CN111861817B

CN111861817B - Memory strength calculation method and system for alphabetic language dictation learning

Info

Publication number: CN111861817B
Application number: CN202010568110.3A
Authority: CN
Inventors: 周海滨
Original assignee: Beijing Guoyin Redwood Education Technology Co ltd
Current assignee: Beijing Guoyin Redwood Education Technology Co ltd
Priority date: 2020-06-19
Filing date: 2020-06-19
Publication date: 2023-12-22
Anticipated expiration: 2040-06-19
Also published as: CN111861817A

Abstract

The invention provides a memory strength calculation method and a system for letter language dictation learning, wherein the memory strength calculation method for letter language dictation learning comprises the following steps: generating Chinese speech or alphabetic language speech of the dictation word; matching the generated Chinese voice or the letter language voice with the letter language vocabulary or the Chinese vocabulary with corresponding meaning; acquiring the first dictation information of the user on the dictation word; marking the dictation word according to the primary dictation information, and generating an initial memory strength value of the dictation word. The invention also provides a memory strength computing system for the dictation learning of the alphabetic language. The invention can mark the learned words according to the first learning information of the user, generate different current memory strength values according to different marks of different dictation words, and primarily distinguish different mastery degrees of the user on different words.

Description

Memory strength calculation method and system for alphabetic language dictation learning

Technical field:

the invention relates to the technical field of intelligent dictation methods, in particular to a memory strength calculation method and system for letter language dictation learning.

The background technology is as follows:

along with the popularization and the high-speed development of the mobile network, the mobile network is gradually an important auxiliary means relied on by the traditional education industry through network teaching, learning-aid software and the like, and especially in a special period that normal field teaching cannot be organized, such as a large epidemic situation, a natural disaster and the like, the application of the network teaching and learning-aid software is wider, so that the limitation of the field can be effectively relieved, and the phenomenon of gathering of large-scale students caused by the field teaching can be remarkably avoided.

The learning-aid software in the prior art is various, and includes most popular courses, especially language learning-aid software requiring long-term learning, along with the current globalization process, china is further comprehensively connected with the international track, and language is used as the basis of people communication and exchange, in many occasions, one-to-one communication with others can be carried out, the interconnection between the two parties can be effectively promoted, and the communication cost is reduced, so that English learning is still an indispensable important ring for the current society. In the process of English learning, the learning process of English can be intuitively influenced by memorizing words or word reserve quantity due to the characteristics of alphabetical language, but the existing English learning-aiding software also aims at solving the learning difficulties, but the existing English learning-aiding software lacks a reasonable mechanism or a representation method to reflect the mastering degree of the words by a learner, so that the learner cannot master the key points and the reasonable learning sequence, and also lacks the functions of combining learning modes such as listening, speaking, reading, writing and the like and improving the learning efficiency.

In view of this, the present invention has been proposed.

The invention comprises the following steps:

the invention provides a memory strength calculation method and a memory strength calculation system for dictation learning of alphabetic languages, which can solve at least one technical problem in the prior art.

Specifically, in a first aspect of the present invention, there is provided a memory strength calculation method for alphabetic language dictation learning, the memory strength calculation method for alphabetic language dictation learning comprising the steps of:

generating Chinese speech or alphabetic language speech of the dictation word;

matching the generated Chinese voice or the letter language voice with the letter language vocabulary or the Chinese vocabulary with corresponding meaning;

acquiring the first dictation information of the user on the dictation word;

marking the dictation word according to the primary dictation information, and generating an initial memory strength value of the dictation word.

By adopting the scheme, the learned words are marked according to the first learning information of the user, different current memory strength values can be generated according to different marks of different dictation words, different mastering degrees of the user on different words can be initially distinguished for the user through the marks, and the initial memory strength values can further represent the different mastering degrees of the user on the different words.

Further, when the first dictation information is a user answer to the dictation word, the mark of the dictation word is a cooked word and the memory strength value is a first initial memory strength value; when the first dictation information is that the user answers the dictation word, the mark of the dictation word is a new word and the memory strength value is a second initial memory strength value.

By adopting the scheme, different marks and initial memory strength values are given through the correct errors of the user response conditions, the user can answer the first dictation, the user is proved to grasp the dictation word very high, the user is then noted as a cooked word, and a first initial memory strength value with a higher memory strength value is given; when the user first dictates and answers wrong, the fact that the user has very low mastering of the dictation words is indicated, the words are recorded as new words, and a second memory strength value with a lower memory strength value is given.

Preferably, the memory strength calculating method for dictation learning of alphabetic language further comprises:

setting an upper limit reaction time and a lower limit reaction time;

the primary dictation information comprises primary dictation time length and primary reply information, and whether the primary reply information is consistent with letter language words or Chinese words with corresponding meanings of dictation words is judged;

If the first reply information is consistent with the letter language vocabulary or the Chinese vocabulary of the meaning corresponding to the dictation word, judging the size relation between the first dictation time length and the upper limit reaction time length and the lower limit reaction time length;

when the primary dictation time length is smaller than or equal to the lower limit reaction time length, marking the dictation word as a cooked word and the memory strength value as a first initial memory strength value;

when the primary dictation time length is longer than the lower limit reaction time length and is smaller than or equal to the upper limit reaction time length, marking the dictation word as a raw word, and the memory strength value as a third initial memory strength value, wherein a calculation formula is I=dz- (D3-Db) x n, dz is an extremum, I is the third initial memory strength value, D3 is the actual reaction time length, db is the lower limit reaction time length, and n is a first influence coefficient;

when the primary dictation time length is longer than the upper limit reaction time length, the marks of the dictation words are new words, and the memory strength value is a second initial memory strength value;

if the first reply information is inconsistent with the letter language vocabulary or the Chinese vocabulary of the corresponding meaning of the dictation word, the mark of the dictation word is a new word and the memory strength value is a second initial memory strength value.

By adopting the scheme, another implementation mode of marking words and copying initial memory strength according to different initial dictation information is provided, the memory strength calculation method for dictation learning of the letter language further comprises setting the upper limit reaction time length and the lower limit reaction time length, and the memory strength value is determined in a distinguishing mode by comparing the actual reaction time length of the user for answering with the upper limit reaction time length and the lower limit reaction time length, so that the memory strength of the dictation words to the user can be more accurately and finely identified, and the upper limit reaction time length and the lower limit reaction time length and the formula can be determined according to actual conditions and human forgetting rules.

Further, the word memory strength calculating method further comprises the following steps:

obtaining the relearning information of the user on the dictation word;

when the relearning times are one time, generating a first current memory strength value according to the first relearning information and the initial memory strength value;

and when the number of the re-learning is multiple, generating an Nth current memory strength value according to the Nth re-learning information and the (N-1) th current memory strength value, wherein N is the number of the re-learning.

Further, the re-learning includes re-review, the re-review information is acquired, the re-review information includes new word review information, and the new word review information includes: when the user answers the new word in the review stage, the memory strength value of the new word is increased, and the increased value comprises a first fixed value; and the user answers the new word in the review stage or the user answers overtime, the memory strength value of the new word is reduced, and the reduced value comprises a second fixed value.

