CN110310086B - Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium - Google Patents
Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium Download PDFInfo
- Publication number
- CN110310086B CN110310086B CN201910490557.0A CN201910490557A CN110310086B CN 110310086 B CN110310086 B CN 110310086B CN 201910490557 A CN201910490557 A CN 201910490557A CN 110310086 B CN110310086 B CN 110310086B
- Authority
- CN
- China
- Prior art keywords
- recitation
- user
- content
- information
- next period
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/109—Time management, e.g. calendars, reminders, meetings or time accounting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention provides an auxiliary recitation reminding method, auxiliary recitation reminding equipment and a storage medium. The method comprises the following steps: determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period; and prompting the user according to the prompting strategy in the next period. According to the method provided by the embodiment of the invention, the determined prompting strategy better meets the requirements of the user through the recitation state of the user and the difficulty coefficient of the recitation content, the prompt can be timely and effectively provided for the user, the effect of practicing the recitation of the user can be improved, and the user experience is improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a recitation assisting reminding method, recitation assisting reminding equipment and a storage medium.
Background
In the course of school learning or self-learning, people often need to recite articles or a certain period of time, but the traditional reciting method is very low in efficiency, and the reciting process is inconvenient to check and manage, so that reciting cannot be well fed back and strengthened.
With the development of artificial intelligence technology, especially the combination of speech technology and deep learning, it is possible to assist user recitation through speech recognition technology. In the related art, a user selects contents to be recited, then the apparatus records the recitation of the user, detects whether the recitation is correct or not after the recitation of the user is completed or in real time, and displays the recitation result.
In the above scheme, prompt can not be provided for the user timely and effectively, so that the user can exercise recitation with poor effect.
Disclosure of Invention
The invention provides a recitation assisting reminding method, recitation assisting reminding equipment and a storage medium, which are used for timely and effectively providing prompts for users and improving user experience.
In a first aspect, the invention provides a recitation-assisted reminding method, comprising:
determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period;
and prompting the user according to the prompting strategy in the next period.
In a possible implementation manner, before the difficulty coefficient of reciting the content according to the reciting state of the user and the next cycle, the method further comprises the following steps:
and determining the recitation state of the user according to the reminding time information and the recitation correct rate information.
In one possible implementation manner, the determining the recitation state of the user according to the reminding time information and the recitation correct rate information includes:
determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factors; the condition affecting factors include at least one of: the current recitation of volume, interfering sound information and speech rate.
In one possible implementation manner, the determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factor includes:
weighting the reminding time information, recitation correct rate information and state influence factors to obtain a first weighted value; the first weighted value is used for measuring the recitation state of the user; the reminding time information is determined according to the reminding time information, and the recitation correct rate information is determined according to the recitation correct rate information.
In a possible implementation manner, before determining the prompt policy of the next period, the method further includes:
and determining the difficulty coefficient of the reciting content of the next period according to the appearance frequency of the uncommon words of the reciting content of the next period.
In one possible implementation, the determining the difficulty factor of the recited content of the next cycle according to the uncommon word occurrence frequency of the recited content of the next cycle comprises:
determining the difficulty coefficient of the recitation content of the next period according to the appearance frequency of the uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period; the difficulty factor includes at least one of: the text book to which the reciting content of the user belongs, the work category of the reciting content of the user, the space of the reciting content of the user and the context of the reciting content of the user.
In one possible implementation manner, determining the difficulty factor of the recitation content of the next cycle according to the appearance frequency of the uncommon word of the recitation content of the next cycle and the difficulty factor corresponding to the recitation content of the next cycle comprises:
weighting the appearance frequency of uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period to obtain a second weighted value, and taking the second weighted value as the difficulty coefficient of the recitation content of the next period; and the weight corresponding to the appearance frequency of the uncommon word of the recitation content of the next period is determined according to the appearance frequency of the uncommon word of the recitation content of the next period.
In one possible implementation, determining the prompting strategy of the next cycle according to the recitation state of the user and the difficulty coefficient of the recitation content of the next cycle comprises:
adjusting the current time threshold value according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period to obtain the time threshold value corresponding to the next period;
and determining the prompting strategy of the next period according to the time threshold corresponding to the next period.
In one possible implementation, the time threshold includes: a first time threshold, in the next period, prompting the user according to the prompting policy, including:
if the card shell recitation time of the user exceeds a first time threshold, outputting first prompt information to the user, wherein the first prompt information is used for inquiring whether the user needs prompting; the card housing duration is recorded upon detecting that the recited speech of the user and the textual information of the recited content do not match;
and if a prompt response message of the user is received, outputting the text content next to the text information at the current card shell to prompt the user.
In one possible implementation, the time threshold further includes: a second time threshold, the method further comprising:
if receiving indication information which is triggered by a user and does not need to be prompted, continuing recording the card shell duration;
and if the card shell duration exceeds a second time threshold, outputting text content information next to the text information at the current card shell to prompt the user.
In one possible implementation, the time threshold includes a third time threshold, and the method further includes:
recording recitation start time of the user;
and if the difference value between the current time and the recitation starting time exceeds a third time threshold, outputting second prompt information, wherein the second prompt information is used for prompting the user that the recitation is overtime.
In a second aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method of any one of the first aspect.
In a third aspect, an embodiment of the present invention provides an electronic device, including:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to:
determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period;
and prompting the user according to the prompting strategy in the next period.
