, ability, quality, family and the like of students can be comprehensively and deeply analyzed according to the comprehensive analysis result obtained by the preset analysis and evaluation system, and a more scientific and objective student growth and development report is further provided.
It should be noted that the audio/video data acquisition device 11, the wearable data acquisition device 12, the input data acquisition device 13, and the external data acquisition device 14 in the embodiment of the present invention are all installed and worn under the authorization of the student and the guardian thereof, and each device also works under the authorization of the student and the guardian thereof and acquires data of the target object.
The student comprehensive quality analysis system based on the long-time-sequence multi-source data comprises a plurality of different data acquisition devices, wherein the different data acquisition devices can be used for acquiring different data, after different data of a target object are acquired through the different data acquisition devices, different special analysis results are generated through the plurality of special analysis modules 2, and finally the comprehensive analysis module 3 carries out statistical analysis on the analysis results obtained by the plurality of special analysis modules 2 according to a preset analysis evaluation system to obtain the comprehensive analysis result of the target object.
In an embodiment of the present invention, since states of the target object in different scenes are different, and a difference in the states of the target object in different scenes may also be considered when analyzing the target object, in an embodiment of the present invention, data acquired by different data acquisition devices should include a scene of the acquired data.
Specifically, for different scenes, the research emphasis on the target object may also be different, for example, if the scene of the collected data is a classroom, the teaching state of the student may be researched according to the expression and the action of the target object in the classroom; if the scene of the collected data is a playground, the identification of the limb action amplitude, the exercise capacity, the exercise skill and the like of the physical exercise of the personnel can be realized by identifying the human skeleton of the target object; if the scene of the collected data is a dining room, the student activity groups, the eating habits of the analysts and the like can be analyzed through crowd aggregation, crowd classification and the like.
In an optional embodiment, as shown in fig. 2, the student comprehensive quality analysis system based on long-time-series multi-source data according to the embodiment of the present invention further includes: and the data storage module 4 is used for storing video data information, audio data information, somatosensory information, offline reference information, test data, special analysis results and comprehensive analysis results of the target object, and storing analysis templates corresponding to a preset analysis and evaluation system. The data acquired by each data acquisition device is gathered and stored through the data storage module 4, and when the special analysis module 2 and the comprehensive analysis module 3 analyze the target object, the required data can be directly acquired from the data storage module 4 and analyzed.
In an optional embodiment, as shown in fig. 3, the student comprehensive quality analysis system based on long-time-series multi-source data provided in the embodiment of the present invention further includes a data transmission module 5, where the data transmission module 5 is respectively connected to the audio and video data acquisition device 11, the wearable data acquisition device 12, the input data acquisition device 13, and the external data acquisition device 14, and transmits video data information, audio data information, somatosensory information, offline reference information, and test data to the data storage module 4. In a specific embodiment, when the data transmission module 5 performs data transmission, the data front-end data acquisition and transmission may be implemented by using optical fiber/network cable, 4G/5G, NB-IoT, and the like, and the data is collected to the data storage module 4 in a unified manner, so as to implement preliminary collection of data.
In an optional embodiment, the student comprehensive quality analysis system based on the long-time-sequence multi-source data further comprises an alarm module, each special analysis module 2 corresponds to an alarm condition, and if the special analysis result obtained by each special analysis module 2 reaches the alarm condition corresponding to the special analysis module 2, the alarm module sends out an alarm signal.
In a specific embodiment, the alarm condition in each specific analysis module 2 can be set according to the content of the study, for example, for the specific analysis module 2 for analyzing the mental health status of the study target object, the alarm condition can be set to a degree of depression greater than or equal to moderate depression, that is, when the analysis result of the specific analysis module 2 for analyzing the mental health status of the study target object on the depression status of the target object is severe depression, the alarm module gives an alarm signal.