By adopting the scheme, the user is inevitably influenced by forgetting factors after finishing the first dictation of the word, so that the user needs to learn again to consolidate, further the grasping degree of the user for the word is influenced, the second learning comprises the second review, the memory strength change value can be calculated by acquiring the second review information, when the first second review is finished, the change value of the first second review on the memory strength is calculated, and then the change value is calculated with the initial memory strength value to generate a first current memory strength value; when the re-review is repeated, the change value of the memory strength generated by the latest re-review information of the user is required to be calculated, and then the change value is calculated with the current memory strength value of the last time, so that the current memory strength value after the latest re-review, namely the Nth current memory strength value, is obtained, and the current memory strength value represents the grasping degree of the user on the dictation word at the latest time according to the number of re-review.

Because the mastering degree of the cooked words of the user is higher, the cooked words can be temporarily not listed in the review stage for more targeted help of the user to learn; the increased first fixed value indicates that the user's mastering degree of the new word is increased, and the decreased second fixed value indicates that the user's mastering degree of the new word is decreased; the first fixed value and the second fixed value can be adjusted according to the magnitude of the human forgetting curve and the initial memory strength value.

Preferably, the first fixed value is smaller than the second fixed value.

By adopting the scheme, the first fixed value is smaller than the second fixed value, so that the time for the memory strength of the new word to reach the full value can be prolonged, the number of times of review of the new word by a user can be increased, and the impression of the user is further deepened.

acquiring voice adjustment information;

and adjusting the dictation voice playing condition according to voice adjusting information, wherein the voice adjusting information comprises a voice speed adjusting value and voice color information, the first initial memory strength value comprises a first initial voice speed threshold value, the second initial memory strength value comprises a second initial voice speed threshold value, and the third initial memory strength value comprises a third upper limit voice speed threshold value and a third lower limit voice speed threshold value.

By adopting the scheme, the effective dictation process can be adjusted according to the difference of the memory rules of the user, so that the learning efficiency of the user is ensured.

Further, the adjusting the dictation voice playing condition according to the voice adjusting information includes:

and judging the current memory intensity value, wherein the current memory intensity value comprises a first initial memory intensity value, a second initial memory intensity value and a third initial memory intensity value, and adjusting the speech rate according to the judging result.

Further, the judging process includes the steps of:

if the current memory strength value is the first initial memory strength value, judging the magnitudes of the speech speed adjusting value and the first initial speech speed threshold value;

when the speech speed adjusting value is larger than or equal to the first initial speech speed threshold value, the dictation speech speed is adjusted to be the first initial speech speed threshold value;

when the speech speed adjustment value is smaller than the first initial speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjustment value;

if the current memory strength value is the second initial memory strength value, judging the magnitudes of the speech speed adjusting value and the second initial speech speed threshold value;

when the speech speed adjustment value is larger than the second initial speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjustment value;

when the speech speed adjusting value is smaller than or equal to the second initial speech speed threshold value, the dictation speech speed is adjusted to be the second initial speech speed threshold value;

If the current memory strength value is the third initial memory strength value, judging the magnitudes of the speech speed adjusting value, the third upper limit speech speed threshold value and the third lower limit speech speed threshold value;

when the speech speed adjusting value is larger than the third upper limit speech speed threshold value, the dictation speech speed is adjusted to be the third upper limit speech speed threshold value;

when the speech speed adjusting value is smaller than or equal to the third upper limit speech speed threshold value and larger than or equal to the third lower limit speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjusting value;

and when the speech speed adjusting value is smaller than the third lower limit speech speed threshold value, adjusting the dictation speech speed to be the third lower limit speech speed threshold value.

By adopting the scheme, the calculation method provided by the invention can be effectively attached, the memory strength of a user can be reasonably quantized, the feedback and dictation processes can be realized, the effective linkage of learning and memory can be reasonably controlled, and the learning efficiency can be improved.

Preferably, the increased or decreased memory strength value further includes a difficulty influence value, and the difficulty influence value is calculated according to the formula:

df=dti×mdt, dti= (dm+am), dm=rwr×λ, rwr=crw/Crt; df is a difficulty influence value, dti is a difficulty index, mdt is a memory strength basic value influenced by the difficulty index, dm is learning data calculation difficulty, am is artificial annotation difficulty, rwr is error rate of answering the new word in the user review process, λ is a difficulty mark, crw is sum of times of answering the new word in the user review process and in the first dictation process, and Crt is total times of answering the new word in the user review process.

By adopting the scheme, the difficulty influence value can comprise manual marking difficulty and learning data calculation difficulty, wherein the manual marking difficulty is the difficulty of a word or sentence; the calculation difficulty of the learning data is that the error rate of word response is calculated by a user; the difficulty mark lambda is used for calculating the learning data calculation difficulty, the difficulty mark lambda can be displayed on a response interface in the form of an energy grid, the memory strength basic value Mdt influenced by the difficulty index is determined according to the overall assignment condition and the human forgetting rule, and the difficulty mark lambda is expressed as the influence of the word difficulty on the memory strength value.

Further, the memory strength increasing value further includes a reaction duration influencing value, and a calculation formula of the reaction duration influencing value is as follows: rd= (1-Mrd/20) x Srd, wherein Mrd is response time length, srd is reaction time length influence memory strength basic value, and Rd is reaction time length influence value.

By adopting the scheme, the response time length influence memory strength basic value Srd can be determined according to the overall assignment situation and the human forgetting rule, and the embodiment is that the response time length influence memory strength basic value Srd8, which represents the influence of the response time length on the memory strength value at most, and Mrd is the response time length unit of seconds.

Further, the memory strength increasing value or the memory strength decreasing value further includes a fatigue influence value, and the fatigue influence value is calculated by the following formula: fa= (1-Fi) × Mfa, fi=de/30×60, where Fa is a fatigue influence value, fi is a fatigue index, mfa is a fatigue index influence memory strength base value, and De is a learning effective duration.

With the above-described scheme, the fatigue index-affected memory strength base value Mfa is expressed as how much the degree of fatigue affects the memory strength value at most, the longer the learning time, the more tired the user, the fewer the memory strength values are increased and decreased, and conversely the greater the memory strength values are increased and decreased.

Preferably, the relearning further includes a test, the relearning information further includes test information including: when the user answers the cooked word in the test stage, the memory strength value of the cooked word is not changed; when the user answers the cooked word in the test stage, the cooked word is re-marked as a new word and the memory strength value becomes a second initial memory strength value; when the user answers the new word, the memory strength value of the new word is reduced; when the user answers to the new word, the memory strength value of the new word is increased.

