A kind of children cognition capability evaluation learning machine and methodTechnical field
The invention belongs to capability evaluation technical fields, and in particular to a kind of children cognition capability evaluation learning machine and method.
Background technique
Understand the developmental potency of children, and formulated for the developmental potency of children and bring up strategy, is the child-bearing of current scienceMode.Wherein, for different age brackets, the evaluation item of child development ability is also different, for example, for 0~3 years old children'sDevelopment evaluation needs to assess big movement, fine movement, cognitive ability, language, Social behaviors etc..
Currently, common assessment mode is manual evaluation, i.e., it will be in the assessment table according to children to be assessed by appraiserThe assessed value of each evaluation item determines the comprehensive scores of children to be assessed, to complete to assess.However, the mode of manual evaluation willA lot of manpower and time, at high cost, low efficiency are consumed, and the mode of manual evaluation is limited to the professional ability of appraiser,The accuracy of assessment can not ensure.
Therefore a kind of children cognition ability for designing reasonable, at low cost, high-efficient, assessment profession and interacting entertaining is needed to commentEstimate learning machine and method.
Summary of the invention
The object of the present invention is to provide a kind of children cognition capability evaluation learning machine and methods, to solve people in the prior artThe mode of work assessment is there are at high cost, low efficiency and the technical problems such as accuracy is low of assessment.
The present invention provides the following technical solutions:
A kind of children cognition capability evaluation learning machine, the learning machine include swipe the card interaction end, learning card and voice friendshipMutually end, learning card interacts the interaction end of swiping the card for identification, the interactive voice end for identification voice messaging intoRow interacts, and is previously stored in audiovisual corresponding with each learning card and the voice messaging in the learning machineHold.
Preferably, the audio-visual content is video, audio, dynamic image or/and the text of teaching.
A kind of children cognition capability assessment method, which comprises the following steps:
S1, learning card type carry out three kinds of calibration, the first is content card and game card, second for it is primary, inGrade and advanced, the third for recognize oneself, Animal World, the vehicles and world of art；
S2, interaction scenario of being swiped the card according to learning card and learning machine, learning machine playback of audio-visual content simultaneously record interaction of swiping the cardTime and number information, while time and number information are reported into cloud server；
S3, according to voice messaging and learning machine interactive voice situation, learning machine reports voice messaging to cloud server, leads toIt crosses speech recognition module and converts speech information into text information, text information is loaded into data processing centre by cloud server；
S4, data processing centre carry out division processing to text information according to five big fields of preschool education, and return neckDomain information is to learning machine, and learning machine is according to realm information playback of audio-visual content；
S5, setting sample time choose swipe the card interaction time and the number letter of children in sample time from cloud serverBreath is used as sample data；
S6, sum of effectively swiping the card are as follows: wherein count1 is total=count1*weight1+count2*weight2+ ...Reality in sample time in the 1st period is always swiped the card number, and weight1 is the 1st period corresponding power in sample timeWeight；
S7, effectively swipe the card number that effectively swipe the card sum count world of art is demarcated in type and S7 according to learning cardFor artTotal；
S8, children are in sample time to the correlation M of world of art are as follows: M=artTotal/total；
S9, the text information in sample time, obtained after voice messaging conversion from cloud server is divided into according to the age2-8 years old 7 groups of samples of text；
S10, using in neural LISP program LISP participle and sorting technique secondary return is carried out again to each group samples of textClass；
S11, calculate separately every group of samples of text segmented under secondary classification number always participle number in accounting；
S12, according to the language competence and deviation of different age group children in the accounting extrapolated sample time；
S13, basis are inferred in sample time the correlation M and language competence and deviation of world of art, not the same yearCognition and ability of the age section children in different worlds of art.
Preferably, in the S4, the five big field is health, language, society, science, art.
Preferably, in the S10, the secondary classification includes folded word utilization, clause complexity, words and phrases accounting, uncommon word, wordRemittance amount, English use.
The beneficial effects of the present invention are:
A kind of children cognition capability evaluation learning machine of the present invention and method, overall flow design are reasonable；Pass through learning cardWith the interaction design process of voice messaging, data analysis in open interaction and sample time, provide one it is simple, profession, haveThe children cognition appraisal procedure of interest；After the acquisition of data and analysis, export following information: swiping the card in sample time is totalThe number of swiping the card of several and all types of cards；Test result in sample time, including according to the correlation M and language to world of artSpeech ability and deviation are inferred in sample time, cognition and ability of the different age group children in different worlds of art；TogetherWhen can be suitble to the content and discovery capabilities of children in time of its children's gender, point of interest and age bracket according to these information recommendationsVariation tendency；Profession, suitable early education scheme can be provided to different children according to the appraisal procedure.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the inventionIt applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is structure of the invention flow diagram.
Specific embodiment
As shown in Figure 1, a kind of children cognition capability evaluation learning machine, the learning machine includes swipe the card interaction end, learning cardPiece and interactive voice end, learning card interacts the interaction end of swiping the card for identification, and the interactive voice end is for identificationVoice messaging interacts, and is previously stored in the learning machine and respectively corresponds with each learning card and the voice messagingAudio-visual content.
Specifically, the audio-visual content is video, audio, dynamic image or/and the text of teaching.
A kind of children cognition capability assessment method, which comprises the following steps:
S1, learning card type carry out three kinds of calibration, the first is content card and game card, second for it is primary, inGrade and advanced, the third for recognize oneself, Animal World, the vehicles and world of art；
S2, interaction scenario of being swiped the card according to learning card and learning machine, learning machine playback of audio-visual content simultaneously record interaction of swiping the cardTime and number information, while time and number information are reported into cloud server；
S3, according to voice messaging and learning machine interactive voice situation, learning machine reports voice messaging to cloud server, leads toIt crosses speech recognition module and converts speech information into text information, text information is loaded into data processing centre by cloud server；
S4, data processing centre carry out division processing to text information according to five big fields of preschool education, and return neckDomain information is to learning machine, and learning machine is according to realm information playback of audio-visual content；
S5, setting sample time choose swipe the card interaction time and the number letter of children in sample time from cloud serverBreath is used as sample data；
S6, sum of effectively swiping the card are as follows: wherein count1 is total=count1*weight1+count2*weight2+ ...Reality in sample time in the 1st period is always swiped the card number, and weight1 is the 1st period corresponding power in sample timeWeight；
S7, effectively swipe the card number that effectively swipe the card sum count world of art is demarcated in type and S7 according to learning cardFor artTotal；
S8, children are in sample time to the correlation M of world of art are as follows: M=artTotal/total；
S9, the text information in sample time, obtained after voice messaging conversion from cloud server is divided into according to the age2-8 years old 7 groups of samples of text；
S10, using in neural LISP program LISP participle and sorting technique secondary return is carried out again to each group samples of textClass；
S11, calculate separately every group of samples of text segmented under secondary classification number always participle number in accounting；
S12, according to the language competence and deviation of different age group children in the accounting extrapolated sample time；
S13, basis are inferred in sample time the correlation M and language competence and deviation of world of art, not the same yearCognition and ability of the age section children in different worlds of art.
Specifically, the five big field is health, language, society, science, art in the S4.
Specifically, the secondary classification includes folded word utilization, clause complexity, words and phrases accounting, uncommon word, word in the S10Remittance amount, English use.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, although referring to aforementioned realityApplying example, invention is explained in detail, for those skilled in the art, still can be to aforementioned each implementationTechnical solution documented by example is modified or equivalent replacement of some of the technical features.It is all in essence of the inventionWithin mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.