According to the student comprehensive quality analysis system based on the long-time-sequence multi-source data, provided by the embodiment of the invention, the alarm conditions are set in the special analysis modules 2, and the alarm modules give alarm and early warning to dangerous behaviors and abnormal behaviors, so that the safety and the healthy development of students are further ensured.
In an optional embodiment, as shown in fig. 4, the student comprehensive quality analysis system based on long-time-series multi-source data according to the embodiment of the present invention further includes:
and the development trend analysis module 6 is used for generating the development trend of the target object according to the special analysis result and the comprehensive analysis result of the target object.
And the development suggestion module 7 is used for generating development suggestions of the target object according to the development trends of the target object.
In a specific embodiment, personalized life planning and guide suggestions are provided according to the development trend of the target object, and students can be helped to select a proper learning method and development direction as soon as possible. For example, more than 6 months of data may be analyzed, and then a development recommendation for the target object may be generated based on the more than 6 months of data analysis results. According to the embodiment of the invention, the state of the student is evaluated through more data accumulation for a long time, and development suggestions more suitable for the target object can be given.
In an optional embodiment, the student comprehensive quality analysis system based on the long-time-series multi-source data further includes an information pushing module, configured to send the special analysis result and the comprehensive analysis result to a terminal device associated with the target object. The special analysis result and the comprehensive analysis result are sent to the terminal equipment associated with the target object, so that information leakage of the target object can be avoided, and damage to the target object caused by information leakage is prevented.
In a specific embodiment, the information pushing module can push information such as learning materials, psychological consultation, health guidance and the like to the terminal equipment associated with the target object besides the terminal equipment associated with the target object.
In an optional embodiment, as shown in fig. 5, the student comprehensive quality analysis system based on long-time-series multi-source data according to the embodiment of the present invention further includes:
and the requirement receiving module 8 is used for acquiring analysis requirements.
And the directional analysis module 9 is configured to acquire data associated with the analysis requirement, in which at least one of the video data information, the audio data information, the somatosensory information, the offline reference information, and the test data is acquired according to the analysis requirement, and generate a directional analysis result corresponding to the analysis requirement according to the data associated with the analysis requirement.
In the specific embodiment, for different service groups, the analysis results output by the student comprehensive quality analysis system based on the long-time-sequence multi-source data provided by the embodiment of the invention are required to be different, so that the embodiment of the invention also provides the requirement receiving module 8, a user can input the analysis requirement into the system according to the requirement of the user, and the system outputs the directional analysis result according to the requirement of the user.
In an optional embodiment, the result of the special analysis includes an expression capability of the target object, and the special analysis module 2 obtains the expression capability of the target object by the following steps:
the method comprises the steps of firstly, acquiring audio data information and video data information of a target object in the same scene and time period, wherein the audio data information comprises audio when a target student speaks, and the video data information comprises a video image when the target student speaks.
And secondly, acquiring the audio characteristics of the target object according to the audio data information, wherein the audio characteristics at least comprise one audio index, and the audio index can comprise one or more of a pronunciation index value, a intonation index value, a speech speed index value and a volume index value. Wherein, the pronunciation index value is used for expressing whether difficult sounds such as flat warped tongue sound, front and back nasal sound, lip and tooth sound and the like meet the standard of Mandarin; the tone index value is used for representing whether dialect tones and inaccurate tones exist; the speech speed index value and the volume index value are used for expressing the skill, and the expression effect is influenced when the speech speed is too high or too low and the volume is too low.
The pronunciation index value and the intonation index value are expressed by the accuracy (%) of the Putonghua. The pronunciation index value and the intonation index value comprise two evaluation modes of text-related evaluation and text-unrelated evaluation. In a reading scene, adopting a text-related evaluation method: establishing a text standard reference voice library, performing parameter comparison on pronunciation and intonation of students during reading and standard reference voice of the same text, and determining a pronunciation index value and an intonation index value according to pronunciation accuracy and intonation accuracy; under the scene of autonomous expression, an evaluation method irrelevant to the text is adopted: and performing voice recognition on the student utterance by adopting a voice recognition model to obtain a corresponding pronunciation content text, and then calculating a pronunciation index value and a tone index value by adopting an evaluation method related to the text.