By adopting the scheme, the test information comprises the answer condition of the same user in the test stage, the cooked word can appear in the test, and when the user answers the wrong cooked word, the user is considered to have lower mastery degree due to the influence of forgetting factors on the cooked word, and the user needs to learn again, so that the value of the memory strength of the generated word is marked as a second initial memory strength value; when the user answers the new word, the memory strength value of the new word is reduced, and the reduced value is a value directly reduced by the new word test; when the user answers the new word, the memory strength value of the new word is increased, and the increased value is a value directly increased by the new word test.

Further, the calculation formula of the direct reduced value of the new word test is sqr=16+16× Rqw, rqw = Cqw/Cqt, where Sqr is the direct reduced value of the new word test, rqw is the answering error rate of the new word in the test, cqw is the total number of times the new word is answered in the test, and Cqt is the total number of times the new word is answered in the test.

By calculating the response error rate of the new words in the test and further calculating the memory strength value reduced by the new words due to the response error in the test according to the response error rate, the user can analyze the mastering degree of the new words more accurately and more on basis.

A time interval Tit is determined from the current test time point Tq and the best review time point Tbr,

by adopting the scheme, tbr=Tq+Tit is adopted, so that the user can review the memory at the optimal review time point with the best effect and the maximum accumulated memory strength.

Further, when Tit <24×60×60, the calculation formula of the value directly added by the word test is Sqi = (14+12×meg×0.2)/3; when Tit >3×24×60×60, the calculation formula of the value directly added by the word test is Sqi = (14+12×meg×0.2); when 24×60×60 is equal to or less than Tit is equal to or less than 3×24×60×60, the calculation formula of the directly added value of the new word test is Sqi = (14+12×meg×0.2); wherein Sqi is a value directly increased by the word test, meg is an engine gear.

By adopting the scheme, the answer accuracy of the new words in the test is calculated, the memory strength value of the new words reduced by the answers in the test is calculated according to the answer accuracy, and the comparison of the test time point and the optimal review time point is introduced, so that the user can more accurately and more conveniently analyze the mastering degree of the new words.

Further, the engine gear is divided into 10 gears, and Rrt is less than or equal to 5: the gear value is 1; rrt is greater than 5 and less than or equal to 15: the gear value is 2; rrt is greater than 15 and less than or equal to 25: the gear value is 3; rrt is greater than 25 and less than or equal to 40: the gear value is 4; rrt is greater than 40 and less than or equal to 60: the gear value is 5; rrt is greater than 60 and less than or equal to 75: the gear value is 6; rrt is greater than 75 and less than or equal to 85: the gear value is 7; rrt is greater than 85 and less than or equal to 93: the gear value is 8; rrt is greater than 93 and less than or equal to 98: the gear value is 9; rrt is greater than 98: the gear value is 10.

Further, the calculation formula of the total accuracy of the new word answer is as follows: rrt= (Crr + Cqr)/(Crt+ Cqt), wherein Crr is the total number of times the user answers the new word in the review process, cqr is the total number of times the user answers the new word in the test, crt is the total number of times the user answers the new word in the review process, and Cqt is the total number of times the user answers the new word in the test.

By adopting the scheme, the speed of memorizing each new word by a user can be reflected through the setting of the engine gear, and the test information and the review information are counted, so that the accuracy of the user response can be analyzed more comprehensively, and the analysis data is more authoritative.

Further, the total number Cqr of answers to the new words by the user in the test is determined according to the time interval Tit between the current test time point Tq and the best review time point Tbr, i.e. tit=tq-Tbr. When Tit < -7×24×60×60, the total number Cqr of user pairs of the new word answers in the test is not increased; when Tit >7 x 24 x 60, the user increases the total number of times Cqr of the new word answer pairs by 2 times in the test; when the Tit is less than or equal to 7 multiplied by 24 multiplied by 60 and less than or equal to 7 multiplied by 24 multiplied by 60, the total number Cqr of the user's answering pairs of the new words in the test is 1+Tit/(7 multiplied by 24 multiplied by 60); when Tit < -7×24×60×60, the total number Cqw of user's mistakes the new word in the test is increased by 2 times; when Tit >7×24×60×60, the total number Cqw of user mistakes the new word in the test does not increase; when Tit is less than or equal to 7 multiplied by 24 multiplied by 60 and less than or equal to 7 multiplied by 24 multiplied by 60, the total number Cqw of times the user answers the new word in the test is 1-Tit/(7 multiplied by 24 multiplied by 60).

By adopting the scheme, the representation modes of the optimal review time point and the test time point adopt a time stamp mode, namely the number of seconds from 1 month, 1 day, 00:00:00 in 1970 to the corresponding time point; when the test time point is 7 days or more earlier than the optimal review time point, the number of test answer pairs Cqr is not increased because the user is considered to respond to the answer pairs in the time period, but the user does not answer pairs; when the test time point is 7 days later than the optimal review time point, the test answer number Cqr is increased by 2 because the user is considered to have forgotten in the time period, but the user still can answer the answer; when the test time point is not earlier than 7 days or not later than 7 days of the optimal review time point, then the calculation is reasonably performed according to a formula.

Further, the calculation formula of the optimal review time point is as follows: tbr=trc+d when the nth secondary word review answer; when the N-th secondary word review is wrong, tbr=tbr' +d; d=c1×ep, p= (c2×sn/10) +c3, where D is the review interval duration, C1 is a power value coefficient, e is a natural constant, P is a power value, C2 is an intensity coefficient, sn is the nth current memory intensity value, and C3 is a power value constant; and calculating an optimal review time point according to the formula Tbr=Tc+D, wherein Tbr is the optimal review time point, trc is the Nth review time point, and Tbr' is the optimal review time calculated by the (N-1) th secondary word review.

By adopting the scheme, the Nth rechecking time point Trc is the rechecking time point closest to the current test time point Tq, and Trc is earlier than Tq; the values of C1, e, C2 and C3 are all determined according to the human forgetting rule, the value of C1 can be 1, e= 2.7183, the value of C2 can be 1.6, and the value of C3 can be 0; sn is the current memory intensity value of the word after the latest user review before the current test time point, namely the Nth current memory intensity value; and adding the N-th review time point and the review interval time length to obtain the optimal review time point.

Preferably, the memory strength calculating method for dictation learning of alphabetic language further comprises the steps of:

judging the number of continuous answer pairs of the same word;

if the number is equal to three, judging whether the first optimal review time point and the continuous three reviews are in the same review period;

if yes, the optimal review time point is set in the next review period.

With the adoption of the scheme, the effect of sleep on memory is considered.

Preferably, when the user performs word-making review, the increased or decreased memory strength value further includes a correction difficulty influence value, and the calculation of the correction difficulty influence value is as follows: df ' =Dti ' x Mdt, dti ' = (Dm ' +Am), dm ' =Rwr ' ×λ, rwr ' =crw+ Cqw/crt+ Cqt; df 'is a correction difficulty influence value, dti' is a correction difficulty index, mdt is a difficulty index influence memory strength basic value, dm 'is correction learning data calculation difficulty, am is artificial annotation difficulty, rwr' is error rate of answering the raw word in the process of user review and test, lambda is difficulty mark, crw is sum of times of answering the raw word in the process of user review, crt is total times of answering the raw word in the process of user review, cqw is total times of answering the raw word in the process of test, and Cqt is total times of answering the raw word in the process of test.