In one possible implementation, the processor is configured to:
and determining the recitation state of the user according to the reminding time information and the recitation correct rate information.
In one possible implementation, the processor is configured to:
determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factors; the condition affecting factors include at least one of: the current recitation of volume, interfering sound information and speech rate.
In one possible implementation, the processor is configured to:
weighting the reminding time information, recitation correct rate information and state influence factors to obtain a first weighted value; the first weighted value is used for measuring the recitation state of the user; the reminding time information is determined according to the reminding time information, and the recitation correct rate information is determined according to the recitation correct rate information.
In one possible implementation, the processor is configured to:
and determining the difficulty coefficient of the reciting content of the next period according to the appearance frequency of the uncommon words of the reciting content of the next period.
In one possible implementation, the processor is configured to:
determining the difficulty coefficient of the recitation content of the next period according to the appearance frequency of the uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period; the difficulty factor includes at least one of: the text book to which the reciting content of the user belongs, the work category of the reciting content of the user, the space of the reciting content of the user and the context of the reciting content of the user.
In one possible implementation, the processor is configured to:
weighting the appearance frequency of uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period to obtain a second weighted value, and taking the second weighted value as the difficulty coefficient of the recitation content of the next period; and the weight corresponding to the appearance frequency of the uncommon word of the recitation content of the next period is determined according to the appearance frequency of the uncommon word of the recitation content of the next period.
In one possible implementation, the processor is configured to:
adjusting the current time threshold value according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period to obtain the time threshold value corresponding to the next period;
and determining the prompting strategy of the next period according to the time threshold corresponding to the next period.
In one possible implementation, the processor is configured to:
if the card shell recitation time of the user exceeds a first time threshold, outputting first prompt information to the user, wherein the first prompt information is used for inquiring whether the user needs prompting; the card housing duration is recorded upon detecting that the recited speech of the user and the textual information of the recited content do not match;
and if a prompt response message of the user is received, outputting the text content next to the text information at the current card shell to prompt the user.
In one possible implementation, the processor is configured to:
if receiving indication information which is triggered by a user and does not need to be prompted, continuing recording the card shell duration;
and if the card shell duration exceeds a second time threshold, outputting text content information next to the text information at the current card shell to prompt the user.
In one possible implementation, the processor is configured to:
recording recitation start time of the user;
and if the difference value between the current time and the recitation starting time exceeds a third time threshold, outputting second prompt information, wherein the second prompt information is used for prompting the user that the recitation is overtime.
The method, the equipment and the storage medium for assisting recitation reminding provided by the embodiment of the invention determine a prompting strategy of the next period according to the recitation state of a user and the difficulty coefficient of the recitation content of the next period; in the next cycle, according to the suggestion strategy is right the user is reminded, through the difficulty coefficient of reciting the state and reciting the content of user, the suggestion strategy of determining more accords with user's demand, can in time effectually provide the suggestion for the user, can improve the effect that the user practised reciting, improves user experience.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
FIG. 1 is a schematic flow chart diagram illustrating an exemplary method of assisted recitation prompting in accordance with the present invention;
fig. 2 is a schematic structural diagram of an embodiment of an electronic device provided in the present invention.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terms "comprising" and "having," and any variations thereof, in the description and claims of this invention and the drawings described herein are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Firstly, the application scene related to the invention is introduced:
the auxiliary recitation prompting method provided by the embodiment of the invention is applied to a scene of assisting a user in reciting so as to realize timely and effective prompt for the user and improve the effect of practicing reciting of the user.
The method provided by the embodiment of the invention is suitable for electronic equipment, such as mobile phones, tablet computers, wearable equipment (such as smart watches and smart bracelets), smart sound boxes, various learning machines, family education machines and other terminal equipment.
Further, the electronic device may further include a display screen for displaying user recitation content.
The method provided by the invention can be realized by the electronic equipment such as a processor executing corresponding software codes, and can also be realized by the electronic equipment performing data interaction with the server while executing the corresponding software codes, for example, the server performs part of operations to control the electronic equipment to execute the auxiliary recitation reminding method.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 1 is a flowchart illustrating an exemplary method of the present invention. As shown in fig. 1, the method provided by this embodiment includes:
And 102, prompting the user according to the prompting strategy in the next period.
Further, the method of this embodiment further includes:
recording recitation voice of a user after receiving an operation instruction of the user, wherein the operation instruction is used for instructing the user to start reciting; or the like, or, alternatively,
and determining the recitation content of the user according to the detected recitation voice of the user.
Specifically, when the user uses the electronic equipment to perform the auxiliary recitation, for example, an application program (APP) is loaded in the electronic equipment, and the APP realizes the function of the auxiliary recitation reminding. The user can open the APP, for example, click a start button in the APP, begin to perform the recitation prompting function, detect the recitation speech of the user, record the recitation speech, and determine the recitation content of the user, for example, which paragraph of which article through the recitation speech.
Alternatively, the user may select the content to be recited first after entering the APP, for example, after inputting an operation instruction to start recording, the user starts recording the recitation voice and starts to execute the recitation reminding function.
The recitation state of the user is analyzed according to the recitation voice of the user, for example, the recitation correct rate of the user is obtained according to the recitation voice of the user and the text information corresponding to the recitation content, the recitation correct rate of the user can be used for measuring the recitation state of the user, and the higher the recitation correct rate is, the better the recitation state of the user is.