The speech rate index value is expressed by a rate (word/minute). The phoneme strings are identified to be combined into syllables, then the number of syllables in unit time is calculated, and the number of syllables in unit time is determined as the speech speed index value.
The volume index value is expressed by decibel (dB). The volume decibel value of the target student during speaking in the audio data is determined as a volume index value, and because the perception of the sound receiving device on the volume index is influenced by the distance from the student, different compensation values are set for different positions in a classroom, so that the volume index values of the students with the same volume during speaking are consistent.
And thirdly, obtaining the expression characteristics of the target object according to the video data information, wherein the expression characteristics at least comprise one expression index, and the expression index comprises at least one of smile, neutrality, photophobia and fear. Facial expressions reflect mainly the infectivity and confidence level of the expressors. Wherein, smile conveys the attitude of positive and self-confidence in the expression process, and when the expression is right, the expression is richer in infectivity and is easier to generate benign interaction with audiences; expressions such as photophobia and fear reflect the emotional conflict and negative emotion of the expressors, and teachers and parents are required to give help and train in time.
Smile, neutral, aversion, and fear index values are expressed by ratios (%), i.e., the duration of each expression accounts for the total expression time. Video data in the classroom is collected through a camera, a video sequence is modeled, key points such as pupils, canthus, eyebrows, noses, lips and chin are detected, and real-time expression characteristics of all students are recognized.
And fourthly, respectively determining the comprehensive weight of each audio index and the comprehensive weight of each expression index.
Fifthly, calculating the expression ability score of the target object according to the value of each audio index, the value of the expression index and the comprehensive weight of each audio index and expression index:
wherein, ciRepresents the integrated weight of the i-th index,
indicates the value of the i-th index after the normalization process.
Sixthly, calculating the comprehensive expression ability score of the target object in the preset period according to the expression ability scores of the target object in different time periods in the preset period and the time weights of the target object in different time periods in the preset period:
wherein T represents the number of time segments within a preset period,
representing the time weight, L, of the t-th time segmentj(t) represents the expressive power score of the jth student in the tth time period.
The student comprehensive quality analysis system based on the long-time-sequence multi-source data provided by the embodiment of the invention not only extracts the audio index, but also extracts the expression index when calculating the comprehensive expression capability score of the target student, and besides pronunciation, the expression of the student during speaking is also an important index for embodying the expression capability of the student, so that the comprehensive expression capability score obtained through the pronunciation and the expression of the target student during speaking is higher in accuracy, and because the expression of the student during speaking is influenced by external objective factors, the student comprehensive quality analysis system based on the long-time-sequence multi-source data provided by the embodiment of the invention calculates the comprehensive expression capability score of the student in the preset period through the expression capability scores of the target student in different time periods in the preset period and the time weights of the student in different time periods in the preset period, and sets different time weights for different time periods, the influence of objective factors on results is reduced, so that the comprehensive expression ability score of the target student calculated by the student comprehensive quality analysis system based on the long-time-sequence multi-source data provided by the invention is more accurate.
In an optional embodiment, the step of acquiring the expression capability of the target object by the special analysis module 2 further includes:
firstly, calculating the increase value of the comprehensive expressive power score of the target object in the target period according to the comprehensive expressive power score of the target object in the target period and the previous period of the target period.