By adopting the scheme, the change of the influence value of the test on the difficulty can be calculated, so that the mastering degree of the user on the dictation word can be analyzed more accurately and finely.

Preferably, when the user performs word-making review, the increased memory strength value further includes a value of increasing gear influence, and the calculation formula of the value of increasing gear influence may be g1=meg×0.1×reg, where Meg is an engine gear, and Reg is an answer pair engine constant.

By adopting the scheme, G1 is a value with increased gear influence, and the answer pair engine constant Reg is determined according to the human forgetting rule.

Preferably, when the user performs the new word review, the reduced memory strength value further includes a value with reduced gear influence, and the calculation formula of the value with reduced gear influence may be g2=weg×crw/Crt, where Weg is an error answering engine constant, crw is a total number of times the new word is answered in review, and Crt is a total number of times the new word is answered in review.

By adopting the scheme, G2 is a value with reduced gear influence, and the error-answering engine constant Weg is determined according to a human forgetting rule.

Preferably, when the user performs a word review, the increased or decreased memory strength value further includes a diligence impact value, and the calculation formula of the diligence impact value may be: dli= Dgi × Mdg, dgi = (Trc-Tbr)/24×60×60, where Dli is a diligence impact value, dgi is a diligence impact index, mdg is a diligence index impact memory strength base value, tbr is the best review time point, trc is the current review time point.

By adopting the scheme, the number of the memory strength values is calculated according to the review time of the user.

In particular, in a second aspect of the present invention, there is provided a memory strength computing system for alphabetic language dictation learning, the memory strength computing system for alphabetic language dictation learning including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the word memory strength computing method when executing the program.

Further, the memory strength computing system for dictation learning of alphabetic languages comprises: the display unit is used for displaying an interface when a user learns the dictation word; the acquisition unit is used for acquiring the first dictation information and the second learning information; and the calculating unit is used for calculating the memory strength value.

Further, the display unit includes a voice input and output device.

The invention has the beneficial effects that:

1. the invention marks the dictation word and generates the initial memory strength value, thereby solving the problem that a user cannot intuitively know the mastering degree of the dictation word and enabling the user to reasonably arrange and learn;

2. The setting of the upper limit reaction time and the lower limit reaction time solves the problem that the user cannot distinguish according to the answering speed when answering, and shows the mastering degree of the user on the dictation word, and brings the technical effects of finer learning results and better learning effects for the user;

3. the N current intensity value solves the technical problem that the memory intensity of the dictation word can not be updated after a plurality of times of review by a user;

4. the speech speed adjustment value, the first initial speech speed threshold value, the second initial speech speed threshold value, the third upper speech speed threshold value and the third lower speech speed threshold value set by the invention can effectively promote the establishment of the dictation habit of a user, and ensure that the dictation capability trained by the user has practical use value.

Description of the drawings:

in order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of a calculation flow of the present invention;

FIG. 2 is a general flow chart of the present invention;

FIG. 3 is a review flow chart of the present invention;

FIG. 4 is a user answer chart of the present invention;

FIG. 5 is a graph of the user response results of the present invention.

The specific embodiment is as follows:

reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.

The word can refer to but is not limited to an English word, and the memory strength refers to the mastering degree of the word by a user, and the higher the memory strength value is, the higher the mastering degree of the word by the user is; the lower the memory strength value, the lower the user's grasp of the word; for convenience of unified calculation, the unit of operation related to the duration is unified as seconds.

Experimental example

Method one

Generating Chinese speech or alphabetic language speech of the dictation word;

acquiring the first dictation information of the user on the dictation word;

marking the dictation word according to the primary dictation information;

judging whether the word is correctly written by the user, if so, marking the word as a cooked word and the memory strength value as a first initial memory strength value 100; if not, the word is marked as a new word and the memory strength value is a second initial memory strength value 13.

The user carries out targeted learning according to the memory strength degree, the cooked words are not learned any more, the memory strength value of each review of the new words is increased by 1, the new words are added to 100 marks to be the cooked words, the words are not learned any more, and the words with low memory strength values are preferably reviewed.

Method II

Similar to method one, the difference is that: the user is correctly listened to in 5 seconds (including 5 seconds), marked as a cooked word, and a first initial memory strength value of 100 is given; when the user dictation time exceeds 20 seconds, a second initial memory strength value 33 is assigned; when the dictation time of the user is more than 5 seconds and less than or equal to 20 seconds, the dictation is still correct, the memory intensity value of the words given to the user is a third initial memory intensity value, the third initial memory intensity value can be calculated according to the formula I= (20- (D3-5))x2 because of the difference of dictation time, I is the third initial memory intensity value, D3 is more than 5 and less than or equal to 20, and D3 is the actual reaction time. When the user first dictates a dictation error, when the error letter is higher than 3 or the word error rate is higher than 50%, the second memory strength value takes the low level value 10, otherwise takes the high level value 33.

Method III

Generating Chinese speech or alphabetic language speech of the dictation word;

acquiring the first dictation information of the user on the dictation word;

marking the dictation word according to the primary dictation information, and generating an initial memory strength value of the word;

Acquiring the re-dictation information of the user on the word;

generating a current memory strength value by increasing or decreasing the memory strength value;

and updating the displayed memory intensity degree by using the current memory intensity value.

The user can write correctly for the first time, marks as cooked words, and endows the first initial memory strength value 100 with higher memory strength value; when the user first dictates that the word is wrong, when the wrong letter is higher than 3 or the word error rate is higher than 50%, the second memory strength value takes the low level value 10, otherwise takes the high level value 33.

The user reviews according to the memory strength degree, when the user listens to correct the new word in the review stage, the memory strength value of the new word is increased by a strength increasing value, and the strength increasing value comprises a first fixed value 12; the user listens to the wrong word in the review phase or the user listens to the time-out, the memory strength value of the word is reduced by the strength reduction value, and the strength reduction value comprises a second fixed value 12.

The strength increasing value or the strength reducing value further comprises a difficulty influence value, and the calculation formula of the difficulty influence value is as follows: df=dti×mdt, dti= (dm+am), dm=rwr×λ, rwr=crw/Crt; df is a difficulty influence value, dti is a difficulty index, mdt is a memory strength basic value influenced by the difficulty index, dm is learning data calculation difficulty, am is manual annotation difficulty, rwr is error rate of the raw word dictation in a user review process, lambda is a difficulty mark, if the value is 5, crw is the sum of times of the raw word dictation error in the user review process, and Crt is the total times of the raw word dictation in the user review process.

The intensity increasing value further comprises a reaction time length influence value, and the calculation formula of the reaction time length influence value is as follows: rd= (1-Mrd/Da) x Srd, wherein Mrd is dictation time length, srd is a basic value of influence on memory strength of reaction time length, rd is a reaction time length influence value, and Da is an upper limit reaction time length.