When the user recites, the difficulty coefficient of the reciting content of the user can be analyzed, for example, the higher the frequency of appearance of uncommon words in the reciting content is, the larger the difficulty coefficient is; or, the simpler the context, the smaller the difficulty factor; or reciting the textbook to which the content belongs, such as a grade of the primary school stage or a grade of the junior middle school stage, the corresponding difficulty coefficients are different.
The difficulty factor may be different for different sentences or paragraphs of recited content, so the user may divide into different periods when reciting, and different prompting strategies may be used for different periods.
Therefore, the prompting strategy of the next period can be determined according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period. Wherein, different periods can adopt the same or different prompting strategies to prompt. And in the current period, prompting the user by using a prompting strategy of the current period. And prompting the user in the next period by using the updated prompting strategy in the next period.
It should be noted that the next period may be divided according to the text length of the user recitation or according to the time, for example, each time the current time is used as a limit and the next period is backward from the current time.
The prompting policy may for example contain an indication of under what conditions to prompt, or contain a prompting means, for example by voice or text, or may also contain content of a prompt, for example prompting a sentence, a word, etc.
Further, after the recitation of the user is completed, the recitation condition of the user can be evaluated, and the method of the embodiment further comprises the following steps:
and if the user is detected to complete the recitation content, evaluating the recitation voice of the user and outputting an evaluation result.
Specifically, the recitation speech of the user can be evaluated after recitation is finished, and an evaluation result can be displayed, for example, the recitation correct rate of the whole recitation process is 80%, the recitation of the content is wrong, what the correct content is, and the like. The user can also playback his own audio of the recited voice.
Further, the method of this embodiment further includes:
and displaying the text information of the reciting voice of the user, the text information of the reciting content of the user and the distinguishing information of the text information of the reciting voice and the text information of the reciting content of the user.
Specifically, in the reciting process, the text information of reciting the voice, the text information of the original text of the reciting content and the contrast information of the text information and the reciting content can be displayed on the operation interface of the display screen of the electronic equipment, and further, the prompting content and other prompting information can be displayed.
The method of the embodiment determines the prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period; in the next period, the user is prompted according to the prompting strategy, the determined prompting strategy better meets the requirements of the user through the recitation state of the user and the difficulty coefficient of the recitation content, the prompt can be timely and effectively provided for the user, the effect of practicing the recitation by the user can be improved, the user experience is improved,
on the basis of the above embodiment, further, before step 101, the following operations may be performed:
and determining the recitation state of the user according to the reminding time information and the recitation correct rate information.
Specifically, the recitation state of the user can be measured by reminding the number of times information and the recitation correct rate information, and if the recitation correct rate is higher, the reminding number of times is less, so that the current recitation state is better. If the reciting accuracy is lower and the reminding times are more, the current reciting state is worse.
Further, other influence factors, such as the current recitation volume, the interfering sound information, the speech speed and the like, may also be considered, that is, the step "determining the recitation state of the user according to the reminding time information and the recitation accuracy rate information" may specifically be implemented in the following manner:
determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factors; the condition affecting factors include at least one of: the current recitation of volume, interfering sound information and speech rate.
Further, determining the recitation state of the user may be specifically implemented as follows:
weighting the reminding time information, recitation correct rate information and state influence factors to obtain a first weighted value; the first weighted value is used for measuring the recitation state of the user; the reminding time information is determined according to the reminding time information, and the recitation correct rate information is determined according to the recitation correct rate information.
Specifically, the weight corresponding to the reminding time information may be adjusted according to the reminding time information, the weight corresponding to the recitation correct rate information may also be adjusted according to the recitation correct rate information, and the weight corresponding to other state influencing factors may be determined, for example, by an empirical value, or may be determined according to other information, which is not limited in the embodiment of the present invention.
In other embodiments of the present invention, for example, the reminding times information, recitation accuracy information, state influence factors and the like are input into an algorithm model such as a neural network, and the like, so as to obtain an output result for measuring the recitation state of the user.
Further, reciting the accuracy rate information may include, for the same user: the current recitation correct rate and the historical average recitation correct rate, the reminding times information can include: the current reminding times and the historical average reminding times can refer to historical data of the same content recited by the user, and it needs to be noted that the historical average recitation correct rate and the historical average reminding times are average values of the same user when reciting the content the same as the current reciting content. The current recitation correct rate is the recitation correct rate from the recitation starting moment to the current moment of the user; the current reminding times are reminding times of the user from the recitation starting moment to the current moment.
In another embodiment of the present invention, recitation correctness rate information may include only the current recitation correctness rate; the reminding time information may include only: the current reminding times do not take the influence of historical information into consideration.
In an embodiment of the present invention, the recitation state of the user can be measured according to the ratio of the current recitation correct rate to the historical average recitation correct rate and the ratio of the current reminding times to the historical average reminding times.
If the ratio of the current recitation correct rate to the historical average recitation correct rate is larger, the ratio of the current reminding times to the historical average reminding times is smaller, and then the current recitation state is better. Otherwise, the worse the current recitation is.