Growth value is used to indicate that the target student is at [ d-1, d]The increase degree of the inner comprehensive expressive power score, d represents the target period, and d-1 represents the previous period of the target period. The growth value is calculated by the following formula:
the initial time d is 1, at which the value v is increasedjd＝0。
Secondly, calculating a development factor of the target object in the target period according to the increase value of the comprehensive expression ability score of the target object in the target period:
wherein, p and q are undetermined parameters larger than 1, and the values of p and q are determined by a preset coefficient, a development factor corresponding to the period with the maximum growth value in the preset time period and a development factor corresponding to the period with the minimum growth value in the preset time period:
gamma is the ratio of the optimal change degree and the worst change degree of the target student set by the evaluator, gamma is better integrated with the preference judgment of the evaluator, and the preset time period is in actualThe application process can be adjusted, for example, the application process can be a month, a school period, a school year and the like. v. ofjdWhen equal to 0, ρjd1, indicates that the overall expression ability score of the target student has not changed, when vjdAt > 0, ρjdIf the total expression capacity score of the target student is more than 1, the score shows that the total expression capacity score of the target student is in an ascending trend; when v isjdAt < 0, ρjdAnd less than 1, the comprehensive expression ability score of the target student is in a descending trend.
Then, calculating a comprehensive expression ability evaluation result of the target object in the target period according to the development factor and the comprehensive expression ability score of the target object in the target period:
in an optional embodiment, the special analysis module 2 determines the comprehensive weight of each audio index and the comprehensive weight of each expression index by the following steps:
first, a first weight of each audio index and each expression index is determined through an analytic hierarchy process. The analytic hierarchy process is a qualitative and quantitative combined multi-target decision analysis method, and provides a way for reasonably utilizing expert experience.
Please the expert to fill in the scoring table, judge the relative importance by 1-9 scale method, and list the comparison matrix a ═ a by the scoring resultlk(l, k ═ 1, 2, 3.., n), where alk represents the relative importance of the l index to the k index, and there are:
calculating the eigenvalues and eigenvectors, determining a first weight (a) for each index1，a2，...，an)。
And secondly, determining a second weight of each audio index and each expression index by an entropy weight method. The entropy weight method determines the index weight by utilizing the entropy values of all indexes, the larger the information entropy is, the higher the disorder degree of the information is, and the smaller the utility value of the information is; conversely, the smaller the information entropy is, the smaller the disorder degree of the information is, and the larger the utility value of the information is. The calculation of the weight is based on the original data, the result is real and reliable, and the influence of subjective factors can be eliminated. The specific step of determining the index weight includes:
marking each index value after standardization processing as
Conversion to specific gravity form:
∑pi＝1；
secondly, determining the entropy of each evaluation index: h ═ k ∑ pi ln pi，
H∈[0，1]Wherein I represents the number of evaluation indexes;
thirdly, determining the weight according to the entropy of each index value,
then, the integrated weight of each audio index and each expression index is determined according to the first weight and the second weight, and in the embodiment of the invention, the integrated weight of each audio index and each expression index is calculated according to the sum of the product of the first weight and the second weight of each audio index and each expression index and the product of the first weight and the second weight of all indexes:
according to the student comprehensive quality analysis system based on the long-time-sequence multi-source data, when the comprehensive weight of each audio index and each expression index is determined, the first weight of each audio index and each expression index is determined through an analytic hierarchy process, the second weight of each audio index and each expression index is determined through an entropy weight method, and finally the comprehensive weight of each audio index and each expression index is determined according to the first weight and the second weight. The first weight obtained through the analytic hierarchy process contains certain subjective factors, the second weight determined through the entropy weight method is completely obtained from the value of each index, the comprehensive weight is objectively obtained by complementing the first weight and the second weight, and the comprehensive expression ability score calculated through the comprehensive weight is more accurate.
In a specific embodiment, as shown in fig. 6, a specific application scenario architecture diagram of a student comprehensive quality analysis system based on long-time-series multi-source data provided in an embodiment of the present invention is shown.
In the application scenario shown in fig. 6, the system comprises six layers of a data acquisition layer, a data transmission layer, a data aggregation and storage layer, an AI intelligent data analysis platform, a service application layer and a user side, wherein the data acquisition layer comprises five acquisition modes of video monitoring, voice acquisition, a somatosensory device, a special test device and a daily condition entry system.