The strength increasing value or the strength reducing value further comprises a fatigue influence value, and the calculation formula of the fatigue influence value is as follows:

fa= (1-Fi) × Mfa, fi=min (De, ds)/Ds, where Fa is a fatigue influence value, fi is a fatigue index, mfa is a fatigue index influence memory strength basic value, de is a learning effective duration, ds is a fatigue setting duration, and Ds can be set to 30 minutes according to a human forgetting rule. min () represents a smaller value in brackets, and if the duration of De exceeds 30 minutes, the value of min (De, ds) is 30 x 60.

Method IV

Similar to method three, the difference is that: in the actual use process, a user can adjust the speed of broadcasting, and the judgment basis of the adjustment process is as follows: judging a current memory intensity value, wherein the current memory intensity value comprises a first initial memory intensity value, a second initial memory intensity value and a third initial memory intensity value; if the current memory strength value is the first initial memory strength value, judging the magnitudes of the speech speed adjusting value and the first initial speech speed threshold value; when the speech speed adjusting value is larger than or equal to the first initial speech speed threshold value, the dictation speech speed is adjusted to be the first initial speech speed threshold value; when the speech speed adjustment value is smaller than the first initial speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjustment value; if the current memory strength value is the second initial memory strength value, judging the magnitudes of the speech speed adjusting value and the second initial speech speed threshold value; when the speech speed adjustment value is larger than the second initial speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjustment value; when the speech speed adjusting value is smaller than or equal to the second initial speech speed threshold value, the dictation speech speed is adjusted to be the second initial speech speed threshold value; if the current memory strength value is the third initial memory strength value, judging the magnitudes of the speech speed adjusting value, the third upper limit speech speed threshold value and the third lower limit speech speed threshold value; when the speech speed adjusting value is larger than the third upper limit speech speed threshold value, the dictation speech speed is adjusted to be the third upper limit speech speed threshold value; when the speech speed adjusting value is smaller than or equal to the third upper limit speech speed threshold value and larger than or equal to the third lower limit speech speed threshold value, the dictation speech speed is adjusted to be the speech speed adjusting value; and when the speech speed adjusting value is smaller than the third lower limit speech speed threshold value, adjusting the dictation speech speed to be the third lower limit speech speed threshold value.

Method five

Similar to method four, the difference is that: the relearning further includes a test, the relearning information further includes test information including: when the user listens to the correct cooked words in the test stage, the memory strength of the cooked words is not changed; when the user listens to the wrongly-written word in the test stage, the wrongly-written word is re-marked as a new word and the memory strength value becomes a second initial memory strength value; when the user dictates the word, the memory strength value of the word is reduced by the strength reduction value; when the user listens to the word correctly, the memory strength value of the word increases by the strength increasing value.

60 volunteers aged 15-18 years old are divided into 6 groups of 10 people each, 500 English words are learned by the same volunteers, and the learning time is 2 weeks; the test results after the learning of each group are shown in the following table:

table 1 test results obtained with different learning methods

Group of	Method	Accuracy rate of	Accuracy of cooked words
				Group I	Free learning	53％	/
Group II	Method one	64％	70％
				Group III	Method II	67％	75％
Group IV	Method III	80％	90％
				Group five	Method IV	87％	92％
Group six	Method five	90％	98％

Referring to the results in table 1, the accuracy is obviously improved (P < 0.01) from group two to group six compared with group one, which illustrates that the marking of new words and cooked words is carried out on the words, and the user is helped to better conduct targeted learning through the displayed memory strength degree, so that the learning effectiveness is improved; compared with the group II, the group III and the group IV have obviously improved accuracy (P < 0.01), divide the memory intensity degree more finely and learn more specifically; compared with the group IV, the group IV shows that the adjustment of the broadcasting speed has a stronger exercise effect on dictation capability; the improvement of the word-cooked accuracy (P < 0.01) is obviously improved in the group five and the group six compared with the group two, which means that the increased or decreased value in the group five and the group six can be changed according to the fatigue degree, the word difficulty degree and the like, and compared with the mechanically increased or decreased fixed value, the memory strength value can more accurately reflect the mastery degree of the user; and compared with the group five, the group six has the advantages that the accuracy rate of the cooked words is improved (P < 0.01), the increase test is described, and the identification of the cooked words is dynamically changed, so that the memory strength value can more accurately reflect the actual mastering condition of a user.

Examples

Referring to fig. 1, 2, 4 and 5, the invention provides a memory strength calculation method for letter language dictation learning, which comprises the following steps:

generating Chinese speech or alphabetic language speech of the dictation word;

acquiring the first dictation information of the user on the dictation word;

In the specific implementation process, the memory strength calculation method of the alphabetic language dictation learning can be realized by computer software or mobile phone APP, etc., a user can select any word stock, for example, a college English four-level word stock, a college six-level word stock or a business English word stock, and then can select an intelligent dictation module for learning, and the intelligent dictation module spells by listening to pronunciation; the display interface of fig. 4 sends out the pronunciation of the corresponding word in the selected word stock, and the user can spell according to the pronunciation, and the answering situation is as shown in fig. 5, and the corresponding position is wrongly displayed.

In some preferred embodiments of the present invention, computer software or a display interface of the mobile phone APP may present a corresponding word in the selected word stock, for example, the display interface of fig. 4 may issue a pronunciation of the corresponding word in the selected word stock, at this time, the user may spell according to the pronunciation, and answer the question as in fig. 5, and answer the corresponding position display fork; and then marking the learned words according to the first learning information of the user, and generating different current memory strength values according to different marks of different dictation words.

In the implementation process, when the primary dictation information is that a user answers the dictation word, the mark of the dictation word is a cooked word and the memory strength value is a first initial memory strength value; when the first dictation information is that the user answers the dictation word, the mark of the dictation word is a new word and the memory strength value is a second initial memory strength value.

By adopting the scheme, the implementation mode of marking the words and copying the initial memory strength according to different primary dictation information is provided, different marks and initial memory strength values are given through the correct errors of the response conditions of the user, the primary dictation of the user can answer, the fact that the user has very high grasp of the dictation words is explained, the words are recorded as cooked words, and the first initial memory strength value with higher memory strength value is given; when the user first dictates and answers wrong, the fact that the user has very low mastering of the dictation words is indicated, the words are recorded as new words, and a second memory strength value with a lower memory strength value is given.

In a specific implementation process, the memory strength calculation method for the alphabetic language dictation learning further comprises setting an upper limit reaction time length and a lower limit reaction time length, and when the primary dictation information is that a user answers the dictation word and the answer time length is smaller than or equal to the lower limit reaction time length, marking the dictation word as a cooked word and the memory strength value as a first initial memory strength value; when the primary dictation information is that a user answers the dictation word and the answer time is longer than the lower limit reaction time and shorter than or equal to the upper limit reaction time, the marks of the dictation word are raw words, the memory strength value is a third initial memory strength value, a calculation formula is I=dz- (D3-Db) x n, dz is an extremum, I is the third initial memory strength value, D3 is the actual reaction time, db is the lower limit reaction time, and n is a first influence coefficient; when the first learning information is that the user answers the learning word by mistake or the answering time exceeds the upper limit reaction time, the learning word is marked as a new word and the memory strength value is a second initial memory strength value.