In the weighting process, the following method may be specifically adopted:
calculating the ratio of the current recitation correct rate to the historical average recitation correct rate to obtain a first ratio;
calculating the ratio of the current reminding times to the historical average reminding times to obtain a second ratio;
weighting the first ratio, the second ratio and the state influence factors to obtain a first weighted value;
wherein the weight of the first ratio can be determined according to the current recitation correct rate, or can also be determined according to the current recitation correct rate and the historical average recitation correct rate; the weight of the second ratio can be determined according to the current reminding times, or can also be determined according to the current reminding times and the historical average reminding times.
For example, a first weighting value by which the recitation state of the user is expressed may be calculated with reference to the following equation (1).
Wherein Sta1 represents the first weighting value, P is the current recitation correct rate, P is the historical average recitation correct rate, N is the current reminding times, and N is the historical average reminding times. Vol is the current recitation volume level, the Vol value can be acquired by the sound sensor, and the larger the volume, the better the current recitation state. Noi represents disturbing sound information, for example, the current disturbing sound of other people or other noise disturbance, such as dog beep, vehicle whistling, etc., which is disturbed by sound, the recitation state of the user may be affected and may be deteriorated, and in the formula (1), for example, 0 may represent a non-disturbing sound, and 1 may represent a disturbing sound.
For example, a first weighting value by which the recitation state of the user is expressed may be calculated with reference to the following equation (2).
Sta2＝w0p-w1n+k2Vol-k3Noi (2)
Wherein Sta2 represents the first weighting value, p is the current recitation correct rate, and n is the current reminding times. Vol is the current recitation volume level, the Vol value can be acquired by the sound sensor, and the larger the volume, the better the current recitation state. Noi represents disturbing sound information, for example, the current disturbing sound of other people or other noise disturbance, such as dog beep, vehicle whistling, etc., which is disturbed by sound, the recitation state of the user may be affected and may be deteriorated, and in the formula (1), for example, 0 may represent a non-disturbing sound, and 1 may represent a disturbing sound.
When the user detects a non-user voice while reciting, the user can be asked whether to continue reciting, such as outputting a text or voice prompt. Distinguishing the user voice and the non-user voice can be realized by using a Linear Discriminant Analysis (PLDA) algorithm, a voice recognition model is trained by collecting the user voice and the non-user voice, and whether the currently detected voice is the user voice is judged through the voice recognition model.
Wherein k is2、k3May be determined based on empirical values.
Because the recitation correct rate and reminding times of the user are main feedback indexes, in the embodiment of the invention, in order to better reflect the current recitation state, w0、w1The value of (b) is updated in real time. If the current accuracy is higher, the current number of reminders is lower, the better the current recitation state is, and the lower the degree to which the current recitation state is affected by these two factors is. If the current accuracy rate is lower and the current reminding times are more, the current recitation state is worse, and the degree of influence of the two factors on the recitation state is higher at the moment.
W in the above-mentioned formula (1) and formula (2)0、w1Can be obtained by the following formula:
w0＝e-p+k0
w1＝loga(n+1)+k1
wherein k is0、k1The value of a can be determined empirically to be a constant greater than a preset number threshold Thr 2.
In one embodiment of the invention, different recitation modes can be set in the electronic device, different recitation modes, and different ways of determining the recitation status of the user. For example, a personal recitation mode is selected, in which the historical average recitation correct rate, historical average reminding times and other factors of the user can be taken into consideration, that is, the recitation condition is recorded every time the user recites, and the recitation condition is used as a reference for the next time. For example, a public mode may be selected, in which historical data of the user need not be considered.
In an embodiment of the present invention, if it is monitored that the current recitation correct rate of the user is smaller than a preset correct rate threshold, and/or the current reminding times is larger than a preset times threshold, a third prompt message is output, where the third prompt message is used to prompt the user to finish reciting.
Specifically, in the process of detecting user recitation, the current recitation correct rate and the current reminding times of the user can be monitored in real time, when the current recitation correct rate of the user is smaller than a correct rate threshold Thr1 or the current reminding times is larger than a times threshold Thr2, the current recitation state of the user can be directly prompted to be too poor, the user is advised to read a plurality of lessons first and then try again to recite, and the recitation is finished.
In this embodiment, can confirm user's recitation state through reminding factors such as number of times, recitation correct rate, and then through user's recitation state and the degree of difficulty coefficient of reciting the content, the suggestion strategy of determining more accords with user's demand, can in time effectually provide the suggestion for the user, can improve the effect that the user practised reciting, improves user experience.
On the basis of the above embodiment, further, before step 101, the following operations may be performed:
and determining the difficulty coefficient of the reciting content of the next period according to the appearance frequency of the uncommon word of the reciting content of the next period.
Specifically, the greater the frequency of appearance of uncommon words, the greater the difficulty coefficient of reciting the content.
Further, in addition to considering the occurrence frequency of uncommon words, for the accuracy of difficulty coefficient, other difficulty factors such as the space of recited content, the textbook to which the recited content belongs, the work category of the recited content, the context of the recited content, etc. may also be considered, and then the difficulty coefficient of the recited content of the next period is determined, which may be implemented as follows:
determining the difficulty coefficient of the reciting content in the next period according to the appearance frequency of the uncommon words of the reciting content in the next period and the difficulty factor corresponding to the reciting content in the next period; the difficulty factor includes at least one of the following factors: the textbook to which the reciting content of the user belongs, the work category of the reciting content of the user, the space of the reciting content of the user and the context of the reciting content of the user.