The data transmission layer comprises three transmission modes of optical fiber/network cable and 4G/5G, NB-IoT, and one of the transmission modes can be selected for use.
Video data, voice data, somatosensory equipment data, special testing equipment data and other data are stored in the data gathering and storage layer, wherein the video data are acquired through video monitoring, the voice data are acquired through voice acquisition, the somatosensory equipment data are acquired through the somatosensory equipment, the special testing equipment data are acquired through special testing equipment, and the other data are acquired through a daily condition recording system.
The AI intelligent data analysis platform is used for analyzing data in the data aggregation and storage layer, wherein the data analysis comprises intelligent video analysis, intelligent voice analysis, intelligent somatosensory data analysis, establishment of a student cognitive ability development knowledge graph and AI intelligent fusion analysis.
Specifically, the intelligent speech analysis comprises: semantic recognition: and recognizing the words of the classroom teacher to form classroom teaching records. And identifying semantic information of the students and generating a keyword map. Context recognition: and (3) synthesizing scenes, namely semantic keywords of the teacher and the students, and generating a classroom response radar map (the radar map comprises positive expression, negative expression, positive speech and the like) of each scene of the students, wherein the radar map can be applied to evaluating the response capability of the students.
The somatosensory data analysis comprises the following steps: track identification: according to the somatosensory data, the activity track of the student is identified, and information such as a main activity place and a main activity partner of the student is identified by combining a campus map. The sports physical ability is identified: according to the exercise step number, the heartbeat information and the like, the physical ability information of the students is identified, and the physical ability exercise suggestion and the like are given at the later stage.
The cognitive ability development knowledge map of the student comprises: mental development ability: physiological development, cognition, sociality, and the like. Classroom concentration situation: the classroom concentration degree mainly comprises classroom concentration degree, interestingness degree, participation degree and liveness degree. Learning ability condition: learning method, learning efficiency, knowledge mastering conditions and the like.
And the business application layer is used for providing a physical and mental health report, a classroom concentration report, a learning ability report and comprehensive quality assessment. The comprehensive quality evaluation specifically refers to the evaluation of the comprehensive development ability of the De-Chi-Med.
In the application scenario illustrated in fig. 6, the user side includes a B/S side, an APP side, and a large screen side.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A student comprehensive quality analysis system based on long-time sequence multi-source data is characterized by comprising:
the audio and video data acquisition equipment is used for acquiring video data information and audio data information of target objects in different scenes;
the wearable data acquisition equipment is used for acquiring somatosensory information of the target object;
the input type data acquisition equipment is used for acquiring offline reference information which is input by a user and is related to the target object;
the external data acquisition equipment is used for providing a test environment and acquiring test data corresponding to the target object and the test environment according to the behavior of the target object in the test environment;
the data special analysis modules are respectively used for analyzing data acquired by at least one of the audio and video data acquisition equipment, the wearable data acquisition equipment, the input type data acquisition equipment and the external type data acquisition equipment to generate a special analysis result;
and the comprehensive analysis module is used for carrying out statistical analysis on the analysis results obtained by the plurality of special analysis modules according to a preset analysis and evaluation system to obtain a comprehensive analysis result of the target object.
2. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 1, further comprising:
and the data storage module is used for storing video data information, audio data information, somatosensory information, offline reference information, test data, special analysis results and comprehensive analysis results of the target object, and storing an analysis template corresponding to the preset analysis and evaluation system.
3. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 2, further comprising a data transmission module,
the data transmission module is respectively connected with the audio and video data acquisition equipment, the wearable data acquisition equipment, the input type data acquisition equipment and the external data acquisition equipment, and transmits the video data information, the audio data information, the somatosensory information, the offline reference information and the test data to the data storage module.
4. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 1, further comprising an alarm module,
and each special analysis module corresponds to an alarm condition, and if the special analysis result obtained by each special analysis module reaches the alarm condition corresponding to the special analysis module, the alarm module sends out an alarm signal.
5. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 1, further comprising:
the development trend analysis module is used for generating the development trend of the target object according to the special analysis result and the comprehensive analysis result of the target object;
and the development suggestion module is used for generating development suggestions of the target object according to the development trends of the target object.
6. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 1, further comprising:
and the information pushing module is used for sending the special analysis result and the comprehensive analysis result to the terminal equipment associated with the target object.
7. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 1, further comprising:
the demand receiving module is used for acquiring analysis demands;
and the directional analysis module is used for acquiring data related to the analysis requirement from at least one of video data information, audio data information, somatosensory information, offline reference information and test data according to the analysis requirement, and generating a directional analysis result corresponding to the analysis requirement according to the data related to the analysis requirement.
8. The student integrated literacy analysis system based on long-time series multi-source data of claim 1, wherein the special analysis result comprises an expressive power of the target object,
the special analysis module obtains the expression ability of the target object through the following steps:
acquiring audio data information and video data information of the target object in the same scene and time period;
acquiring audio features of the target object according to the audio data information, wherein the audio features at least comprise an audio index;
acquiring expression characteristics of the target object according to the video data information, wherein the expression characteristics at least comprise one expression index;
respectively determining the comprehensive weight of each audio index and the comprehensive weight of each expression index;
calculating the expression ability score of the target object according to the value of each audio index, the value of each expression index and the comprehensive weight of each audio index and each expression index;
and calculating the comprehensive expression ability score of the target object in the preset period according to the expression ability scores of the target object in different time periods in the preset period and the time weights of the target object in different time periods in the preset period.
9. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 8, wherein the step of the special analysis module obtaining the expression ability of the target object further comprises:
calculating the increase value of the comprehensive expressive power score of the target object in the target period according to the comprehensive expressive power score of the target object in the target period and the previous period of the target period;
calculating a development factor of the target object in the target period according to the increase value of the comprehensive expressive power score of the target object in the target period;
and calculating a comprehensive expression ability evaluation result of the target object in the target period according to the development factor and the comprehensive expression ability score of the target object in the target period.
10. The student comprehensive quality analysis system based on long-time-series multi-source data according to claim 8, wherein the special analysis module determines the comprehensive weight of each audio index and the comprehensive weight of each expression index by:
determining first weights of the audio indexes and the expression indexes through an analytic hierarchy process;
determining a second weight of each audio index and each expression index through an entropy weight method;
and respectively determining the comprehensive weight of each audio index and each expression index according to the first weight and the second weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011480695.XA CN112365106A (en) | 2020-12-17 | 2020-12-17 | Student comprehensive quality analysis system based on long-time sequence multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011480695.XA CN112365106A (en) | 2020-12-17 | 2020-12-17 | Student comprehensive quality analysis system based on long-time sequence multi-source data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112365106A true CN112365106A (en) | 2021-02-12 |
Family