By adopting the scheme, another implementation mode for marking the words and copying the initial memory strength according to different primary dictation information is provided, and the memory strength calculation method for the letter language dictation learning further comprises the step of setting the upper limit reaction time length and the lower limit reaction time length, so that the memory strength value of the dictation words to the user can be accurately and finely identified, and the upper limit reaction time length and the lower limit reaction time length can be determined according to actual conditions.

In some preferred embodiments of the present invention, the upper limit reaction duration and the lower limit reaction duration are obtained according to a human memory reaction rule, the upper limit reaction duration may be 20 seconds, the lower limit reaction duration may be 5 seconds, and the user is correctly answered within 5 seconds (including 5 seconds), which indicates that the user has a very high mastery degree for the dictation word; when the answer time of the user exceeds 20 seconds, the answer is considered to be overtime, and the explanation shows that the user can grasp the word very low and needs to think for a long time to answer, so that setting the answer overtime avoids the user from consuming too much time, and the user does not grasp the dictation word no matter how much the answer time is wrong; when the answer time of the user is more than 5 seconds and less than or equal to 20 seconds, the user still answers, and the user is proved to have a certain mastering degree of the dictation word, but the mastering degree is not high, at the moment, the memory intensity value given to the dictation word by the user is a third initial memory intensity value, the third initial memory intensity value is more than the second initial memory intensity value but less than the first initial memory intensity value, the size of the initial memory intensity value can be determined according to actual conditions, for example, the highest first initial memory intensity value is 100, the second initial memory intensity value is 10, the third initial memory intensity value can be calculated according to the formula i=dz- (D3-Db) x n because of the difference of answer time, I is the third initial memory intensity value, D3 is more than or equal to 20, and D3 is the actual reaction time. By adding the settings of the upper limit reaction time and the lower limit reaction time, the mastering degree of the user on the dictation word can be further and more carefully and accurately reflected according to the answering time of the user, and the concentration degree of the user can be increased, so that the user has a sense of urgency and the learning efficiency is further increased.

In the specific implementation process, the word memory strength calculation method further comprises the steps that a user learns the dictation word again, so that the user learns the dictation word again, and when the number of times of the re-learning is one time, a first current memory strength value is generated according to the first learning information and the initial memory strength value; and when the number of the re-learning is multiple, generating an Nth current memory strength value according to the Nth re-learning information and the (N-1) th current memory strength value, wherein N is the number of the re-learning.

In the specific implementation process, the re-learning comprises re-review, the re-review information is acquired, the re-review information comprises word-giving review information, and the word-giving review information comprises: when the user answers the new word in the review stage, the memory strength value of the new word is increased, and the increased value comprises a first fixed value; and when the user answers the new word in the review stage or the user answers overtime, the memory strength value of the new word is reduced, and the reduced value comprises a second fixed value.

In the implementation process, the first fixed value is smaller than the second fixed value.

By adopting the scheme, the first fixed value is smaller than the second fixed value, so that the time for the memory strength of the new word to reach the full value can be prolonged, the number of times of review of the new word by a user can be increased, and the impression of the user is further enhanced; for example, the first fixed value may be 2 and the second fixed value may be 9.

In some preferred embodiments of the present invention, the memory strength calculation method for alphabetic language dictation learning further includes:

acquiring voice adjustment information;

In some preferred embodiments of the present invention, the adjusting the dictation voice playing condition according to the voice adjusting information includes:

judging a current memory intensity value, wherein the current memory intensity value comprises a first initial memory intensity value, a second initial memory intensity value and a third initial memory intensity value;

In the implementation process, the increased or decreased memory strength value further comprises a difficulty influence value, and the calculation formula of the difficulty influence value is as follows:

df=dti×mdt, dti= (dm+am), dm=rwr×λ, rwr=crw/Crt; df is a difficulty influence value, dti is a difficulty index, mdt is a memory strength basic value influenced by the difficulty index, dm is learning data calculation difficulty, am is artificial annotation difficulty, rwr is error rate of answering the new word in the user review process, λ is a difficulty mark, crw is sum of times of answering the new word in the user review process, and Crt is total times of answering the new word in the user review process.

By adopting the scheme, the difficulty influence value can comprise manual marking difficulty and learning data calculation difficulty, for example, the manual marking difficulty is the difficulty of a word or a sentence, the length, the word forming rule, chinese interpretation and other aspects are reflected, the words with more letters than letters are difficult to record, the letters are arranged regularly and more than irregularly difficult to record, and the different difficulty of different words need to be marked manually to distinguish; the calculation difficulty of the learning data is that the error rate of word response is calculated by a user; the difficulty mark lambda is used for calculating the learning data calculation difficulty, the difficulty mark lambda can be displayed on a response interface in the form of an energy grid, the difficulty index influences the memory strength basic value Mdt to be determined according to the overall assignment condition and the human forgetting rule, the difficulty mark lambda is expressed as the influence of word difficulty on the memory strength value, and the Mdt in the embodiment takes the value of 3; a value of 5 for λ is represented in fig. 3 as 5 difficulty cases, in the sense that the error rate can affect how much Dm is the greatest.

In the specific implementation process, the memory strength increasing value further comprises a reaction duration influence value, and the calculation formula of the reaction duration influence value is as follows:

rd= (1-Mrd/20) x Srd, wherein Mrd is response time length, srd is reaction time length influence memory strength basic value, and Rd is reaction time length influence value.

By adopting the scheme, the basic value Srd of the response time length influence on the memory strength can be determined according to the overall assignment situation and the human forgetting rule, in the embodiment, the basic value Srd of the response time length influence on the memory strength is 8, and the response time length unit of Mrd is seconds; the influence value of the reaction time is calculated, so that the grasping degree of the user on the word can be accurately and finely calculated according to the speed of the user to answer.

In the implementation process, the memory strength increasing value or the memory strength decreasing value further comprises a fatigue influence value, and the calculation formula of the fatigue influence value is as follows:

fa= (1-Fi) × Mfa, fi=de/30×60, where Fa is a fatigue influence value, fi is a fatigue index, mfa is a fatigue index influence memory strength base value, and De is a learning effective duration. The increased value is a memory strength value which is increased based on the original memory strength value when the user answers the new word, and the decreased value is a memory strength value which is decreased based on the original memory strength value when the user answers the new word by mistake or overtime.

With the above scheme, the learning effective duration De is the interaction time of the user and the learning interface, and as the learning time of 30 minutes per day is most suitable according to the human forgetting curve, 30×60 is the conversion of 30 minutes into 1800 seconds, the fatigue index influences the memory strength basic value Mfa to represent the fatigue degree to influence the memory strength value most, the longer the learning time is, the fatigued the user is, the less the memory strength values are increased and decreased, and otherwise the larger the memory strength values are increased and decreased. The fatigue influence value is sufficiently calculated from the physiological law of the person to take the influence on the memory ability into consideration, and the increase and decrease of the memory strength value is more accurately and finely calculated, and the Mfa value is 4 in the embodiment according to the human forgetting law.

In the specific implementation process, the relearning further comprises a test, the relearning information further comprises test information, and the test information comprises: when the user answers the cooked word in the test stage, the memory strength of the cooked word is not changed; when the user answers the cooked word in the test stage, the cooked word is re-marked as a new word and the memory strength value becomes a second initial memory strength value; when the user answers the new word, the memory strength value of the new word is reduced; when the user answers to the new word, the memory strength value of the new word is increased.

By adopting the scheme, the test information comprises the answer condition of the same user in the test stage, the cooked word can appear in the test, and when the user answers the wrong cooked word, the user is considered to have lower mastery degree due to the influence of forgetting factors on the cooked word, and the user needs to learn again, so that the value of the memory strength of the generated word is marked as a second initial memory strength value; when the user answers the new word, the memory strength value of the new word is reduced, and the reduced value is a value directly reduced by the new word test; when the user answers the new word, the memory strength value of the new word is increased, and the increased value is a value directly increased by the new word test. The test can be performed on a regular basis by artificial arrangement, the test can also be automatically arranged for the user after each chapter of the word stock is learned, and the like, and the grasping degree of the user on the dictation word can be more comprehensively and comprehensively reflected by integrating the influence of the test information on the memory strength value and the influence of the review information on the memory strength value.

In the specific implementation process, the calculation formula of the direct reduced value of the new word test is Sqr=16+16× Rqw, rqw = Cqw/Cqt, wherein Sqr is the direct reduced value of the new word test, rqw is the error rate of the new word in the test, cqw is the total number of times of the new word in the test, cqt is the total number of times of the new word in the test, and the constant 16 in the formula is determined according to a human forgetting curve; by calculating the response error rate of the new words in the test and further calculating the memory strength value reduced by the new words due to the response error in the test according to the response error rate, the user can analyze the mastering degree of the new words more accurately and more on basis.

In some preferred embodiments of the present invention, the time interval Tit is determined according to the current test time point Tq and the optimal review time point Tbr, tit=tq-Tbr, and the user reviews the best effect on memory enhancement at the optimal review time point, and the accumulated memory strength is the largest.

In some preferred embodiments of the present invention, when Tit <24×60×60, the calculation formula of the directly increased value of the raw word test is Sqi = (14+12×meg×0.2)/3; when Tit >3×24×60×60, the calculation formula of the value directly added by the word test is Sqi = (14+12×meg×0.2); when 24×60×60 is equal to or less than Tit is equal to or less than 3×24×60×60, the calculation formula of the directly added value of the new word test is Sqi = (14+12×meg×0.2); wherein Sqi is a value directly increased by a word test, meg is an engine gear, and constants 14 and 12 in the formula are determined according to a human forgetting curve; the method comprises the steps of calculating the response accuracy of the new words in the test, further calculating the memory strength value of the response to the new words in the test according to the response accuracy, and enabling a user to analyze the mastering degree of the new words more accurately and more on the basis by introducing the comparison between the test time point and the optimal review time point.

As shown in fig. 1-3, the engine gear, which reflects the memory level of the user for the words, is represented as a memory speed, can be determined by the total accuracy Rrt of the user in answering the new words in review information and test information.

In some preferred embodiments of the present invention, the engine gear may be divided into 10 gears as follows: rrt is less than or equal to 5: the gear value is 1; rrt is greater than 5 and less than or equal to 15: the gear value is 2; rrt is greater than 15 and less than or equal to 25: the gear value is 3; rrt is greater than 25 and less than or equal to 40: the gear value is 4; rrt is greater than 40 and less than or equal to 60: the gear value is 5; rrt is greater than 60 and less than or equal to 75: the gear value is 6; rrt is greater than 75 and less than or equal to 85: the gear value is 7; rrt is greater than 85 and less than or equal to 93: the gear value is 8; rrt is greater than 93 and less than or equal to 98: the gear value is 9; rrt is greater than 98: the gear value is 10.

In the implementation process, the calculation formula of the total accuracy of the new word response can be: rrt= (Crr + Cqr)/(Crt+ Cqt), wherein Crr is the total number of times the user answers the new word in the review process, cqr is the total number of times the user answers the new word in the test, crt is the total number of times the user answers the new word in the review process, and Cqt is the total number of times the user answers the new word in the test. The speed of memorizing each new word by the user can be reflected through the setting of the engine gear, and the test information and the review information are counted, so that the accuracy of the user response can be more comprehensively analyzed, and the analysis data is more authoritative.

In a specific implementation process, the total number Cqr of the user answering the new word in the test is determined according to the time interval Tit between the current test time point Tq and the best review time point Tbr, namely tit=tq-Tbr.

When Tit < -7×24×60×60, the total number Cqr of user pairs of the new word answers in the test is not increased; when Tit >7 x 24 x 60, the user increases the total number of times Cqr of the new word answer pairs by 2 times in the test; when the Tit is less than or equal to 7×24×60 and less than or equal to 7×24×60×60, the total number Cqr of the user's answers to the new word in the test is increased by 1+Tit/(7×24×60×60).

When Tit < -7×24×60×60, the total number Cqw of user's mistakes the new word in the test is increased by 2 times;

when Tit >7×24×60×60, the total number Cqw of user mistakes the new word in the test does not increase; when Tit is less than or equal to 7 multiplied by 24 multiplied by 60 and less than or equal to 7 multiplied by 24 multiplied by 60, the total number Cqw of times the user answers the new word in the test is 1-Tit/(7 multiplied by 24 multiplied by 60).

By adopting the scheme, the representation modes of the optimal review time point and the test time point adopt a time stamp mode, namely the number of seconds from 1 month, 1 day, 00:00:00 in 1970 to the corresponding time point; the influence of forgetting on human memory is comprehensively considered by determining according to the time interval Tit, so that the fact that the answer pair or the answer mistake is recorded as one time in a general way is avoided, and statistics can be accurately carried out by combining human physiological and psychological rules. When the test time point is 7 days or more earlier than the optimal review time point, the number of test answer pairs Cqr is not increased because the user is considered to respond to the answer pairs in the time period, but the user does not answer pairs; when the test time point is 7 days later than the optimal review time point, the test answer number Cqr is increased by 2 because the user is considered to have forgotten in the time period, but the user still can answer the answer; when the test time point is not earlier than 7 days or not later than 7 days of the optimal review time point, then the calculation is reasonably performed according to a formula.

In the specific implementation process, the calculation formula of the optimal review time point is as follows: tbr=trc+d when the nth secondary word review answer; when the N-th secondary word review is wrong, tbr=tbr' +d; d=c1×ep, p= (c2×sn/10) +c3, where D is the review interval duration, C1 is a power value coefficient, e is a natural constant, P is a power value, C2 is an intensity coefficient, sn is the nth current memory intensity value, and C3 is a power value constant; and calculating an optimal review time point according to the formula Tbr=Tc+D, wherein Tbr is the optimal review time point, trc is the Nth review time point, and Tbr' is the optimal review time calculated by the (N-1) th secondary word review.

In the implementation process, when the user reviews the new word answer pairs three times continuously on the same day and the calculated optimal review time point is still on the same day as the user reviews three times continuously, the optimal review time point Tbr is adjusted to 6 in the morning of the next day.

With the adoption of the scheme, the effect of sleep on memory is considered.

In the specific implementation process, when the user carries out word review, the increased or decreased memory strength value further comprises a correction difficulty influence value, and the calculation of the correction difficulty influence value is as follows: df ' =Dti ' x Mdt, dti ' = (Dm ' +Am), dm ' =Rwr ' ×λ, rwr ' =crw+ Cqw/crt+ Cqt; df 'is a correction difficulty influence value, dti' is a correction difficulty index, mdt is a difficulty index influence memory strength basic value, dm 'is correction learning data calculation difficulty, am is artificial annotation difficulty, rwr' is error rate of answering the raw word in the process of user review and test, lambda is difficulty mark, crw is sum of times of answering the raw word in the process of user review, crt is total times of answering the raw word in the process of user review, cqw is total times of answering the raw word in the process of test, and Cqt is total times of answering the raw word in the process of test.

By adopting the scheme, the change of the difficulty influence value is calculated and tested, and the difficulty influence value is corrected, so that the mastering degree of a user on the dictation word can be analyzed more accurately and finely.

In the implementation process, when the user performs the word review, the increased memory strength value further includes a value of increasing gear influence, and a calculation formula of the value of increasing gear influence may be g1=meg×0.1×reg, where Meg is an engine gear, and Reg is an answer pair engine constant.

By adopting the scheme, G1 is a value with increased gear influence, the answer pair engine constant Reg is determined according to the human forgetting rule, and the value can be 6 in the embodiment.

In the specific implementation process, when the user performs the word-learning, the reduced memory strength value further includes a value with reduced gear influence, and the calculation formula of the value with reduced gear influence may be g2=weg×crw/Crt, where Weg is an error-learning engine constant, crw is the total number of times of error-learning the word-learning in the learning, and Crt is the total number of times of error-learning the word-learning in the learning.

By adopting the scheme, G2 is a value with reduced gear influence, the error-answering engine constant Weg is determined according to the human forgetting rule, and the value can be 7.5 in the embodiment.

In the implementation process, when the user carries out the word review, the increased or decreased memory strength value further comprises a diligence influence value, and the calculation formula of the diligence influence value can be as follows: dli= Dgi × Mdg, dgi = (Trc-Tbr)/24×60×60, where Dli is a diligence impact value, dgi is a diligence impact index, mdg is a diligence index impact memory strength base value, tbr is the best review time point, trc is the current review time point.

The invention also provides a memory strength computing system for the dictation learning of the alphabetic language, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the word memory strength computing method when executing the program.

In the implementation process, the memory strength computing system for dictation learning of the alphabetic language comprises: the display unit is used for displaying an interface when a user learns the dictation word; the acquisition unit is used for acquiring the first dictation information and the second learning information; and the calculating unit is used for calculating the memory strength value.

In some preferred embodiments of the invention, the display unit comprises voice input and output means.

It should be noted that it will be apparent to those skilled in the art that various changes and modifications can be made to the present invention without departing from the principles of the invention, and such changes and modifications will fall within the scope of the appended claims.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

It should be understood that in the embodiments of the present application, the claims, the various embodiments, and the features may be combined with each other, so as to solve the foregoing technical problems.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a read-Only Memory (ROM), a random-access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein, so as to enable or to enable persons skilled in the art with the aid of the foregoing description of the disclosed embodiments. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A memory strength calculation method for letter language dictation learning is characterized in that: the memory strength calculating method for the dictation learning of the alphabetic language comprises the following steps:

Generating Chinese speech or alphabetic language speech of the dictation word;

acquiring the first dictation information of the user on the dictation word;

marking the dictation word according to the primary dictation information, and generating an initial memory strength value of the dictation word;

the memory strength calculation method for the dictation learning of the alphabetic language further comprises the following steps:

setting an upper limit reaction time and a lower limit reaction time;

if the first reply information is inconsistent with the letter language vocabulary or the Chinese vocabulary of the corresponding meaning of the dictation word, the mark of the dictation word is a new word and the memory strength value is a second initial memory strength value;

the word memory strength calculation method further comprises the following steps:

obtaining the relearning information of the user on the dictation word;

when the number of rechecks is multiple, generating an Nth current memory strength value according to the Nth recheck information and the (N-1) th current memory strength value, wherein N is the number of rechecks;

the increased or decreased memory strength value also comprises a difficulty influence value, and the calculation formula of the difficulty influence value is as follows:

df=dti×mdt, dti= (dm+am), dm=rwr×λ, rwr=crw/Crt; df is a difficulty influence value, dti is a difficulty index, mdt is a memory strength basic value influenced by the difficulty index, dm is learning data calculation difficulty, am is artificial annotation difficulty, rwr is error rate of answering the raw word in a user review process, λ is a difficulty mark, crw is sum of times of answering the raw word in the user review process and in primary dictation, and Crt is total times of answering the raw word in the user review process;

The memory strength increasing value further comprises a reaction time length influence value, and the calculation formula of the reaction time length influence value is as follows: rd= (1-Mrd/20) x Srd, wherein Mrd is response time length, srd is reaction time length influence memory strength basic value, and Rd is reaction time length influence value;

the memory strength increasing value or the memory strength decreasing value further comprises a fatigue influence value, and the fatigue influence value is calculated according to the formula: fa= (1-Fi) × Mfa, fi=de/30×60, where Fa is a fatigue influence value, fi is a fatigue index, mfa is a fatigue index influence memory strength base value, and De is a learning effective duration.

2. The memory strength calculation method for alphabetic language dictation learning according to claim 1, characterized in that: the re-learning comprises re-review, the re-review information is acquired, the re-review information comprises raw word review information, and the raw word review information comprises: when the user answers the new word in the review stage, the memory strength value of the new word is increased, and the increased value comprises a first fixed value; and the user answers the new word in the review stage or the user answers overtime, the memory strength value of the new word is reduced, and the reduced value comprises a second fixed value.

3. The memory strength calculation method for alphabetic language dictation learning according to claim 2, characterized in that: the memory strength calculation method for the dictation learning of the alphabetic language further comprises the following steps:

acquiring voice adjustment information;

4. A memory strength calculation method for alphabetic language dictation learning according to claim 3, characterized in that: the adjusting the dictation voice playing condition according to the voice adjusting information comprises the following steps:

5. A memory strength computing system for dictation learning of alphabetic languages is characterized in that: the memory strength computing system for dictation learning of a mother language comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of the preceding claims 1-4 when executing the program.