In an embodiment of the present invention, the difficulty factor may be determined specifically by the following method:
weighting the appearance frequency of uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period to obtain a second weighted value, and taking the second weighted value as the difficulty coefficient of the recitation content of the next period; and the weight corresponding to the appearance frequency of the uncommon word of the recitation content of the next period is determined according to the appearance frequency of the uncommon word of the recitation content of the next period.
In other embodiments of the present invention, for example, the rarely-used word occurrence frequency and other difficulty factors may be input into an algorithm model such as a neural network, so as to obtain an output result of the difficulty coefficient.
Illustratively, the difficulty factor Dif of the recitation of the next cycle can be determined by the following equation (3):
Dif＝w’0Fre+k’1Con+k’2Len+k’3Tex+k’4Typ (3)
wherein Fre represents the appearance frequency of uncommon words, the greater the frequency, the greater the difficulty of reciting the contents (i.e. reciting the contents in the next period), i.e. the greater the difficulty coefficient. Con is the context of reciting the content, the simpler the context, the less difficulty of reciting, i.e., the difficulty factor. Tex is the textbook that reciting content belongs to, reciting content probably belongs to the fourth grade of primary school's stage, also can belong to the first of middle school's stage, and the difficulty of reciting content of different grades is different in different stages, and the grade is bigger, and the degree of difficulty is higher, and Tex can be measured through a numerical value. The Typ is a work category of reciting content, the work category is temporarily divided into poetry word song, dialect and dialect, for example, the literary word song is most difficult to recite, the dialect is second, and the poetry word song is easiest, or the difficulty corresponding to the work category can be obtained through historical error rate statistics, and the Typ can be measured through a numerical value. Len is the space for reciting the content, and the longer the space, the greater the difficulty of reciting, i.e., the greater the difficulty factor.
Context refers to reciting the character, story line or environment described by the content. The content that an article or a piece of article wants to express is not a person, or a thing, or an environment, or a storyline formed by mixing the things. The simpler the context can be considered, the less difficult the recitation. The context information can embody the whole difficulty information of the reciting content, and the score of the context information can be obtained by inputting the recived text or the full text of the current reciting lesson text into the neural network model.
Wherein, k'1、k’2、k’3、k’4May be determined based on empirical values.
The weight corresponding to the appearance frequency of the uncommon word can be obtained by referring to the following formula:
w’0＝eFre-1+k’0
wherein, k'0May be determined based on empirical values.
The appearance frequency of the uncommon word can be obtained by the following method:
determining the range of uncommon words according to the textbook to which the reciting content of the next period belongs;
and determining the rare word occurrence frequency of the recitation content of the next period according to the rare word range and the recitation content of the next period.
The rarely-used word is not standard at present, and refers to an uncommon word in a textbook, and the range of the rarely-used word in different levels is different, wherein the lower the level is, the larger the range of the rarely-used word is; the higher the grade, the smaller the range of uncommon words. According to the embodiment of the invention, the uncommon word range corresponding to each grade can be preliminarily formulated by collecting lessons of each grade in the national range. During recitation, the uncommon word range is determined according to recitation contents, and then the rare word occurrence frequency of the recitation contents in the next period is determined.
In this embodiment, can confirm the difficulty coefficient of reciting the content through rare word frequency of occurrence and other difficulty factors, and then through the difficulty coefficient of reciting state and reciting the content of user, the suggestion strategy of determining more accords with user's demand, can in time effectually provide the suggestion for the user, can improve the effect that the user practised reciting, improves user experience.
Based on the above embodiment, further, the recitation state of the user and the difficulty coefficient of reciting the content are mainly used for adjusting several time thresholds of the recitation prompting strategy. In step 101, the following method may be specifically adopted to determine the prompt policy of the next period:
adjusting the current time threshold value according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period to obtain the time threshold value corresponding to the next period;
and determining the prompting strategy of the next period according to the time threshold corresponding to the next period.
Furthermore, an adjusting coefficient can be determined according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period;
and adjusting the current time threshold according to the adjustment coefficient and the adjusted time interval to obtain the time threshold corresponding to the next period.
For example, the time threshold includes a first time threshold and a second time threshold, the first time threshold may be a time threshold for asking the user whether the prompt is required, and the second time threshold may be a time threshold for directly giving the prompt content to the user.
For example,
T’1＝T1+a1*Δt1
T’2＝T2+a2*Δt2
first time threshold T'1And a second time threshold T'2Is the adjusted time threshold, T, of the prompt used in the next cycle1And T2A first time threshold and a second time threshold that are currently in use. Wherein the coefficient a1、a2The value representing the adjustment coefficient, Δ t1、Δt2Indicating the time interval of each adjustment.
a1、a2The relationship of value to the user's recitation state and difficulty factor of reciting content can be expressed as:
a1＝ln(Sta+1)+e-Dif；a2＝ln(Sta+1)+e-Dif
where Sta represents the recitation state of the user and Dif represents the difficulty factor of reciting the content.
The prompting strategy can be effectively adjusted according to the recitation state of the user and the difficulty coefficient of recitation content by adjusting the prompting time threshold.
Further, step 102 may specifically be implemented as follows:
if the card shell recitation time of the user exceeds a first time threshold, outputting first prompt information to the user, wherein the first prompt information is used for inquiring whether the user needs prompting; the card housing duration is recorded upon detecting that the recited speech of the user and the textual information of the recited content do not match;
and if a prompt response message of the user is received, outputting the text content next to the text information at the current card shell to prompt the user.
In other embodiments of the present invention, if receiving an indication message triggered by a user and not required to be prompted, continuing to record the card shell duration;
and if the card shell duration exceeds a second time threshold, outputting text content information next to the text information at the current card shell to prompt the user.
Specifically, the time is counted from the moment when the user starts to "jam the shell", that is, the time duration of the jam is recorded. With respect to "card cases," for example, after the user has correctly recited a period, the detected speech is analyzed for a mismatch with the text of the recited content, and timing begins with the end of reciting the correct last word.
When the card shell duration exceeds the first time threshold, the user is asked whether to prompt, if the user needs to prompt, an operation instruction can be input into the equipment, the equipment can prompt the user with specific content, if the user does not need to prompt, indication information which does not need to prompt can be input into the equipment, and then the equipment can continue to match the recitation records of the user and record the card shell duration.
When the card shell duration exceeds the second time threshold, that is, the user has not recited the correct content, the device may directly prompt the user with the information of the text content immediately adjacent to the current card shell, for example, the device may prompt the user in the form of voice or image to prompt the text content immediately adjacent to the card shell, or the explanation content of the immediately adjacent text, or the core word in the immediately adjacent text sentence, etc., which may be set according to the requirement.
Further, recording the card shell duration includes:
if the reciting voice is successfully matched with the text information which is already recited by the user, stopping recording the card shell duration;
if the reciting voice is successfully matched with the text information of the unrecited content of the user, resetting the card shell duration;
and if the reciting voice is failed to be matched with the text information which is already recited by the user and the reciting voice is failed to be matched with the text information of the unrecited content of the user, continuing to record the length of the card shell.
Specifically, consider that the user can jump to recite, or recite repeatedly the content of reciting, when the equipment detects that reciting pronunciation is unmatched with reciting content characters, can be with the user's reciting pronunciation with the preceding characters that have been recited completion to and the characters that have not been recited (i.e. the not reciting characters of the whole reciting content) search for the matching, it is long to match the card shell that can not update when the content that has been recited before, when the content that the user has not been recited is matched, the long zero clearing of card shell is long, and detect backward from this content begins.
On the basis of the foregoing embodiment, further, the time threshold includes a third time threshold, and the method of this embodiment further includes:
recording recitation start time of the user;
and if the difference value between the current time and the recitation starting time exceeds a third time threshold, outputting second prompt information, wherein the second prompt information is used for prompting the user that the recitation is overtime.
Specifically, the user is when reciting, and equipment can record user's reciting start time, if the length of time of the whole process of reciting, reciting start time and interval of current time exceed third time threshold value promptly, then the suggestion user reciting is overtime, can be with this reciting result record for reciting failure.
Wherein a third time threshold may also be included in the prompting strategy, which may be determined by recitation status and difficulty factor of reciting the content.
The adjustment manner of the third time threshold may refer to the adjustment manners of the first time threshold and the second time threshold. For example,
T′3＝T3+a3*Δt3
a3＝ln(Sta+1)+e-Difthe third time threshold value T'3Is the time threshold for the prompt to be used in the next cycle after adjustment, and T3 is the third time threshold currently used. Wherein the coefficient a3The value representing the adjusted ratio, Δ t3Indicating the time interval of each adjustment.
Further, in addition to prompting the user through the prompting policy, the method of the present embodiment may also prompt the user through the user actively initiating a prompting request, and further includes:
and if a prompt request of the user is received, outputting fourth prompt information according to the content of the prompt request so as to prompt the user.
Fig. 2 is a structural diagram of an embodiment of an electronic device provided in the present invention, and as shown in fig. 2, the electronic device includes:
a processor 201, and a memory 202 for storing executable instructions for the processor 201.
The above components may communicate over one or more buses.
Wherein the processor 201 is configured to:
determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period;
and prompting the user according to the prompting strategy in the next period.
In one possible implementation, the processor 201 is configured to:
and determining the recitation state of the user according to the reminding time information and the recitation correct rate information.
In one possible implementation, the processor 201 is configured to:
determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factors; the condition affecting factors include at least one of: the current recitation of volume, interfering sound information and speech rate.
In one possible implementation, the processor 201 is configured to:
weighting the reminding time information, recitation correct rate information and state influence factors to obtain a first weighted value; the first weighted value is used for measuring the recitation state of the user; the reminding time information is determined according to the reminding time information, and the recitation correct rate information is determined according to the recitation correct rate information.
In one possible implementation, the processor 201 is configured to:
and determining the difficulty coefficient of the reciting content of the next period according to the appearance frequency of the uncommon words of the reciting content of the next period.
In one possible implementation, the processor 201 is configured to:
determining the difficulty coefficient of the recitation content of the next period according to the appearance frequency of the uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period; the difficulty factor includes at least one of: the text book to which the reciting content of the user belongs, the work category of the reciting content of the user, the space of the reciting content of the user and the context of the reciting content of the user.
In one possible implementation, the processor 201 is configured to:
weighting the appearance frequency of uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period to obtain a second weighted value, and taking the second weighted value as the difficulty coefficient of the recitation content of the next period; and the weight corresponding to the appearance frequency of the uncommon word of the recitation content of the next period is determined according to the appearance frequency of the uncommon word of the recitation content of the next period.
In one possible implementation, the processor 201 is configured to:
adjusting the current time threshold value according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period to obtain the time threshold value corresponding to the next period;
and determining the prompting strategy of the next period according to the time threshold corresponding to the next period.
In one possible implementation, the processor 201 is configured to:
if the card shell recitation time of the user exceeds a first time threshold, outputting first prompt information to the user, wherein the first prompt information is used for inquiring whether the user needs prompting; the card housing duration is recorded upon detecting that the recited speech of the user and the textual information of the recited content do not match;
and if a prompt response message of the user is received, outputting the text content next to the text information at the current card shell to prompt the user.
In one possible implementation, the processor 201 is configured to:
if receiving indication information which is triggered by a user and does not need to be prompted, continuing recording the card shell duration;
and if the card shell duration exceeds a second time threshold, outputting text content information next to the text information at the current card shell to prompt the user.
In one possible implementation, the processor 201 is configured to:
recording recitation start time of the user;
and if the difference value between the current time and the recitation starting time exceeds a third time threshold, outputting second prompt information, wherein the second prompt information is used for prompting the user that the recitation is overtime.
In one possible implementation, the electronic device may also include a display screen that may display, for example, recitations, as well as text for prompts, or an audio component that may output prompts for audio signals, etc.
The electronic device of this embodiment executes the corresponding method in the foregoing method embodiment by executing the executable instruction, and the specific implementation process of the electronic device may refer to the foregoing method embodiment, which is not described herein again.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the method in the foregoing method embodiment is implemented.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (11)
1. An auxiliary recitation reminding method is characterized by comprising the following steps:
determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period;
in the next period, prompting the user according to the prompting strategy;
determining a prompting strategy of the next period according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period, wherein the prompting strategy comprises the following steps:
adjusting the current time threshold value according to the recitation state of the user and the difficulty coefficient of the recitation content of the next period to obtain the time threshold value corresponding to the next period;
determining a prompt strategy of the next period according to the time threshold corresponding to the next period;
the time threshold includes: a first time threshold, in the next period, prompting the user according to the prompting policy, including:
if the card shell recitation time of the user exceeds a first time threshold, outputting first prompt information to the user, wherein the first prompt information is used for inquiring whether the user needs prompting; the card housing duration is recorded upon detecting that the recited speech of the user and the textual information of the recited content do not match;
and if a prompt response message of the user is received, outputting the text content next to the text information at the current card shell to prompt the user.
2. The method of claim 1 wherein said associating with a user recitation status and difficulty factor of recited content for a next cycle further comprises:
and determining the recitation state of the user according to the reminding time information and the recitation correct rate information.
3. The method of claim 2 wherein said determining recited status of said user based on said reminder times information and recitation correctness rate information comprises:
determining the recitation state of the user according to the reminding time information, the recitation correct rate information and the state influence factors; the condition affecting factors include at least one of: the current recitation of volume, interfering sound information and speech rate.
4. The method of claim 3 wherein said determining a recitation status of said user based on said reminder times information, said recitation correctness rate information, and status-affecting factors comprises:
weighting the reminding time information, recitation correct rate information and state influence factors to obtain a first weighted value; the first weighted value is used for measuring the recitation state of the user; the reminding time information is determined according to the reminding time information, and the recitation correct rate information is determined according to the recitation correct rate information.
5. The method of claim 1, wherein before determining the prompt policy for the next cycle, further comprising:
and determining the difficulty coefficient of the reciting content of the next period according to the appearance frequency of the uncommon words of the reciting content of the next period.
6. The method of claim 5 wherein said determining a difficulty factor for said next cycle of recited content based on a rare word occurrence frequency of said next cycle of recited content comprises:
determining the difficulty coefficient of the recitation content of the next period according to the appearance frequency of the uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period; the difficulty factor includes at least one of: the text book to which the reciting content of the user belongs, the work category of the reciting content of the user, the space of the reciting content of the user and the context of the reciting content of the user.
7. The method of claim 6 wherein determining the difficulty factor of recited content for said next cycle based on the uncommon word occurrence frequency of recited content for said next cycle and the difficulty factor corresponding to recited content for said next cycle comprises:
weighting the appearance frequency of uncommon words of the recitation content of the next period and the difficulty factor corresponding to the recitation content of the next period to obtain a second weighted value, and taking the second weighted value as the difficulty coefficient of the recitation content of the next period; and the weight corresponding to the appearance frequency of the uncommon word of the recitation content of the next period is determined according to the appearance frequency of the uncommon word of the recitation content of the next period.
8. The method of any of claims 1-7, wherein the time threshold further comprises: a second time threshold, the method further comprising:
if receiving indication information which is triggered by a user and does not need to be prompted, continuing recording the card shell duration;
and if the card shell duration exceeds a second time threshold, outputting text content information next to the text information at the current card shell to prompt the user.
9. The method of claim 8, wherein the time threshold comprises a third time threshold, the method further comprising:
recording recitation start time of the user;
and if the difference value between the current time and the recitation starting time exceeds a third time threshold, outputting second prompt information, wherein the second prompt information is used for prompting the user that the recitation is overtime.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1-9.
11. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-9 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490557.0A CN110310086B (en) | 2019-06-06 | 2019-06-06 | Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490557.0A CN110310086B (en) | 2019-06-06 | 2019-06-06 | Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110310086A CN110310086A (en) | 2019-10-08 |
| CN110310086B true CN110310086B (en) | 2022-04-05 |
Family
ID=68075738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910490557.0A Active CN110310086B (en) | 2019-06-06 | 2019-06-06 | Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110310086B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225179A (en) * | 2015-08-28 | 2016-01-06 | 广东小天才科技有限公司 | A kind of learning process method for supervising and learning process supervising device |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US577948A (en) * | 1897-03-02 | Campbell ford and frank mahler | ||
| CN1959765A (en) * | 2006-09-11 | 2007-05-09 | 中山大学 | System and method for reciting words based on sections and chapters |
| CN101814066A (en) * | 2009-02-23 | 2010-08-25 | 富士通株式会社 | Text reading difficulty judging device and method thereof |
| CN101826263B (en) * | 2009-03-04 | 2012-01-04 | 中国科学院自动化研究所 | Objective standard based automatic oral evaluation system |
| CN101593438B (en) * | 2009-06-05 | 2010-12-01 | 创而新（中国）科技有限公司 | Recitation-assistant document display method and recitation-assistant document display system |
| CN103971675B (en) * | 2013-01-29 | 2016-03-02 | 腾讯科技（深圳）有限公司 | Automatic speech recognition method and system |
| CN105426511A (en) * | 2015-11-30 | 2016-03-23 | 广东小天才科技有限公司 | Recitation assistance method and apparatus |
| CN105825852A (en) * | 2016-05-23 | 2016-08-03 | 渤海大学 | Oral English reading test scoring method |
| CN106205253A (en) * | 2016-09-25 | 2016-12-07 | 姚前 | One recites method, device and platform |
| CN107316638A (en) * | 2017-06-28 | 2017-11-03 | 北京粉笔未来科技有限公司 | A kind of poem recites evaluating method and system, a kind of terminal and storage medium |
| CN108389440A (en) * | 2018-03-15 | 2018-08-10 | 广东小天才科技有限公司 | A kind of speech playing method, device and voice playing equipment based on microphone |
| CN109523194B (en) * | 2018-12-14 | 2021-06-01 | 深圳市小柠檬教育科技有限公司 | Chinese reading ability evaluation method and device and readable storage medium |
| CN109658776A (en) * | 2018-12-17 | 2019-04-19 | 广东小天才科技有限公司 | A kind of detection method that reciting fluency and electronic equipment |
| CN109326178A (en) * | 2018-12-20 | 2019-02-12 | 广东小天才科技有限公司 | A kind of auxiliary recites method and terminal device |
| CN109448455A (en) * | 2018-12-20 | 2019-03-08 | 广东小天才科技有限公司 | A kind of real-time error recites method and private tutor's equipment |
-
2019
- 2019-06-06 CN CN201910490557.0A patent/CN110310086B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225179A (en) * | 2015-08-28 | 2016-01-06 | 广东小天才科技有限公司 | A kind of learning process method for supervising and learning process supervising device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110310086A (en) | 2019-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108563780B (en) | Course content recommendation method and device | |
| CN109271585B (en) | Information pushing method and family education equipment | |
| CN110085261A (en) | A kind of pronunciation correction method, apparatus, equipment and computer readable storage medium | |
| EP3319081A1 (en) | On-board voice command identification method and apparatus, and storage medium | |
| US20160293036A1 (en) | System and method for adaptive assessment and training | |
| US8234114B2 (en) | Speech interactive system and method | |
| US20130262365A1 (en) | Educational system, method and program to adapt learning content based on predicted user reaction | |
| CN109074345A (en) | Course is automatically generated and presented by digital media content extraction | |
| CN108874935B (en) | Review content recommendation method based on voice search and electronic equipment | |
| CN111833853A (en) | Voice processing method and device, electronic equipment and computer readable storage medium | |
| JP5105943B2 (en) | Utterance evaluation device and utterance evaluation program | |
| CN113486970B (en) | Reading capability evaluation method and device | |
| US11587460B2 (en) | Method and system for adaptive language learning | |
| CN110310086B (en) | Recitation-assisted reminding method, recitation-assisted reminding equipment and storage medium | |
| JP7376071B2 (en) | Computer program, pronunciation learning support method, and pronunciation learning support device | |
| US20210056957A1 (en) | Ability Classification | |
| US11636858B2 (en) | Audio analysis system for automatic language proficiency assessment | |
| US11250874B2 (en) | Audio quality enhancement system | |
| JP6656529B2 (en) | Foreign language conversation training system | |
| JP7294637B2 (en) | Dialogue adaptation device, dialogue adaptation method, program, and recording medium | |
| CN110516043A (en) | Answer generation method and device for question answering system | |
| US7039578B2 (en) | Method and apparatus for training foreign languages | |
| CN110444065A (en) | Aid reading method, apparatus, storage medium and smart machine | |
| CN110895891A (en) | Control method and early education equipment | |
| US11404051B2 (en) | Textual analysis system for automatic language proficiency assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 6 / F and 23 / F, scientific research building, No.2 building, zone a, China sound Valley, 3333 Xiyou Road, high tech Zone, Hefei City, Anhui Province, 230000 Patentee after: Anhui taoyun Technology Co.,Ltd. Address before: 230000 9, level 1, Tiandi science and Technology Park, 66 dive East Road, hi tech Zone, Hefei, Anhui. Patentee before: ANHUI TAOYUN TECHNOLOGY Co.,Ltd. |