ID=74534488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011480695.XA Pending CN112365106A (en) | 2020-12-17 | 2020-12-17 | Student comprehensive quality analysis system based on long-time sequence multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365106A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966959A (en) * | 2021-03-23 | 2021-06-15 | 海南电网有限责任公司 | Comprehensive evaluation method of power distribution network structure considering load release |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364513A (en) * | 2011-10-24 | 2012-02-29 | 彭苏勉 | Undergraduate comprehensive quality and capability evaluation system |
| CN106447560A (en) * | 2016-09-22 | 2017-02-22 | 福建省百互联网科技有限公司 | Student comprehensive quality assessment system |
| CN108596420A (en) * | 2018-02-02 | 2018-09-28 | 武汉文都创新教育研究院（有限合伙） | A kind of talent assessment system and method for Behavior-based control |
| CN111127263A (en) * | 2019-11-21 | 2020-05-08 | 张梓恒 | Intelligent analysis platform for student growth and development based on block chain |
| CN111612352A (en) * | 2020-05-22 | 2020-09-01 | 北京易华录信息技术股份有限公司 | Student expression ability assessment method and device |
-
2020
- 2020-12-17 CN CN202011480695.XA patent/CN112365106A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102364513A (en) * | 2011-10-24 | 2012-02-29 | 彭苏勉 | Undergraduate comprehensive quality and capability evaluation system |
| CN106447560A (en) * | 2016-09-22 | 2017-02-22 | 福建省百互联网科技有限公司 | Student comprehensive quality assessment system |
| CN108596420A (en) * | 2018-02-02 | 2018-09-28 | 武汉文都创新教育研究院（有限合伙） | A kind of talent assessment system and method for Behavior-based control |
| CN111127263A (en) * | 2019-11-21 | 2020-05-08 | 张梓恒 | Intelligent analysis platform for student growth and development based on block chain |
| CN111612352A (en) * | 2020-05-22 | 2020-09-01 | 北京易华录信息技术股份有限公司 | Student expression ability assessment method and device |
Non-Patent Citations (1)
| Title |
|---|
| 范长军;高飞;: "基于可穿戴传感器的普适化人体活动识别", 传感技术学报, vol. 2, no. 07, pages 148 - 155 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966959A (en) * | 2021-03-23 | 2021-06-15 | 海南电网有限责任公司 | Comprehensive evaluation method of power distribution network structure considering load release |
| CN112966959B (en) * | 2021-03-23 | 2024-04-09 | 海南电网有限责任公司 | Comprehensive evaluation method for grid structure of power distribution network considering load release |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108281052B (en) | A kind of on-line teaching system and online teaching method | |
| US10478111B2 (en) | Systems for speech-based assessment of a patient's state-of-mind | |
| JP5604033B2 (en) | Learning system and method using situation feedback | |
| Dykstra et al. | Using the Language Environment Analysis (LENA) system in preschool classrooms with children with autism spectrum disorders | |
| Bachorowski | Vocal expression and perception of emotion | |
| US9819711B2 (en) | Online social interaction, education, and health care by analysing affect and cognitive features | |
| McKechnie et al. | Automated speech analysis tools for children’s speech production: A systematic literature review | |
| CN105139317B (en) | The cognition index analysis method of interest orientation value test | |
| CN111612352A (en) | Student expression ability assessment method and device | |
| Greenwood et al. | Preliminary investigations of the application of the Early Communication Indicator (ECI) for infants and toddlers | |
| CN110930781B (en) | Recording and broadcasting system | |
| CN112184503A (en) | Children multinomial ability scoring method and system for preschool education quality evaluation | |
| McLeod et al. | Screening children's speech: The impact of imitated elicitation and word position | |
| CN112365106A (en) | Student comprehensive quality analysis system based on long-time sequence multi-source data | |
| Guhan et al. | ABC-Net: Semi-supervised multimodal GAN-based engagement detection using an affective, behavioral and cognitive model | |
| KR20230043080A (en) | Method for screening psychiatric disorder based on voice and apparatus therefor | |
| Seven et al. | Capturing the quantity and location of adult wh-words in the preschool classroom using a sensing tool system | |
| Gromang et al. | The development of video analysis instrument to determine teacher's character | |
| Lyakso et al. | Recognition of the emotional state of children with down syndrome by video, audio and text modalities: human and automatic | |
| Gweon | Assessment and support of the idea co-construction process that influences collaboration | |
| Kahawanugoda et al. | Development of low resource machine learning models for child cognitive ability assessments | |
| Kobayashi et al. | Using deep learning to classify English native pronunciation level from acoustic information | |
| Helvert et al. | Observing, coaching and reflecting: A multi-modal natural language-based dialogue system in a learning context | |
| Chanda et al. | A deep audiovisual approach for human confidence classification | |
| CN111461153A (en) | Crowd characteristic deep learning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |